assays.bib

@article{sourisseau_deep_2019,
	title = {Deep {Mutational} {Scanning} {Comprehensively} {Maps} {How} {Zika} {Envelope} {Protein} {Mutations} {Affect} {Viral} {Growth} and {Antibody} {Escape}},
	volume = {93},
	issn = {0022-538X, 1098-5514},
	url = {https://journals.asm.org/doi/10.1128/JVI.01291-19},
	doi = {10.1128/JVI.01291-19},
	abstract = {Zika virus has recently been shown to be associated with severe birth defects. The virus’s E protein mediates its ability to infect cells and is also the primary target of the antibodies that are elicited by natural infection and vaccines that are being developed against the virus. Therefore, determining the effects of mutations to this protein is important for understanding its function, its susceptibility to vaccine-mediated immunity, and its potential for future evolution. We completely mapped how amino acid mutations to the E protein affected the virus’s ability to grow in cells in the laboratory and escape from several antibodies. The resulting maps relate changes in the E protein’s sequence to changes in viral function and therefore provide a valuable complement to existing maps of the physical structure of the protein.
          , 
            ABSTRACT
            Functional constraints on viral proteins are often assessed by examining sequence conservation among natural strains, but this approach is relatively ineffective for Zika virus because all known sequences are highly similar. Here, we take an alternative approach to map functional constraints on Zika virus’s envelope (E) protein by using deep mutational scanning to measure how all amino acid mutations to the E protein affect viral growth in cell culture. The resulting sequence-function map is consistent with existing knowledge about E protein structure and function but also provides insight into mutation-level constraints in many regions of the protein that have not been well characterized in prior functional work. In addition, we extend our approach to completely map how mutations affect viral neutralization by two monoclonal antibodies, thereby precisely defining their functional epitopes. Overall, our study provides a valuable resource for understanding the effects of mutations to this important viral protein and also offers a roadmap for future work to map functional and antigenic selection to Zika virus at high resolution.
            
              IMPORTANCE
              Zika virus has recently been shown to be associated with severe birth defects. The virus’s E protein mediates its ability to infect cells and is also the primary target of the antibodies that are elicited by natural infection and vaccines that are being developed against the virus. Therefore, determining the effects of mutations to this protein is important for understanding its function, its susceptibility to vaccine-mediated immunity, and its potential for future evolution. We completely mapped how amino acid mutations to the E protein affected the virus’s ability to grow in cells in the laboratory and escape from several antibodies. The resulting maps relate changes in the E protein’s sequence to changes in viral function and therefore provide a valuable complement to existing maps of the physical structure of the protein.},
	language = {en},
	number = {23},
	urldate = {2022-07-11},
	journal = {Journal of Virology},
	author = {Sourisseau, Marion and Lawrence, Daniel J. P. and Schwarz, Megan C. and Storrs, Carina H. and Veit, Ethan C. and Bloom, Jesse D. and Evans, Matthew J.},
	editor = {Pfeiffer, Julie K.},
	month = dec,
	year = {2019},
	pages = {e01291--19},
	file = {Full Text:/Users/admin/Zotero/storage/D4BDUGQ6/Sourisseau et al. - 2019 - Deep Mutational Scanning Comprehensively Maps How .pdf:application/pdf},
}

@article{deng_deep_2012,
	title = {Deep {Sequencing} of {Systematic} {Combinatorial} {Libraries} {Reveals} Beta-{Lactamase} {Sequence} {Constraints} at {High} {Resolution}},
	volume = {424},
	issn = {00222836},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0022283612007711},
	doi = {10.1016/j.jmb.2012.09.014},
	language = {en},
	number = {3-4},
	urldate = {2022-07-11},
	journal = {Journal of Molecular Biology},
	author = {Deng, Zhifeng and Huang, Wanzhi and Bakkalbasi, Erol and Brown, Nicholas G. and Adamski, Carolyn J. and Rice, Kacie and Muzny, Donna and Gibbs, Richard A. and Palzkill, Timothy},
	month = dec,
	year = {2012},
	pages = {150--167},
	file = {Accepted Version:/Users/admin/Zotero/storage/X5RENMCM/Deng et al. - 2012 - Deep Sequencing of Systematic Combinatorial Librar.pdf:application/pdf},
}

@article{amorosi_massively_2021,
	title = {Massively parallel characterization of {CYP2C9} variant enzyme activity and abundance},
	volume = {108},
	issn = {00029297},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S000292972100269X},
	doi = {10.1016/j.ajhg.2021.07.001},
	language = {en},
	number = {9},
	urldate = {2022-07-11},
	journal = {The American Journal of Human Genetics},
	author = {Amorosi, Clara J. and Chiasson, Melissa A. and McDonald, Matthew G. and Wong, Lai Hong and Sitko, Katherine A. and Boyle, Gabriel and Kowalski, John P. and Rettie, Allan E. and Fowler, Douglas M. and Dunham, Maitreya J.},
	month = sep,
	year = {2021},
	pages = {1735--1751},
	file = {Full Text:/Users/admin/Zotero/storage/8DWGHK9I/Amorosi et al. - 2021 - Massively parallel characterization of CYP2C9 vari.pdf:application/pdf},
}

@article{chiasson_multiplexed_2020,
	title = {Multiplexed measurement of variant abundance and activity reveals {VKOR} topology, active site and human variant impact},
	volume = {9},
	issn = {2050-084X},
	url = {https://elifesciences.org/articles/58026},
	doi = {10.7554/eLife.58026},
	abstract = {Vitamin K epoxide reductase (VKOR) drives the vitamin K cycle, activating vitamin K-dependent blood clotting factors. VKOR is also the target of the widely used anticoagulant drug, warfarin. Despite VKOR’s pivotal role in coagulation, its structure and active site remain poorly understood. In addition, VKOR variants can cause vitamin K-dependent clotting factor deficiency or alter warfarin response. Here, we used multiplexed, sequencing-based assays to measure the effects of 2,695 VKOR missense variants on abundance and 697 variants on activity in cultured human cells. The large-scale functional data, along with an evolutionary coupling analysis, supports a four transmembrane domain topology, with variants in transmembrane domains exhibiting strongly deleterious effects on abundance and activity. Functionally constrained regions of the protein define the active site, and we find that, of four conserved cysteines putatively critical for function, only three are absolutely required. Finally, 25\% of human VKOR missense variants show reduced abundance or activity, possibly conferring warfarin sensitivity or causing disease.},
	language = {en},
	urldate = {2022-07-11},
	journal = {eLife},
	author = {Chiasson, Melissa A and Rollins, Nathan J and Stephany, Jason J and Sitko, Katherine A and Matreyek, Kenneth A and Verby, Marta and Sun, Song and Roth, Frederick P and DeSloover, Daniel and Marks, Debora S and Rettie, Allan E and Fowler, Douglas M},
	month = sep,
	year = {2020},
	pages = {e58026},
	file = {Full Text:/Users/admin/Zotero/storage/GWWNSVDK/Chiasson et al. - 2020 - Multiplexed measurement of variant abundance and a.pdf:application/pdf},
}

@article{wrenbeck_single-mutation_2017,
	title = {Single-mutation fitness landscapes for an enzyme on multiple substrates reveal specificity is globally encoded},
	volume = {8},
	issn = {2041-1723},
	url = {http://www.nature.com/articles/ncomms15695},
	doi = {10.1038/ncomms15695},
	language = {en},
	number = {1},
	urldate = {2022-07-11},
	journal = {Nature Communications},
	author = {Wrenbeck, Emily E. and Azouz, Laura R. and Whitehead, Timothy A.},
	month = aug,
	year = {2017},
	pages = {15695},
	file = {Full Text:/Users/admin/Zotero/storage/7WF3NED2/Wrenbeck et al. - 2017 - Single-mutation fitness landscapes for an enzyme o.pdf:application/pdf},
}

@article{brenan_phenotypic_2016,
	title = {Phenotypic {Characterization} of a {Comprehensive} {Set} of {MAPK1} /{ERK2} {Missense} {Mutants}},
	volume = {17},
	issn = {22111247},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S2211124716313171},
	doi = {10.1016/j.celrep.2016.09.061},
	language = {en},
	number = {4},
	urldate = {2022-07-11},
	journal = {Cell Reports},
	author = {Brenan, Lisa and Andreev, Aleksandr and Cohen, Ofir and Pantel, Sasha and Kamburov, Atanas and Cacchiarelli, Davide and Persky, Nicole S. and Zhu, Cong and Bagul, Mukta and Goetz, Eva M. and Burgin, Alex B. and Garraway, Levi A. and Getz, Gad and Mikkelsen, Tarjei S. and Piccioni, Federica and Root, David E. and Johannessen, Cory M.},
	month = oct,
	year = {2016},
	pages = {1171--1183},
	file = {Full Text:/Users/admin/Zotero/storage/W3B46C64/Brenan et al. - 2016 - Phenotypic Characterization of a Comprehensive Set.pdf:application/pdf},
}

@article{kozek_high-throughput_2020,
	title = {High-throughput discovery of trafficking-deficient variants in the cardiac potassium channel {KV11}.1},
	volume = {17},
	issn = {15475271},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S1547527120305427},
	doi = {10.1016/j.hrthm.2020.05.041},
	language = {en},
	number = {12},
	urldate = {2022-07-11},
	journal = {Heart Rhythm},
	author = {Kozek, Krystian A. and Glazer, Andrew M. and Ng, Chai-Ann and Blackwell, Daniel and Egly, Christian L. and Vanags, Loren R. and Blair, Marcia and Mitchell, Devyn and Matreyek, Kenneth A. and Fowler, Douglas M. and Knollmann, Bjorn C. and Vandenberg, Jamie I. and Roden, Dan M. and Kroncke, Brett M.},
	month = dec,
	year = {2020},
	pages = {2180--2189},
	file = {Accepted Version:/Users/admin/Zotero/storage/JETSTCHG/Kozek et al. - 2020 - High-throughput discovery of trafficking-deficient.pdf:application/pdf},
}

@article{davidi_highly_2020,
	title = {Highly active rubiscos discovered by systematic interrogation of natural sequence diversity},
	volume = {39},
	issn = {0261-4189, 1460-2075},
	url = {https://onlinelibrary.wiley.com/doi/10.15252/embj.2019104081},
	doi = {10.15252/embj.2019104081},
	language = {en},
	number = {18},
	urldate = {2022-07-11},
	journal = {The EMBO Journal},
	author = {Davidi, Dan and Shamshoum, Melina and Guo, Zhijun and Bar‐On, Yinon M and Prywes, Noam and Oz, Aia and Jablonska, Jagoda and Flamholz, Avi and Wernick, David G and Antonovsky, Niv and Pins, Benoit and Shachar, Lior and Hochhauser, Dina and Peleg, Yoav and Albeck, Shira and Sharon, Itai and Mueller‐Cajar, Oliver and Milo, Ron},
	month = sep,
	year = {2020},
	file = {Full Text:/Users/admin/Zotero/storage/PYUPVUZK/Davidi et al. - 2020 - Highly active rubiscos discovered by systematic in.pdf:application/pdf},
}

@article{sarkisyan_local_2016,
	title = {Local fitness landscape of the green fluorescent protein},
	volume = {533},
	issn = {0028-0836, 1476-4687},
	url = {http://www.nature.com/articles/nature17995},
	doi = {10.1038/nature17995},
	language = {en},
	number = {7603},
	urldate = {2022-07-11},
	journal = {Nature},
	author = {Sarkisyan, Karen S. and Bolotin, Dmitry A. and Meer, Margarita V. and Usmanova, Dinara R. and Mishin, Alexander S. and Sharonov, George V. and Ivankov, Dmitry N. and Bozhanova, Nina G. and Baranov, Mikhail S. and Soylemez, Onuralp and Bogatyreva, Natalya S. and Vlasov, Peter K. and Egorov, Evgeny S. and Logacheva, Maria D. and Kondrashov, Alexey S. and Chudakov, Dmitry M. and Putintseva, Ekaterina V. and Mamedov, Ilgar Z. and Tawfik, Dan S. and Lukyanov, Konstantin A. and Kondrashov, Fyodor A.},
	month = may,
	year = {2016},
	pages = {397--401},
	file = {Accepted Version:/Users/admin/Zotero/storage/KPQ2DLXG/Sarkisyan et al. - 2016 - Local fitness landscape of the green fluorescent p.pdf:application/pdf},
}

@article{olson_comprehensive_2014,
	title = {A {Comprehensive} {Biophysical} {Description} of {Pairwise} {Epistasis} throughout an {Entire} {Protein} {Domain}},
	volume = {24},
	issn = {09609822},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0960982214012688},
	doi = {10.1016/j.cub.2014.09.072},
	language = {en},
	number = {22},
	urldate = {2022-07-11},
	journal = {Current Biology},
	author = {Olson, C. Anders and Wu, Nicholas C. and Sun, Ren},
	month = nov,
	year = {2014},
	pages = {2643--2651},
	file = {Full Text:/Users/admin/Zotero/storage/XHQR6TLB/Olson et al. - 2014 - A Comprehensive Biophysical Description of Pairwis.pdf:application/pdf},
}

@article{duenas-decamp_saturation_2016,
	title = {Saturation {Mutagenesis} of the {HIV}-1 {Envelope} {CD4} {Binding} {Loop} {Reveals} {Residues} {Controlling} {Distinct} {Trimer} {Conformations}},
	volume = {12},
	issn = {1553-7374},
	url = {https://dx.plos.org/10.1371/journal.ppat.1005988},
	doi = {10.1371/journal.ppat.1005988},
	language = {en},
	number = {11},
	urldate = {2022-07-11},
	journal = {PLOS Pathogens},
	author = {Duenas-Decamp, Maria and Jiang, Li and Bolon, Daniel and Clapham, Paul R.},
	editor = {Desrosiers, Ronald C.},
	month = nov,
	year = {2016},
	pages = {e1005988},
	file = {Full Text:/Users/admin/Zotero/storage/B948VI9X/Duenas-Decamp et al. - 2016 - Saturation Mutagenesis of the HIV-1 Envelope CD4 B.pdf:application/pdf},
}

@article{thompson_altered_2020,
	title = {Altered expression of a quality control protease in {E}. coli reshapes the in vivo mutational landscape of a model enzyme},
	volume = {9},
	issn = {2050-084X},
	url = {https://elifesciences.org/articles/53476},
	doi = {10.7554/eLife.53476},
	abstract = {Protein mutational landscapes are shaped by the cellular environment, but key factors and their quantitative effects are often unknown. Here we show that Lon, a quality control protease naturally absent in common
              E. coli
              expression strains, drastically reshapes the mutational landscape of the metabolic enzyme dihydrofolate reductase (DHFR). Selection under conditions that resolve highly active mutants reveals that 23.3\% of all single point mutations in DHFR are advantageous in the absence of Lon, but advantageous mutations are largely suppressed when Lon is reintroduced. Protein stability measurements demonstrate extensive activity-stability tradeoffs for the advantageous mutants and provide a mechanistic explanation for Lon’s widespread impact. Our findings suggest possibilities for tuning mutational landscapes by modulating the cellular environment, with implications for protein design and combatting antibiotic resistance.},
	language = {en},
	urldate = {2022-07-11},
	journal = {eLife},
	author = {Thompson, Samuel and Zhang, Yang and Ingle, Christine and Reynolds, Kimberly A and Kortemme, Tanja},
	month = jul,
	year = {2020},
	pages = {e53476},
	file = {Full Text:/Users/admin/Zotero/storage/4U2CHYQR/Thompson et al. - 2020 - Altered expression of a quality control protease i.pdf:application/pdf},
}

@article{starita_activity-enhancing_2013,
	title = {Activity-enhancing mutations in an {E3} ubiquitin ligase identified by high-throughput mutagenesis},
	volume = {110},
	issn = {0027-8424, 1091-6490},
	url = {https://pnas.org/doi/full/10.1073/pnas.1303309110},
	doi = {10.1073/pnas.1303309110},
	abstract = {Significance
            Ubiquitin is a 76 residue protein that is attached to target proteins as a posttranslational modification. This modification is dependent on the successive activity of three enzymes, designated E1, E2, and E3. We developed a high-throughput mutagenesis strategy to probe the mechanism of E3-catalyzed transfer of ubiquitin from the E2 to the target protein. By scoring the effect of nearly 100,000 mutations in an E3, we identified mutations that affect direct and allosteric interactions between the E3 and the E2. These results highlight the general utility of high-throughput mutagenesis in delineating the molecular basis of enzyme activity.
          , 
            Although ubiquitination plays a critical role in virtually all cellular processes, mechanistic details of ubiquitin (Ub) transfer are still being defined. To identify the molecular determinants within E3 ligases that modulate activity, we scored each member of a library of nearly 100,000 protein variants of the murine ubiquitination factor E4B (Ube4b) U-box domain for auto-ubiquitination activity in the presence of the E2 UbcH5c. This assay identified mutations that enhance activity both in vitro and in cellular p53 degradation assays. The activity-enhancing mutations fall into two distinct mechanistic classes: One increases the U-box:E2-binding affinity, and the other allosterically stimulates the formation of catalytically active conformations of the E2∼Ub conjugate. The same mutations enhance E3 activity in the presence of another E2, Ube2w, implying a common allosteric mechanism, and therefore the general applicability of our observations to other E3s. A comparison of the E3 activity with the two different E2s identified an additional variant that exhibits E3:E2 specificity. Our results highlight the general utility of high-throughput mutagenesis in delineating the molecular basis of enzyme activity.},
	language = {en},
	number = {14},
	urldate = {2022-07-11},
	journal = {Proceedings of the National Academy of Sciences},
	author = {Starita, Lea M. and Pruneda, Jonathan N. and Lo, Russell S. and Fowler, Douglas M. and Kim, Helen J. and Hiatt, Joseph B. and Shendure, Jay and Brzovic, Peter S. and Fields, Stanley and Klevit, Rachel E.},
	month = apr,
	year = {2013},
	file = {Full Text:/Users/admin/Zotero/storage/FBVQ2HYR/Starita et al. - 2013 - Activity-enhancing mutations in an E3 ubiquitin li.pdf:application/pdf;Full Text:/Users/admin/Zotero/storage/SF4WML4G/Starita et al. - 2013 - Activity-enhancing mutations in an E3 ubiquitin li.pdf:application/pdf},
}

@article{araya_fundamental_2012,
	title = {A fundamental protein property, thermodynamic stability, revealed solely from large-scale measurements of protein function},
	volume = {109},
	issn = {0027-8424, 1091-6490},
	url = {https://pnas.org/doi/full/10.1073/pnas.1209751109},
	doi = {10.1073/pnas.1209751109},
	abstract = {The ability of a protein to carry out a given function results from fundamental physicochemical properties that include the protein’s structure, mechanism of action, and thermodynamic stability. Traditional approaches to study these properties have typically required the direct measurement of the property of interest, oftentimes a laborious undertaking. Although protein properties can be probed by mutagenesis, this approach has been limited by its low throughput. Recent technological developments have enabled the rapid quantification of a protein’s function, such as binding to a ligand, for numerous variants of that protein. Here, we measure the ability of 47,000 variants of a WW domain to bind to a peptide ligand and use these functional measurements to identify stabilizing mutations without directly assaying stability. Our approach is rooted in the well-established concept that protein function is closely related to stability. Protein function is generally reduced by destabilizing mutations, but this decrease can be rescued by stabilizing mutations. Based on this observation, we introduce partner potentiation, a metric that uses this rescue ability to identify stabilizing mutations, and identify 15 candidate stabilizing mutations in the WW domain. We tested six candidates by thermal denaturation and found two highly stabilizing mutations, one more stabilizing than any previously known mutation. Thus, physicochemical properties such as stability are latent within these large-scale protein functional data and can be revealed by systematic analysis. This approach should allow other protein properties to be discovered.},
	language = {en},
	number = {42},
	urldate = {2022-07-11},
	journal = {Proceedings of the National Academy of Sciences},
	author = {Araya, Carlos L. and Fowler, Douglas M. and Chen, Wentao and Muniez, Ike and Kelly, Jeffery W. and Fields, Stanley},
	month = oct,
	year = {2012},
	pages = {16858--16863},
	file = {Full Text:/Users/admin/Zotero/storage/KR46AVWQ/Araya et al. - 2012 - A fundamental protein property, thermodynamic stab.pdf:application/pdf},
}

@article{wu_high-throughput_2014,
	title = {High-throughput profiling of influenza {A} virus hemagglutinin gene at single-nucleotide resolution},
	volume = {4},
	issn = {2045-2322},
	url = {https://www.nature.com/articles/srep04942},
	doi = {10.1038/srep04942},
	abstract = {Abstract
            Genetic research on influenza virus biology has been informed in large part by nucleotide variants present in seasonal or pandemic samples, or individual mutants generated in the laboratory, leaving a substantial part of the genome uncharacterized. Here, we have developed a single-nucleotide resolution genetic approach to interrogate the fitness effect of point mutations in 98\% of the amino acid positions in the influenza A virus hemagglutinin (HA) gene. Our HA fitness map provides a reference to identify indispensable regions to aid in drug and vaccine design as targeting these regions will increase the genetic barrier for the emergence of escape mutations. This study offers a new platform for studying genome dynamics, structure-function relationships, virus-host interactions and can further rational drug and vaccine design. Our approach can also be applied to any virus that can be genetically manipulated.},
	language = {en},
	number = {1},
	urldate = {2022-07-11},
	journal = {Scientific Reports},
	author = {Wu, Nicholas C. and Young, Arthur P. and Al-Mawsawi, Laith Q. and Olson, C. Anders and Feng, Jun and Qi, Hangfei and Chen, Shu-Hwa and Lu, I.-Hsuan and Lin, Chung-Yen and Chin, Robert G. and Luan, Harding H. and Nguyen, Nguyen and Nelson, Stanley F. and Li, Xinmin and Wu, Ting-Ting and Sun, Ren},
	month = dec,
	year = {2014},
	pages = {4942},
	file = {Full Text:/Users/admin/Zotero/storage/IPZQQNJQ/Wu et al. - 2014 - High-throughput profiling of influenza A virus hem.pdf:application/pdf},
}

@techreport{young_deep_2021,
	type = {preprint},
	title = {Deep {Mutagenesis} of a {Transporter} for {Uptake} of a {Non}-{Native} {Substrate} {Identifies} {Conformationally} {Dynamic} {Regions}},
	url = {http://biorxiv.org/lookup/doi/10.1101/2021.04.19.440442},
	abstract = {Abstract
          
            The serotonin transporter, SERT, catalyzes serotonin reuptake at the synapse to terminate neurotransmission via an alternating access mechanism, and SERT inhibitors are the most widely prescribed antidepressants. Here, deep mutagenesis is used to determine the effects of nearly all amino acid substitutions on human SERT surface expression and transport of the fluorescent substrate analogue APP+, identifying many mutations that enhance APP+ import. Comprehensive simulations of the entire ion-coupled import process reveal that while binding of the native substrate, serotonin, reduces free energy barriers between conformational states to promote SERT dynamics, the conformational free energy landscape in the presence of APP+ instead resembles Na
            +
            bound-SERT, with a higher free energy barrier for transitioning to an inward-facing state. The deep mutational scan for SERT-catalyzed import of APP+ finds mutations that promote the necessary conformational changes that would otherwise be facilitated by the native substrate. Indeed, hundreds of gain-of-function mutations for APP+ import are found along the permeation pathway, most notably mutations that favor opening of a solvent-exposed intracellular vestibule. The mutagenesis data support the simulated mechanism in which the neurotransmitter and a symported sodium share a common cytosolic exit pathway to achieve coupling. Furthermore, the mutational landscape for SERT surface trafficking, which likely filters out misfolded sequences, reveals that residues along the permeation pathway are mutationally tolerant, providing plausible evolutionary pathways for changes in transporter properties while maintaining folded structure.},
	language = {en},
	urldate = {2022-07-11},
	institution = {Biochemistry},
	author = {Young, Heather J. and Chan, Matthew and Selvam, Balaji and Szymanski, Steven K. and Shukla, Diwakar and Procko, Erik},
	month = apr,
	year = {2021},
	doi = {10.1101/2021.04.19.440442},
	file = {Submitted Version:/Users/admin/Zotero/storage/T69VH4DC/Young et al. - 2021 - Deep Mutagenesis of a Transporter for Uptake of a .pdf:application/pdf},
}

@article{jiang_balance_2016,
	title = {A {Balance} between {Inhibitor} {Binding} and {Substrate} {Processing} {Confers} {Influenza} {Drug} {Resistance}},
	volume = {428},
	issn = {00222836},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0022283615006907},
	doi = {10.1016/j.jmb.2015.11.027},
	language = {en},
	number = {3},
	urldate = {2022-07-11},
	journal = {Journal of Molecular Biology},
	author = {Jiang, Li and Liu, Ping and Bank, Claudia and Renzette, Nicholas and Prachanronarong, Kristina and Yilmaz, Lutfu S. and Caffrey, Daniel R. and Zeldovich, Konstantin B. and Schiffer, Celia A. and Kowalik, Timothy F. and Jensen, Jeffrey D. and Finberg, Robert W. and Wang, Jennifer P. and Bolon, Daniel N.A.},
	month = feb,
	year = {2016},
	pages = {538--553},
	file = {Accepted Version:/Users/admin/Zotero/storage/TJGBH3YJ/Jiang et al. - 2016 - A Balance between Inhibitor Binding and Substrate .pdf:application/pdf},
}

@article{melamed_deep_2013,
	title = {Deep mutational scanning of an {RRM} domain of the \textit{{Saccharomyces} cerevisiae} poly({A})-binding protein},
	volume = {19},
	issn = {1355-8382, 1469-9001},
	url = {http://rnajournal.cshlp.org/lookup/doi/10.1261/rna.040709.113},
	doi = {10.1261/rna.040709.113},
	abstract = {The RNA recognition motif (RRM) is the most common RNA-binding domain in eukaryotes. Differences in RRM sequences dictate, in part, both RNA and protein-binding specificities and affinities. We used a deep mutational scanning approach to study the sequence-function relationship of the RRM2 domain of the
              Saccharomyces cerevisiae
              poly(A)-binding protein (Pab1). By scoring the activity of more than 100,000 unique Pab1 variants, including 1246 with single amino acid substitutions, we delineated the mutational constraints on each residue. Clustering of residues with similar mutational patterns reveals three major classes, composed principally of RNA-binding residues, of hydrophobic core residues, and of the remaining residues. The first class also includes a highly conserved residue not involved in RNA binding, G150, which can be mutated to destabilize Pab1. A comparison of the mutational sensitivity of yeast Pab1 residues to their evolutionary conservation reveals that most residues tolerate more substitutions than are present in the natural sequences, although other residues that tolerate fewer substitutions may point to specialized functions in yeast. An analysis of ∼40,000 double mutants indicates a preference for a short distance between two mutations that display an epistatic interaction. As examples of interactions, the mutations N139T, N139S, and I157L suppress other mutations that interfere with RNA binding and protein stability. Overall, this study demonstrates that living cells can be subjected to a single assay to analyze hundreds of thousands of protein variants in parallel.},
	language = {en},
	number = {11},
	urldate = {2022-07-11},
	journal = {RNA},
	author = {Melamed, Daniel and Young, David L. and Gamble, Caitlin E. and Miller, Christina R. and Fields, Stanley},
	month = nov,
	year = {2013},
	pages = {1537--1551},
	file = {Full Text:/Users/admin/Zotero/storage/AFZEI4G6/Melamed et al. - 2013 - Deep mutational scanning of an RRM domain of the .pdf:application/pdf},
}

@article{jia_massively_2021,
	title = {Massively parallel functional testing of {MSH2} missense variants conferring {Lynch} syndrome risk},
	volume = {108},
	issn = {00029297},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0002929720304390},
	doi = {10.1016/j.ajhg.2020.12.003},
	language = {en},
	number = {1},
	urldate = {2022-07-11},
	journal = {The American Journal of Human Genetics},
	author = {Jia, Xiaoyan and Burugula, Bala Bharathi and Chen, Victor and Lemons, Rosemary M. and Jayakody, Sajini and Maksutova, Mariam and Kitzman, Jacob O.},
	month = jan,
	year = {2021},
	pages = {163--175},
	file = {Full Text:/Users/admin/Zotero/storage/4J7YRE9U/Jia et al. - 2021 - Massively parallel functional testing of MSH2 miss.pdf:application/pdf},
}

@article{mavor_determination_2016,
	title = {Determination of ubiquitin fitness landscapes under different chemical stresses in a classroom setting},
	volume = {5},
	issn = {2050-084X},
	url = {https://elifesciences.org/articles/15802},
	doi = {10.7554/eLife.15802},
	abstract = {Ubiquitin is essential for eukaryotic life and varies in only 3 amino acid positions between yeast and humans. However, recent deep sequencing studies indicate that ubiquitin is highly tolerant to single mutations. We hypothesized that this tolerance would be reduced by chemically induced physiologic perturbations. To test this hypothesis, a class of first year UCSF graduate students employed deep mutational scanning to determine the fitness landscape of all possible single residue mutations in the presence of five different small molecule perturbations. These perturbations uncover 'shared sensitized positions' localized to areas around the hydrophobic patch and the C-terminus. In addition, we identified perturbation specific effects such as a sensitization of His68 in HU and a tolerance to mutation at Lys63 in DTT. Our data show how chemical stresses can reduce buffering effects in the ubiquitin proteasome system. Finally, this study demonstrates the potential of lab-based interdisciplinary graduate curriculum.
          , 
            The ability of an organism to grow and reproduce, that is, it’s “fitness”, is determined by how its genes interact with the environment. Yeast is a model organism in which researchers can control the exact mutations present in the yeast’s genes (its genotype) and the conditions in which the yeast cells live (their environment). This allows researchers to measure how a yeast cell’s genotype and environment affect its fitness.
            Ubiquitin is a protein that many organisms depend on to manage cell stress by acting as a tag that targets other proteins for degradation. Essential proteins such as ubiquitin often remain unchanged by mutation over long periods of time. As a result, these proteins evolve very slowly. Like all proteins, ubiquitin is built from a chain of amino acid molecules linked together, and the ubiquitin proteins of yeast and humans are made of almost identical sequences of amino acids.
            Although ubiquitin has barely changed its sequence over evolution, previous studies have shown that – under normal growth conditions in the laboratory – most amino acids in ubiquitin can be mutated without any loss of cell fitness. This led Mavor et al. to hypothesize that treating the yeast cells with chemicals that cause cell stress might lead to amino acids in ubiquitin becoming more sensitive to mutation.
            To test this idea, a class of graduate students at the University of California, San Francisco grew yeast cells with different ubiquitin mutations together, and with different chemicals that induce cell stress, and measured their growth rates. Sequencing the ubiquitin gene in the thousands of tested yeast cells revealed that three of the chemicals cause a shared set of amino acids in ubiquitin to become more sensitive to mutation.
            This result suggests that these amino acids are important for the stress response, possibly by altering the ability of yeast cells to target certain proteins for degradation. Conversely, another chemical causes yeast to become more tolerant to changes in the ubiquitin sequence. The experiments also link changes in particular amino acids in ubiquitin to specific stress responses.
            Mavor et al. show that many of ubquitin’s amino acids are sensitive to mutation under different stress conditions, while others can be mutated to form different amino acids without effecting fitness. By testing the effects of other chemicals, future experiments could further characterize how the yeast’s genotype and environment interact.},
	language = {en},
	urldate = {2022-07-11},
	journal = {eLife},
	author = {Mavor, David and Barlow, Kyle and Thompson, Samuel and Barad, Benjamin A and Bonny, Alain R and Cario, Clinton L and Gaskins, Garrett and Liu, Zairan and Deming, Laura and Axen, Seth D and Caceres, Elena and Chen, Weilin and Cuesta, Adolfo and Gate, Rachel E and Green, Evan M and Hulce, Kaitlin R and Ji, Weiyue and Kenner, Lillian R and Mensa, Bruk and Morinishi, Leanna S and Moss, Steven M and Mravic, Marco and Muir, Ryan K and Niekamp, Stefan and Nnadi, Chimno I and Palovcak, Eugene and Poss, Erin M and Ross, Tyler D and Salcedo, Eugenia C and See, Stephanie K and Subramaniam, Meena and Wong, Allison W and Li, Jennifer and Thorn, Kurt S and Conchúir, Shane Ó and Roscoe, Benjamin P and Chow, Eric D and DeRisi, Joseph L and Kortemme, Tanja and Bolon, Daniel N and Fraser, James S},
	month = apr,
	year = {2016},
	pages = {e15802},
	file = {Full Text:/Users/admin/Zotero/storage/H2575JWN/Mavor et al. - 2016 - Determination of ubiquitin fitness landscapes unde.pdf:application/pdf},
}

@article{glazer_deep_2020,
	title = {Deep {Mutational} {Scan} of an \textit{{SCN5A}} {Voltage} {Sensor}},
	volume = {13},
	issn = {2574-8300},
	url = {https://www.ahajournals.org/doi/10.1161/CIRCGEN.119.002786},
	doi = {10.1161/CIRCGEN.119.002786},
	abstract = {Background:
              Variants in ion channel genes have classically been studied in low throughput by patch clamping. Deep mutational scanning is a complementary approach that can simultaneously assess function of thousands of variants.
            
            
              Methods:
              
                We have developed and validated a method to perform a deep mutational scan of variants in
                SCN5A
                , which encodes the major voltage-gated sodium channel in the heart. We created a library of nearly all possible variants in a 36 base region of
                SCN5A
                in the S4 voltage sensor of domain IV and stably integrated the library into HEK293T cells.
              
            
            
              Results:
              In preliminary experiments, challenge with 3 drugs (veratridine, brevetoxin, and ouabain) could discriminate wild-type channels from gain- and loss-of-function pathogenic variants. High-throughput sequencing of the pre- and postdrug challenge pools was used to count the prevalence of each variant and identify variants with abnormal function. The deep mutational scan scores identified 40 putative gain-of-function and 33 putative loss-of-function variants. For 8 of 9 variants, patch clamping data were consistent with the scores.
            
            
              Conclusions:
              
                These experiments demonstrate the accuracy of a high-throughput in vitro scan of
                SCN5A
                variant function, which can be used to identify deleterious variants in
                SCN5A
                and other ion channel genes.},
	language = {en},
	number = {1},
	urldate = {2022-07-11},
	journal = {Circulation: Genomic and Precision Medicine},
	author = {Glazer, Andrew M. and Kroncke, Brett M. and Matreyek, Kenneth A. and Yang, Tao and Wada, Yuko and Shields, Tiffany and Salem, Joe-Elie and Fowler, Douglas M. and Roden, Dan M.},
	month = feb,
	year = {2020},
	pages = {e002786},
	file = {Full Text:/Users/admin/Zotero/storage/AHYB9LRW/Glazer et al. - 2020 - Deep Mutational Scan of an SCN5A Voltage Se.pdf:application/pdf},
}

@article{kelsic_rna_2016,
	title = {{RNA} {Structural} {Determinants} of {Optimal} {Codons} {Revealed} by {MAGE}-{Seq}},
	volume = {3},
	issn = {24054712},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S2405471216303684},
	doi = {10.1016/j.cels.2016.11.004},
	language = {en},
	number = {6},
	urldate = {2022-07-11},
	journal = {Cell Systems},
	author = {Kelsic, Eric D. and Chung, Hattie and Cohen, Niv and Park, Jimin and Wang, Harris H. and Kishony, Roy},
	month = dec,
	year = {2016},
	pages = {563--571.e6},
	file = {Full Text:/Users/admin/Zotero/storage/IF39P5MD/Kelsic et al. - 2016 - RNA Structural Determinants of Optimal Codons Reve.pdf:application/pdf},
}

@article{rockah-shmuel_systematic_2015,
	title = {Systematic {Mapping} of {Protein} {Mutational} {Space} by {Prolonged} {Drift} {Reveals} the {Deleterious} {Effects} of {Seemingly} {Neutral} {Mutations}},
	volume = {11},
	issn = {1553-7358},
	url = {https://dx.plos.org/10.1371/journal.pcbi.1004421},
	doi = {10.1371/journal.pcbi.1004421},
	language = {en},
	number = {8},
	urldate = {2022-07-11},
	journal = {PLOS Computational Biology},
	author = {Rockah-Shmuel, Liat and Tóth-Petróczy, Ágnes and Tawfik, Dan S.},
	editor = {Orengo, Christine A.},
	month = aug,
	year = {2015},
	pages = {e1004421},
	file = {Full Text:/Users/admin/Zotero/storage/QVEEKDBN/Rockah-Shmuel et al. - 2015 - Systematic Mapping of Protein Mutational Space by .pdf:application/pdf},
}

@article{kitzman_massively_2015,
	title = {Massively parallel single-amino-acid mutagenesis},
	volume = {12},
	issn = {1548-7091, 1548-7105},
	url = {http://www.nature.com/articles/nmeth.3223},
	doi = {10.1038/nmeth.3223},
	language = {en},
	number = {3},
	urldate = {2022-07-11},
	journal = {Nature Methods},
	author = {Kitzman, Jacob O and Starita, Lea M and Lo, Russell S and Fields, Stanley and Shendure, Jay},
	month = mar,
	year = {2015},
	pages = {203--206},
	file = {Accepted Version:/Users/admin/Zotero/storage/SSUEVZ32/Kitzman et al. - 2015 - Massively parallel single-amino-acid mutagenesis.pdf:application/pdf},
}

@article{aakre_evolving_2015,
	title = {Evolving {New} {Protein}-{Protein} {Interaction} {Specificity} through {Promiscuous} {Intermediates}},
	volume = {163},
	issn = {00928674},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0092867415012726},
	doi = {10.1016/j.cell.2015.09.055},
	language = {en},
	number = {3},
	urldate = {2022-07-11},
	journal = {Cell},
	author = {Aakre, Christopher D. and Herrou, Julien and Phung, Tuyen N. and Perchuk, Barrett S. and Crosson, Sean and Laub, Michael T.},
	month = oct,
	year = {2015},
	pages = {594--606},
	file = {Full Text:/Users/admin/Zotero/storage/4IIQTP93/Aakre et al. - 2015 - Evolving New Protein-Protein Interaction Specifici.pdf:application/pdf},
}

@article{bolognesi_mutational_2019,
	title = {The mutational landscape of a prion-like domain},
	volume = {10},
	issn = {2041-1723},
	url = {http://www.nature.com/articles/s41467-019-12101-z},
	doi = {10.1038/s41467-019-12101-z},
	abstract = {Abstract
            Insoluble protein aggregates are the hallmarks of many neurodegenerative diseases. For example, aggregates of TDP-43 occur in nearly all cases of amyotrophic lateral sclerosis (ALS). However, whether aggregates cause cellular toxicity is still not clear, even in simpler cellular systems. We reasoned that deep mutagenesis might be a powerful approach to disentangle the relationship between aggregation and toxicity. We generated {\textgreater}50,000 mutations in the prion-like domain (PRD) of TDP-43 and quantified their toxicity in yeast cells. Surprisingly, mutations that increase hydrophobicity and aggregation strongly decrease toxicity. In contrast, toxic variants promote the formation of dynamic liquid-like condensates. Mutations have their strongest effects in a hotspot that genetic interactions reveal to be structured in vivo, illustrating how mutagenesis can probe the in vivo structures of unstructured proteins. Our results show that aggregation of TDP-43 is not harmful but protects cells, most likely by titrating the protein away from a toxic liquid-like phase.},
	language = {en},
	number = {1},
	urldate = {2022-07-11},
	journal = {Nature Communications},
	author = {Bolognesi, Benedetta and Faure, Andre J. and Seuma, Mireia and Schmiedel, Jörn M. and Tartaglia, Gian Gaetano and Lehner, Ben},
	month = dec,
	year = {2019},
	pages = {4162},
	file = {Full Text:/Users/admin/Zotero/storage/3J8H73B4/Bolognesi et al. - 2019 - The mutational landscape of a prion-like domain.pdf:application/pdf},
}

@techreport{flynn_comprehensive_2022,
	type = {preprint},
	title = {Comprehensive fitness landscape of {SARS}-{CoV}-2 {M} $^{\textrm{pro}}$ reveals insights into viral resistance mechanisms},
	url = {http://biorxiv.org/lookup/doi/10.1101/2022.01.26.477860},
	abstract = {Abstract
          
            With the continual evolution of new strains of SARS-CoV-2 that are more virulent, transmissible, and able to evade current vaccines, there is an urgent need for effective anti-viral drugs. SARS-CoV-2 main protease (M
            pro
            ) is a leading target for drug design due to its conserved and indispensable role in the viral life cycle. Drugs targeting M
            pro
            appear promising but will elicit selection pressure for resistance. To understand resistance potential in M
            pro
            , we performed a comprehensive mutational scan of the protease that analyzed the function of all possible single amino acid changes. We developed three separate high-throughput assays of M
            pro
            function in yeast, based on either the ability of M
            pro
            variants to cleave at a defined cut-site or on the toxicity of their expression to yeast. We used deep sequencing to quantify the functional effects of each variant in each screen. The protein fitness landscapes from all three screens were strongly correlated, indicating that they captured the biophysical properties critical to M
            pro
            function. The fitness landscapes revealed a non-active site location on the surface that is extremely sensitive to mutation making it a favorable location to target with inhibitors. In addition, we found a network of critical amino acids that physically bridge the two active sites of the M
            pro
            dimer. The clinical variants of M
            pro
            were predominantly functional in our screens, indicating that M
            pro
            is under strong selection pressure in the human population. Our results provide predictions of mutations that will be readily accessible to M
            pro
            evolution and that are likely to contribute to drug resistance. This complete mutational guide of M
            pro
            can be used in the design of inhibitors with reduced potential of evolving viral resistance.},
	language = {en},
	urldate = {2022-07-11},
	institution = {Molecular Biology},
	author = {Flynn, Julia M. and Samant, Neha and Schneider-Nachum, Gily and Barkan, David T. and Yilmaz, Nese Kurt and Schiffer, Celia A. and Moquin, Stephanie A. and Dovala, Dustin and Bolon, Daniel N.A.},
	month = jan,
	year = {2022},
	doi = {10.1101/2022.01.26.477860},
	file = {Submitted Version:/Users/admin/Zotero/storage/MR6KIKAK/Flynn et al. - 2022 - Comprehensive fitness landscape of SARS-CoV-2 M s.pdf:application/pdf},
}

@article{haddox_mapping_2018,
	title = {Mapping mutational effects along the evolutionary landscape of {HIV} envelope},
	volume = {7},
	issn = {2050-084X},
	url = {https://elifesciences.org/articles/34420},
	doi = {10.7554/eLife.34420},
	abstract = {The immediate evolutionary space accessible to HIV is largely determined by how single amino acid mutations affect fitness. These mutational effects can shift as the virus evolves. However, the prevalence of such shifts in mutational effects remains unclear. Here, we quantify the effects on viral growth of all amino acid mutations to two HIV envelope (Env) proteins that differ at
              
                {\textgreater}
              
              100 residues. Most mutations similarly affect both Envs, but the amino acid preferences of a minority of sites have clearly shifted. These shifted sites usually prefer a specific amino acid in one Env, but tolerate many amino acids in the other. Surprisingly, shifts are only slightly enriched at sites that have substituted between the Envs—and many occur at residues that do not even contact substitutions. Therefore, long-range epistasis can unpredictably shift Env’s mutational tolerance during HIV evolution, although the amino acid preferences of most sites are conserved between moderately diverged viral strains.
            
          , 
            The virus that causes AIDS, or HIV, has a protein called Env on its surface, which is essential for the virus to infect cells. Env can also be recognized by the immune system, which then targets the virus for destruction or blocks it from infecting cells. Unfortunately, Env evolves very quickly, which means that HIV can evade our defenses. However, there are limits to how much this protein can change, since it still needs to perform its essential role in helping viruses enter cells.
            In the century since HIV first appeared in human populations, the virus has evolved considerably. There are now many HIV strains that infect people, and they bear Env proteins with substantially different sequences. However, it is not clear if these changes in sequence have resulted in Envs from distinct strains being able to tolerate different mutations.
            To examine this question, Haddox et al. compared how the Envs from two strains of HIV react to modifications in their sequences. They created all possible individual mutations in the proteins, and the resulting collections of mutated viruses were then tested for their ability to infect cells in the laboratory.
            Most mutations had similar effects in both Env proteins. This allowed Haddox et al. to identify portions of the protein that easily accommodate changes, and portions that must remain unchanged for viruses to remain infectious—at least in the laboratory. Some of these mutations are under different types of pressures when the virus faces the immune system, and those were identified using computational approaches.
            However, some mutations were tolerated differently by the two Env proteins. Therefore, viral strains differ in how their Env proteins can evolve. The parts of Env that showed differences in mutational tolerance between the strains were not necessarily the parts that differ in sequence. This shows that changes in sequence in one part of the protein can modify how other portions evolve.
            It remains to be determined whether changes in tolerance to mutations translate into differences in how the virus can escape immunity. This is an important question given that the rapid evolution of Env is a major obstacle to creating a vaccine for HIV.},
	language = {en},
	urldate = {2022-07-11},
	journal = {eLife},
	author = {Haddox, Hugh K and Dingens, Adam S and Hilton, Sarah K and Overbaugh, Julie and Bloom, Jesse D},
	month = mar,
	year = {2018},
	pages = {e34420},
	file = {Full Text:/Users/admin/Zotero/storage/2JX4KQTR/Haddox et al. - 2018 - Mapping mutational effects along the evolutionary .pdf:application/pdf},
}

@article{stiffler_evolvability_2015,
	title = {Evolvability as a {Function} of {Purifying} {Selection} in {TEM}-1 Beta-{Lactamase}},
	volume = {160},
	issn = {00928674},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0092867415000781},
	doi = {10.1016/j.cell.2015.01.035},
	language = {en},
	number = {5},
	urldate = {2022-07-11},
	journal = {Cell},
	author = {Stiffler, Michael A. and Hekstra, Doeke R. and Ranganathan, Rama},
	month = feb,
	year = {2015},
	pages = {882--892},
	file = {Full Text:/Users/admin/Zotero/storage/D95TSRL8/Stiffler et al. - 2015 - Evolvability as a Function of Purifying Selection .pdf:application/pdf},
}

@article{tripathi_molecular_2016,
	title = {Molecular {Determinants} of {Mutant} {Phenotypes}, {Inferred} from {Saturation} {Mutagenesis} {Data}},
	volume = {33},
	issn = {0737-4038, 1537-1719},
	url = {https://academic.oup.com/mbe/article-lookup/doi/10.1093/molbev/msw182},
	doi = {10.1093/molbev/msw182},
	language = {en},
	number = {11},
	urldate = {2022-07-11},
	journal = {Molecular Biology and Evolution},
	author = {Tripathi, Arti and Gupta, Kritika and Khare, Shruti and Jain, Pankaj C. and Patel, Siddharth and Kumar, Prasanth and Pulianmackal, Ajai J. and Aghera, Nilesh and Varadarajan, Raghavan},
	month = nov,
	year = {2016},
	pages = {2960--2975},
	file = {Full Text:/Users/admin/Zotero/storage/UFKDKVYH/Tripathi et al. - 2016 - Molecular Determinants of Mutant Phenotypes, Infer.pdf:application/pdf},
}

@article{findlay_accurate_2018,
	title = {Accurate classification of {BRCA1} variants with saturation genome editing},
	volume = {562},
	issn = {0028-0836, 1476-4687},
	url = {http://www.nature.com/articles/s41586-018-0461-z},
	doi = {10.1038/s41586-018-0461-z},
	language = {en},
	number = {7726},
	urldate = {2022-07-11},
	journal = {Nature},
	author = {Findlay, Gregory M. and Daza, Riza M. and Martin, Beth and Zhang, Melissa D. and Leith, Anh P. and Gasperini, Molly and Janizek, Joseph D. and Huang, Xingfan and Starita, Lea M. and Shendure, Jay},
	month = oct,
	year = {2018},
	pages = {217--222},
	file = {Accepted Version:/Users/admin/Zotero/storage/QFJF3L2Y/Findlay et al. - 2018 - Accurate classification of BRCA1 variants with sat.pdf:application/pdf},
}

@article{lee_deep_2018,
	title = {Deep mutational scanning of hemagglutinin helps predict evolutionary fates of human {H3N2} influenza variants},
	volume = {115},
	issn = {0027-8424, 1091-6490},
	url = {https://pnas.org/doi/full/10.1073/pnas.1806133115},
	doi = {10.1073/pnas.1806133115},
	abstract = {Significance
            A key goal in the study of influenza virus evolution is to forecast which viral strains will persist and which ones will die out. Here we experimentally measure the effects of all amino acid mutations to the hemagglutinin protein from a human H3N2 influenza strain on viral growth in cell culture. We show that these measurements have utility for distinguishing among viral strains that do and do not succeed in nature. Overall, our work suggests that new high-throughput experimental approaches may be useful for understanding virus evolution in nature.
          , 
            Human influenza virus rapidly accumulates mutations in its major surface protein hemagglutinin (HA). The evolutionary success of influenza virus lineages depends on how these mutations affect HA’s functionality and antigenicity. Here we experimentally measure the effects on viral growth in cell culture of all single amino acid mutations to the HA from a recent human H3N2 influenza virus strain. We show that mutations that are measured to be more favorable for viral growth are enriched in evolutionarily successful H3N2 viral lineages relative to mutations that are measured to be less favorable for viral growth. Therefore, despite the well-known caveats about cell-culture measurements of viral fitness, such measurements can still be informative for understanding evolution in nature. We also compare our measurements for H3 HA to similar data previously generated for a distantly related H1 HA and find substantial differences in which amino acids are preferred at many sites. For instance, the H3 HA has less disparity in mutational tolerance between the head and stalk domains than the H1 HA. Overall, our work suggests that experimental measurements of mutational effects can be leveraged to help understand the evolutionary fates of viral lineages in nature—but only when the measurements are made on a viral strain similar to the ones being studied in nature.},
	language = {en},
	number = {35},
	urldate = {2022-07-11},
	journal = {Proceedings of the National Academy of Sciences},
	author = {Lee, Juhye M. and Huddleston, John and Doud, Michael B. and Hooper, Kathryn A. and Wu, Nicholas C. and Bedford, Trevor and Bloom, Jesse D.},
	month = aug,
	year = {2018},
	file = {Full Text:/Users/admin/Zotero/storage/HG3QHAPN/Lee et al. - 2018 - Deep mutational scanning of hemagglutinin helps pr.pdf:application/pdf},
}

@article{weile_framework_2017,
	title = {A framework for exhaustively mapping functional missense variants},
	volume = {13},
	issn = {1744-4292, 1744-4292},
	url = {https://onlinelibrary.wiley.com/doi/10.15252/msb.20177908},
	doi = {10.15252/msb.20177908},
	language = {en},
	number = {12},
	urldate = {2022-07-11},
	journal = {Molecular Systems Biology},
	author = {Weile, Jochen and Sun, Song and Cote, Atina G and Knapp, Jennifer and Verby, Marta and Mellor, Joseph C and Wu, Yingzhou and Pons, Carles and Wong, Cassandra and Lieshout, Natascha and Yang, Fan and Tasan, Murat and Tan, Guihong and Yang, Shan and Fowler, Douglas M and Nussbaum, Robert and Bloom, Jesse D and Vidal, Marc and Hill, David E and Aloy, Patrick and Roth, Frederick P},
	month = dec,
	year = {2017},
	pages = {957},
	file = {Full Text:/Users/admin/Zotero/storage/YYUXTHFT/Weile et al. - 2017 - A framework for exhaustively mapping functional mi.pdf:application/pdf;Full Text:/Users/admin/Zotero/storage/HCRUH6RQ/Weile et al. - 2017 - A framework for exhaustively mapping functional mi.pdf:application/pdf},
}

@article{qi_quantitative_2014,
	title = {A {Quantitative} {High}-{Resolution} {Genetic} {Profile} {Rapidly} {Identifies} {Sequence} {Determinants} of {Hepatitis} {C} {Viral} {Fitness} and {Drug} {Sensitivity}},
	volume = {10},
	issn = {1553-7374},
	url = {https://dx.plos.org/10.1371/journal.ppat.1004064},
	doi = {10.1371/journal.ppat.1004064},
	language = {en},
	number = {4},
	urldate = {2022-07-11},
	journal = {PLoS Pathogens},
	author = {Qi, Hangfei and Olson, C. Anders and Wu, Nicholas C. and Ke, Ruian and Loverdo, Claude and Chu, Virginia and Truong, Shawna and Remenyi, Roland and Chen, Zugen and Du, Yushen and Su, Sheng-Yao and Al-Mawsawi, Laith Q. and Wu, Ting-Ting and Chen, Shu-Hua and Lin, Chung-Yen and Zhong, Weidong and Lloyd-Smith, James O. and Sun, Ren},
	editor = {Wilke, Claus O.},
	month = apr,
	year = {2014},
	pages = {e1004064},
	file = {Full Text:/Users/admin/Zotero/storage/ZXNH72PK/Qi et al. - 2014 - A Quantitative High-Resolution Genetic Profile Rap.pdf:application/pdf},
}

@article{chan_correlation_2017,
	title = {Correlation of fitness landscapes from three orthologous {TIM} barrels originates from sequence and structure constraints},
	volume = {8},
	issn = {2041-1723},
	url = {http://www.nature.com/articles/ncomms14614},
	doi = {10.1038/ncomms14614},
	language = {en},
	number = {1},
	urldate = {2022-07-11},
	journal = {Nature Communications},
	author = {Chan, Yvonne H. and Venev, Sergey V. and Zeldovich, Konstantin B. and Matthews, C. Robert},
	month = apr,
	year = {2017},
	pages = {14614},
	file = {Full Text:/Users/admin/Zotero/storage/A6E42JVX/Chan et al. - 2017 - Correlation of fitness landscapes from three ortho.pdf:application/pdf},
}

@article{melnikov_comprehensive_2014,
	title = {Comprehensive mutational scanning of a kinase \textit{in vivo} reveals substrate-dependent fitness landscapes},
	volume = {42},
	issn = {0305-1048, 1362-4962},
	url = {https://academic.oup.com/nar/article-lookup/doi/10.1093/nar/gku511},
	doi = {10.1093/nar/gku511},
	language = {en},
	number = {14},
	urldate = {2022-07-11},
	journal = {Nucleic Acids Research},
	author = {Melnikov, Alexandre and Rogov, Peter and Wang, Li and Gnirke, Andreas and Mikkelsen, Tarjei S.},
	month = aug,
	year = {2014},
	pages = {e112--e112},
	file = {Full Text:/Users/admin/Zotero/storage/U454BG33/Melnikov et al. - 2014 - Comprehensive mutational scanning of a kinase i.pdf:application/pdf},
}

@article{nutschel_systematically_2020,
	title = {Systematically {Scrutinizing} the {Impact} of {Substitution} {Sites} on {Thermostability} and {Detergent} {Tolerance} for \textit{{Bacillus} subtilis} {Lipase} {A}},
	volume = {60},
	issn = {1549-9596, 1549-960X},
	url = {https://pubs.acs.org/doi/10.1021/acs.jcim.9b00954},
	doi = {10.1021/acs.jcim.9b00954},
	language = {en},
	number = {3},
	urldate = {2022-07-11},
	journal = {Journal of Chemical Information and Modeling},
	author = {Nutschel, Christina and Fulton, Alexander and Zimmermann, Olav and Schwaneberg, Ulrich and Jaeger, Karl-Erich and Gohlke, Holger},
	month = mar,
	year = {2020},
	pages = {1568--1584},
}

@article{jacquier_capturing_2013,
	title = {Capturing the mutational landscape of the beta-lactamase {TEM}-1},
	volume = {110},
	issn = {0027-8424, 1091-6490},
	url = {https://pnas.org/doi/full/10.1073/pnas.1215206110},
	doi = {10.1073/pnas.1215206110},
	abstract = {Adaptation proceeds through the selection of mutations. The distribution of mutant fitness effect and the forces shaping this distribution are therefore keys to predict the evolutionary fate of organisms and their constituents such as enzymes. Here, by producing and sequencing a comprehensive collection of 10,000 mutants, we explore the mutational landscape of one enzyme involved in the spread of antibiotic resistance, the beta-lactamase TEM-1. We measured mutation impact on the enzyme activity through the estimation of amoxicillin minimum inhibitory concentration on a subset of 990 mutants carrying a unique missense mutation, representing 64\% of possible amino acid changes in that protein reachable by point mutation. We established that mutation type, solvent accessibility of residues, and the predicted effect of mutations on protein stability primarily determined alone or in combination changes in minimum inhibitory concentration of mutants. Moreover, we were able to capture the drastic modification of the mutational landscape induced by a single stabilizing point mutation (M182T) by a simple model of protein stability. This work thereby provides an integrated framework to study mutation effects and a tool to understand/define better the epistatic interactions.},
	language = {en},
	number = {32},
	urldate = {2022-07-11},
	journal = {Proceedings of the National Academy of Sciences},
	author = {Jacquier, Hervé and Birgy, André and Le Nagard, Hervé and Mechulam, Yves and Schmitt, Emmanuelle and Glodt, Jérémy and Bercot, Beatrice and Petit, Emmanuelle and Poulain, Julie and Barnaud, Guilène and Gros, Pierre-Alexis and Tenaillon, Olivier},
	month = aug,
	year = {2013},
	pages = {13067--13072},
	file = {Full Text:/Users/admin/Zotero/storage/KCXP8PUL/Jacquier et al. - 2013 - Capturing the mutational landscape of the beta-lac.pdf:application/pdf},
}

@article{mishra_systematic_2016,
	title = {Systematic {Mutant} {Analyses} {Elucidate} {General} and {Client}-{Specific} {Aspects} of {Hsp90} {Function}},
	volume = {15},
	issn = {22111247},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S2211124716303175},
	doi = {10.1016/j.celrep.2016.03.046},
	language = {en},
	number = {3},
	urldate = {2022-07-11},
	journal = {Cell Reports},
	author = {Mishra, Parul and Flynn, Julia M. and Starr, Tyler N. and Bolon, Daniel N.A.},
	month = apr,
	year = {2016},
	pages = {588--598},
	file = {Full Text:/Users/admin/Zotero/storage/N3VLLXTY/Mishra et al. - 2016 - Systematic Mutant Analyses Elucidate General and C.pdf:application/pdf},
}

@article{pokusaeva_experimental_2019,
	title = {An experimental assay of the interactions of amino acids from orthologous sequences shaping a complex fitness landscape},
	volume = {15},
	issn = {1553-7404},
	url = {https://dx.plos.org/10.1371/journal.pgen.1008079},
	doi = {10.1371/journal.pgen.1008079},
	language = {en},
	number = {4},
	urldate = {2022-07-11},
	journal = {PLOS Genetics},
	author = {Pokusaeva, Victoria O. and Usmanova, Dinara R. and Putintseva, Ekaterina V. and Espinar, Lorena and Sarkisyan, Karen S. and Mishin, Alexander S. and Bogatyreva, Natalya S. and Ivankov, Dmitry N. and Akopyan, Arseniy V. and Avvakumov, Sergey Ya. and Povolotskaya, Inna S. and Filion, Guillaume J. and Carey, Lucas B. and Kondrashov, Fyodor A.},
	editor = {Petrov, Dmitri A.},
	month = apr,
	year = {2019},
	pages = {e1008079},
	file = {Full Text:/Users/admin/Zotero/storage/39VZ7AQN/Pokusaeva et al. - 2019 - An experimental assay of the interactions of amino.pdf:application/pdf},
}

@article{fernandes_functional_2016,
	title = {Functional {Segregation} of {Overlapping} {Genes} in {HIV}},
	volume = {167},
	issn = {00928674},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0092867416316038},
	doi = {10.1016/j.cell.2016.11.031},
	language = {en},
	number = {7},
	urldate = {2022-07-11},
	journal = {Cell},
	author = {Fernandes, Jason D. and Faust, Tyler B. and Strauli, Nicolas B. and Smith, Cynthia and Crosby, David C. and Nakamura, Robert L. and Hernandez, Ryan D. and Frankel, Alan D.},
	month = dec,
	year = {2016},
	pages = {1762--1773.e12},
	file = {Full Text:/Users/admin/Zotero/storage/M2JCUQLM/Fernandes et al. - 2016 - Functional Segregation of Overlapping Genes in HIV.pdf:application/pdf},
}

@techreport{sinai_generative_2021,
	type = {preprint},
	title = {Generative {AAV} capsid diversification by latent interpolation},
	url = {http://biorxiv.org/lookup/doi/10.1101/2021.04.16.440236},
	abstract = {Summary
          Adeno-associated virus (AAV) capsids have shown clinical promise as delivery vectors for gene therapy. However, the high prevalence of pre-existing immunity against natural capsids poses a challenge for widespread treatment. The generation of diverse capsids that are potentially more capable of immune evasion is challenging because introducing multiple mutations often breaks capsid assembly. Here we target a representative, immunologically relevant 28-amino-acid segment of the AAV2 capsid and show that a low-complexity Variational Auto-encoder (VAE) can interpolate in sequence space to produce diverse and novel capsids capable of packaging their own genomes. We first train the VAE on a 564-sample Multiple-Sequence Alignment (MSA) of dependo-parvoviruses, and then further augment this dataset by adding 22,704 samples from a deep mutational exploration (DME) on the target region. In both cases the VAE generated viable variants with many mutations, which we validated experimentally. We propose that this simple approach can be used to optimize and diversify other proteins, as well as other capsid traits of interest for gene delivery.},
	language = {en},
	urldate = {2022-07-11},
	institution = {Synthetic Biology},
	author = {Sinai, Sam and Jain, Nina and Church, George M and Kelsic, Eric D},
	month = apr,
	year = {2021},
	doi = {10.1101/2021.04.16.440236},
	file = {Submitted Version:/Users/admin/Zotero/storage/TEMTVFT7/Sinai et al. - 2021 - Generative AAV capsid diversification by latent in.pdf:application/pdf},
}

@article{wu_functional_2015,
	title = {Functional {Constraint} {Profiling} of a {Viral} {Protein} {Reveals} {Discordance} of {Evolutionary} {Conservation} and {Functionality}},
	volume = {11},
	issn = {1553-7404},
	url = {https://dx.plos.org/10.1371/journal.pgen.1005310},
	doi = {10.1371/journal.pgen.1005310},
	language = {en},
	number = {7},
	urldate = {2022-07-11},
	journal = {PLOS Genetics},
	author = {Wu, Nicholas C. and Olson, C. Anders and Du, Yushen and Le, Shuai and Tran, Kevin and Remenyi, Roland and Gong, Danyang and Al-Mawsawi, Laith Q. and Qi, Hangfei and Wu, Ting-Ting and Sun, Ren},
	editor = {Worobey, Michael},
	month = jul,
	year = {2015},
	pages = {e1005310},
	file = {Full Text:/Users/admin/Zotero/storage/NNQX65KR/Wu et al. - 2015 - Functional Constraint Profiling of a Viral Protein.pdf:application/pdf},
}

@article{matreyek_integrating_2021,
	title = {Integrating thousands of {PTEN} variant activity and abundance measurements reveals variant subgroups and new dominant negatives in cancers},
	volume = {13},
	issn = {1756-994X},
	url = {https://genomemedicine.biomedcentral.com/articles/10.1186/s13073-021-00984-x},
	doi = {10.1186/s13073-021-00984-x},
	abstract = {Abstract
            
              Background
              PTEN is a multi-functional tumor suppressor protein regulating cell growth, immune signaling, neuronal function, and genome stability. Experimental characterization can help guide the clinical interpretation of the thousands of germline or somatic PTEN variants observed in patients. Two large-scale mutational datasets, one for PTEN variant intracellular abundance encompassing 4112 missense variants and one for lipid phosphatase activity encompassing 7244 variants, were recently published. The combined information from these datasets can reveal variant-specific phenotypes that may underlie various clinical presentations, but this has not been comprehensively examined, particularly for somatic PTEN variants observed in cancers.
            
            
              Methods
              Here, we add to these efforts by measuring the intracellular abundance of 764 new PTEN variants and refining abundance measurements for 3351 previously studied variants. We use this expanded and refined PTEN abundance dataset to explore the mutational patterns governing PTEN intracellular abundance, and then incorporate the phosphatase activity data to subdivide PTEN variants into four functionally distinct groups.
            
            
              Results
              This analysis revealed a set of highly abundant but lipid phosphatase defective variants that could act in a dominant-negative fashion to suppress PTEN activity. Two of these variants were, indeed, capable of dysregulating Akt signaling in cells harboring a WT PTEN allele. Both variants were observed in multiple breast or uterine tumors, demonstrating the disease relevance of these high abundance, inactive variants.
            
            
              Conclusions
              We show that multidimensional, large-scale variant functional data, when paired with public cancer genomics datasets and follow-up assays, can improve understanding of uncharacterized cancer-associated variants, and provide better insights into how they contribute to oncogenesis.},
	language = {en},
	number = {1},
	urldate = {2022-07-11},
	journal = {Genome Medicine},
	author = {Matreyek, Kenneth A. and Stephany, Jason J. and Ahler, Ethan and Fowler, Douglas M.},
	month = dec,
	year = {2021},
	pages = {165},
	file = {Full Text:/Users/admin/Zotero/storage/8VXIZT8Q/Matreyek et al. - 2021 - Integrating thousands of PTEN variant activity and.pdf:application/pdf},
}

@article{mighell_saturation_2018,
	title = {A {Saturation} {Mutagenesis} {Approach} to {Understanding} {PTEN} {Lipid} {Phosphatase} {Activity} and {Genotype}-{Phenotype} {Relationships}},
	volume = {102},
	issn = {00029297},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0002929718301071},
	doi = {10.1016/j.ajhg.2018.03.018},
	language = {en},
	number = {5},
	urldate = {2023-06-14},
	journal = {The American Journal of Human Genetics},
	author = {Mighell, Taylor L. and Evans-Dutson, Sara and O’Roak, Brian J.},
	month = may,
	year = {2018},
	pages = {943--955},
	file = {Full Text:/Users/admin/Zotero/storage/9UEQ49C4/Mighell et al. - 2018 - A Saturation Mutagenesis Approach to Understanding.pdf:application/pdf},
}

@article{russ_evolution-based_2020,
	title = {An evolution-based model for designing chorismate mutase enzymes},
	volume = {369},
	issn = {0036-8075, 1095-9203},
	url = {https://www.sciencemag.org/lookup/doi/10.1126/science.aba3304},
	doi = {10.1126/science.aba3304},
	abstract = {The rational design of enzymes is an important goal for both fundamental and practical reasons. Here, we describe a process to learn the constraints for specifying proteins purely from evolutionary sequence data, design and build libraries of synthetic genes, and test them for activity in vivo using a quantitative complementation assay. For chorismate mutase, a key enzyme in the biosynthesis of aromatic amino acids, we demonstrate the design of natural-like catalytic function with substantial sequence diversity. Further optimization focuses the generative model toward function in a specific genomic context. The data show that sequence-based statistical models suffice to specify proteins and provide access to an enormous space of functional sequences. This result provides a foundation for a general process for evolution-based design of artificial proteins.},
	language = {en},
	number = {6502},
	urldate = {2023-06-14},
	journal = {Science},
	author = {Russ, William P. and Figliuzzi, Matteo and Stocker, Christian and Barrat-Charlaix, Pierre and Socolich, Michael and Kast, Peter and Hilvert, Donald and Monasson, Remi and Cocco, Simona and Weigt, Martin and Ranganathan, Rama},
	month = jul,
	year = {2020},
	pages = {440--445},
}

@article{gonzalez_fitness_2019,
	title = {Fitness {Effects} of {Single} {Amino} {Acid} {Insertions} and {Deletions} in {TEM}-1 Beta-{Lactamase}},
	volume = {431},
	issn = {00222836},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0022283619302372},
	doi = {10.1016/j.jmb.2019.04.030},
	language = {en},
	number = {12},
	urldate = {2023-06-14},
	journal = {Journal of Molecular Biology},
	author = {Gonzalez, Courtney E. and Roberts, Paul and Ostermeier, Marc},
	month = may,
	year = {2019},
	pages = {2320--2330},
	file = {Accepted Version:/Users/admin/Zotero/storage/ZWGQXGBD/Gonzalez et al. - 2019 - Fitness Effects of Single Amino Acid Insertions an.pdf:application/pdf},
}

@article{macdonald_dimple_2023,
	title = {{DIMPLE}: deep insertion, deletion, and missense mutation libraries for exploring protein variation in evolution, disease, and biology},
	volume = {24},
	issn = {1474-760X},
	shorttitle = {{DIMPLE}},
	url = {https://genomebiology.biomedcentral.com/articles/10.1186/s13059-023-02880-6},
	doi = {10.1186/s13059-023-02880-6},
	abstract = {Abstract
            Insertions and deletions (indels) enable evolution and cause disease. Due to technical challenges, indels are left out of most mutational scans, limiting our understanding of them in disease, biology, and evolution. We develop a low cost and bias method, DIMPLE, for systematically generating deletions, insertions, and missense mutations in genes, which we test on a range of targets, including Kir2.1. We use DIMPLE to study how indels impact potassium channel structure, disease, and evolution. We find deletions are most disruptive overall, beta sheets are most sensitive to indels, and flexible loops are sensitive to deletions yet tolerate insertions.},
	language = {en},
	number = {1},
	urldate = {2023-06-14},
	journal = {Genome Biology},
	author = {Macdonald, Christian B. and Nedrud, David and Grimes, Patrick Rockefeller and Trinidad, Donovan and Fraser, James S. and Coyote-Maestas, Willow},
	month = feb,
	year = {2023},
	pages = {36},
	file = {Full Text:/Users/admin/Zotero/storage/3MMXFUJ4/Macdonald et al. - 2023 - DIMPLE deep insertion, deletion, and missense mut.pdf:application/pdf},
}

@article{jones_structural_2020,
	title = {Structural and functional characterization of {G} protein–coupled receptors with deep mutational scanning},
	volume = {9},
	issn = {2050-084X},
	url = {https://elifesciences.org/articles/54895},
	doi = {10.7554/eLife.54895},
	abstract = {The {\textgreater}800 human G protein–coupled receptors (GPCRs) are responsible for transducing diverse chemical stimuli to alter cell state- and are the largest class of drug targets. Their myriad structural conformations and various modes of signaling make it challenging to understand their structure and function. Here, we developed a platform to characterize large libraries of GPCR variants in human cell lines with a barcoded transcriptional reporter of G protein signal transduction. We tested 7800 of 7828 possible single amino acid substitutions to the beta-2 adrenergic receptor (Beta
              2
              AR) at four concentrations of the agonist isoproterenol. We identified residues specifically important for Beta
              2
              AR signaling, mutations in the human population that are potentially loss of function, and residues that modulate basal activity. Using unsupervised learning, we identify residues critical for signaling, including all major structural motifs and molecular interfaces. We also find a previously uncharacterized structural latch spanning the first two extracellular loops that is highly conserved across Class A GPCRs and is conformationally rigid in both the inactive and active states of the receptor. More broadly, by linking deep mutational scanning with engineered transcriptional reporters, we establish a generalizable method for exploring pharmacogenomics, structure and function across broad classes of drug receptors.},
	language = {en},
	urldate = {2023-06-14},
	journal = {eLife},
	author = {Jones, Eric M and Lubock, Nathan B and Venkatakrishnan, Aj and Wang, Jeffrey and Tseng, Alex M and Paggi, Joseph M and Latorraca, Naomi R and Cancilla, Daniel and Satyadi, Megan and Davis, Jessica E and Babu, M Madan and Dror, Ron O and Kosuri, Sriram},
	month = oct,
	year = {2020},
	pages = {e54895},
	file = {Full Text:/Users/admin/Zotero/storage/T2SD9K3D/Jones et al. - 2020 - Structural and functional characterization of G pr.pdf:application/pdf;Submitted Version:/Users/admin/Zotero/storage/WYWCXHH9/Jones et al. - 2020 - Structural and functional characterization of G pr.pdf:application/pdf},
}

@article{chen_comprehensive_2020,
	title = {Comprehensive exploration of the translocation, stability and substrate recognition requirements in {VIM}-2 lactamase},
	volume = {9},
	issn = {2050-084X},
	url = {https://elifesciences.org/articles/56707},
	doi = {10.7554/eLife.56707},
	abstract = {Metallo-Beta-lactamases (MBLs) degrade a broad spectrum of Beta-lactam antibiotics, and are a major disseminating source for multidrug resistant bacteria. Despite many biochemical studies in diverse MBLs, molecular understanding of the roles of residues in the enzyme’s stability and function, and especially substrate specificity, is lacking. Here, we employ deep mutational scanning (DMS) to generate comprehensive single amino acid variant data on a major clinical MBL, VIM-2, by measuring the effect of thousands of VIM-2 mutants on the degradation of three representative classes of Beta-lactams (ampicillin, cefotaxime, and meropenem) and at two different temperatures (25°C and 37°C). We revealed residues responsible for expression and translocation, and mutations that increase resistance and/or alter substrate specificity. The distribution of specificity-altering mutations unveiled distinct molecular recognition of the three substrates. Moreover, these function-altering mutations are frequently observed among naturally occurring variants, suggesting that the enzymes have continuously evolved to become more potent resistance genes.},
	language = {en},
	urldate = {2023-06-14},
	journal = {eLife},
	author = {Chen, John Z and Fowler, Douglas M and Tokuriki, Nobuhiko},
	month = jun,
	year = {2020},
	pages = {e56707},
	file = {Full Text:/Users/admin/Zotero/storage/LBP8NZRP/Chen et al. - 2020 - Comprehensive exploration of the translocation, st.pdf:application/pdf},
}

@article{kennouche_deep_2019,
	title = {Deep mutational scanning of the \textit{{Neisseria} meningitidis} major pilin reveals the importance of pilus tip‐mediated adhesion},
	volume = {38},
	issn = {0261-4189, 1460-2075},
	url = {https://www.embopress.org/doi/10.15252/embj.2019102145},
	doi = {10.15252/embj.2019102145},
	language = {en},
	number = {22},
	urldate = {2023-06-14},
	journal = {The EMBO Journal},
	author = {Kennouche, Paul and Charles‐Orszag, Arthur and Nishiguchi, Daiki and Goussard, Sylvie and Imhaus, Anne‐Flore and Dupré, Mathieu and Chamot‐Rooke, Julia and Duménil, Guillaume},
	month = nov,
	year = {2019},
	pages = {e102145},
	file = {Full Text:/Users/admin/Zotero/storage/K9LIAMBH/Kennouche et al. - 2019 - Deep mutational scanning of the Neisseria menin.pdf:application/pdf;Submitted Version:/Users/admin/Zotero/storage/9587BW8A/Kennouche et al. - 2019 - Deep mutational scanning of the Neisseria menin.pdf:application/pdf},
}

@article{haddox_experimental_2016,
	title = {Experimental {Estimation} of the {Effects} of {All} {Amino}-{Acid} {Mutations} to {HIV}’s {Envelope} {Protein} on {Viral} {Replication} in {Cell} {Culture}},
	volume = {12},
	issn = {1553-7374},
	url = {https://dx.plos.org/10.1371/journal.ppat.1006114},
	doi = {10.1371/journal.ppat.1006114},
	language = {en},
	number = {12},
	urldate = {2023-06-14},
	journal = {PLOS Pathogens},
	author = {Haddox, Hugh K. and Dingens, Adam S. and Bloom, Jesse D.},
	editor = {Swanstrom, Ronald},
	month = dec,
	year = {2016},
	pages = {e1006114},
	file = {Full Text:/Users/admin/Zotero/storage/MJ2VVEBN/Haddox et al. - 2016 - Experimental Estimation of the Effects of All Amin.pdf:application/pdf},
}

@article{roscoe_systematic_2014,
	title = {Systematic {Exploration} of {Ubiquitin} {Sequence}, {E1} {Activation} {Efficiency}, and {Experimental} {Fitness} in {Yeast}},
	volume = {426},
	issn = {00222836},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0022283614002587},
	doi = {10.1016/j.jmb.2014.05.019},
	language = {en},
	number = {15},
	urldate = {2023-06-14},
	journal = {Journal of Molecular Biology},
	author = {Roscoe, Benjamin P. and Bolon, Daniel N.A.},
	month = jul,
	year = {2014},
	pages = {2854--2870},
	file = {Accepted Version:/Users/admin/Zotero/storage/ZZGGND7E/Roscoe and Bolon - 2014 - Systematic Exploration of Ubiquitin Sequence, E1 A.pdf:application/pdf},
}

@article{klesmith_comprehensive_2015,
	title = {Comprehensive {Sequence}-{Flux} {Mapping} of a {Levoglucosan} {Utilization} {Pathway} in \textit{{E}. coli}},
	volume = {4},
	issn = {2161-5063, 2161-5063},
	url = {https://pubs.acs.org/doi/10.1021/acssynbio.5b00131},
	doi = {10.1021/acssynbio.5b00131},
	language = {en},
	number = {11},
	urldate = {2023-06-14},
	journal = {ACS Synthetic Biology},
	author = {Klesmith, Justin R. and Bacik, John-Paul and Michalczyk, Ryszard and Whitehead, Timothy A.},
	month = nov,
	year = {2015},
	pages = {1235--1243},
	file = {Submitted Version:/Users/admin/Zotero/storage/EPYWRHC2/Klesmith et al. - 2015 - Comprehensive Sequence-Flux Mapping of a Levogluco.pdf:application/pdf},
}

@article{gonzalez_somermeyer_heterogeneity_2022,
	title = {Heterogeneity of the {GFP} fitness landscape and data-driven protein design},
	volume = {11},
	issn = {2050-084X},
	url = {https://elifesciences.org/articles/75842},
	doi = {10.7554/eLife.75842},
	abstract = {Studies of protein fitness landscapes reveal biophysical constraints guiding protein evolution and empower prediction of functional proteins. However, generalisation of these findings is limited due to scarceness of systematic data on fitness landscapes of proteins with a defined evolutionary relationship. We characterized the fitness peaks of four orthologous fluorescent proteins with a broad range of sequence divergence. While two of the four studied fitness peaks were sharp, the other two were considerably flatter, being almost entirely free of epistatic interactions. Mutationally robust proteins, characterized by a flat fitness peak, were not optimal templates for machine-learning-driven protein design – instead, predictions were more accurate for fragile proteins with epistatic landscapes. Our work paves insights for practical application of fitness landscape heterogeneity in protein engineering.},
	language = {en},
	urldate = {2023-06-14},
	journal = {eLife},
	author = {Gonzalez Somermeyer, Louisa and Fleiss, Aubin and Mishin, Alexander S and Bozhanova, Nina G and Igolkina, Anna A and Meiler, Jens and Alaball Pujol, Maria-Elisenda and Putintseva, Ekaterina V and Sarkisyan, Karen S and Kondrashov, Fyodor A},
	month = may,
	year = {2022},
	pages = {e75842},
	file = {Full Text:/Users/admin/Zotero/storage/N7EZUGF7/Gonzalez Somermeyer et al. - 2022 - Heterogeneity of the GFP fitness landscape and dat.pdf:application/pdf},
}

@article{doud_accurate_2016,
	title = {Accurate {Measurement} of the {Effects} of {All} {Amino}-{Acid} {Mutations} on {Influenza} {Hemagglutinin}},
	volume = {8},
	issn = {1999-4915},
	url = {http://www.mdpi.com/1999-4915/8/6/155},
	doi = {10.3390/v8060155},
	language = {en},
	number = {6},
	urldate = {2023-06-14},
	journal = {Viruses},
	author = {Doud, Michael and Bloom, Jesse},
	month = jun,
	year = {2016},
	pages = {155},
	file = {Full Text:/Users/admin/Zotero/storage/Z3RRFCKV/Doud and Bloom - 2016 - Accurate Measurement of the Effects of All Amino-A.pdf:application/pdf},
}

@article{soh_comprehensive_2019,
	title = {Comprehensive mapping of adaptation of the avian influenza polymerase protein {PB2} to humans},
	volume = {8},
	issn = {2050-084X},
	url = {https://elifesciences.org/articles/45079},
	doi = {10.7554/eLife.45079},
	abstract = {Viruses like influenza are infamous for their ability to adapt to new hosts. Retrospective studies of natural zoonoses and passaging in the lab have identified a modest number of host-adaptive mutations. However, it is unclear if these mutations represent all ways that influenza can adapt to a new host. Here we take a prospective approach to this question by completely mapping amino-acid mutations to the avian influenza virus polymerase protein PB2 that enhance growth in human cells. We identify numerous previously uncharacterized human-adaptive mutations. These mutations cluster on PB2’s surface, highlighting potential interfaces with host factors. Some previously uncharacterized adaptive mutations occur in avian-to-human transmission of H7N9 influenza, showing their importance for natural virus evolution. But other adaptive mutations do not occur in nature because they are inaccessible via single-nucleotide mutations. Overall, our work shows how selection at key molecular surfaces combines with evolutionary accessibility to shape viral host adaptation.
          , 
            Viruses copy themselves by hijacking the cells of an infected host, but this comes with some limitations. Cells from different species have different molecular machinery and so viruses often have to specialize to a narrow group of species. This specialization consists largely of fine-tuning the way that viral proteins interact with host proteins.
            For instance, in bird flu viruses, a protein known as PB2 does not interact well with the machinery in human cells. Because PB2 proteins form part of the viral polymerase (the structure that copies the viral genome), this prevents bird flu viruses from replicating efficiently in humans. Sometimes however, changes in the PB2 protein allow bird flu viruses to better replicate in humans, potentially leading to deadly flu pandemics.
            To understand exactly how this happens, researchers have previously used two approaches: examining the changes that have happened in past flu viruses, and monitoring the evolution of bird flu viruses grown in human cells in the lab. However, these approaches can only look at a small number of the many possible genetic changes to the virus. This makes it hard to anticipate the new ways that flu might adapt to human cells in the future.
            To overcome this problem, Soh et al. systematically created all of the single changes to the bird flu PB2, altering every element of the protein sequence one-by-one. They then tested which of the changes to PB2 helped the virus grow better in human cells. The modifications that made the viruses thrive were on the surface of the protein, suggesting that they might improve interaction with the cell machinery of the host. Some changes have been found in bird flu viruses that have recently jumped into humans in nature, although fortunately none of these viruses have yet spread widely to cause a pandemic.
            Many factors affect the evolution of viruses, and their ability to infect new species. Understanding which changes in proteins help these microbes adapt to new hosts is an important element that scientists could consider to assess future risks of pandemics.},
	language = {en},
	urldate = {2023-06-14},
	journal = {eLife},
	author = {Soh, Yq Shirleen and Moncla, Louise H and Eguia, Rachel and Bedford, Trevor and Bloom, Jesse D},
	month = apr,
	year = {2019},
	pages = {e45079},
	file = {Full Text:/Users/admin/Zotero/storage/U4C4J7MA/Soh et al. - 2019 - Comprehensive mapping of adaptation of the avian i.pdf:application/pdf},
}

@article{seuma_genetic_2021,
	title = {The genetic landscape for amyloid beta fibril nucleation accurately discriminates familial {Alzheimer}’s disease mutations},
	volume = {10},
	issn = {2050-084X},
	url = {https://elifesciences.org/articles/63364},
	doi = {10.7554/eLife.63364},
	abstract = {Plaques of the amyloid beta (Aß) peptide are a pathological hallmark of Alzheimer’s disease (AD), the most common form of dementia. Mutations in Aß also cause familial forms of AD (fAD). Here, we use deep mutational scanning to quantify the effects of {\textgreater}14,000 mutations on the aggregation of Aß. The resulting genetic landscape reveals mechanistic insights into fibril nucleation, including the importance of charge and gatekeeper residues in the disordered region outside of the amyloid core in preventing nucleation. Strikingly, unlike computational predictors and previous measurements, the empirical nucleation scores accurately identify all known dominant fAD mutations in Aß, genetically validating that the mechanism of nucleation in a cell-based assay is likely to be very similar to the mechanism that causes the human disease. These results provide the first comprehensive atlas of how mutations alter the formation of any amyloid fibril and a resource for the interpretation of genetic variation in Aß.
          , 
            Alzheimer’s disease is the most common form of dementia, affecting more than 50 million people worldwide. Despite more than 400 clinical trials, there are still no effective drugs that can prevent or treat the disease. A common target in Alzheimer’s disease trials is a small protein called amyloid beta. Amyloid beta proteins are ‘sticky’ molecules. In the brains of people with Alzheimer’s disease, they join to form first small aggregates and then long chains called fibrils, a process which is toxic to neurons.
            Specific mutations in the gene for amyloid beta are known to cause rare, aggressive forms of Alzheimer’s disease that typically affect people in their fifties or sixties. But these are not the only mutations that can occur in amyloid beta. In principle, any part of the protein could undergo mutation. And given the size of the human population, it is likely that each of these mutations exists in someone alive today.
            Seuma et al. reasoned that studying these mutations could help us understand the process by which amyloid beta forms new aggregates. Using an approach called deep mutational scanning, Seuma et al. mutated each point in the protein, one at a time. This produced more than 14,000 different versions of amyloid beta. Seuma et al. then measured how quickly these mutants were able to form aggregates by introducing them into yeast cells.
            All the mutations known to cause early-onset Alzheimer’s disease accelerated amyloid beta aggregation in the yeast. But the results also revealed previously unknown properties that control how fast aggregation occurs. In addition, they highlighted a number of positions in the amyloid beta sequence that act as ‘gatekeepers’. In healthy brains, these gatekeepers prevent amyloid beta proteins from sticking together. When mutated, they drive the protein to form aggregates.
            This comprehensive dataset will help researchers understand how proteins form toxic aggregates, which could in turn help them find ways to prevent this from happening. By providing an ‘atlas’ of all possible amyloid beta mutations, the dataset will also help clinicians interpret any new mutations they encounter in patients. By showing whether or not a mutation speeds up aggregation, the atlas will help clinicians predict whether that mutation increases the risk of Alzheimer’s disease.},
	language = {en},
	urldate = {2023-06-14},
	journal = {eLife},
	author = {Seuma, Mireia and Faure, Andre J and Badia, Marta and Lehner, Ben and Bolognesi, Benedetta},
	month = feb,
	year = {2021},
	pages = {e63364},
	file = {Full Text:/Users/admin/Zotero/storage/8WFU6TK4/Seuma et al. - 2021 - The genetic landscape for amyloid beta fibril nucl.pdf:application/pdf},
}

@article{dandage_differential_2018,
	title = {Differential strengths of molecular determinants guide environment specific mutational fates},
	volume = {14},
	issn = {1553-7404},
	url = {https://dx.plos.org/10.1371/journal.pgen.1007419},
	doi = {10.1371/journal.pgen.1007419},
	language = {en},
	number = {5},
	urldate = {2023-06-14},
	journal = {PLOS Genetics},
	author = {Dandage, Rohan and Pandey, Rajesh and Jayaraj, Gopal and Rai, Manish and Berger, David and Chakraborty, Kausik},
	editor = {Matic, Ivan},
	month = may,
	year = {2018},
	pages = {e1007419},
	file = {Full Text:/Users/admin/Zotero/storage/GELATYV7/Dandage et al. - 2018 - Differential strengths of molecular determinants g.pdf:application/pdf},
}

@article{firnberg_comprehensive_2014,
	title = {A {Comprehensive}, {High}-{Resolution} {Map} of a {Gene}’s {Fitness} {Landscape}},
	volume = {31},
	issn = {1537-1719, 0737-4038},
	url = {https://academic.oup.com/mbe/article-lookup/doi/10.1093/molbev/msu081},
	doi = {10.1093/molbev/msu081},
	language = {en},
	number = {6},
	urldate = {2023-06-14},
	journal = {Molecular Biology and Evolution},
	author = {Firnberg, Elad and Labonte, Jason W. and Gray, Jeffrey J. and Ostermeier, Marc},
	month = jun,
	year = {2014},
	pages = {1581--1592},
	file = {Full Text:/Users/admin/Zotero/storage/9TTFDAL5/Firnberg et al. - 2014 - A Comprehensive, High-Resolution Map of a Gene’s F.pdf:application/pdf},
}

@article{adkar_protein_2012,
	title = {Protein {Model} {Discrimination} {Using} {Mutational} {Sensitivity} {Derived} from {Deep} {Sequencing}},
	volume = {20},
	issn = {09692126},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0969212612000068},
	doi = {10.1016/j.str.2011.11.021},
	language = {en},
	number = {2},
	urldate = {2023-06-14},
	journal = {Structure},
	author = {Adkar, Bharat V. and Tripathi, Arti and Sahoo, Anusmita and Bajaj, Kanika and Goswami, Devrishi and Chakrabarti, Purbani and Swarnkar, Mohit K. and Gokhale, Rajesh S. and Varadarajan, Raghavan},
	month = feb,
	year = {2012},
	pages = {371--381},
	file = {Full Text:/Users/admin/Zotero/storage/TIV665XI/Adkar et al. - 2012 - Protein Model Discrimination Using Mutational Sens.pdf:application/pdf},
}

@article{giacomelli_mutational_2018,
	title = {Mutational processes shape the landscape of {TP53} mutations in human cancer},
	volume = {50},
	issn = {1061-4036, 1546-1718},
	url = {https://www.nature.com/articles/s41588-018-0204-y},
	doi = {10.1038/s41588-018-0204-y},
	language = {en},
	number = {10},
	urldate = {2023-06-14},
	journal = {Nature Genetics},
	author = {Giacomelli, Andrew O. and Yang, Xiaoping and Lintner, Robert E. and McFarland, James M. and Duby, Marc and Kim, Jaegil and Howard, Thomas P. and Takeda, David Y. and Ly, Seav Huong and Kim, Eejung and Gannon, Hugh S. and Hurhula, Brian and Sharpe, Ted and Goodale, Amy and Fritchman, Briana and Steelman, Scott and Vazquez, Francisca and Tsherniak, Aviad and Aguirre, Andrew J. and Doench, John G. and Piccioni, Federica and Roberts, Charles W. M. and Meyerson, Matthew and Getz, Gad and Johannessen, Cory M. and Root, David E. and Hahn, William C.},
	month = oct,
	year = {2018},
	pages = {1381--1387},
	file = {Accepted Version:/Users/admin/Zotero/storage/EFU93FB6/Giacomelli et al. - 2018 - Mutational processes shape the landscape of TP53 m.pdf:application/pdf},
}

@article{suiter_massively_2020,
	title = {Massively parallel variant characterization identifies \textit{{NUDT15}} alleles associated with thiopurine toxicity},
	volume = {117},
	issn = {0027-8424, 1091-6490},
	url = {https://pnas.org/doi/full/10.1073/pnas.1915680117},
	doi = {10.1073/pnas.1915680117},
	abstract = {Significance
            
              Pharmacogenetics is a prototype of genomics-guided precision medicine. While there is a rapid expansion of novel pharmacogenetic variants discovered by genome sequencing, the lack of variant interpretation in a scalable fashion is a formidable barrier in this field.
              NUDT15
              polymorphism is a major genetic cause for hematopoietic toxicity during thiopurine therapy. Motivated by the need to understand
              NUDT15
              variant effects for clinical actions, we developed a massively parallel assay to preemptively characterize 91.8\% of all possible missense variants in
              NUDT15
              . Our function-based variant classification accurately predicted thiopurine toxicity risk alleles in patients. These results vastly improved the ability to implement genotype-guided thiopurine therapy and illustrated the value and potential of a high-throughput variant effect screen in general.
            
          , 
            
              As a prototype of genomics-guided precision medicine, individualized thiopurine dosing based on pharmacogenetics is a highly effective way to mitigate hematopoietic toxicity of this class of drugs. Recently,
              NUDT15
              deficiency was identified as a genetic cause of thiopurine toxicity, and
              NUDT15
              -informed preemptive dose reduction was quickly adopted in clinical settings. To exhaustively identify pharmacogenetic variants in this gene, we developed massively parallel NUDT15 function assays to determine the variants’ effect on protein abundance and thiopurine cytotoxicity. Of the 3,097 possible missense variants, we characterized the abundance of 2,922 variants and found 54 hotspot residues at which variants resulted in complete loss of protein stability. Analyzing 2,935 variants in the thiopurine cytotoxicity-based assay, we identified 17 additional residues where variants altered NUDT15 activity without affecting protein stability. We identified structural elements key to NUDT15 stability and/or catalytical activity with single amino acid resolution. Functional effects for
              NUDT15
              variants accurately predicted toxicity risk alleles in patients treated with thiopurines with far superior sensitivity and specificity compared to bioinformatic prediction algorithms. In conclusion, our massively parallel variant function assays identified 1,152 deleterious
              NUDT15
              variants, providing a comprehensive reference of variant function and vastly improving the ability to implement pharmacogenetics-guided thiopurine treatment individualization.},
	language = {en},
	number = {10},
	urldate = {2023-06-14},
	journal = {Proceedings of the National Academy of Sciences},
	author = {Suiter, Chase C. and Moriyama, Takaya and Matreyek, Kenneth A. and Yang, Wentao and Scaletti, Emma Rose and Nishii, Rina and Yang, Wenjian and Hoshitsuki, Keito and Singh, Minu and Trehan, Amita and Parish, Chris and Smith, Colton and Li, Lie and Bhojwani, Deepa and Yuen, Liz Y. P. and Li, Chi-kong and Li, Chak-ho and Yang, Yung-li and Walker, Gareth J. and Goodhand, James R. and Kennedy, Nicholas A. and Klussmann, Federico Antillon and Bhatia, Smita and Relling, Mary V. and Kato, Motohiro and Hori, Hiroki and Bhatia, Prateek and Ahmad, Tariq and Yeoh, Allen E. J. and Stenmark, Pål and Fowler, Douglas M. and Yang, Jun J.},
	month = mar,
	year = {2020},
	pages = {5394--5401},
	file = {Full Text:/Users/admin/Zotero/storage/CALTVXTU/Suiter et al. - 2020 - Massively parallel variant characterization identi.pdf:application/pdf},
}

@article{hobbs_saturation_2022,
	title = {Saturation mutagenesis of a predicted ancestral {Syk}‐family kinase},
	volume = {31},
	issn = {0961-8368, 1469-896X},
	url = {https://onlinelibrary.wiley.com/doi/10.1002/pro.4411},
	doi = {10.1002/pro.4411},
	language = {en},
	number = {10},
	urldate = {2023-06-14},
	journal = {Protein Science},
	author = {Hobbs, Helen T. and Shah, Neel H. and Shoemaker, Sophie R. and Amacher, Jeanine F. and Marqusee, Susan and Kuriyan, John},
	month = oct,
	year = {2022},
	file = {Full Text:/Users/admin/Zotero/storage/5TCADGH8/Hobbs et al. - 2022 - Saturation mutagenesis of a predicted ancestral Sy.pdf:application/pdf},
}

@techreport{gersing_comprehensive_2022,
	type = {preprint},
	title = {A comprehensive map of human glucokinase variant activity},
	url = {http://biorxiv.org/lookup/doi/10.1101/2022.05.04.490571},
	abstract = {Abstract
          
            Glucokinase (GCK) regulates insulin secretion to maintain appropriate blood glucose levels. Sequence variants can alter GCK activity to cause hyperinsulinemic hypoglycemia (HH) or hyperglycemia associated with GCK-maturity-onset diabetes of the young (GCK-MODY), collectively affecting up to 10 million people worldwide. Patients with GCK-MODY are frequently misdiagnosed and treated unnecessarily. Genetic testing can prevent this but is hampered by the challenge of interpreting novel missense variants. Here we exploited a multiplexed yeast complementation assay to measure both hyper- and hypoactive GCK variation, capturing 97\% of all possible missense and nonsense variants. Activity scores correlated with
            in vitro
            catalytic efficiency, fasting glucose levels in carriers of
            GCK
            variants and with evolutionary conservation. Hypoactive variants were concentrated at buried positions, near the active site, and at a region of known importance for GCK conformational dynamics. Some hyperactive variants shifted the conformational equilibrium towards the active state through a relative destabilization of the inactive conformation. Our comprehensive assessment of GCK variant activity promises to facilitate variant interpretation and diagnosis, expand our mechanistic understanding of hyperactive variants, and inform development of therapeutics targeting GCK.},
	language = {en},
	urldate = {2023-06-14},
	institution = {Genetics},
	author = {Gersing, Sarah and Cagiada, Matteo and Gebbia, Marinella and Gjesing, Anette P. and Coté, Atina G. and Seesankar, Gireesh and Li, Roujia and Tabet, Daniel and Stein, Amelie and Gloyn, Anna L. and Hansen, Torben and Roth, Frederick P. and Lindorff-Larsen, Kresten and Hartmann-Petersen, Rasmus},
	month = may,
	year = {2022},
	doi = {10.1101/2022.05.04.490571},
	file = {Submitted Version:/Users/admin/Zotero/storage/U2HI9MX9/Gersing et al. - 2022 - A comprehensive map of human glucokinase variant a.pdf:application/pdf},
}

@article{staller_high-throughput_2018,
	title = {A {High}-{Throughput} {Mutational} {Scan} of an {Intrinsically} {Disordered} {Acidic} {Transcriptional} {Activation} {Domain}},
	volume = {6},
	issn = {24054712},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S2405471218300528},
	doi = {10.1016/j.cels.2018.01.015},
	language = {en},
	number = {4},
	urldate = {2023-06-14},
	journal = {Cell Systems},
	author = {Staller, Max V. and Holehouse, Alex S. and Swain-Lenz, Devjanee and Das, Rahul K. and Pappu, Rohit V. and Cohen, Barak A.},
	month = apr,
	year = {2018},
	pages = {444--455.e6},
	file = {Full Text:/Users/admin/Zotero/storage/WTXI6TPC/Staller et al. - 2018 - A High-Throughput Mutational Scan of an Intrinsica.pdf:application/pdf},
}

@article{bandaru_deconstruction_2017,
	title = {Deconstruction of the {Ras} switching cycle through saturation mutagenesis},
	volume = {6},
	issn = {2050-084X},
	url = {https://elifesciences.org/articles/27810},
	doi = {10.7554/eLife.27810},
	abstract = {Ras proteins are highly conserved signaling molecules that exhibit regulated, nucleotide-dependent switching between active and inactive states. The high conservation of Ras requires mechanistic explanation, especially given the general mutational tolerance of proteins. Here, we use deep mutational scanning, biochemical analysis and molecular simulations to understand constraints on Ras sequence. Ras exhibits global sensitivity to mutation when regulated by a GTPase activating protein and a nucleotide exchange factor. Removing the regulators shifts the distribution of mutational effects to be largely neutral, and reveals hotspots of activating mutations in residues that restrain Ras dynamics and promote the inactive state. Evolutionary analysis, combined with structural and mutational data, argue that Ras has co-evolved with its regulators in the vertebrate lineage. Overall, our results show that sequence conservation in Ras depends strongly on the biochemical network in which it operates, providing a framework for understanding the origin of global selection pressures on proteins.},
	language = {en},
	urldate = {2023-06-14},
	journal = {eLife},
	author = {Bandaru, Pradeep and Shah, Neel H and Bhattacharyya, Moitrayee and Barton, John P and Kondo, Yasushi and Cofsky, Joshua C and Gee, Christine L and Chakraborty, Arup K and Kortemme, Tanja and Ranganathan, Rama and Kuriyan, John},
	month = jul,
	year = {2017},
	pages = {e27810},
	file = {Full Text:/Users/admin/Zotero/storage/GX5ZXSNL/Bandaru et al. - 2017 - Deconstruction of the Ras switching cycle through .pdf:application/pdf},
}

@article{bridgford_novel_2020,
	title = {Novel drivers and modifiers of {MPL}-dependent oncogenic transformation identified by deep mutational scanning},
	volume = {135},
	issn = {0006-4971, 1528-0020},
	url = {https://ashpublications.org/blood/article/135/4/287/381157/Novel-drivers-and-modifiers-of-MPLdependent},
	doi = {10.1182/blood.2019002561},
	abstract = {Abstract
            The single transmembrane domain (TMD) of the human thrombopoietin receptor (TpoR/myeloproliferative leukemia [MPL] protein), encoded by exon 10 of the MPL gene, is a hotspot for somatic mutations associated with myeloproliferative neoplasms (MPNs). Approximately 6\% and 14\% of JAK2 V617F− essential thrombocythemia and primary myelofibrosis patients, respectively, have “canonical” MPL exon 10 driver mutations W515L/K/R/A or S505N, which generate constitutively active receptors and consequent loss of Tpo dependence. Other “noncanonical” MPL exon 10 mutations have also been identified in patients, both alone and in combination with canonical mutations, but, in almost all cases, their functional consequences and relevance to disease are unknown. Here, we used a deep mutational scanning approach to evaluate all possible single amino acid substitutions in the human TpoR TMD for their ability to confer cytokine-independent growth in Ba/F3 cells. We identified all currently recognized driver mutations and 7 novel mutations that cause constitutive TpoR activation, and a much larger number of second-site mutations that enhance S505N-driven activation. We found examples of both of these categories in published and previously unpublished MPL exon 10 sequencing data from MPN patients, demonstrating that some, if not all, of the new mutations reported here represent likely drivers or modifiers of myeloproliferative disease.},
	language = {en},
	number = {4},
	urldate = {2023-06-14},
	journal = {Blood},
	author = {Bridgford, Jessica L. and Lee, Su Min and Lee, Christine M. M. and Guglielmelli, Paola and Rumi, Elisa and Pietra, Daniela and Wilcox, Stephen and Chhabra, Yash and Rubin, Alan F. and Cazzola, Mario and Vannucchi, Alessandro M. and Brooks, Andrew J. and Call, Matthew E. and Call, Melissa J.},
	month = jan,
	year = {2020},
	pages = {287--292},
	file = {Full Text:/Users/admin/Zotero/storage/EAT9FPV2/Bridgford et al. - 2020 - Novel drivers and modifiers of MPL-dependent oncog.pdf:application/pdf},
}

@article{spencer_deep_2017,
	title = {Deep mutational scanning of {S}. pyogenes {Cas9} reveals important functional domains},
	volume = {7},
	issn = {2045-2322},
	url = {https://www.nature.com/articles/s41598-017-17081-y},
	doi = {10.1038/s41598-017-17081-y},
	abstract = {Abstract
            
              RNA-guided endonucleases (RGENs) have invigorated the field of site-specific nucleases. The success of
              Streptococcus pyogenes
              Cas9 (SpCas9) has led to the discovery of several other CRISPR-associated RGENs. As more RGENs become available, it will be necessary to refine their activity before they can be translated into the clinic. With this in mind, we sought to demonstrate how deep mutational scanning (DMS) could provide details about important functional regions in SpCas9 and speed engineering efforts. Consequently, we developed a nuclease screening platform which could distinguish active Cas9 mutants. We screened a library of 1.9 × 10
              7
              with over 8500 possible non-synonymous mutations and inferred the effects of each mutation using DMS. We demonstrate that the RuvC and HNH domains are the least tolerant regions to mutation. In contrast, the Rec2 and PI domains tolerate mutation better than other regions. The mutation information defined in this work provides a foundation for further SpCas9 engineering. Together, our results demonstrate how DMS can be a powerful tool to uncover features important to RGEN function. Application of this approach to emerging RGENs should enhance their engineering and optimization for therapeutic and other applications.},
	language = {en},
	number = {1},
	urldate = {2023-06-14},
	journal = {Scientific Reports},
	author = {Spencer, Jeffrey M. and Zhang, Xiaoliu},
	month = dec,
	year = {2017},
	pages = {16836},
	file = {Full Text:/Users/admin/Zotero/storage/BWJHTMKA/Spencer and Zhang - 2017 - Deep mutational scanning of S. pyogenes Cas9 revea.pdf:application/pdf},
}

@article{mclaughlin_jr_spatial_2012,
	title = {The spatial architecture of protein function and adaptation},
	volume = {491},
	issn = {0028-0836, 1476-4687},
	url = {https://www.nature.com/articles/nature11500},
	doi = {10.1038/nature11500},
	language = {en},
	number = {7422},
	urldate = {2023-06-14},
	journal = {Nature},
	author = {McLaughlin, Jr., Richard N. and Poelwijk, Frank J. and Raman, Arjun and Gosal, Walraj S. and Ranganathan, Rama},
	month = nov,
	year = {2012},
	pages = {138--142},
	file = {Accepted Version:/Users/admin/Zotero/storage/8SK84J8S/McLaughlin Jr et al. - 2012 - The spatial architecture of protein function and a.pdf:application/pdf},
}

@article{doud_site-specific_2015,
	title = {Site-{Specific} {Amino} {Acid} {Preferences} {Are} {Mostly} {Conserved} in {Two} {Closely} {Related} {Protein} {Homologs}},
	volume = {32},
	issn = {0737-4038, 1537-1719},
	url = {https://academic.oup.com/mbe/article-lookup/doi/10.1093/molbev/msv167},
	doi = {10.1093/molbev/msv167},
	language = {en},
	number = {11},
	urldate = {2023-06-14},
	journal = {Molecular Biology and Evolution},
	author = {Doud, Michael B. and Ashenberg, Orr and Bloom, Jesse D.},
	month = nov,
	year = {2015},
	pages = {2944--2960},
	file = {Full Text:/Users/admin/Zotero/storage/KVBHH6S5/Doud et al. - 2015 - Site-Specific Amino Acid Preferences Are Mostly Co.pdf:application/pdf},
}

@article{mattenberger_globally_2021,
	title = {Globally defining the effects of mutations in a picornavirus capsid},
	volume = {10},
	issn = {2050-084X},
	url = {https://elifesciences.org/articles/64256},
	doi = {10.7554/eLife.64256},
	abstract = {The capsids of non-enveloped viruses are highly multimeric and multifunctional protein assemblies that play key roles in viral biology and pathogenesis. Despite their importance, a comprehensive understanding of how mutations affect viral fitness across different structural and functional attributes of the capsid is lacking. To address this limitation, we globally define the effects of mutations across the capsid of a human picornavirus. Using this resource, we identify structural and sequence determinants that accurately predict mutational fitness effects, refine evolutionary analyses, and define the sequence specificity of key capsid-encoded motifs. Furthermore, capitalizing on the derived sequence requirements for capsid-encoded protease cleavage sites, we implement a bioinformatic approach for identifying novel host proteins targeted by viral proteases. Our findings represent the most comprehensive investigation of mutational fitness effects in a picornavirus capsid to date and illuminate important aspects of viral biology, evolution, and host interactions.
          , 
            A virus is made up of genetic material that is encased with a protective protein coat called the capsid. The capsid also helps the virus to infect host cells by binding to the host receptor proteins and releasing its genetic material. Inside the cell, the virus hitchhikes the infected cell’s machinery to grow or replicate its own genetic material.
            Viral capsids are the main target of the host’s defence system, and therefore, continuously change in an attempt to escape the immune system by introducing alterations (known as mutations) into the genes encoding viral capsid proteins. Mutations occur randomly, and so while some changes to the viral capsid might confer an advantage, others may have no effect at all, or even weaken the virus.
            To better understand the effect of capsid mutations on the virus’ ability to infect host cells, Mattenberger et al. studied the Coxsackievirus B3, which is linked to heart problems and acute heart failure in humans. The researchers analysed around 90\% of possible amino acid mutations (over 14,800 mutations) and correlated each mutation to how it influenced the virus’ ability to replicate in human cells grown in the laboratory.
            Based on these results, Mattenberger et al. developed a computer model to predict how a particular mutation might affect the virus. The analysis also identified specific amino acid sequences of capsid proteins that are essential for certain tasks, such as building the capsid. It also included an analysis of sequences in the capsid that allow it to be recognized by another viral protein, which cuts the capsid proteins into the right size from a larger precursor. By looking for similar sequences in human genes, the researchers identified several ones that the virus may attack and inactivate to support its own replication.
            These findings may help identify potential drug targets to develop new antiviral therapies. For example, proteins of the capsid that are less likely to mutate will provide a better target as they lower the possibility of the virus to become resistant to the treatment. They also highlight new proteins in human cells that could potentially block the virus in cells.},
	language = {en},
	urldate = {2023-06-14},
	journal = {eLife},
	author = {Mattenberger, Florian and Latorre, Victor and Tirosh, Omer and Stern, Adi and Geller, Ron},
	month = jan,
	year = {2021},
	pages = {e64256},
	file = {Full Text:/Users/admin/Zotero/storage/Z7NP9QNK/Mattenberger et al. - 2021 - Globally defining the effects of mutations in a pi.pdf:application/pdf},
}

@article{matreyek_multiplex_2018,
	title = {Multiplex assessment of protein variant abundance by massively parallel sequencing},
	volume = {50},
	issn = {1061-4036, 1546-1718},
	url = {https://www.nature.com/articles/s41588-018-0122-z},
	doi = {10.1038/s41588-018-0122-z},
	language = {en},
	number = {6},
	urldate = {2023-06-14},
	journal = {Nature Genetics},
	author = {Matreyek, Kenneth A. and Starita, Lea M. and Stephany, Jason J. and Martin, Beth and Chiasson, Melissa A. and Gray, Vanessa E. and Kircher, Martin and Khechaduri, Arineh and Dines, Jennifer N. and Hause, Ronald J. and Bhatia, Smita and Evans, William E. and Relling, Mary V. and Yang, Wenjian and Shendure, Jay and Fowler, Douglas M.},
	month = jun,
	year = {2018},
	pages = {874--882},
	file = {Accepted Version:/Users/admin/Zotero/storage/IRF7FEAI/Matreyek et al. - 2018 - Multiplex assessment of protein variant abundance .pdf:application/pdf},
}

@article{flynn_comprehensive_2020,
	title = {Comprehensive fitness maps of {Hsp90} show widespread environmental dependence},
	volume = {9},
	issn = {2050-084X},
	url = {https://elifesciences.org/articles/53810},
	doi = {10.7554/eLife.53810},
	abstract = {Gene-environment interactions have long been theorized to influence molecular evolution. However, the environmental dependence of most mutations remains unknown. Using deep mutational scanning, we engineered yeast with all 44,604 single codon changes encoding 14,160 amino acid variants in Hsp90 and quantified growth effects under standard conditions and under five stress conditions. To our knowledge, these are the largest determined comprehensive fitness maps of point mutants. The growth of many variants differed between conditions, indicating that environment can have a large impact on Hsp90 evolution. Multiple variants provided growth advantages under individual conditions; however, these variants tended to exhibit growth defects in other environments. The diversity of Hsp90 sequences observed in extant eukaryotes preferentially contains variants that supported robust growth under all tested conditions. Rather than favoring substitutions in individual conditions, the long-term selective pressure on Hsp90 may have been that of fluctuating environments, leading to robustness under a variety of conditions.},
	language = {en},
	urldate = {2023-06-14},
	journal = {eLife},
	author = {Flynn, Julia M and Rossouw, Ammeret and Cote-Hammarlof, Pamela and Fragata, Inês and Mavor, David and Hollins, Carl and Bank, Claudia and Bolon, Daniel Na},
	month = mar,
	year = {2020},
	pages = {e53810},
	file = {Full Text:/Users/admin/Zotero/storage/CQWF9FY9/Flynn et al. - 2020 - Comprehensive fitness maps of Hsp90 show widesprea.pdf:application/pdf},
}

@article{ahler_combined_2019,
	title = {A {Combined} {Approach} {Reveals} a {Regulatory} {Mechanism} {Coupling} {Src}’s {Kinase} {Activity}, {Localization}, and {Phosphotransferase}-{Independent} {Functions}},
	volume = {74},
	issn = {10972765},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S1097276519300930},
	doi = {10.1016/j.molcel.2019.02.003},
	language = {en},
	number = {2},
	urldate = {2023-06-14},
	journal = {Molecular Cell},
	author = {Ahler, Ethan and Register, Ames C. and Chakraborty, Sujata and Fang, Linglan and Dieter, Emily M. and Sitko, Katherine A. and Vidadala, Rama Subba Rao and Trevillian, Bridget M. and Golkowski, Martin and Gelman, Hannah and Stephany, Jason J. and Rubin, Alan F. and Merritt, Ethan A. and Fowler, Douglas M. and Maly, Dustin J.},
	month = apr,
	year = {2019},
	pages = {393--408.e20},
	file = {Full Text:/Users/admin/Zotero/storage/BAUMXZ8I/Ahler et al. - 2019 - A Combined Approach Reveals a Regulatory Mechanism.pdf:application/pdf},
}

@article{romero_dissecting_2015,
	title = {Dissecting enzyme function with microfluidic-based deep mutational scanning},
	volume = {112},
	issn = {0027-8424, 1091-6490},
	url = {https://pnas.org/doi/full/10.1073/pnas.1422285112},
	doi = {10.1073/pnas.1422285112},
	abstract = {Significance
            As powerful biological catalysts, enzymes can solve challenging problems that range from the industrial production of chemicals to the treatment of human disease. The ability to design new enzymes with tailor-made chemical functions would have a far-reaching impact. However, this important capability has been limited by our cursory understanding of enzyme catalysis. Here, we report a method that uses unbiased empirical analysis to dissect the molecular basis of enzyme function. By comprehensively mapping how changes in an enzyme’s amino acid sequence affect its activity, we obtain a detailed view of the interactions that shape the enzyme function landscape. Large, unbiased analyses of enzyme function allow the discovery of new biochemical mechanisms that will improve our ability to engineer custom biocatalysts.
          , 
            Natural enzymes are incredibly proficient catalysts, but engineering them to have new or improved functions is challenging due to the complexity of how an enzyme’s sequence relates to its biochemical properties. Here, we present an ultrahigh-throughput method for mapping enzyme sequence–function relationships that combines droplet microfluidic screening with next-generation DNA sequencing. We apply our method to map the activity of millions of glycosidase sequence variants. Microfluidic-based deep mutational scanning provides a comprehensive and unbiased view of the enzyme function landscape. The mapping displays expected patterns of mutational tolerance and a strong correspondence to sequence variation within the enzyme family, but also reveals previously unreported sites that are crucial for glycosidase function. We modified the screening protocol to include a high-temperature incubation step, and the resulting thermotolerance landscape allowed the discovery of mutations that enhance enzyme thermostability. Droplet microfluidics provides a general platform for enzyme screening that, when combined with DNA-sequencing technologies, enables high-throughput mapping of enzyme sequence space.},
	language = {en},
	number = {23},
	urldate = {2023-06-14},
	journal = {Proceedings of the National Academy of Sciences},
	author = {Romero, Philip A. and Tran, Tuan M. and Abate, Adam R.},
	month = jun,
	year = {2015},
	pages = {7159--7164},
	file = {Full Text:/Users/admin/Zotero/storage/7D996XKU/Romero et al. - 2015 - Dissecting enzyme function with microfluidic-based.pdf:application/pdf},
}

@article{faure_mapping_2022,
	title = {Mapping the energetic and allosteric landscapes of protein binding domains},
	volume = {604},
	issn = {0028-0836, 1476-4687},
	url = {https://www.nature.com/articles/s41586-022-04586-4},
	doi = {10.1038/s41586-022-04586-4},
	language = {en},
	number = {7904},
	urldate = {2023-06-14},
	journal = {Nature},
	author = {Faure, Andre J. and Domingo, Júlia and Schmiedel, Jörn M. and Hidalgo-Carcedo, Cristina and Diss, Guillaume and Lehner, Ben},
	month = apr,
	year = {2022},
	pages = {175--183},
	file = {Accepted Version:/Users/admin/Zotero/storage/H46C8P4R/Faure et al. - 2022 - Mapping the energetic and allosteric landscapes of.pdf:application/pdf},
}

@article{roscoe_analyses_2013,
	title = {Analyses of the {Effects} of {All} {Ubiquitin} {Point} {Mutants} on {Yeast} {Growth} {Rate}},
	volume = {425},
	issn = {00222836},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0022283613000636},
	doi = {10.1016/j.jmb.2013.01.032},
	language = {en},
	number = {8},
	urldate = {2023-06-14},
	journal = {Journal of Molecular Biology},
	author = {Roscoe, Benjamin P. and Thayer, Kelly M. and Zeldovich, Konstantin B. and Fushman, David and Bolon, Daniel N.A.},
	month = apr,
	year = {2013},
	pages = {1363--1377},
	file = {Accepted Version:/Users/admin/Zotero/storage/Z4CIGXLZ/Roscoe et al. - 2013 - Analyses of the Effects of All Ubiquitin Point Mut.pdf:application/pdf},
}

@article{newberry_robust_2020,
	title = {Robust {Sequence} {Determinants} of alpha-{Synuclein} {Toxicity} in {Yeast} {Implicate} {Membrane} {Binding}},
	volume = {15},
	issn = {1554-8929, 1554-8937},
	url = {https://pubs.acs.org/doi/10.1021/acschembio.0c00339},
	doi = {10.1021/acschembio.0c00339},
	language = {en},
	number = {8},
	urldate = {2023-06-14},
	journal = {ACS Chemical Biology},
	author = {Newberry, Robert W. and Arhar, Taylor and Costello, Jean and Hartoularos, George C. and Maxwell, Alison M. and Naing, Zun Zar Chi and Pittman, Maureen and Reddy, Nishith R. and Schwarz, Daniel M. C. and Wassarman, Douglas R. and Wu, Taia S. and Barrero, Daniel and Caggiano, Christa and Catching, Adam and Cavazos, Taylor B. and Estes, Laurel S. and Faust, Bryan and Fink, Elissa A. and Goldman, Miriam A. and Gomez, Yessica K. and Gordon, M. Grace and Gunsalus, Laura M. and Hoppe, Nick and Jaime-Garza, Maru and Johnson, Matthew C. and Jones, Matthew G. and Kung, Andrew F. and Lopez, Kyle E. and Lumpe, Jared and Martyn, Calla and McCarthy, Elizabeth E. and Miller-Vedam, Lakshmi E. and Navarro, Erik J. and Palar, Aji and Pellegrino, Jenna and Saylor, Wren and Stephens, Christina A. and Strickland, Jack and Torosyan, Hayarpi and Wankowicz, Stephanie A. and Wong, Daniel R. and Wong, Garrett and Redding, Sy and Chow, Eric D. and DeGrado, William F. and Kampmann, Martin},
	month = aug,
	year = {2020},
	pages = {2137--2153},
	file = {Accepted Version:/Users/admin/Zotero/storage/NQ4BLNN6/Newberry et al. - 2020 - Robust Sequence Determinants of alpha-Synuclein Toxici.pdf:application/pdf;Submitted Version:/Users/admin/Zotero/storage/7IFR9453/Newberry et al. - 2020 - Robust Sequence Determinants of alpha-Synuclein Toxici.pdf:application/pdf},
}

@article{wu_adaptation_2016,
	title = {Adaptation in protein fitness landscapes is facilitated by indirect paths},
	volume = {5},
	issn = {2050-084X},
	url = {https://elifesciences.org/articles/16965},
	doi = {10.7554/eLife.16965},
	abstract = {The structure of fitness landscapes is critical for understanding adaptive protein evolution. Previous empirical studies on fitness landscapes were confined to either the neighborhood around the wild type sequence, involving mostly single and double mutants, or a combinatorially complete subgraph involving only two amino acids at each site. In reality, the dimensionality of protein sequence space is higher (20L) and there may be higher-order interactions among more than two sites. Here we experimentally characterized the fitness landscape of four sites in protein GB1, containing 204 = 160,000 variants. We found that while reciprocal sign epistasis blocked many direct paths of adaptation, such evolutionary traps could be circumvented by indirect paths through genotype space involving gain and subsequent loss of mutations. These indirect paths alleviate the constraint on adaptive protein evolution, suggesting that the heretofore neglected dimensions of sequence space may change our views on how proteins evolve.
          , 
            Proteins can evolve over time by changing their component parts, which are called amino acids. These changes usually happen one at a time and natural selection tends to preserve those changes that make the protein more efficient at its specific tasks, while discarding those that impair the protein’s activity. However the effect of each change depends on the protein as a whole, and so two changes that separately make the protein worse can make it much better if they occur together. This phenomenon is called epistasis and in some cases it can trap proteins in a sub-optimal form and prevent them from improving further.
            Proteins are made from twenty different kinds of amino acid, and there are millions of different combinations of amino acids that could, in theory, make a protein of a given length. Studying protein evolution involves making variants of the same protein, each with just a few changes, and comparing how efficient, or “fit”, they are. Previous studies only measured the fitness of a few variants and showed that epistasis could block protein evolution by requiring the protein to lose some fitness before it could improve further. However, new techniques have now made it easier to study protein evolution by testing many more protein variants.
            Wu, Dai et al. focused on four amino acids in part of a protein called GB1 and tested the efficiency of every possible combination of these four amino acids, a total of 160,000 (204) variants. Contrary to expectations, the results suggested that the protein could evolve quickly to maximise fitness despite there being epistasis between the four amino acids. Overcoming epistasis typically involved making a change to one amino acid that paved the way for further changes while avoiding the need to lose fitness. The original change could then be reversed once the epistasis was overcome. The complexity of this solution means it can only be seen by studying a large number of protein variants that represent many alternative sequences of protein changes.
            Wu, Dai et al. conclude that proteins are able to achieve a higher level of fitness through evolution by exploring a large number of changes. There are many possible changes for each protein and it is this variety that, despite epistasis, allows proteins to become naturally optimised for the tasks that they perform. While the full complexity of protein evolution cannot be explored at the moment, as technology advances it will become possible to study more protein variants. Such advances would therefore hopefully allow researchers to discover even more about the natural mechanisms of protein evolution.},
	language = {en},
	urldate = {2023-06-14},
	journal = {eLife},
	author = {Wu, Nicholas C and Dai, Lei and Olson, C Anders and Lloyd-Smith, James O and Sun, Ren},
	month = jul,
	year = {2016},
	pages = {e16965},
	file = {Full Text:/Users/admin/Zotero/storage/GYE5JDBN/Wu et al. - 2016 - Adaptation in protein fitness landscapes is facili.pdf:application/pdf},
}

@article{starr_deep_2020,
	title = {Deep {Mutational} {Scanning} of {SARS}-{CoV}-2 {Receptor} {Binding} {Domain} {Reveals} {Constraints} on {Folding} and {ACE2} {Binding}},
	volume = {182},
	issn = {00928674},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0092867420310035},
	doi = {10.1016/j.cell.2020.08.012},
	language = {en},
	number = {5},
	urldate = {2023-06-14},
	journal = {Cell},
	author = {Starr, Tyler N. and Greaney, Allison J. and Hilton, Sarah K. and Ellis, Daniel and Crawford, Katharine H.D. and Dingens, Adam S. and Navarro, Mary Jane and Bowen, John E. and Tortorici, M. Alejandra and Walls, Alexandra C. and King, Neil P. and Veesler, David and Bloom, Jesse D.},
	month = sep,
	year = {2020},
	pages = {1295--1310.e20},
	file = {Submitted Version:/Users/admin/Zotero/storage/TCMBL3SJ/Starr et al. - 2020 - Deep Mutational Scanning of SARS-CoV-2 Receptor Bi.pdf:application/pdf},
}

@techreport{brauer_comprehensive_2021,
	type = {preprint},
	title = {Comprehensive {Fitness} {Landscape} of a {Multi}-{Geometry} {Protein} {Capsid} {Informs} {Machine} {Learning} {Models} of {Assembly}},
	url = {http://biorxiv.org/lookup/doi/10.1101/2021.12.21.473721},
	abstract = {Abstract
          
            Virus-like particles (VLPs) are non-infections viral-derived nanomaterials poised for biotechnological applications due to their well-defined, modular self-assembling architecture. Although progress has been made in understanding the complex effects that mutations may have on VLPs, nuanced understanding of the influence particle mutability has on quaternary structure has yet to be achieved. Here, we generate and compare the apparent fitness landscapes of two capsid geometries (T=3 and T=1 icosahedral) of the bacteriophage MS2 VLP. We find significant shifts in mutability at the symmetry interfaces of the T=1 capsid when compared to the wildtype T=3 assembly. Furthermore, we use the generated landscapes to benchmark the performance of
            in silico
            mutational scanning tools in capturing the effect of missense mutation on complex particle assembly. Finding that predicted stability effects correlated relatively poorly with assembly phenotype, we used a combination of
            de novo
            features in tandem with
            in silico
            results to train machine learning algorithms for the classification of variant effects on assembly. Our findings not only reveal ways that assembly geometry affects the mutable landscape of a self-assembled particle, but also establish a template for the generation of predictive mutational models of self-assembled capsids using minimal empirical training data.},
	language = {en},
	urldate = {2023-06-14},
	institution = {Bioengineering},
	author = {Brauer, Daniel D. and Santiago, Celine B. and Merz, Zoe N. and McCarthy, Esther and Tullman-Ercek, Danielle and Francis, Matthew B.},
	month = dec,
	year = {2021},
	doi = {10.1101/2021.12.21.473721},
	file = {Submitted Version:/Users/admin/Zotero/storage/TRVZDGPY/Brauer et al. - 2021 - Comprehensive Fitness Landscape of a Multi-Geometr.pdf:application/pdf},
}

@article{linsky_novo_2020,
	title = {De novo design of potent and resilient {hACE2} decoys to neutralize {SARS}-{CoV}-2},
	volume = {370},
	issn = {0036-8075, 1095-9203},
	url = {https://www.science.org/doi/10.1126/science.abe0075},
	doi = {10.1126/science.abe0075},
	abstract = {A decoy to neutralize SARS-CoV-2
            
              Many efforts to develop therapies against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) are focused on the interaction between the spike protein, which decorates the surface of the virus, and its host receptor, human angiotensin-converting enzyme 2 (hACE2). Linsky
              et al.
              describe a de novo design strategy that allowed them to engineer decoy proteins that bind to the spike protein by replicating the hACE2 interface. The best decoy, CTC-445, bound with low nanomolar affinity, and selection of viral mutants that decrease binding is unlikely because this would also affect binding to hACE2. A bivalent version of CTC-445 bound even more tightly, neutralized SARS-CoV-2 infection of cells, and protected hamsters from a SARS-CoV-2 challenge. The stable decoy has the potential for respiratory therapeutic delivery.
            
            
              Science
              , this issue p.
              1208
            
          , 
            Designed de novo protein decoys neutralize SARS-CoV-2 in vitro and in vivo and are resilient to viral mutational escape.
          , 
            We developed a de novo protein design strategy to swiftly engineer decoys for neutralizing pathogens that exploit extracellular host proteins to infect the cell. Our pipeline allowed the design, validation, and optimization of de novo human angiotensin-converting enzyme 2 (hACE2) decoys to neutralize severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The best monovalent decoy, CTC-445.2, bound with low nanomolar affinity and high specificity to the receptor-binding domain (RBD) of the spike protein. Cryo–electron microscopy (cryo-EM) showed that the design is accurate and can simultaneously bind to all three RBDs of a single spike protein. Because the decoy replicates the spike protein target interface in hACE2, it is intrinsically resilient to viral mutational escape. A bivalent decoy, CTC-445.2d, showed {\textasciitilde}10-fold improvement in binding. CTC-445.2d potently neutralized SARS-CoV-2 infection of cells in vitro, and a single intranasal prophylactic dose of decoy protected Syrian hamsters from a subsequent lethal SARS-CoV-2 challenge.},
	language = {en},
	number = {6521},
	urldate = {2023-06-14},
	journal = {Science},
	author = {Linsky, Thomas W. and Vergara, Renan and Codina, Nuria and Nelson, Jorgen W. and Walker, Matthew J. and Su, Wen and Barnes, Christopher O. and Hsiang, Tien-Ying and Esser-Nobis, Katharina and Yu, Kevin and Reneer, Z. Beau and Hou, Yixuan J. and Priya, Tanu and Mitsumoto, Masaya and Pong, Avery and Lau, Uland Y. and Mason, Marsha L. and Chen, Jerry and Chen, Alex and Berrocal, Tania and Peng, Hong and Clairmont, Nicole S. and Castellanos, Javier and Lin, Yu-Ru and Josephson-Day, Anna and Baric, Ralph S. and Fuller, Deborah H. and Walkey, Carl D. and Ross, Ted M. and Swanson, Ryan and Bjorkman, Pamela J. and Gale, Michael and Blancas-Mejia, Luis M. and Yen, Hui-Ling and Silva, Daniel-Adriano},
	month = dec,
	year = {2020},
	pages = {1208--1214},
	file = {Full Text:/Users/admin/Zotero/storage/RDJMYBGK/Linsky et al. - 2020 - De novo design of potent and resilient hACE2 decoy.pdf:application/pdf},
}

@techreport{stadelmann_deep_2021,
	type = {preprint},
	title = {A deep mutational scanning platform to characterize the fitness landscape of anti-{CRISPR} proteins},
	url = {http://biorxiv.org/lookup/doi/10.1101/2021.08.21.457204},
	abstract = {ABSTRACT
          
            Deep mutational scanning is a powerful method to explore the mutational fitness landscape of proteins. Its adaptation to anti-CRISPR proteins, which are natural CRISPR-Cas inhibitors and key players in the co-evolution of microbes and phages, would facilitate their in-depth characterization and optimization. Here, we developed a robust anti-CRISPR deep mutational scanning pipeline in
            Escherichia coli
            combining synthetic gene circuits based on CRISPR interference with flow cytometry-coupled sequencing and mathematical modeling. Using this pipeline, we created and characterized comprehensive single point mutation libraries for AcrIIA4 and AcrIIA5, two potent inhibitors of
            Streptococcus pyogenes
            Cas9. The resulting mutational fitness landscapes revealed that both Acrs possess a considerable mutational tolerance as well as an intrinsic redundancy with respect to Cas9 inhibitory features, suggesting evolutionary pressure towards high plasticity and robustness. Finally, to demonstrate that our pipeline can inform the optimization and fine-tuning of Acrs for genome editing applications, we cross-validated a subset of AcrIIA4 mutants via gene editing assays in mammalian cells and
            in vitro
            affinity measurements. Together, our work establishes deep mutational scanning as powerful method for anti-CRISPR protein characterization and optimization.},
	language = {en},
	urldate = {2023-06-14},
	institution = {Synthetic Biology},
	author = {Stadelmann, Tobias and Heid, Daniel and Jendrusch, Michael and Mathony, Jan and Rosset, Stéphane and Correia, Bruno E. and Niopek, Dominik},
	month = aug,
	year = {2021},
	doi = {10.1101/2021.08.21.457204},
	file = {Submitted Version:/Users/admin/Zotero/storage/WPHVK96E/Stadelmann et al. - 2021 - A deep mutational scanning platform to characteriz.pdf:application/pdf},
}

@article{koch_optimization_2022,
	title = {Optimization of the antimicrobial peptide {Bac7} by deep mutational scanning},
	volume = {20},
	issn = {1741-7007},
	url = {https://bmcbiol.biomedcentral.com/articles/10.1186/s12915-022-01304-4},
	doi = {10.1186/s12915-022-01304-4},
	abstract = {Abstract
            
              Background
              
                Intracellularly active antimicrobial peptides are promising candidates for the development of antibiotics for human applications. However, drug development using peptides is challenging as, owing to their large size, an enormous sequence space is spanned. We built a high-throughput platform that incorporates rapid investigation of the sequence-activity relationship of peptides and enables rational optimization of their antimicrobial activity. The platform is based on deep mutational scanning of DNA-encoded peptides and employs highly parallelized bacterial self-screening coupled to next-generation sequencing as a readout for their antimicrobial activity. As a target, we used Bac7
                1-23
                , a 23 amino acid residues long variant of bactenecin-7, a potent translational inhibitor and one of the best researched proline-rich antimicrobial peptides.
              
            
            
              Results
              
                Using the platform, we simultaneously determined the antimicrobial activity of {\textgreater}600,000 Bac7
                1-23
                variants and explored their sequence-activity relationship. This dataset guided the design of a focused library of {\textasciitilde}160,000 variants and the identification of a lead candidate Bac7PS. Bac7PS showed high activity against multidrug-resistant clinical isolates of
                E. coli,
                and its activity was less dependent on SbmA, a transporter commonly used by proline-rich antimicrobial peptides to reach the cytosol and then inhibit translation. Furthermore, Bac7PS displayed strong ribosomal inhibition and low toxicity against eukaryotic cells and demonstrated good efficacy in a murine septicemia model induced by
                E. coli
                .
              
            
            
              Conclusion
              We demonstrated that the presented platform can be used to establish the sequence-activity relationship of antimicrobial peptides, and showed its usefulness for hit-to-lead identification and optimization of antimicrobial drug candidates.},
	language = {en},
	number = {1},
	urldate = {2023-06-14},
	journal = {BMC Biology},
	author = {Koch, Philipp and Schmitt, Steven and Heynisch, Alexander and Gumpinger, Anja and Wüthrich, Irene and Gysin, Marina and Shcherbakov, Dimitri and Hobbie, Sven N. and Panke, Sven and Held, Martin},
	month = dec,
	year = {2022},
	pages = {114},
	file = {Full Text:/Users/admin/Zotero/storage/8QZH39IE/Koch et al. - 2022 - Optimization of the antimicrobial peptide Bac7 by .pdf:application/pdf},
}

@article{kotler_systematic_2018,
	title = {A {Systematic} p53 {Mutation} {Library} {Links} {Differential} {Functional} {Impact} to {Cancer} {Mutation} {Pattern} and {Evolutionary} {Conservation}},
	volume = {71},
	issn = {10972765},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S1097276518304544},
	doi = {10.1016/j.molcel.2018.06.012},
	language = {en},
	number = {1},
	urldate = {2023-06-14},
	journal = {Molecular Cell},
	author = {Kotler, Eran and Shani, Odem and Goldfeld, Guy and Lotan-Pompan, Maya and Tarcic, Ohad and Gershoni, Anat and Hopf, Thomas A. and Marks, Debora S. and Oren, Moshe and Segal, Eran},
	month = jul,
	year = {2018},
	pages = {178--190.e8},
	file = {Full Text:/Users/admin/Zotero/storage/7M4DXV8M/Kotler et al. - 2018 - A Systematic p53 Mutation Library Links Differenti.pdf:application/pdf},
}

@article{campbell_determinants_2022,
	title = {Determinants of {Multiheme} {Cytochrome} {Extracellular} {Electron} {Transfer} {Uncovered} by {Systematic} {Peptide} {Insertion}},
	volume = {61},
	issn = {0006-2960, 1520-4995},
	url = {https://pubs.acs.org/doi/10.1021/acs.biochem.2c00148},
	doi = {10.1021/acs.biochem.2c00148},
	language = {en},
	number = {13},
	urldate = {2023-06-14},
	journal = {Biochemistry},
	author = {Campbell, Ian J. and Atkinson, Joshua T. and Carpenter, Matthew D. and Myerscough, Dru and Su, Lin and Ajo-Franklin, Caroline M. and Silberg, Jonathan J.},
	month = jul,
	year = {2022},
	pages = {1337--1350},
	file = {Submitted Version:/Users/admin/Zotero/storage/CQJVV8DL/Campbell et al. - 2022 - Determinants of Multiheme Cytochrome Extracellular.pdf:application/pdf},
}

@article{ding_co-evolution_2022,
	title = {Co-evolution of interacting proteins through non-contacting and non-specific mutations},
	volume = {6},
	issn = {2397-334X},
	url = {https://www.nature.com/articles/s41559-022-01688-0},
	doi = {10.1038/s41559-022-01688-0},
	language = {en},
	number = {5},
	urldate = {2023-06-14},
	journal = {Nature Ecology \& Evolution},
	author = {Ding, David and Green, Anna G. and Wang, Boyuan and Lite, Thuy-Lan Vo and Weinstein, Eli N. and Marks, Debora S. and Laub, Michael T.},
	month = mar,
	year = {2022},
	pages = {590--603},
	file = {Accepted Version:/Users/admin/Zotero/storage/RIQVW8ID/Ding et al. - 2022 - Co-evolution of interacting proteins through non-c.pdf:application/pdf},
}

% pgv1

@article{tsuboyama_mega-scale_2023,
	title = {Mega-scale experimental analysis of protein folding stability in biology and design},
	volume = {620},
	issn = {0028-0836, 1476-4687},
	url = {https://www.nature.com/articles/s41586-023-06328-6},
	doi = {10.1038/s41586-023-06328-6},
	abstract = {Abstract
            
              Advances in DNA sequencing and machine learning are providing insights into protein sequences and structures on an enormous scale
              1
              . However, the energetics driving folding are invisible in these structures and remain largely unknown
              2
              . The hidden thermodynamics of folding can drive disease
              3,4
              , shape protein evolution
              5–7
              and guide protein engineering
              8–10
              , and new approaches are needed to reveal these thermodynamics for every sequence and structure. Here we present cDNA display proteolysis, a method for measuring thermodynamic folding stability for up to 900,000 protein domains in a one-week experiment. From 1.8 million measurements in total, we curated a set of around 776,000 high-quality folding stabilities covering all single amino acid variants and selected double mutants of 331 natural and 148 de novo designed protein domains 40–72 amino acids in length. Using this extensive dataset, we quantified (1) environmental factors influencing amino acid fitness, (2) thermodynamic couplings (including unexpected interactions) between protein sites, and (3) the global divergence between evolutionary amino acid usage and protein folding stability. We also examined how our approach could identify stability determinants in designed proteins and evaluate design methods. The cDNA display proteolysis method is fast, accurate and uniquely scalable, and promises to reveal the quantitative rules for how amino acid sequences encode folding stability.},
	language = {en},
	number = {7973},
	urldate = {2023-08-15},
	journal = {Nature},
	author = {Tsuboyama, Kotaro and Dauparas, Justas and Chen, Jonathan and Laine, Elodie and Mohseni Behbahani, Yasser and Weinstein, Jonathan J. and Mangan, Niall M. and Ovchinnikov, Sergey and Rocklin, Gabriel J.},
	month = aug,
	year = {2023},
	pages = {434--444},
	file = {Full Text:/Users/admin/Zotero/storage/54IHFJGX/Tsuboyama et al. - 2023 - Mega-scale experimental analysis of protein foldin.pdf:application/pdf},
}


@UNPUBLISHED{suphatrakul_functional_2023,
  title    = "Functional analysis of flavivirus replicase by deep mutational
              scanning of dengue {NS5}",
  author   = "Suphatrakul, Amporn and Posiri, Pratsaneeyaporn and Srisuk,
              Nittaya and Nantachokchawapan, Rapirat and Onnome, Suppachoke and
              Mongkolsapaya, Juthathip and Siridechadilok, Bunpote",
  abstract = "Flavivirus NS5 is multi-functional viral protein that play
              critical roles in virus replication, evolution, and immune
              antagonism against the hosts. Its error-prone replicase activity
              copies viral RNA for progeny virus particles and shapes virus
              evolution. Its methyltransferase activity and STAT2-targeting
              activity compromise type-I interferon signalling, dampening
              protective immune response during infection. It interacts with
              several host factors to shape the host-cell environment for virus
              replication. Thus, NS5 represents a critical target for both
              vaccine and antiviral drug development. Here, we performed deep
              mutational scanning (DMS) on the NS5 of dengue virus serotype 2
              in mammalian cells. In combination with available structural and
              biochemical data, the comprehensive single amino-acid mutational
              data corroborated key residues and interactions involved in
              enzymatic functions of the replicase and suggested potential
              plasticity in NS5 guanylyl transferase. Strikingly, we identified
              that a set of strictly conserved residues in the motifs lining
              the replicase active site could tolerate mutations, suggesting
              additional roles of the priming loop in viral RNA synthesis and
              possible strategies to modulate the error rate of viral replicase
              activity through active-site engineering. Our DMS dataset and NS5
              libraries could provide a framework and a resource to investigate
              molecular, evolutionary, and immunological aspects of NS5
              functions, with relevance to vaccine and antiviral drug
              development. \#\#\# Competing Interest Statement B.S., A.S.,
              P.P., N.S., R.N., and S.O. have filed a patent application
              related to this work.",
  journal  = "bioRxiv",
  pages    = "2023.03.07.531617",
  month    =  mar,
  year     =  2023,
  language = "en"
}

@ARTICLE{weile_shifting_2021,
  title    = "Shifting landscapes of human {MTHFR} missense-variant effects",
  author   = "Weile, Jochen and Kishore, Nishka and Sun, Song and Maaieh, Ranim
              and Verby, Marta and Li, Roujia and Fotiadou, Iosifina and
              Kitaygorodsky, Julia and Wu, Yingzhou and Holenstein, Alexander
              and B{\"u}rer, C{\'e}line and Blomgren, Linnea and Yang, Shan and
              Nussbaum, Robert and Rozen, Rima and Watkins, David and Gebbia,
              Marinella and Kozich, Viktor and Garton, Michael and Froese, D
              Sean and Roth, Frederick P",
  abstract = "Most rare clinical missense variants cannot currently be
              classified as pathogenic or benign. Deficiency in human
              5,10-methylenetetrahydrofolate reductase (MTHFR), the most common
              inherited disorder of folate metabolism, is caused primarily by
              rare missense variants. Further complicating variant
              interpretation, variant impacts often depend on environment. An
              important example of this phenomenon is the MTHFR variant
              p.Ala222Val (c.665C>T), which is carried by half of all humans
              and has a phenotypic impact that depends on dietary folate. Here
              we describe the results of 98,336 variant functional-impact
              assays, covering nearly all possible MTHFR amino acid
              substitutions in four folinate environments, each in the presence
              and absence of p.Ala222Val. The resulting atlas of MTHFR variant
              effects reveals many complex dependencies on both folinate and
              p.Ala222Val. MTHFR atlas scores can distinguish pathogenic from
              benign variants and, among individuals with severe MTHFR
              deficiency, correlate with age of disease onset. Providing a
              powerful tool for understanding structure-function relationships,
              the atlas suggests a role for a disordered loop in retaining
              cofactor at the active site and identifies variants that enable
              escape of inhibition by S-adenosylmethionine. Thus, a model based
              on eight MTHFR variant effect maps illustrates how shifting
              landscapes of environment- and genetic-background-dependent
              missense variation can inform our clinical, structural, and
              functional understanding of MTHFR deficiency.",
  journal  = "American Journal of Human Genetics",
  volume   =  108,
  number   =  7,
  pages    = "1283--1300",
  month    =  jul,
  year     =  2021,
  keywords = "clinical variant interpretation; cystathionine beta synthase;
              deep mutational scanning; folate; gene- environment interaction;
              homocystinuria; methylenetetrahydrofolate reductase; molecular
              dynamics; mthfr; variant effect mapping",
  language = "en"
}

@ARTICLE{xie_predicting_2023,
  title    = "Predicting the functional effect of compound heterozygous
              genotypes from large scale variant effect maps",
  author   = "Xie, Michael J and Cromie, Gareth A and Owens, Katherine and
              Timour, Martin S and Tang, Michelle and Kutz, J Nathan and
              El-Hattab, Ayman W and McLaughlin, Richard N and Dudley,
              Aim{\'e}e M",
  abstract = "BACKGROUND: Pathogenic variants in PHGDH, PSAT1 , and PSPH cause
              a set of rare, autosomal recessive diseases known as serine
              biosynthesis defects. Serine biosynthesis defects present in a
              broad phenotypic spectrum that includes, at the severe end,
              Neu-Laxova syndrome, a lethal multiple congenital anomaly
              disease, intermediately in the form of infantile serine
              biosynthesis defects with severe neurological manifestations and
              growth deficiency, and at the mild end, as childhood disease with
              intellectual disability. However, because L-serine
              supplementation, especially if started early, can ameliorate and
              in some cases even prevent symptoms, knowledge of pathogenic
              variants is highly actionable. METHODS: Recently, our laboratory
              established a yeast-based assay for human PSAT1 function. We have
              now applied it at scale to assay the functional impact of 1,914
              SNV-accessible amino acid substitutions. In addition to assaying
              the functional impact of individual variants in yeast haploid
              cells, we can assay pairwise combinations of PSAT1 alleles that
              recapitulate human genotypes, including compound heterozygotes,
              in yeast diploids. RESULTS: Results of our assays of individual
              variants (in haploid yeast cells) agree well with clinical
              interpretations and protein structure-function relationships,
              supporting the use of our data as functional evidence under the
              ACMG interpretation guidelines. Results from our diploid assay
              successfully distinguish patient genotypes from those of healthy
              carriers and agree well with disease severity. Finally, we
              present a linear model that uses individual allele measurements
              (in haploid yeast cells) to accurately predict the biallelic
              function (in diploid yeast cells) of ~ 1.8 million allele
              combinations corresponding to potential human genotypes.
              CONCLUSIONS: Taken together, our work provides an example of how
              large-scale functional assays in model systems can be powerfully
              applied to the study of a rare disease.",
  journal  = "bioRxiv",
  month    =  jan,
  year     =  2023,
  language = "en"
}

@ARTICLE{roychowdhury_microfluidic_2022,
  title    = "Microfluidic deep mutational scanning of the human executioner
              caspases reveals differences in structure and regulation",
  author   = "Roychowdhury, Hridindu and Romero, Philip A",
  abstract = "The human caspase family comprises 12 cysteine proteases that are
              centrally involved in cell death and inflammation responses. The
              members of this family have conserved sequences and structures,
              highly similar enzymatic activities and substrate preferences,
              and overlapping physiological roles. In this paper, we present a
              deep mutational scan of the executioner caspases CASP3 and CASP7
              to dissect differences in their structure, function, and
              regulation. Our approach leverages high-throughput microfluidic
              screening to analyze hundreds of thousands of caspase variants in
              tightly controlled in vitro reactions. The resulting data
              provides a large-scale and unbiased view of the impact of amino
              acid substitutions on the proteolytic activity of CASP3 and
              CASP7. We use this data to pinpoint key functional differences
              between CASP3 and CASP7, including a secondary internal cleavage
              site, CASP7 Q196 that is not present in CASP3. Our results will
              open avenues for inquiry in caspase function and regulation that
              could potentially inform the development of future
              caspase-specific therapeutics.",
  journal  = "Cell Death Discovery",
  volume   =  8,
  number   =  1,
  pages    = "7",
  month    =  jan,
  year     =  2022,
  language = "en"
}

@ARTICLE{andrews_distinct_2020,
  title    = "Distinct patterns of mutational sensitivity for $\lambda$
              resistance and maltodextrin transport in Escherichia coli {LamB}",
  author   = "Andrews, Bryan and Fields, Stanley",
  abstract = "Bacteria can evade cohabiting phages through mutations in phage
              receptors, but these mutations may come at a cost if they disrupt
              the receptor's native cellular function. To investigate the
              relationship between these two conflicting activities, we
              generated sequence-function maps of Escherichia coli LamB with
              respect to sensitivity to phage $\lambda$ and transport of
              maltodextrin. By comparing 413 missense mutations whose effect on
              both traits could be analysed, we find that these two phenotypes
              were correlated, implying that most mutations affect these
              phenotypes through a common mechanism such as loss of protein
              stability. However, individual mutations could be found that
              specifically disrupt $\lambda$-sensitivity without affecting
              maltodextrin transport. We identify and individually assay nine
              such mutations, whose spatial positions implicate loop L6 of LamB
              in $\lambda$ binding. Although missense mutations that lead to
              $\lambda$-resistance are rare, they were approximately as likely
              to be maltodextrin-utilizing (Mal+) as not (Mal-), implying that
              E. coli can adapt to $\lambda$ while conserving the receptor's
              native function. We propose that in order for E. coli and
              $\lambda$ to stably cohabitate, selection for
              $\lambda$-resistance and maltose transport must be spatially or
              temporally separated.",
  journal  = "Microbial Genomics",
  volume   =  6,
  number   =  4,
  month    =  apr,
  year     =  2020,
  keywords = "Escherichia coli; LamB; evolution; nutrient transport; phage
              $\lambda$",
  language = "en"
}

@ARTICLE{lo_functional_2023,
  title    = "The functional impact of 1,570 individual amino acid
              substitutions in human {OTC}",
  author   = "Lo, Russell S and Cromie, Gareth A and Tang, Michelle and Teng,
              Kevin and Owens, Katherine and Sirr, Amy and Kutz, J Nathan and
              Morizono, Hiroki and Caldovic, Ljubica and Ah Mew, Nicholas and
              Gropman, Andrea and Dudley, Aim{\'e}e M",
  abstract = "Deleterious mutations in the X-linked gene encoding ornithine
              transcarbamylase (OTC) cause the most common urea cycle disorder,
              OTC deficiency. This rare but highly actionable disease can
              present with severe neonatal onset in males or with later onset
              in either sex. Individuals with neonatal onset appear normal at
              birth but rapidly develop hyperammonemia, which can progress to
              cerebral edema, coma, and death, outcomes ameliorated by rapid
              diagnosis and treatment. Here, we develop a high-throughput
              functional assay for human OTC and individually measure the
              impact of 1,570 variants, 84\% of all SNV-accessible missense
              mutations. Comparison to existing clinical significance calls,
              demonstrated that our assay distinguishes known benign from
              pathogenic variants and variants with neonatal onset from
              late-onset disease presentation. This functional stratification
              allowed us to identify score ranges corresponding to clinically
              relevant levels of impairment of OTC activity. Examining the
              results of our assay in the context of protein structure further
              allowed us to identify a 13 amino acid domain, the SMG loop,
              whose function appears to be required in human cells but not in
              yeast. Finally, inclusion of our data as PS3 evidence under the
              current ACMG guidelines, in a pilot reclassification of 34
              variants with complete loss of activity, would change the
              classification of 22 from variants of unknown significance to
              clinically actionable likely pathogenic variants. These results
              illustrate how large-scale functional assays are especially
              powerful when applied to rare genetic diseases.",
  journal  = "American Journal of Human Genetics",
  volume   =  110,
  number   =  5,
  pages    = "863--879",
  month    =  may,
  year     =  2023,
  keywords = "OTC deficiency; Oxford Nanopore sequencing; SNV
              analysis/discovery; X-linked disease; metabolic disorder; model
              organisms; multiplexed assays of variant effect; rare disease;
              rare variants; urea cycle disorder; variant interpretation",
  language = "en"
}

@ARTICLE{gajula_high_2014,
  title    = "High-throughput mutagenesis reveals functional determinants for
              {DNA} targeting by activation-induced deaminase",
  author   = "Gajula, Kiran S and Huwe, Peter J and Mo, Charlie Y and Crawford,
              Daniel J and Stivers, James T and Radhakrishnan, Ravi and Kohli,
              Rahul M",
  abstract = "Antibody maturation is a critical immune process governed by the
              enzyme activation-induced deaminase (AID), a member of the
              AID/APOBEC DNA deaminase family. AID/APOBEC deaminases
              preferentially target cytosine within distinct preferred sequence
              motifs in DNA, with specificity largely conferred by a small 9-11
              residue protein loop that differs among family members. Here, we
              aimed to determine the key functional characteristics of this
              protein loop in AID and to thereby inform our understanding of
              the mode of DNA engagement. To this end, we developed a
              methodology (Sat-Sel-Seq) that couples saturation mutagenesis at
              each position across the targeting loop, with iterative
              functional selection and next-generation sequencing. This
              high-throughput mutational analysis revealed dominant
              characteristics for residues within the loop and additionally
              yielded enzymatic variants that enhance deaminase activity. To
              rationalize these functional requirements, we performed molecular
              dynamics simulations that suggest that AID and its hyperactive
              variants can engage DNA in multiple specific modes. These
              findings align with AID's competing requirements for specificity
              and flexibility to efficiently drive antibody maturation. Beyond
              insights into the AID-DNA interface, our Sat-Sel-Seq approach
              also serves to further expand the repertoire of techniques for
              deep positional scanning and may find general utility for
              high-throughput analysis of protein function.",
  journal  = "Nucleic Acids Research",
  volume   =  42,
  number   =  15,
  pages    = "9964--9975",
  month    =  sep,
  year     =  2014,
  language = "en"
}

% The entry below contains non-ASCII chars that could not be converted
% to a LaTeX equivalent.
@UNPUBLISHED{chakraborty_profiling_2021,
  title    = "Profiling of the drug resistance of thousands of Src tyrosine
              kinase mutants uncovers a regulatory network that couples
              autoinhibition to catalytic domain dynamics",
  author   = "Chakraborty, Sujata and Ahler, Ethan and Simon, Jessica J and
              Fang, Linglan and Potter, Zachary E and Sitko, Katherine A and
              Stephany, Jason J and Guttman, Miklos and Fowler, Douglas M and
              Maly, Dustin J",
  abstract = "SUMMARYKinase inhibitors are effective cancer therapies but
              resistance often limits clinical efficacy. Despite the
              cataloguing of numerous resistance mutations, our understanding
              of kinase inhibitor resistance is still incomplete. Here, we
              comprehensively profiled the resistance of ∼3500 Src tyrosine
              kinase mutants to four different ATP-competitive inhibitors. We
              found that ATP-competitive inhibitor resistance mutations are
              distributed throughout Src's catalytic domain. In addition to
              inhibitor contact residues, residues that participate in
              regulating Src's phosphotransferase activity were prone to the
              development of resistance. Unexpectedly, we found that a
              resistance-prone cluster of residues located on the top face of
              the N-terminal lobe of Src's catalytic domain contributes to
              autoinhibition by reducing catalytic domain dynamics, and
              mutations in this cluster led to resistance by lowering inhibitor
              affinity and promoting kinase hyperactivation. Together, our
              studies demonstrate how drug resistance profiling can be used to
              define potential resistance pathways and uncover new mechanisms
              of kinase regulation.",
  journal  = "bioRxiv",
  month    =  dec,
  year     =  2021
}

@UNPUBLISHED{weng_energetic_2022,
  title    = "The energetic and allosteric landscape for {KRAS} inhibition",
  author   = "Weng, Chenchun and Faure, Andre J and Lehner, Ben",
  abstract = "Thousands of proteins have now been genetically-validated as
              therapeutic targets in hundreds of human diseases. However, very
              few have actually been successfully targeted and many are
              considered `undruggable'. This is particularly true for proteins
              that function via protein-protein interactions: direct inhibition
              of binding interfaces is difficult, requiring the identification
              of allosteric sites. However, most proteins have no known
              allosteric sites and a comprehensive allosteric map does not
              exist for any protein. Here we address this shortcoming by
              charting multiple global atlases of inhibitory allosteric
              communication in KRAS, a protein mutated in 1 in 10 human
              cancers. We quantified the impact of >26,000 mutations on the
              folding of KRAS and its binding to six interaction partners.
              Genetic interactions in double mutants allowed us to perform
              biophysical measurements at scale, inferring >22,000 causal free
              energy changes, a similar number of measurements as the total
              made for proteins to date. These energy landscapes quantify how
              mutations tune the binding specificity of a signalling protein
              and map the inhibitory allosteric sites for an important
              therapeutic target. Allosteric propagation is particularly
              effective across the central beta sheet of KRAS and multiple
              surface pockets are genetically-validated as allosterically
              active, including a distal pocket in the C-terminal lobe of the
              protein. Allosteric mutations typically inhibit binding to all
              tested effectors but they can also change the binding
              specificity, revealing the regulatory, evolutionary and
              therapeutic potential to tune pathway activation. Using the
              approach described here it should be possible to rapidly and
              comprehensively identify allosteric target sites in many
              important proteins. \#\#\# Competing Interest Statement The
              authors have declared no competing interest.",
  journal  = "bioRxiv",
  pages    = "2022.12.06.519122",
  month    =  dec,
  year     =  2022,
  language = "en"
}

% The entry below contains non-ASCII chars that could not be converted
% to a LaTeX equivalent.
@UNPUBLISHED{ding_protein_2023,
  title    = "Protein design using structure-based residue preferences",
  author   = "Ding, David and Shaw, Ada and Sinai, Sam and Rollins, Nathan and
              Prywes, Noam and Savage, David F and Laub, Michael T and Marks,
              Debora S",
  abstract = "Recent developments in protein design have adapted large neural
              networks with up to 100s of millions of parameters to learn
              complex sequence-function mappings. However, it is unclear which
              dependencies between residues are critical for determining
              protein function, and a better empirical understanding could
              enable high quality models that are also more data- and
              resource-efficient. Here, we observe that the per residue amino
              acid preferences - without considering interactions between
              mutations are sufficient to explain much, and sometimes virtually
              all of the combinatorial mutation effects across 7 datasets (R2 ∼
              78-98\%), including one generated here. These preference
              parameters (20*N, where N is the number of mutated residues) can
              be learned from as few as ∼5\textbackslash*20\textbackslash*N
              observations to predict a much larger number (potentially up to
              20N) of combinatorial variant effects with high accuracy (Pearson
              r > 0.8). We hypothesized that the local structural dependencies
              surrounding a residue could be sufficient to learn these required
              mutation preferences, and developed an unsupervised design
              approach, which we term CoVES for `Combinatorial Variant Effects
              from Structure'. We show that CoVES outperforms not just model
              free sampling approaches but also complicated, high-capacity
              autoregressive neural networks in generating functional and
              diverse sequence variants for two example proteins. This simple,
              biologically-rooted model can be an effective alternative to
              high-capacity, out of domain models for the design of functional
              proteins. \#\#\# Competing Interest Statement SS is employed by
              Dyno Therapeutics. DSM is an advisor for Dyno Therapeutics,
              Octant, Jura Bio, Tectonic Therapeutics, and Genentech, and a
              co-founder of Seismic. NR is employed by Seismic. DFS is a
              co-founder and scientific advisory board member of Scribe
              Therapeutics. The remaining authors declare no competing
              interests.",
  journal  = "bioRxiv",
  pages    = "2022.10.31.514613",
  month    =  jun,
  year     =  2023,
  language = "en"
}

@ARTICLE{nguyen_molecular_2023,
  title    = "Molecular determinants of Hsp90 dependence of Src kinase revealed
              by deep mutational scanning",
  author   = "Nguyen, Vanessa and Ahler, Ethan and Sitko, Katherine A and
              Stephany, Jason J and Maly, Dustin J and Fowler, Douglas M",
  abstract = "Hsp90 is a molecular chaperone involved in the refolding and
              activation of numerous protein substrates referred to as clients.
              While the molecular determinants of Hsp90 client specificity are
              poorly understood and limited to a handful of client proteins,
              strong clients are thought to be destabilized and
              conformationally extended. Here, we measured the
              phosphotransferase activity of 3929 variants of the tyrosine
              kinase Src in both the presence and absence of an Hsp90
              inhibitor. We identified 84 previously unknown functionally
              dependent client variants. Unexpectedly, many destabilized or
              extended variants were not functionally dependent on Hsp90.
              Instead, functionally dependent client variants were clustered in
              the $\alpha$F pocket and $\beta$1-$\beta$2 strand regions of Src,
              which have yet to be described in driving Hsp90 dependence. Hsp90
              dependence was also strongly correlated with kinase activity. We
              found that a combination of activation, global extension, and
              general conformational flexibility, primarily induced by variants
              at the $\alpha$F pocket and $\beta$1-$\beta$2 strands, was
              necessary to render Src functionally dependent on Hsp90.
              Moreover, the degree of activation and flexibility required to
              transform Src into a functionally dependent client varied with
              variant location, suggesting that a combination of regulatory
              domain disengagement and catalytic domain flexibility are
              required for chaperone dependence. Thus, by studying the
              chaperone dependence of a massive number of variants, we
              highlight factors driving Hsp90 client specificity and propose a
              model of chaperone-kinase interactions.",
  journal  = "Protein Science",
  volume   =  32,
  number   =  7,
  pages    = "e4656",
  month    =  jul,
  year     =  2023,
  keywords = "Hsp90; Hsp90 inhibitor; chaperone; client; src kinase; tyrosine
              kinase",
  language = "en"
}

@ARTICLE{seuma_atlas_2022,
  title    = "An atlas of amyloid aggregation: the impact of substitutions,
              insertions, deletions and truncations on amyloid beta fibril
              nucleation",
  author   = "Seuma, Mireia and Lehner, Ben and Bolognesi, Benedetta",
  abstract = "Multiplexed assays of variant effects (MAVEs) guide clinical
              variant interpretation and reveal disease mechanisms. To date,
              MAVEs have focussed on a single mutation type-amino acid (AA)
              substitutions-despite the diversity of coding variants that cause
              disease. Here we use Deep Indel Mutagenesis (DIM) to generate a
              comprehensive atlas of diverse variant effects for a disease
              protein, the amyloid beta (A$\beta$) peptide that aggregates in
              Alzheimer's disease (AD) and is mutated in familial AD (fAD). The
              atlas identifies known fAD mutations and reveals that many
              variants beyond substitutions accelerate A$\beta$ aggregation and
              are likely to be pathogenic. Truncations, substitutions,
              insertions, single- and internal multi-AA deletions differ in
              their propensity to enhance or impair aggregation, but likely
              pathogenic variants from all classes are highly enriched in the
              polar N-terminal region of A$\beta$. This comparative atlas
              highlights the importance of including diverse mutation types in
              MAVEs and provides important mechanistic insights into amyloid
              nucleation.",
  journal  = "Nature Communications",
  volume   =  13,
  number   =  1,
  pages    = "7084",
  month    =  nov,
  year     =  2022,
  language = "en"
}

@ARTICLE{ursu_massively_2022,
  title    = "Massively parallel phenotyping of coding variants in cancer with
              Perturb-seq",
  author   = "Ursu, Oana and Neal, James T and Shea, Emily and Thakore,
              Pratiksha I and Jerby-Arnon, Livnat and Nguyen, Lan and Dionne,
              Danielle and Diaz, Celeste and Bauman, Julia and Mosaad, Mariam
              Mounir and Fagre, Christian and Lo, April and McSharry, Maria and
              Giacomelli, Andrew O and Ly, Seav Huong and Rozenblatt-Rosen,
              Orit and Hahn, William C and Aguirre, Andrew J and Berger, Alice
              H and Regev, Aviv and Boehm, Jesse S",
  abstract = "Genome sequencing studies have identified millions of somatic
              variants in cancer, but it remains challenging to predict the
              phenotypic impact of most. Experimental approaches to distinguish
              impactful variants often use phenotypic assays that report on
              predefined gene-specific functional effects in bulk cell
              populations. Here, we develop an approach to functionally assess
              variant impact in single cells by pooled Perturb-seq. We measured
              the impact of 200 TP53 and KRAS variants on RNA profiles in over
              300,000 single lung cancer cells, and used the profiles to
              categorize variants into phenotypic subsets to distinguish
              gain-of-function, loss-of-function and dominant negative
              variants, which we validated by comparison with orthogonal
              assays. We discovered that KRAS variants did not merely fit into
              discrete functional categories, but spanned a continuum of
              gain-of-function phenotypes, and that their functional impact
              could not have been predicted solely by their frequency in
              patient cohorts. Our work provides a scalable, gene-agnostic
              method for coding variant impact phenotyping, with potential
              applications in multiple disease settings.",
  journal  = "Nature Biotechnology",
  volume   =  40,
  number   =  6,
  pages    = "896--905",
  month    =  jun,
  year     =  2022,
  language = "en"
}

% The entry below contains non-ASCII chars that could not be converted
% to a LaTeX equivalent.
@ARTICLE{wrenbeck_automated_2019,
  title    = "An Automated {Data-Driven} Pipeline for Improving Heterologous
              Enzyme Expression",
  author   = "Wrenbeck, Emily E and Bedewitz, Matthew A and Klesmith, Justin R
              and Noshin, Syeda and Barry, Cornelius S and Whitehead, Timothy A",
  abstract = "Enzymes are the ultimate entities responsible for chemical
              transformations in natural and engineered biosynthetic pathways.
              However, many natural enzymes suffer from suboptimal functional
              expression due to poor intrinsic protein stability. Further,
              stability enhancing mutations often come at the cost of impaired
              function. Here we demonstrate an automated protein engineering
              strategy for stabilizing enzymes while retaining catalytic
              function using deep mutational scanning coupled to
              multiple-filter based screening and combinatorial mutagenesis. We
              validated this strategy by improving the functional expression of
              a Type III polyketide synthase from the Atropa belladonna
              biosynthetic pathway for tropane alkaloids. The best variant had
              a total of 8 mutations with over 25-fold improved activity over
              wild-type in E. coli cell lysates, an improved melting
              temperature of 11.5 $\pm$ 0.6 °C, and only minimal reduction in
              catalytic efficiency. We show that the multiple-filter approach
              maintains acceptable sensitivity with homology modeling
              structures up to 4 {\AA} RMS. Our results highlight an automated
              protein engineering tool for improving the stability and
              solubility of difficult to express enzymes, which has impact for
              biotechnological applications.",
  journal  = "ACS Synthetic Biology",
  volume   =  8,
  number   =  3,
  pages    = "474--481",
  month    =  mar,
  year     =  2019,
  keywords = "deep mutational scanning; enzyme stability; heterologous pathway
              expression; high-throughput screening; polyketide synthase;
              tropane alkaloids",
  language = "en"
}

@ARTICLE{hom_deep_2019,
  title    = "Deep Mutational Scan of the Highly Conserved Influenza A Virus
              {M1} Matrix Protein Reveals Substantial Intrinsic Mutational
              Tolerance",
  author   = "Hom, Nancy and Gentles, Lauren and Bloom, Jesse D and Lee, Kelly
              K",
  abstract = "Influenza A virus matrix protein M1 is involved in multiple
              stages of the viral infectious cycle. Despite its functional
              importance, our present understanding of this essential viral
              protein is limited. The roles of a small subset of specific amino
              acids have been reported, but a more comprehensive understanding
              of the relationship between M1 sequence, structure, and virus
              fitness remains elusive. In this study, we used deep mutational
              scanning to measure the effect of every amino acid substitution
              in M1 on viral replication in cell culture. The map of amino acid
              mutational tolerance we have generated allows us to identify
              sites that are functionally constrained in cell culture as well
              as sites that are less constrained. Several sites that exhibit
              low tolerance to mutation have been found to be critical for M1
              function and production of viable virions. Surprisingly,
              significant portions of the M1 sequence, especially in the
              C-terminal domain, whose structure is undetermined, were found to
              be highly tolerant of amino acid variation, despite having
              extremely low levels of sequence diversity among natural
              influenza virus strains. This unexpected discrepancy indicates
              that not all sites in M1 that exhibit high sequence conservation
              in nature are under strong constraint during selection for viral
              replication in cell culture.IMPORTANCE The M1 matrix protein is
              critical for many stages of the influenza virus infection cycle.
              Currently, we have an incomplete understanding of this highly
              conserved protein's function and structure. Key regions of M1,
              particularly in the C terminus of the protein, remain poorly
              characterized. In this study, we used deep mutational scanning to
              determine the extent of M1's tolerance to mutation. Surprisingly,
              nearly two-thirds of the M1 sequence exhibits a high tolerance
              for substitutions, contrary to the extremely low sequence
              diversity observed across naturally occurring M1 isolates. Sites
              with low mutational tolerance were also identified, suggesting
              that they likely play critical functional roles and are under
              selective pressure. These results reveal the intrinsic mutational
              tolerance throughout M1 and shape future inquiries probing the
              functions of this essential influenza A virus protein.",
  journal  = "Journal of Virology",
  volume   =  93,
  number   =  13,
  month    =  jul,
  year     =  2019,
  keywords = "M1 matrix; codon library; deep mutational scan; influenza A
              virus; mutational tolerance; selection; viral evolution",
  language = "en"
}

% The entry below contains non-ASCII chars that could not be converted
% to a LaTeX equivalent.
@ARTICLE{gray_elucidating_2019,
  title    = "Elucidating the Molecular Determinants of {A$\beta$} Aggregation
              with Deep Mutational Scanning",
  author   = "Gray, Vanessa E and Sitko, Katherine and Kameni, Floriane Z Ngako
              and Williamson, Miriam and Stephany, Jason J and Hasle, Nicholas
              and Fowler, Douglas M",
  abstract = "Despite the importance of A$\beta$ aggregation in Alzheimer's
              disease etiology, our understanding of the sequence determinants
              of aggregation is sparse and largely derived from in vitro
              studies. For example, in vitro proline and alanine scanning
              mutagenesis of A$\beta$40 proposed core regions important for
              aggregation. However, we lack even this limited mutagenesis data
              for the more disease-relevant A$\beta$42 Thus, to better
              understand the molecular determinants of A$\beta$42 aggregation
              in a cell-based system, we combined a yeast DHFR aggregation
              assay with deep mutational scanning. We measured the effect of
              791 of the 798 possible single amino acid substitutions on the
              aggregation propensity of A$\beta$42 We found that ∼75\% of
              substitutions, largely to hydrophobic residues, maintained or
              increased aggregation. We identified 11 positions at which
              substitutions, particularly to hydrophilic and charged amino
              acids, disrupted A$\beta$ aggregation. These critical positions
              were similar but not identical to critical positions identified
              in previous A$\beta$ mutagenesis studies. Finally, we analyzed
              our large-scale mutagenesis data in the context of different
              A$\beta$ aggregate structural models, finding that the
              mutagenesis data agreed best with models derived from fibrils
              seeded using brain-derived A$\beta$ aggregates.",
  journal  = "G3",
  volume   =  9,
  number   =  11,
  pages    = "3683--3689",
  month    =  nov,
  year     =  2019,
  keywords = "Amyloid; Amyloid beta; Deep mutational scanning; Protein
              aggregation",
  language = "en"
}

@ARTICLE{veerapandian_directed_2018,
  title    = "Directed Evolution of Reprogramming Factors by Cell Selection and
              Sequencing",
  author   = "Veerapandian, Veeramohan and Ackermann, Jan Ole and Srivastava,
              Yogesh and Malik, Vikas and Weng, Mingxi and Yang, Xiaoxiao and
              Jauch, Ralf",
  abstract = "Directed biomolecular evolution is widely used to tailor and
              enhance enzymes, fluorescent proteins, and antibodies but has
              hitherto not been applied in the reprogramming of mammalian
              cells. Here, we describe a method termed directed evolution of
              reprogramming factors by cell selection and sequencing
              (DERBY-seq) to identify artificially enhanced and evolved
              reprogramming transcription factors. DERBY-seq entails pooled
              screens with libraries of positionally randomised genes, cell
              selection based on phenotypic readouts, and genotyping by
              amplicon sequencing for candidate identification. We benchmark
              this approach using pluripotency reprogramming with libraries
              based on the reprogramming factor SOX2 and the reprogramming
              incompetent endodermal factor SOX17. We identified several SOX2
              variants outperforming the wild-type protein in three- and
              four-factor cocktails. The most effective variants were
              discovered from the SOX17 library, demonstrating that this factor
              can be converted into a highly potent inducer of pluripotency
              with a range of diverse modifications. We propose DERBY-seq as a
              broad-based approach to discover reprogramming factors for any
              donor/target cell combination applicable to direct lineage
              reprogramming in vitro and in vivo.",
  journal  = "Stem Cell Reports",
  volume   =  11,
  number   =  2,
  pages    = "593--606",
  month    =  aug,
  year     =  2018,
  keywords = "OCT4; SOX17; SOX2; cellular reprogramming; deep mutational
              scanning; directed evolution; protein engineering; synthetic
              biology; synthetic transcription factors",
  language = "en"
}

@ARTICLE{thyagarajan_inherent_2014,
  title    = "The inherent mutational tolerance and antigenic evolvability of
              influenza hemagglutinin",
  author   = "Thyagarajan, Bargavi and Bloom, Jesse D",
  abstract = "Influenza is notable for its evolutionary capacity to escape
              immunity targeting the viral hemagglutinin. We used deep
              mutational scanning to examine the extent to which a high
              inherent mutational tolerance contributes to this antigenic
              evolvability. We created mutant viruses that incorporate most of
              the $\approx$10(4) amino-acid mutations to hemagglutinin from
              A/WSN/1933 (H1N1) influenza. After passaging these viruses in
              tissue culture to select for functional variants, we used deep
              sequencing to quantify mutation frequencies before and after
              selection. These data enable us to infer the preference for each
              amino acid at each site in hemagglutinin. These inferences are
              consistent with existing knowledge about the protein's structure
              and function, and can be used to create a model that describes
              hemagglutinin's evolution far better than existing phylogenetic
              models. We show that hemagglutinin has a high inherent tolerance
              for mutations at antigenic sites, suggesting that this is one
              factor contributing to influenza's antigenic evolution.",
  journal  = "Elife",
  volume   =  3,
  month    =  jul,
  year     =  2014,
  keywords = "antigenic evolution; deep mutational scanning; evolutionary
              biology; evolvability; genomics; hemagglutinin; infectious
              disease; influenza; microbiology; phylogenetics; viruses",
  language = "en"
}

@ARTICLE{ostermaier_functional_2014,
  title    = "Functional map of arrestin-1 at single amino acid resolution",
  author   = "Ostermaier, Martin K and Peterhans, Christian and Jaussi, Rolf
              and Deupi, Xavier and Standfuss, J{\"o}rg",
  abstract = "Arrestins function as adapter proteins that mediate G
              protein-coupled receptor (GPCR) desensitization, internalization,
              and additional rounds of signaling. Here we have compared binding
              of the GPCR rhodopsin to 403 mutants of arrestin-1 covering its
              complete sequence. This comprehensive and unbiased mutagenesis
              approach provides a functional dimension to the crystal
              structures of inactive, preactivated p44 and phosphopeptide-bound
              arrestins and will guide our understanding of arrestin-GPCR
              complexes. The presented functional map quantitatively connects
              critical interactions in the polar core and along the C tail of
              arrestin. A series of amino acids (Phe375, Phe377, Phe380, and
              Arg382) anchor the C tail in a position that blocks binding of
              the receptor. Interaction of phosphates in the rhodopsin C
              terminus with Arg29 controls a C-tail exchange mechanism in which
              the C tail of arrestin is released and exposes several charged
              amino acids (Lys14, Lys15, Arg18, Lys20, Lys110, and Lys300) for
              binding of the phosphorylated receptor C terminus. In addition to
              this arrestin phosphosensor, our data reveal several patches of
              amino acids in the finger (Gln69 and Asp73-Met75) and the lariat
              loops (L249-S252 and Y254) that can act as direct binding
              interfaces. A stretch of amino acids at the edge of the C domain
              (Trp194-Ser199, Gly337-Gly340, Thr343, and Thr345) could act as
              membrane anchor, binding interface for a second rhodopsin, or
              rearrange closer to the central loops upon complex formation. We
              discuss these interfaces in the context of experimentally guided
              docking between the crystal structures of arrestin and
              light-activated rhodopsin.",
  journal  = "Proceedings of the National Academy of Sciences",
  volume   =  111,
  number   =  5,
  pages    = "1825--1830",
  month    =  feb,
  year     =  2014,
  keywords = "cell signaling; membrane receptor; protein engineering; scanning
              mutagenesis; visual system",
  language = "en"
}

@ARTICLE{bloom_experimentally_2014,
  title    = "An experimentally determined evolutionary model dramatically
              improves phylogenetic fit",
  author   = "Bloom, Jesse D",
  abstract = "All modern approaches to molecular phylogenetics require a
              quantitative model for how genes evolve. Unfortunately, existing
              evolutionary models do not realistically represent the
              site-heterogeneous selection that governs actual sequence change.
              Attempts to remedy this problem have involved augmenting these
              models with a burgeoning number of free parameters. Here, I
              demonstrate an alternative: Experimental determination of a
              parameter-free evolutionary model via mutagenesis, functional
              selection, and deep sequencing. Using this strategy, I create an
              evolutionary model for influenza nucleoprotein that describes the
              gene phylogeny far better than existing models with dozens or
              even hundreds of free parameters. Emerging high-throughput
              experimental strategies such as the one employed here provide
              fundamentally new information that has the potential to transform
              the sensitivity of phylogenetic and genetic analyses.",
  journal  = "Molecular Biology and Evolution",
  volume   =  31,
  number   =  8,
  pages    = "1956--1978",
  month    =  aug,
  year     =  2014,
  keywords = "codon model; deep mutational scanning; influenza; nucleoprotein;
              phylogenetics; substitution model",
  language = "en"
}

@ARTICLE{hietpas_experimental_2011,
  title    = "Experimental illumination of a fitness landscape",
  author   = "Hietpas, Ryan T and Jensen, Jeffrey D and Bolon, Daniel N A",
  abstract = "The genes of all organisms have been shaped by selective
              pressures. The relationship between gene sequence and fitness has
              tremendous implications for understanding both evolutionary
              processes and functional constraints on the encoded proteins.
              Here, we have exploited deep sequencing technology to
              experimentally determine the fitness of all possible individual
              point mutants under controlled conditions for a nine-amino acid
              region of Hsp90. Over the past five decades, limited glimpses
              into the relationship between gene sequence and function have
              sparked a long debate regarding the distribution, relative
              proportion, and evolutionary significance of deleterious,
              neutral, and advantageous mutations. Our systematic experimental
              measurement of fitness effects of Hsp90 mutants in yeast,
              evaluated in the light of existing population genetic theory, are
              remarkably consistent with a nearly neutral model of molecular
              evolution.",
  journal  = "Proceedings of the National Academy of Sciences of the United States of America",
  volume   =  108,
  number   =  19,
  pages    = "7896--7901",
  month    =  may,
  year     =  2011,
  language = "en"
}

@ARTICLE{gill_multiple_2023,
  title    = "Multiple mechanisms of self-association of chemokine receptors
              {CXCR4} and {CCR5} demonstrated by deep mutagenesis",
  author   = "Gill, Kevin S and Mehta, Kritika and Heredia, Jeremiah D and
              Krishnamurthy, Vishnu V and Zhang, Kai and Procko, Erik",
  abstract = "Chemokine receptors are members of the rhodopsin-like class A
              GPCRs whose signaling through G proteins drives the directional
              movement of cells in response to a chemokine gradient. Chemokine
              receptors CXCR4 and CCR5 have been extensively studied due to
              their roles in white blood cell development and inflammation and
              their status as coreceptors for HIV-1 infection, among other
              functions. Both receptors form dimers or oligomers but the
              function/s of self-associations are unclear. While CXCR4 has been
              crystallized in a dimeric arrangement, available atomic
              resolution structures of CCR5 are monomeric. To investigate the
              dimerization interfaces of these chemokine receptors, we used a
              bimolecular fluorescence complementation (BiFC)-based screen and
              deep mutational scanning to find mutations that modify receptor
              self-association. Many disruptive mutations promoted
              self-associations nonspecifically, suggesting they aggregated in
              the membrane. A mutationally intolerant region was found on CXCR4
              that matched the crystallographic dimer interface, supporting
              this dimeric arrangement in living cells. A mutationally
              intolerant region was also observed on the surface of CCR5 by
              transmembrane helices 3 and 4. Mutations from the deep mutational
              scan that reduce BiFC were validated and were localized in the
              transmembrane domains as well as the C-terminal cytoplasmic tails
              where they reduced lipid microdomain localization. The reduced
              self-association mutants of CXCR4 had increased binding to the
              ligand CXCL12 but diminished calcium signaling. There was no
              change in syncytia formation with cells expressing HIV-1 Env. The
              data highlight that multiple mechanisms are involved in
              self-association of chemokine receptor chains.",
  journal  = "bioRxiv",
  month    =  mar,
  year     =  2023,
  language = "en"
}

@ARTICLE{meier_deep_2023,
  title    = "Deep mutational scan of a drug efflux pump reveals its
              structure-function landscape",
  author   = "Meier, Gianmarco and Thavarasah, Sujani and Ehrenbolger, Kai and
              Hutter, Cedric A J and H{\"u}rlimann, Lea M and Barandun, Jonas
              and Seeger, Markus A",
  abstract = "Drug efflux is a common resistance mechanism found in bacteria
              and cancer cells, but studies providing comprehensive functional
              insights are scarce. In this study, we performed deep mutational
              scanning (DMS) on the bacterial ABC transporter EfrCD to
              determine the drug efflux activity profile of more than 1,430
              single variants. These systematic measurements revealed that the
              introduction of negative charges at different locations within
              the large substrate binding pocket results in strongly increased
              efflux activity toward positively charged ethidium, whereas
              additional aromatic residues did not display the same effect.
              Data analysis in the context of an inward-facing cryogenic
              electron microscopy structure of EfrCD uncovered a high-affinity
              binding site, which releases bound drugs through a peristaltic
              transport mechanism as the transporter transits to its
              outward-facing conformation. Finally, we identified substitutions
              resulting in rapid Hoechst influx without affecting the efflux
              activity for ethidium and daunorubicin. Hence, single mutations
              can convert EfrCD into a drug-specific ABC importer.",
  journal  = "Nature Chemical Biology",
  volume   =  19,
  number   =  4,
  pages    = "440--450",
  month    =  apr,
  year     =  2023,
  language = "en"
}

@ARTICLE{tan_high_2023,
  title    = "High-throughput identification of prefusion-stabilizing mutations
              in {SARS-CoV-2} spike",
  author   = "Tan, Timothy J C and Mou, Zongjun and Lei, Ruipeng and Ouyang,
              Wenhao O and Yuan, Meng and Song, Ge and Andrabi, Raiees and
              Wilson, Ian A and Kieffer, Collin and Dai, Xinghong and Matreyek,
              Kenneth A and Wu, Nicholas C",
  abstract = "Designing prefusion-stabilized SARS-CoV-2 spike is critical for
              the effectiveness of COVID-19 vaccines. All COVID-19 vaccines in
              the US encode spike with K986P/V987P mutations to stabilize its
              prefusion conformation. However, contemporary methods on
              engineering prefusion-stabilized spike immunogens involve tedious
              experimental work and heavily rely on structural information.
              Here, we establish a systematic and unbiased method of
              identifying mutations that concomitantly improve expression and
              stabilize the prefusion conformation of the SARS-CoV-2 spike. Our
              method integrates a fluorescence-based fusion assay, mammalian
              cell display technology, and deep mutational scanning. As a
              proof-of-concept, we apply this method to a region in the S2
              domain that includes the first heptad repeat and central helix.
              Our results reveal that besides K986P and V987P, several
              mutations simultaneously improve expression and significantly
              lower the fusogenicity of the spike. As prefusion stabilization
              is a common challenge for viral immunogen design, this work will
              help accelerate vaccine development against different viruses.",
  journal  = "Nature Communications",
  volume   =  14,
  number   =  1,
  pages    = "2003",
  month    =  apr,
  year     =  2023,
  language = "en"
}

@ARTICLE{macrae_protein_2023,
  title    = "Protein-protein interactions in the Mla lipid transport system
              probed by computational structure prediction and deep mutational
              scanning",
  author   = "MacRae, Mark R and Puvanendran, Dhenesh and Haase, Max A B and
              Coudray, Nicolas and Kolich, Ljuvica and Lam, Cherry and Baek,
              Minkyung and Bhabha, Gira and Ekiert, Damian C",
  abstract = "The outer membrane (OM) of Gram-negative bacteria is an
              asymmetric bilayer that protects the cell from external
              stressors, such as antibiotics. The Mla transport system is
              implicated in the Maintenance of OM Lipid Asymmetry by mediating
              retrograde phospholipid transport across the cell envelope. Mla
              uses a shuttle-like mechanism to move lipids between the MlaFEDB
              inner membrane complex and the MlaA-OmpF/C OM complex, via a
              periplasmic lipid-binding protein, MlaC. MlaC binds to MlaD and
              MlaA, but the underlying protein-protein interactions that
              facilitate lipid transfer are not well understood. Here, we take
              an unbiased deep mutational scanning approach to map the fitness
              landscape of MlaC from Escherichia coli, which provides insights
              into important functional sites. Combining this analysis with
              AlphaFold2 structure predictions and binding experiments, we map
              the MlaC-MlaA and MlaC-MlaD protein-protein interfaces. Our
              results suggest that the MlaD and MlaA binding surfaces on MlaC
              overlap to a large extent, leading to a model in which MlaC can
              only bind one of these proteins at a time. Low-resolution
              cryo-electron microscopy (cryo-EM) maps of MlaC bound to MlaFEDB
              suggest that at least two MlaC molecules can bind to MlaD at
              once, in a conformation consistent with AlphaFold2 predictions.
              These data lead us to a model for MlaC interaction with its
              binding partners and insights into lipid transfer steps that
              underlie phospholipid transport between the bacterial inner and
              OMs.",
  journal  = "Journal of Biological Chemistry",
  volume   =  299,
  number   =  6,
  pages    = "104744",
  month    =  jun,
  year     =  2023,
  keywords = "AlphaFold2; E. coli; Mla; bacterial cell envelope; deep
              mutational scanning; lipid transfer; protein interaction",
  language = "en"
}

@ARTICLE{ghose_marginal_2023,
  title    = "Marginal specificity in protein interactions constrains evolution
              of a paralogous family",
  author   = "Ghose, Dia A and Przydzial, Kaitlyn E and Mahoney, Emily M and
              Keating, Amy E and Laub, Michael T",
  abstract = "The evolution of novel functions in biology relies heavily on
              gene duplication and divergence, creating large paralogous
              protein families. Selective pressure to avoid detrimental
              cross-talk often results in paralogs that exhibit exquisite
              specificity for their interaction partners. But how robust or
              sensitive is this specificity to mutation? Here, using deep
              mutational scanning, we demonstrate that a paralogous family of
              bacterial signaling proteins exhibits marginal specificity, such
              that many individual substitutions give rise to substantial
              cross-talk between normally insulated pathways. Our results
              indicate that sequence space is locally crowded despite overall
              sparseness, and we provide evidence that this crowding has
              constrained the evolution of bacterial signaling proteins. These
              findings underscore how evolution selects for ``good enough''
              rather than optimized phenotypes, leading to restrictions on the
              subsequent evolution of paralogs.",
  journal  = "Proceedings of the National Academy of Sciences of the United States of America",
  volume   =  120,
  number   =  18,
  pages    = "e2221163120",
  month    =  may,
  year     =  2023,
  keywords = "gene duplication; paralogous proteins; protein evolution;
              protein-protein interactions; signal transduction",
  language = "en"
}

@UNPUBLISHED{nguyen_genetic_2023,
  title    = "The genetic landscape of a metabolic interaction",
  author   = "Nguyen, Thuy N and Ingle, Christine and Thompson, Samuel and
              Reynolds, Kimberly A",
  abstract = "AbstractEnzyme abundance, catalytic activity, and ultimately
              sequence are all shaped by the need of growing cells to maintain
              metabolic flux while minimizing accumulation of deleterious
              intermediates. To quantify how variation in the activity of one
              enzyme constrains the biochemical parameters and sequence of
              another, we focused on dihydrofolate reductase (DHFR) and
              thymidylate synthase (TYMS), a pair of enzymes catalyzing
              consecutive reactions in folate metabolism. We used deep
              mutational scanning to quantify the growth rate effect of 2,696
              DHFR single mutations in 3 TYMS backgrounds and show that our
              data are well-described by a relatively simple enzyme velocity to
              growth rate model. From the data and model we estimate the
              approximate effects of all single mutations on DHFR catalytic
              power. Together our data provide a comprehensive view of
              epistasis between mutations in a biochemically linked enzyme
              pair, reveal the structural distribution of positions tuning DHFR
              catalysis, and establish a foundation for the design of
              multi-enzyme systems.",
  journal  = "bioRxiv",
  month    =  may,
  year     =  2023
}

@UNPUBLISHED{clausen_mutational_2023,
  title    = "A mutational atlas for Parkin proteostasis",
  author   = "Clausen, Lene and Voutsinos, Vasileios and Cagiada, Matteo and
              Johansson, Kristoffer E and Gr{\o}nb{\ae}k-Thygesen, Martin and
              Nariya, Snehal and Powell, Rachel L and Have, Magnus K N and
              Oestergaard, Vibe H and Stein, Amelie and Fowler, Douglas M and
              Lindorff-Larsen, Kresten and Hartmann-Petersen, Rasmus",
  abstract = "The delicate balance of protein homeostasis can be disturbed by
              mutations that affect folding and stability of the encoded
              protein. More than half of disease-causing missense variants are
              thought to lead to protein degradation, but determining which and
              the molecular mechanisms involved remain enigmatic. To examine
              these issues, we selected the ubiquitin-protein ligase Parkin,
              where known missense variants result in an autosomal recessive,
              early onset Parkinsonism. We used the variant abundance by
              massively parallel sequencing (VAMP-seq) approach to quantify the
              abundance of Parkin missense variants in cultured human cells.
              The resulting mutational map, covering 9219 out of the 9300
              possible single-site amino acid substitutions and nonsense Parkin
              variants, show that most low abundance variants are located
              within the structured domains of the protein, while the flexible
              linker regions are more tolerant. The vast majority of low
              abundance Parkin variants are degraded through the
              ubiquitin-proteasome system and are stabilized at a lowered
              temperature. The cellular abundance data correlate with
              thermodynamic stability, evolutionary conservation, and show that
              half of the known disease-linked variants are found at low
              abundance. Systematic mapping of degradation signals (degrons)
              shows that inherent primary degrons in Parkin largely overlap
              with regions that are buried, and highly sensitive to mutations.
              An exposed degron region proximal to the so-called ``activation
              element'' is enhanced by substitutions to hydrophobic residues
              and destroyed by introduction of hydrophilic residues. The data
              provide examples of how missense variants may cause degradation
              either via destabilization of the native protein, or by
              introducing local signals for degradation. Combined with the
              computational methods based on Parkin structure and conservation,
              our abundance map sheds light on the mechanisms that cause loss
              of function, and points to variants where function potentially
              can be restored. \#\#\# Competing Interest Statement The authors
              have declared no competing interest.",
  journal  = "bioRxiv",
  pages    = "2023.06.08.544160",
  month    =  jun,
  year     =  2023,
  language = "en"
}

@UNPUBLISHED{vanella_understanding_2023,
  title    = "Understanding {Activity-Stability} Tradeoffs in Biocatalysts by
              Enzyme Proximity Sequencing",
  author   = "Vanella, Rosario and K{\"u}ng, Christoph and Schoepfer, Alexandre
              A and Doffini, Vanni and Ren, Jin and Nash, Michael A",
  abstract = "Understanding the complex relationships between enzyme sequence,
              folding stability and catalytic activity is crucial for
              applications in industry and biomedicine. However, current enzyme
              assay technologies are limited by an inability to simultaneously
              resolve both stability and activity phenotypes and to couple
              these to gene sequences at large scale. Here we developed Enzyme
              Proximity Sequencing (EP-Seq), a deep mutational scanning method
              that leverages peroxidase-mediated radical labeling with single
              cell fidelity to dissect the effects of thousands of mutations on
              stability and catalytic activity of oxidoreductase enzymes in a
              single experiment. We used EP-Seq to analyze how 6,387 missense
              mutations influence folding stability and catalytic activity in a
              D-amino acid oxidase (DAOx) from R. gracilis . The resulting
              datasets demonstrate activity-based constraints that limit
              folding stability during natural evolution, and identify hotspots
              distant from the active site as candidates for mutations that
              improve catalytic activity without sacrificing stability. EP-Seq
              can be extended to other enzyme classes and provides valuable
              insights into biophysical principles governing enzyme structure
              and function. \#\#\# Competing Interest Statement The authors
              have declared no competing interest.",
  journal  = "bioRxiv",
  pages    = "2023.02.24.529916",
  month    =  mar,
  year     =  2023,
  language = "en"
}

@ARTICLE{lei_mutational_2023,
  title    = "Mutational fitness landscape of human influenza {H3N2}
              neuraminidase",
  author   = "Lei, Ruipeng and Hernandez Garcia, Andrea and Tan, Timothy J C
              and Teo, Qi Wen and Wang, Yiquan and Zhang, Xiwen and Luo,
              Shitong and Nair, Satish K and Peng, Jian and Wu, Nicholas C",
  abstract = "Influenza neuraminidase (NA) has received increasing attention as
              an effective vaccine target. However, its mutational tolerance is
              not well characterized. Here, the fitness effects of >6,000
              mutations in human H3N2 NA are probed using deep mutational
              scanning. Our result shows that while its antigenic regions have
              high mutational tolerance, there are solvent-exposed regions with
              low mutational tolerance. We also find that protein stability is
              a major determinant of NA mutational fitness. The deep mutational
              scanning result correlates well with mutational fitness inferred
              from natural sequences using a protein language model,
              substantiating the relevance of our findings to the natural
              evolution of circulating strains. Additional analysis further
              suggests that human H3N2 NA is far from running out of mutations
              despite already evolving for >50 years. Overall, this study
              advances our understanding of the evolutionary potential of NA
              and the underlying biophysical constraints, which in turn provide
              insights into NA-based vaccine design.",
  journal  = "Cell Reports",
  volume   =  42,
  number   =  1,
  pages    = "111951",
  month    =  jan,
  year     =  2023,
  keywords = "CP: Molecular biology; deep mutational scanning; evolution;
              influenza; neuraminidase; protein language model; protein
              stability; protein structure",
  language = "en"
}

% The entry below contains non-ASCII chars that could not be converted
% to a LaTeX equivalent.
@ARTICLE{loggerenberg_systematically_2023,
  title    = "Systematically testing human {HMBS} missense variants to reveal
              mechanism and pathogenic variation",
  author   = "van Loggerenberg, Warren and Sowlati-Hashjin, Shahin and Weile,
              Jochen and Hamilton, Rayna and Chawla, Aditya and Gebbia,
              Marinella and Kishore, Nishka and Fr{\'e}sard, Laure and
              Mustajoki, Sami and Pischik, Elena and Pierro, Elena Di and
              Barbaro, Michela and Floderus, Ylva and Schmitt, Caroline and
              Gouya, Laurent and Colavin, Alexandre and Nussbaum, Robert and
              Friesema, Edith C H and Kauppinen, Raili and To-Figueras, Jordi
              and Aarsand, Aasne K and Desnick, Robert J and Garton, Michael
              and Roth, Frederick P",
  abstract = "Defects in hydroxymethylbilane synthase (HMBS) can cause Acute
              Intermittent Porphyria (AIP), an acute neurological disease.
              Although sequencing-based diagnosis can be definitive, ~⅓ of
              clinical HMBS variants are missense variants, and most
              clinically-reported HMBS missense variants are designated as
              ``variants of uncertain significance'' (VUS). Using saturation
              mutagenesis, en masse selection, and sequencing, we applied a
              multiplexed validated assay to both the erythroid-specific and
              ubiquitous isoforms of HMBS, obtaining confident functional
              impact scores for >84\% of all possible amino-acid substitutions.
              The resulting variant effect maps generally agreed with
              biochemical expectation. However, the maps showed variants at the
              dimerization interface to be unexpectedly well tolerated, and
              suggested residue roles in active site dynamics that were
              supported by molecular dynamics simulations. Most importantly,
              these HMBS variant effect maps can help discriminate pathogenic
              from benign variants, proactively providing evidence even for
              yet-to-be-observed clinical missense variants.",
  journal  = "bioRxiv",
  month    =  feb,
  year     =  2023,
  language = "en"
}

% The entry below contains non-ASCII chars that could not be converted
% to a LaTeX equivalent.
@ARTICLE{weeks_fitness_2023,
  title    = "Fitness and Functional Landscapes of the E. coli {RNase} {III}
              Gene rnc",
  author   = "Weeks, Ryan and Ostermeier, Marc",
  abstract = "How protein properties such as protein activity and protein
              essentiality affect the distribution of fitness effects (DFE) of
              mutations are important questions in protein evolution. Deep
              mutational scanning studies typically measure the effects of a
              comprehensive set of mutations on either protein activity or
              fitness. Our understanding of the underpinnings of the DFE would
              be enhanced by a comprehensive study of both for the same gene.
              Here, we compared the fitness effects and in vivo protein
              activity effects of ∼4,500 missense mutations in the E. coli rnc
              gene. This gene encodes RNase III, a global regulator enzyme that
              cleaves diverse RNA substrates including precursor ribosomal RNA
              and various mRNAs including its own 5' untranslated region
              (5'UTR). We find that RNase III's ability to cleave dsRNA is the
              most important determinant of the fitness effects of rnc
              mutations. The DFE of RNase III was bimodal, with mutations
              centered around neutral and deleterious effects, consistent with
              previously reported DFE's of enzymes with a singular
              physiological role. Fitness was buffered to small effects on
              RNase III activity. The enzyme's RNase III domain, which contains
              the RNase III signature motif and all active site residues, was
              more sensitive to mutation than its dsRNA binding domain, which
              is responsible for recognition and binding to dsRNA. Differential
              effects on fitness and functional scores for mutations at highly
              conserved residues G97, G99, and F188 suggest that these
              positions may be important for RNase III cleavage specificity.",
  journal  = "Molecular Biology and Evolution",
  volume   =  40,
  number   =  3,
  month    =  mar,
  year     =  2023,
  keywords = "RNase III; fitness landscape; protein evolution",
  language = "en"
}

@ARTICLE{muhammad_high_2023,
  title    = "High-throughput functional mapping of variants in an arrhythmia
              gene, {KCNE1} , reveals novel biology",
  author   = "Muhammad, Ayesha and Calandranis, Maria E and Li, Bian and Yang,
              Tao and Blackwell, Daniel J and Harvey, M Lorena and Smith,
              Jeremy E and Chew, Ashli E and Capra, John A and Matreyek,
              Kenneth A and Fowler, Douglas M and Roden, Dan M and Glazer,
              Andrew M",
  abstract = "BACKGROUND: KCNE1 encodes a 129-residue cardiac potassium channel
              (I Ks ) subunit. KCNE1 variants are associated with long QT
              syndrome and atrial fibrillation. However, most variants have
              insufficient evidence of clinical consequences and thus limited
              clinical utility. RESULTS: Here, we demonstrate the power of
              variant effect mapping, which couples saturation mutagenesis with
              high-throughput sequencing, to ascertain the function of
              thousands of protein coding KCNE1 variants. We comprehensively
              assayed KCNE1 variant cell surface expression (2,554/2,709
              possible single amino acid variants) and function (2,539
              variants). We identified 470 loss-of-surface expression and 588
              loss-of-function variants. Out of the 588 loss-of-function
              variants, only 155 had low cell surface expression. The latter
              half of the protein is dispensable for protein trafficking but
              essential for channel function. 22 of the 30 KCNE1 residues
              (73\%) highly intolerant of variation were in predicted close
              contact with binding partners KCNQ1 or calmodulin. Our data were
              highly concordant with gold standard electrophysiological data
              ($\rho$ = -0.65), population and patient cohorts (32/38
              concordant variants), and computational metrics ($\rho$ = -0.55).
              Our data provide moderate-strength evidence for the ACMG/AMP
              functional criteria for benign and pathogenic variants.
              CONCLUSIONS: Comprehensive variant effect maps of KCNE1 can both
              provide insight into I Ks channel biology and help reclassify
              variants of uncertain significance.",
  journal  = "bioRxiv",
  month    =  apr,
  year     =  2023,
  language = "en"
}

@ARTICLE{yee_full_2023,
  title    = "The full spectrum of {OCT1} ({SLC22A1}) mutations bridges
              transporter biophysics to drug pharmacogenomics",
  author   = "Yee, Sook Wah and Macdonald, Christian and Mitrovic, Darko and
              Zhou, Xujia and Koleske, Megan L and Yang, Jia and Silva, Dina
              Buitrago and Grimes, Patrick Rockefeller and Trinidad, Donovan
              and More, Swati S and Kachuri, Linda and Witte, John S and
              Delemotte, Lucie and Giacomini, Kathleen M and Coyote-Maestas,
              Willow",
  abstract = "Membrane transporters play a fundamental role in the tissue
              distribution of endogenous compounds and xenobiotics and are
              major determinants of efficacy and side effects profiles.
              Polymorphisms within these drug transporters result in
              inter-individual variation in drug response, with some patients
              not responding to the recommended dosage of drug whereas others
              experience catastrophic side effects. For example, variants
              within the major hepatic Human organic cation transporter OCT1
              (SLC22A1) can change endogenous organic cations and many
              prescription drug levels. To understand how variants
              mechanistically impact drug uptake, we systematically study how
              all known and possible single missense and single amino acid
              deletion variants impact expression and substrate uptake of OCT1.
              We find that human variants primarily disrupt function via
              folding rather than substrate uptake. Our study revealed that the
              major determinants of folding reside in the first 300 amino
              acids, including the first 6 transmembrane domains and the
              extracellular domain (ECD) with a stabilizing and highly
              conserved stabilizing helical motif making key interactions
              between the ECD and transmembrane domains. Using the functional
              data combined with computational approaches, we determine and
              validate a structure-function model of OCT1s conformational
              ensemble without experimental structures. Using this model and
              molecular dynamic simulations of key mutants, we determine
              biophysical mechanisms for how specific human variants alter
              transport phenotypes. We identify differences in frequencies of
              reduced function alleles across populations with East Asians vs
              European populations having the lowest and highest frequency of
              reduced function variants, respectively. Mining human population
              databases reveals that reduced function alleles of OCT1
              identified in this study associate significantly with high LDL
              cholesterol levels. Our general approach broadly applied could
              transform the landscape of precision medicine by producing a
              mechanistic basis for understanding the effects of human
              mutations on disease and drug response.",
  journal  = "bioRxiv",
  month    =  jun,
  year     =  2023,
  language = "en"
}

@ARTICLE{chen_deep_2023,
  title    = "Deep Mutational Scanning of an {Oxygen-Independent} Fluorescent
              Protein {CreiLOV} for Comprehensive Profiling of Mutational and
              Epistatic Effects",
  author   = "Chen, Yongcan and Hu, Ruyun and Li, Keyi and Zhang, Yating and
              Fu, Lihao and Zhang, Jianzhi and Si, Tong",
  abstract = "Oxygen-independent, flavin mononucleotide-based fluorescent
              proteins (FbFPs) are promising alternatives to green fluorescent
              protein in anaerobic contexts. Deep mutational scanning performs
              systematic profiling of protein sequence-function relationships
              but has not been applied to FbFPs. Focusing on CreiLOV from
              Chlamydomonas reinhardtii, we created and analyzed two
              comprehensive mutant collections: (1) single-residue,
              site-saturation mutagenesis libraries covering all 118 residues;
              and (2) a full combinatorial metagenesis library among 20
              mutations at 15 residues, where mutation and residue selection
              was based on single-site mutagenesis results. Notably, the second
              type of library is indispensable to study higher-order epistasis
              but underrepresented in the literature. Using optimized FACS-seq
              assays, 2,185 (>92.5\%) out of 2,360 possible single-site mutants
              and 165,428 (>89.7\%) out of 184,320 possible combinatorial
              mutants were reliably assigned with fitness values. We
              constructed statistical and machine-learning models to analyze
              the CreiLOV data set, enabling accurate fitness prediction of
              higher-order mutants using lower-order mutagenesis data. In
              addition, we successfully isolated CreiLOV variants with improved
              fluorescence quantum yield and thermostability. This work
              provides new empirical data and design rules to engineer
              combinatorial protein variants.",
  journal  = "ACS Synthetic Biology",
  volume   =  12,
  number   =  5,
  pages    = "1461--1473",
  month    =  may,
  year     =  2023,
  keywords = "CreiLOV; FACS-Seq; deep mutational scanning; epistasis; protein
              engineering",
  language = "en"
}

@ARTICLE{gersing_characterizing_2023,
  title    = "Characterizing glucokinase variant mechanisms using a multiplexed
              abundance assay",
  author   = "Gersing, Sarah and Schulze, Thea K and Cagiada, Matteo and Stein,
              Amelie and Roth, Frederick P and Lindorff-Larsen, Kresten and
              Hartmann-Petersen, Rasmus",
  abstract = "Amino acid substitutions can perturb protein activity in multiple
              ways. Understanding their mechanistic basis may pinpoint how
              residues contribute to protein function. Here, we characterize
              the mechanisms of human glucokinase (GCK) variants, building on
              our previous comprehensive study on GCK variant activity. We
              assayed the abundance of 95\% of GCK missense and nonsense
              variants, and found that 43\% of hypoactive variants have a
              decreased cellular abundance. By combining our abundance scores
              with predictions of protein thermodynamic stability, we identify
              residues important for GCK metabolic stability and conformational
              dynamics. These residues could be targeted to modulate GCK
              activity, and thereby affect glucose homeostasis.",
  journal  = "bioRxiv",
  month    =  may,
  year     =  2023,
  language = "en"
}

@ARTICLE{huttinger_deep_2021,
  title    = "Deep mutational scanning of the plasminogen activator inhibitor-1
              functional landscape",
  author   = "Huttinger, Zachary M and Haynes, Laura M and Yee, Andrew and
              Kretz, Colin A and Holding, Matthew L and Siemieniak, David R and
              Lawrence, Daniel A and Ginsburg, David",
  abstract = "The serine protease inhibitor (SERPIN) plasminogen activator
              inhibitor-1 (PAI-1) is a key regulator of the fibrinolytic
              system, inhibiting the serine proteases tissue- and
              urokinase-type plasminogen activator (tPA and uPA, respectively).
              Missense variants render PAI-1 non-functional through misfolding,
              leading to its turnover as a protease substrate, or to a more
              rapid transition to the latent/inactive state. Deep mutational
              scanning was performed to evaluate the impact of amino acid
              sequence variation on PAI-1 inhibition of uPA using an M13
              filamentous phage display system. Error prone PCR was used to
              construct a mutagenized PAI-1 library encompassing ~ 70\% of
              potential single amino acid substitutions. The relative effects
              of 27\% of all possible missense variants on PAI-1 inhibition of
              uPA were determined using high-throughput DNA sequencing. 826
              missense variants demonstrated conserved inhibitory activity
              while 1137 resulted in loss of PAI-1 inhibitory function. The
              least evolutionarily conserved regions of PAI-1 were also
              identified as being the most tolerant of missense mutations. The
              results of this screen confirm previous low-throughput mutational
              studies, including those of the reactive center loop. These data
              provide a powerful resource for explaining structure-function
              relationships for PAI-1 and for the interpretation of human
              genomic sequence variants.",
  journal  = "Scientific Reports",
  volume   =  11,
  number   =  1,
  pages    = "18827",
  month    =  sep,
  year     =  2021,
  language = "en"
}

@article{kwon_structurefunction_2022,
	title = {Structure–function analysis of the {SHOC2}–{MRAS}–{PP1C} holophosphatase complex},
	volume = {609},
	issn = {0028-0836, 1476-4687},
	url = {https://www.nature.com/articles/s41586-022-04928-2},
	doi = {10.1038/s41586-022-04928-2},
	language = {en},
	number = {7926},
	urldate = {2023-10-16},
	journal = {Nature},
	author = {Kwon, Jason J. and Hajian, Behnoush and Bian, Yuemin and Young, Lucy C. and Amor, Alvaro J. and Fuller, James R. and Fraley, Cara V. and Sykes, Abbey M. and So, Jonathan and Pan, Joshua and Baker, Laura and Lee, Sun Joo and Wheeler, Douglas B. and Mayhew, David L. and Persky, Nicole S. and Yang, Xiaoping and Root, David E. and Barsotti, Anthony M. and Stamford, Andrew W. and Perry, Charles K. and Burgin, Alex and McCormick, Frank and Lemke, Christopher T. and Hahn, William C. and Aguirre, Andrew J.},
	month = sep,
	year = {2022},
	pages = {408--415},
	file = {Accepted Version:/Users/admin/Zotero/storage/R96FAMJM/Kwon et al. - 2022 - Structure–function analysis of the SHOC2–MRAS–PP1C.pdf:application/pdf},
}

@article{sun_proactive_2020,
	title = {A proactive genotype-to-patient-phenotype map for cystathionine beta-synthase},
	volume = {12},
	issn = {1756-994X},
	url = {https://genomemedicine.biomedcentral.com/articles/10.1186/s13073-020-0711-1},
	doi = {10.1186/s13073-020-0711-1},
	abstract = {Abstract
            
              Background
              
                For the majority of rare clinical missense variants, pathogenicity status cannot currently be classified. Classical homocystinuria, characterized by elevated homocysteine in plasma and urine, is caused by variants in the cystathionine beta-synthase (
                CBS
                ) gene, most of which are rare. With early detection, existing therapies are highly effective.
              
            
            
              Methods
              
                Damaging
                CBS
                variants can be detected based on their failure to restore growth in yeast cells lacking the yeast ortholog
                CYS4
                . This assay has only been applied reactively, after first observing a variant in patients. Using saturation codon-mutagenesis, en masse growth selection, and sequencing, we generated a comprehensive, proactive map of CBS missense variant function.
              
            
            
              Results
              
                Our CBS variant effect map far exceeds the performance of computational predictors of disease variants. Map scores correlated strongly with both disease severity (Spearman’s
                ϱ
                 = 0.9) and human clinical response to vitamin B
                6
                (
                ϱ
                 = 0.93).
              
            
            
              Conclusions
              We demonstrate that highly multiplexed cell-based assays can yield proactive maps of variant function and patient response to therapy, even for rare variants not previously seen in the clinic.},
	language = {en},
	number = {1},
	urldate = {2023-10-16},
	journal = {Genome Medicine},
	author = {Sun, Song and Weile, Jochen and Verby, Marta and Wu, Yingzhou and Wang, Yang and Cote, Atina G. and Fotiadou, Iosifina and Kitaygorodsky, Julia and Vidal, Marc and Rine, Jasper and Ješina, Pavel and Kožich, Viktor and Roth, Frederick P.},
	month = dec,
	year = {2020},
	pages = {13},
	file = {Full Text:/Users/admin/Zotero/storage/4KCD9FVJ/Sun et al. - 2020 - A proactive genotype-to-patient-phenotype map for .pdf:application/pdf},
}

@article{wan_characterizing_2019,
	title = {Characterizing variants of unknown significance in rhodopsin: {A} functional genomics approach},
	volume = {40},
	issn = {1059-7794, 1098-1004},
	shorttitle = {Characterizing variants of unknown significance in rhodopsin},
	url = {https://onlinelibrary.wiley.com/doi/10.1002/humu.23762},
	doi = {10.1002/humu.23762},
	language = {en},
	number = {8},
	urldate = {2023-10-16},
	journal = {Human Mutation},
	author = {Wan, Aliete and Place, Emily and Pierce, Eric A. and Comander, Jason},
	month = aug,
	year = {2019},
	pages = {1127--1144},
	file = {Full Text:/Users/admin/Zotero/storage/SSKD3J59/Wan et al. - 2019 - Characterizing variants of unknown significance in.pdf:application/pdf},
}

@article{chan_engineering_2020,
	title = {Engineering human {ACE2} to optimize binding to the spike protein of {SARS} coronavirus 2},
	volume = {369},
	issn = {0036-8075, 1095-9203},
	url = {https://www.science.org/doi/10.1126/science.abc0870},
	doi = {10.1126/science.abc0870},
	abstract = {A decoy receptor for SARS-CoV-2
            
              For severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) to enter human cells, the spike protein on the surface of the virus must bind to the host receptor protein, angiotensin-converting enzyme 2 (ACE2). A soluble version of the receptor is being explored as a therapeutic. Chan
              et al.
              used deep mutagenesis to identify ACE2 mutants that bind more tightly to the spike protein and combined mutations to further increase binding affinity (see the Perspective by DeKosky). A promising variant was engineered to be a stable dimer that has a binding affinity for the spike protein; it is comparable with neutralizing antibodies and neutralized both SARS-CoV-2 and SARS-CoV-1 in a cell-based assay. In addition, the similarity to the natural receptor may limit the possibility for viral escape.
            
            
              Science
              , this issue p.
              1261
              ; see also p.
              1167
            
          , 
            A variant of ACE2 based on deep mutagenesis far outcompetes the natural receptor in binding the SARS-CoV-2 spike protein.
          , 
            The spike (S) protein of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) binds angiotensin-converting enzyme 2 (ACE2) on host cells to initiate entry, and soluble ACE2 is a therapeutic candidate that neutralizes infection by acting as a decoy. By using deep mutagenesis, mutations in ACE2 that increase S binding are found across the interaction surface, in the asparagine 90–glycosylation motif and at buried sites. The mutational landscape provides a blueprint for understanding the specificity of the interaction between ACE2 and S and for engineering high-affinity decoy receptors. Combining mutations gives ACE2 variants with affinities that rival those of monoclonal antibodies. A stable dimeric variant shows potent SARS-CoV-2 and -1 neutralization in vitro. The engineered receptor is catalytically active, and its close similarity with the native receptor may limit the potential for viral escape.},
	language = {en},
	number = {6508},
	urldate = {2023-10-16},
	journal = {Science},
	author = {Chan, Kui K. and Dorosky, Danielle and Sharma, Preeti and Abbasi, Shawn A. and Dye, John M. and Kranz, David M. and Herbert, Andrew S. and Procko, Erik},
	month = sep,
	year = {2020},
	pages = {1261--1265},
	file = {Full Text:/Users/admin/Zotero/storage/RHH3R5SV/Chan et al. - 2020 - Engineering human ACE2 to optimize binding to the .pdf:application/pdf},
}

@techreport{silverstein_systematic_2021,
	type = {preprint},
	title = {A systematic genotype-phenotype map for missense variants in the human intellectual disability-associated gene \textit{{GDI1}}},
	url = {http://biorxiv.org/lookup/doi/10.1101/2021.10.06.463360},
	abstract = {Abstract
          
            Next generation sequencing has become a common tool in the diagnosis of genetic diseases. However, for the vast majority of genetic variants that are discovered, a clinical interpretation is not available. Variant effect mapping allows the functional effects of many single amino acid variants to be characterized in parallel. Here, we combine multiplexed functional assays with machine learning to assess the effects of amino acid substitutions in the human intellectual disability-associated gene,
            GDI1
            . We show that the resulting variant effect map can be used to discriminate pathogenic from benign variants. Our variant effect map recovers known biochemical and structural features of
            GDI1
            and reveals additional aspects of
            GDI1
            function. We explore how our functional assays can aid in the interpretation of novel
            GDI1
            variants as they are discovered, and to re-classify previously observed variants of unknown significance.},
	language = {en},
	urldate = {2023-10-16},
	institution = {Genetics},
	author = {Silverstein, Rachel A. and Sun, Song and Verby, Marta and Weile, Jochen and Wu, Yingzhou and Gebbia, Marinella and Fotiadou, Iosifina and Kitaygorodsky, Julia and Roth, Frederick P.},
	month = oct,
	year = {2021},
	doi = {10.1101/2021.10.06.463360},
	file = {Submitted Version:/Users/admin/Zotero/storage/4EYJCVVM/Silverstein et al. - 2021 - A systematic genotype-phenotype map for missense v.pdf:application/pdf},
}

@article{zinkus-boltz_phage-assisted_2019,
	title = {A {Phage}-{Assisted} {Continuous} {Selection} {Approach} for {Deep} {Mutational} {Scanning} of {Protein}–{Protein} {Interactions}},
	volume = {14},
	issn = {1554-8929, 1554-8937},
	url = {https://pubs.acs.org/doi/10.1021/acschembio.9b00669},
	doi = {10.1021/acschembio.9b00669},
	language = {en},
	number = {12},
	urldate = {2023-10-16},
	journal = {ACS Chemical Biology},
	author = {Zinkus-Boltz, Julia and DeValk, Craig and Dickinson, Bryan C.},
	month = dec,
	year = {2019},
	pages = {2757--2767},
	file = {Submitted Version:/Users/admin/Zotero/storage/XRNNITUF/Zinkus-Boltz et al. - 2019 - A Phage-Assisted Continuous Selection Approach for.pdf:application/pdf},
}

@article{klesmith_retargeting_2019,
	title = {Retargeting {CD19} {Chimeric} {Antigen} {Receptor} {T} {Cells} via {Engineered} {CD19}-{Fusion} {Proteins}},
	volume = {16},
	issn = {1543-8384, 1543-8392},
	url = {https://pubs.acs.org/doi/10.1021/acs.molpharmaceut.9b00418},
	doi = {10.1021/acs.molpharmaceut.9b00418},
	language = {en},
	number = {8},
	urldate = {2023-10-16},
	journal = {Molecular Pharmaceutics},
	author = {Klesmith, Justin R. and Su, Lihe and Wu, Lan and Schrack, Ian A. and Dufort, Fay J. and Birt, Alyssa and Ambrose, Christine and Hackel, Benjamin J. and Lobb, Roy R. and Rennert, Paul D.},
	month = aug,
	year = {2019},
	pages = {3544--3558},
}

@article{elazar_mutational_2016,
	title = {Mutational scanning reveals the determinants of protein insertion and association energetics in the plasma membrane},
	volume = {5},
	issn = {2050-084X},
	url = {https://elifesciences.org/articles/12125},
	doi = {10.7554/eLife.12125},
	abstract = {Insertion of helix-forming segments into the membrane and their association determines the structure, function, and expression levels of all plasma membrane proteins. However, systematic and reliable quantification of membrane-protein energetics has been challenging. We developed a deep mutational scanning method to monitor the effects of hundreds of point mutations on helix insertion and self-association within the bacterial inner membrane. The assay quantifies insertion energetics for all natural amino acids at 27 positions across the membrane, revealing that the hydrophobicity of biological membranes is significantly higher than appreciated. We further quantitate the contributions to membrane-protein insertion from positively charged residues at the cytoplasm-membrane interface and reveal large and unanticipated differences among these residues. Finally, we derive comprehensive mutational landscapes in the membrane domains of Glycophorin A and the ErbB2 oncogene, and find that insertion and self-association are strongly coupled in receptor homodimers.
          , 
            Cells are defined by a thin membrane that separates the inside of the cell from the outside. The core of this membrane is hydrophobic, meaning that it repels water. Many signals and nutrients cannot pass through the membrane itself, but can pass through the proteins that span the membrane. Membrane proteins are therefore essential for living cells; yet even after decades of research, it remains unclear how proteins interact with the membrane and which features determine a protein’s stability in a biological membrane.
            Since the early 1980s it was known that the bacterium E. coli could grow on a common antibiotic called ampicillin if it had enough of an antibiotic-degrading enzyme called β-lactamase anchored into its inner membrane. Now, Elazar et al. have used this enzyme to obtain detailed information on the interactions between a biological membrane and a membrane protein. First, hundreds of different mutations were introduced into the gene that encodes the enzyme to generate a population of bacteria that each had a slightly different membrane anchor. The mutant bacteria were then grown in the presence of the antibiotic, meaning that those mutants with a more stable membrane anchor were more likely to survive and grow than those with less stable anchors.
            Elazar et al. then collected all the surviving bacteria, sequenced their DNA and measured how common the different mutations were in the final population. This approach was less labor-intensive and more accurate than traditional methods for monitoring membrane-anchored proteins, and the resulting large dataset was used to uncover which features affect a protein’s stability in a membrane. These results also showed that a biological membrane’s core is considerably more hydrophobic than was previously thought.
            In addition to being hydrophobic, biological membranes have more negative charge in the side that faces into the cell. This means that membrane proteins with a positive charge in this region will be more stable, and Elazar et al. were able to use their new system to measure this effect for the first time.
            Finally, membrane proteins do not only span the membrane; they also bind with other membrane proteins in order to carry out their roles. Elazar et al. used their system to look at the surfaces of human membrane proteins that interact with one another, and build a detailed map of the interaction surfaces, from which they derived accurate models of the membrane proteins.
            Overall, these new findings could now be used to model the three-dimensional structures of membrane proteins and improve their stability. This in turn may help efforts to develop these proteins into more robust experimental tools and in the search for drugs that target membrane proteins.},
	language = {en},
	urldate = {2023-10-16},
	journal = {eLife},
	author = {Elazar, Assaf and Weinstein, Jonathan and Biran, Ido and Fridman, Yearit and Bibi, Eitan and Fleishman, Sarel Jacob},
	month = jan,
	year = {2016},
	pages = {e12125},
	file = {Full Text:/Users/admin/Zotero/storage/UVHQ2HLP/Elazar et al. - 2016 - Mutational scanning reveals the determinants of pr.pdf:application/pdf},
}

@article{coyote-maestas_determinants_2022,
	title = {Determinants of trafficking, conduction, and disease within a {K}+ channel revealed through multiparametric deep mutational scanning},
	volume = {11},
	issn = {2050-084X},
	url = {https://elifesciences.org/articles/76903},
	doi = {10.7554/eLife.76903},
	abstract = {A long-standing goal in protein science and clinical genetics is to develop quantitative models of sequence, structure, and function relationships to understand how mutations cause disease. Deep mutational scanning (DMS) is a promising strategy to map how amino acids contribute to protein structure and function and to advance clinical variant interpretation. Here, we introduce 7429 single-residue missense mutations into the inward rectifier K
              +
              channel Kir2.1 and determine how this affects folding, assembly, and trafficking, as well as regulation by allosteric ligands and ion conduction. Our data provide high-resolution information on a cotranslationally folded biogenic unit, trafficking and quality control signals, and segregated roles of different structural elements in fold stability and function. We show that Kir2.1 surface trafficking mutants are underrepresented in variant effect databases, which has implications for clinical practice. By comparing fitness scores with expert-reviewed variant effects, we can predict the pathogenicity of ‘variants of unknown significance’ and disease mechanisms of known pathogenic mutations. Our study in Kir2.1 provides a blueprint for how multiparametric DMS can help us understand the mechanistic basis of genetic disorders and the structure–function relationships of proteins.},
	language = {en},
	urldate = {2023-10-16},
	journal = {eLife},
	author = {Coyote-Maestas, Willow and Nedrud, David and He, Yungui and Schmidt, Daniel},
	month = may,
	year = {2022},
	pages = {e76903},
	file = {Submitted Version:/Users/admin/Zotero/storage/AB4N657M/Coyote-Maestas et al. - 2022 - Determinants of trafficking, conduction, and disea.pdf:application/pdf},
}

@techreport{li_deep_2023,
	type = {preprint},
	title = {Deep mutational scanning reveals the functional constraints and evolutionary potential of the influenza {A} virus {PB1} protein},
	url = {http://biorxiv.org/lookup/doi/10.1101/2023.08.27.554986},
	abstract = {Abstract
          The influenza virus polymerase is central to influenza virus evolution. Adaptive mutations within the polymerase are often a prerequisite for efficient spread of novel animal-derived viruses in human populations. The polymerase also determines fidelity, and therefore the rate at which the virus will acquire mutations that lead to host range expansion, drug resistance, or antigenic drift. Despite its importance to viral replication and evolution, our understanding of the mutational effects and associated constraints on the influenza RNA-dependent RNA polymerase (RdRp) is relatively limited. We performed deep mutational scanning of the A/WSN/1933(H1N1) PB1, generating a library of 95.4\% of amino acid substitutions at 757 sites. After accuracy filters, we were able to measure replicative fitness for 13,354 (84\%) of all possible amino acid substitutions, and 16 were validated by results from pairwise competition assays. Functional and structural constraints were better revealed by individual sites involved in RNA or protein interactions than by major subdomains defined by sequence conservation. Mutational tolerance, as defined by site entropy, was correlated with evolutionary potential, as captured by diversity in available H1N1 sequences. Of 29 beneficial sites, many have either been identified in the natural evolution of PB1 or shown experimentally to have important impacts on replication and adaptation. Accessibility of amino acid substitutions by single nucleotide mutation was a key factor in determining whether mutations appeared in natural PB1 evolution. Our work provides a comprehensive map of mutational effects on a viral RdRp and a valuable resource for subsequent studies of influenza replication and evolution.},
	language = {en},
	urldate = {2023-10-16},
	institution = {Microbiology},
	author = {Li, Yuan and Arcos, Sarah and Sabsay, Kimberly R. and Te Velthuis, Aartjan J.W. and Lauring, Adam S.},
	month = aug,
	year = {2023},
	doi = {10.1101/2023.08.27.554986},
	file = {Submitted Version:/Users/admin/Zotero/storage/8WM9KUK5/Li et al. - 2023 - Deep mutational scanning reveals the functional co.pdf:application/pdf},
}

@article{meitlis_multiplexed_2020,
	title = {Multiplexed {Functional} {Assessment} of {Genetic} {Variants} in {CARD11}},
	volume = {107},
	issn = {00029297},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0002929720303736},
	doi = {10.1016/j.ajhg.2020.10.015},
	language = {en},
	number = {6},
	urldate = {2023-10-16},
	journal = {The American Journal of Human Genetics},
	author = {Meitlis, Iana and Allenspach, Eric J. and Bauman, Bradly M. and Phan, Isabelle Q. and Dabbah, Gina and Schmitt, Erica G. and Camp, Nathan D. and Torgerson, Troy R. and Nickerson, Deborah A. and Bamshad, Michael J. and Hagin, David and Luthers, Christopher R. and Stinson, Jeffrey R. and Gray, Jessica and Lundgren, Ingrid and Church, Joseph A. and Butte, Manish J. and Jordan, Mike B. and Aceves, Seema S. and Schwartz, Daniella M. and Milner, Joshua D. and Schuval, Susan and Skoda-Smith, Suzanne and Cooper, Megan A. and Starita, Lea M. and Rawlings, David J. and Snow, Andrew L. and James, Richard G.},
	month = dec,
	year = {2020},
	pages = {1029--1043},
	file = {Full Text:/Users/admin/Zotero/storage/CFKJ6Y9I/Meitlis et al. - 2020 - Multiplexed Functional Assessment of Genetic Varia.pdf:application/pdf},
}

@article{uk_monogenic_diabetes_consortium_prospective_2016,
	title = {Prospective functional classification of all possible missense variants in {PPARG}},
	volume = {48},
	issn = {1061-4036, 1546-1718},
	url = {https://www.nature.com/articles/ng.3700},
	doi = {10.1038/ng.3700},
	language = {en},
	number = {12},
	urldate = {2023-10-16},
	journal = {Nature Genetics},
	author = {{UK Monogenic Diabetes Consortium} and {Myocardial Infarction Genetics Consortium} and {UK Congenital Lipodystrophy Consortium} and Majithia, Amit R and Tsuda, Ben and Agostini, Maura and Gnanapradeepan, Keerthana and Rice, Robert and Peloso, Gina and Patel, Kashyap A and Zhang, Xiaolan and Broekema, Marjoleine F and Patterson, Nick and Duby, Marc and Sharpe, Ted and Kalkhoven, Eric and Rosen, Evan D and Barroso, Inês and Ellard, Sian and Kathiresan, Sekar and O'Rahilly, Stephen and Chatterjee, Krishna and Florez, Jose C and Mikkelsen, Tarjei and Savage, David B and Altshuler, David},
	month = dec,
	year = {2016},
	pages = {1570--1575},
	file = {Accepted Version:/Users/admin/Zotero/storage/MEZTM6WW/UK Monogenic Diabetes Consortium et al. - 2016 - Prospective functional classification of all possi.pdf:application/pdf},
}

@techreport{estevam_conserved_2023,
	type = {preprint},
	title = {Conserved regulatory motifs in the juxtamembrane domain and kinase {N}-lobe revealed through deep mutational scanning of the {MET} receptor tyrosine kinase domain},
	url = {http://biorxiv.org/lookup/doi/10.1101/2023.08.03.551866},
	abstract = {Abstract
          MET is a receptor tyrosine kinase (RTK) responsible for initiating signaling pathways involved in development and wound repair. MET activation relies on ligand binding to the extracellular receptor, which prompts dimerization, intracellular phosphorylation, and recruitment of associated signaling proteins. Mutations, which are predominantly observed clinically in the intracellular juxtamembrane and kinase domains, can disrupt typical MET regulatory mechanisms. Understanding how juxtamembrane variants, such as exon 14 skipping (METΔEx14), and rare kinase domain mutations can increase signaling, often leading to cancer, remains a challenge. Here, we perform a parallel deep mutational scan (DMS) of MET intracellular kinase domain in two fusion protein backgrounds: wild type and METΔEx14. Our comparative approach has revealed a critical hydrophobic interaction between a juxtamembrane segment and the kinase ⍺C helix, pointing to differences in regulatory mechanisms between MET and other RTKs. Additionally, we have uncovered a β5 motif that acts as a structural pivot for kinase domain activation in MET and other TAM family of kinases. We also describe a number of previously unknown activating mutations, aiding the effort to annotate driver, passenger, and drug resistance mutations in the MET kinase domain.},
	language = {en},
	urldate = {2023-10-16},
	institution = {Molecular Biology},
	author = {Estevam, Gabriella O. and Linossi, Edmond M. and Macdonald, Christian B. and Espinoza, Carla A. and Michaud, Jennifer M. and Coyote-Maestas, Willow and Collisson, Eric A. and Jura, Natalia and Fraser, James S.},
	month = aug,
	year = {2023},
	doi = {10.1101/2023.08.03.551866},
	file = {Full Text:/Users/admin/Zotero/storage/S7UXHT33/Estevam et al. - 2023 - Conserved regulatory motifs in the juxtamembrane d.pdf:application/pdf},
}

@article{miller_allosteric_2022,
	title = {Allosteric inhibition of {PPM1D} serine/threonine phosphatase via an altered conformational state},
	volume = {13},
	issn = {2041-1723},
	url = {https://www.nature.com/articles/s41467-022-30463-9},
	doi = {10.1038/s41467-022-30463-9},
	abstract = {Abstract
            
              PPM1D
              encodes a serine/threonine phosphatase that regulates numerous pathways including the DNA damage response and p53. Activating mutations and amplification of
              PPM1D
              are found across numerous cancer types. GSK2830371 is a potent and selective allosteric inhibitor of PPM1D, but its mechanism of binding and inhibition of catalytic activity are unknown. Here we use computational, biochemical and functional genetic studies to elucidate the molecular basis of GSK2830371 activity. These data confirm that GSK2830371 binds an allosteric site of PPM1D with high affinity. By further incorporating data from hydrogen deuterium exchange mass spectrometry and sedimentation velocity analytical ultracentrifugation, we demonstrate that PPM1D exists in an equilibrium between two conformations that are defined by the movement of the flap domain, which is required for substrate recognition. A hinge region was identified that is critical for switching between the two conformations and was directly implicated in the high-affinity binding of GSK2830371 to PPM1D. We propose that the two conformations represent active and inactive forms of the protein reflected by the position of the flap, and that binding of GSK2830371 shifts the equilibrium to the inactive form. Finally, we found that C-terminal truncating mutations proximal to residue 400 result in destabilization of the protein via loss of a stabilizing N- and C-terminal interaction, consistent with the observation from human genetic data that nearly all
              PPM1D
              mutations in cancer are truncating and occur distal to residue 400. Taken together, our findings elucidate the mechanism by which binding of a small molecule to an allosteric site of PPM1D inhibits its activity and provides insights into the biology of PPM1D.},
	language = {en},
	number = {1},
	urldate = {2023-10-16},
	journal = {Nature Communications},
	author = {Miller, Peter G. and Sathappa, Murugappan and Moroco, Jamie A. and Jiang, Wei and Qian, Yue and Iqbal, Sumaiya and Guo, Qi and Giacomelli, Andrew O. and Shaw, Subrata and Vernier, Camille and Bajrami, Besnik and Yang, Xiaoping and Raffier, Cerise and Sperling, Adam S. and Gibson, Christopher J. and Kahn, Josephine and Jin, Cyrus and Ranaghan, Matthew and Caliman, Alisha and Brousseau, Merissa and Fischer, Eric S. and Lintner, Robert and Piccioni, Federica and Campbell, Arthur J. and Root, David E. and Garvie, Colin W. and Ebert, Benjamin L.},
	month = jun,
	year = {2022},
	pages = {3778},
	file = {Full Text:/Users/admin/Zotero/storage/93RHZ3F3/Miller et al. - 2022 - Allosteric inhibition of PPM1D serinethreonine ph.pdf:application/pdf},
}

@article{erwood_saturation_2022,
	title = {Saturation variant interpretation using {CRISPR} prime editing},
	volume = {40},
	issn = {1087-0156, 1546-1696},
	url = {https://www.nature.com/articles/s41587-021-01201-1},
	doi = {10.1038/s41587-021-01201-1},
	language = {en},
	number = {6},
	urldate = {2023-10-16},
	journal = {Nature Biotechnology},
	author = {Erwood, Steven and Bily, Teija M. I. and Lequyer, Jason and Yan, Joyce and Gulati, Nitya and Brewer, Reid A. and Zhou, Liangchi and Pelletier, Laurence and Ivakine, Evgueni A. and Cohn, Ronald D.},
	month = jun,
	year = {2022},
	pages = {885--895},
	file = {Submitted Version:/Users/admin/Zotero/storage/Q5IRIPHG/Erwood et al. - 2022 - Saturation variant interpretation using CRISPR pri.pdf:application/pdf},
}

@phdthesis{jiang_exhaustive_2019,
	title = {Exhaustive {Mapping} of {Missense} {Variation} in {Coronary} {Heart} {Disease}-related {Genes}},
	url = {https://hdl.handle.net/1807/98076},
	abstract = {Coronary heart disease (CHD) is a leading cause of death worldwide. A major risk factor of CHD is high low-density lipoprotein cholesterol (LDL-C), which is the defining feature of familial hypercholesterolemia, a genetic disorder characterized by mutations in genes involved in cholesterol uptake, such as LDLRAP1. The risk of CHD can be reduced by LDL-C-lowering medications called statins that potently inhibit HMG-CoA reductase (HMGCR), the enzyme that catalyzes the rate-limiting reaction of the mevalonate pathway. The study of genetic variation in CHD-related genes may contribute to early detection or prevention of CHD. I exhaustively mapped missense variant effects of two CHD-related genes, HMGCR and LDLRAP1. Proactive maps of human HMGCR may be able to model patient response to statins and identify the statin with the greatest likelihood of efficacy. Proactive maps of LDLRAP1 may identify pathogenic variation of autosomal recessive hypercholesterolemia (ARH) for early diagnosis of ARH.},
	school = {University of Toronto},
	author = {Jiang, Rosanna Junchen},
	month = nov,
	year = {2019},
}

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% Moving assays over from references.bib
@inproceedings{chen_hotprotein_2022,
	title = {{HotProtein}: {A} {Novel} {Framework} for {Protein} {Thermostability} {Prediction} and {Editing}},
	shorttitle = {{HotProtein}},
	url = {https://openreview.net/forum?id=RtV_iEbWeGE},
	abstract = {The molecular basis of protein thermal stability is only partially understood and has major significance for drug and vaccine discovery. The lack of datasets and standardized benchmarks considerably limits learning-based discovery methods. We present \${\textbackslash}texttt\{HotProtein\}\$, a large-scale protein dataset with {\textbackslash}textit\{growth temperature\} annotations of thermostability, containing \$182\$K amino acid sequences and \$3\$K folded structures from \$230\$ different species with a wide temperature range \$-20{\textasciicircum}\{{\textbackslash}circ\}{\textbackslash}texttt\{C\}{\textbackslash}sim 120{\textasciicircum}\{{\textbackslash}circ\}{\textbackslash}texttt\{C\}\$. Due to functional domain differences and data scarcity within each species, existing methods fail to generalize well on our dataset. We address this problem through a novel learning framework, consisting of (\$1\$) Protein structure-aware pre-training (SAP) which leverages 3D information to enhance sequence-based pre-training; (\$2\$) Factorized sparse tuning (FST) that utilizes low-rank and sparse priors as an implicit regularization, together with feature augmentations. Extensive empirical studies demonstrate that our framework improves thermostability prediction compared to other deep learning models. Finally, we propose a novel editing algorithm to efficiently generate positive amino acid mutations that improve thermostability.},
	language = {en},
	urldate = {2023-06-05},
	author = {Chen, Tianlong and Gong, Chengyue and Diaz, Daniel Jesus and Chen, Xuxi and Wells, Jordan Tyler and Liu, Qiang and Wang, Zhangyang and Ellington, Andrew and Dimakis, Alex and Klivans, Adam},
	month = oct,
	year = {2022},
	file = {Full Text PDF:/Users/pascalnotin/Zotero/storage/WIGJZS6V/Chen et al. - 2022 - HotProtein A Novel Framework for Protein Thermost.pdf:application/pdf},
}