first big commit

CHANGELOG.md

@@ -0,0 +1,30 @@
+# CHANGELOG for `astrabert/silly-gat-kay`
+
+### v0.0.0
+
+Only for internal testing, not public.
+
+Created the image from `broadinstitute/gatk` adding `bwa-mem2`, `cutadapt`, `platypus` and `picard`.
+
+### v0.1.0
+
+Added `curl`, `tar`, `micro`, `pigz` and `sra-toolkit`.
+
+### v0.2.0
+
+Only for internal testing, not public.
+
+Added `R` conda environment.
+
+### v0.3.0
+
+Added new `python_deps` conda env and its dependencies
+
+### v0.4.0
+
+Added `cmake`.
+
+### v0.5.0
+
+Added `poolfstat` to the `R` conda environment.
+

Dockerfile.latest

@@ -0,0 +1,13 @@
+# v0.5.0
+
+FROM astrabert/silly-gat-kay:latest
+
+WORKDIR /gatk_modified
+
+COPY ./shell/installations/conda_install_for_gatk /gatk_modified/conda_install_for_gatk
+
+RUN bash /gatk_modified/conda_install_for_gatk/install_poolfstat.sh
+
+ENTRYPOINT [ "/bin/bash" ]
+
+# sudo docker build . -f Dockerfile -t astrabert/silly-gat-kay:latest -t astrabert/silly-gat-kay:0.5.0

README.md

@@ -1,2 +1,43 @@
 # silly-gat-kay
 Repository for Docker image `astrabert/silly-gat-kay` info and changelog
+
+## Information on the image
+
+Variant calling and statistical analysis of population genomics data requires a certain number of tools, which can differ for functioning and version between machines and platforms. This is why we created a virtual environment managed through Docker, based on broadinstitute/gatk: you can run the image inside a container, which will produce an isolated machine on which you can carry out your analysis, without conflicts.
+
+The image is easily accessible through;
+
+```bash
+sudo docker pull astrabert/silly-gat-kay:latest
+```
+
+You should run it in interactive mode, possibily mounting your local file system into the container if you want to access data from your real machine inside the virtual one.
+
+```bash
+sudo docker run -v /path/to/your/project:/gatk_modified/drosophila-project -it astrabert/silly-gat-kay
+```
+
+The virtual machine is based on broadinstitute/gatk and provides a fully equipped environment for the analysis, divided into three conda envs:
+
+- **gatk_modified**: contains all GATK dependencies, but also bwa-mem2 and cutadapt
+- **picard**: contains picard-slim a lighter implementation of Picard which does not require r-base to run
+- **platypus**: contains platypus-variants, a SNP-calling focused conda wrapper for Platypus
+- **R**: contains r-base platform for data analysis in R and the library poolfstat
+- **python_deps**: contains python3.11 and various libraries like pandas, biopython, pyyaml.
+
+To activate the conda envs and deactivate them, run:
+
+```bash
+## activate
+source activate platypus
+## deactivate
+conda deactivate
+```
+Apart from these conda envs, it also contains other tools like cmake, the basic text editor micro, the multi-threading gzipper pigz and the SRA toolkit. To make SRA-toolkit CLI work, you should run:
+
+```bash
+cd /gatk_modified
+export PATH=$PATH:$PWD/sratoolkit.3.1.1-ubuntu64/bin
+## check if it was successful
+fastq-dump -h
+```

shell/installations/conda_install_for_gatk/install_cmake.sh

@@ -0,0 +1,16 @@
+apt-get update && apt-get install -y curl zip unzip tar pkg-config
+
+apt update && \
+apt install -y software-properties-common lsb-release && \
+apt clean all
+
+wget -O - https://apt.kitware.com/keys/kitware-archive-latest.asc 2>/dev/null | gpg --dearmor - | tee /etc/apt/trusted.gpg.d/kitware.gpg >/dev/null
+
+apt-add-repository "deb https://apt.kitware.com/ubuntu/ $(lsb_release -cs) main"
+
+apt update
+apt install -y kitware-archive-keyring
+rm /etc/apt/trusted.gpg.d/kitware.gpg
+
+apt update
+apt install -y cmake

shell/installations/conda_install_for_gatk/install_picard.sh

@@ -0,0 +1,6 @@
+eval "$(conda shell.bash hook)"
+
+conda create -y --name picard
+conda activate picard
+conda install -y bioconda::picard-slim
+conda deactivate

shell/installations/conda_install_for_gatk/install_platypus.sh

@@ -0,0 +1,7 @@
+eval "$(conda shell.bash hook)"
+
+conda create -y --name platypus
+conda activate platypus
+conda install -y bioconda::platypus-variant
+# platypus callVariants -h 
+conda deactivate

shell/installations/conda_install_for_gatk/install_poolfstat.sh

@@ -0,0 +1,5 @@
+eval "$(conda shell.bash hook)"
+
+conda activate R
+conda install -y r-poolfstat
+conda deactivate

shell/installations/conda_install_for_gatk/install_python_deps.sh

@@ -0,0 +1,9 @@
+eval "$(conda shell.bash hook)"
+
+conda create -y --name python_deps python=3.11
+
+source activate python_deps
+conda install -y anaconda::pandas
+conda install -y anaconda::pyyaml
+conda install -y conda-forge::biopython
+conda deactivate

shell/installations/conda_install_for_gatk/install_rbase.sh

@@ -0,0 +1,6 @@
+eval "$(conda shell.bash hook)"
+
+conda create -y --name R
+conda activate R
+conda install -y conda-forge::r-base
+conda deactivate

shell/installations/conda_install_for_gatk/install_sra-toolkit.sh

@@ -0,0 +1,4 @@
+wget --output-document sratoolkit.tar.gz https://ftp-trace.ncbi.nlm.nih.gov/sra/sdk/current/sratoolkit.current-ubuntu64.tar.gz 
+tar -vxzf sratoolkit.tar.gz 
+# export PATH=$PATH:$PWD/sratoolkit.3.1.1-ubuntu64/bin
+# fastq-dump -h

shell/installations/conda_install_for_gatk/installations.sh

@@ -0,0 +1,6 @@
+eval "$(conda shell.bash hook)"
+
+conda activate gatk_modified
+conda install -y bioconda::bwa-mem2
+conda install -y bioconda::cutadapt
+conda deactivate

v0.1.0/Dockerfile

@@ -0,0 +1,16 @@
+FROM broadinstitute/gatk:latest
+
+WORKDIR /gatk_modified
+COPY ./shell/installations/conda_install_for_gatk /gatk_modified/conda_install_for_gatk
+
+RUN apt-get update && apt-get install -y tar curl 
+RUN apt update && apt install -y micro pigz
+
+RUN bash /gatk_modified/conda_install_for_gatk/install_sra-toolkit.sh
+RUN conda create -y --name gatk_modified --clone gatk
+RUN bash /gatk_modified/conda_install_for_gatk/installations.sh
+RUN bash /gatk_modified/conda_install_for_gatk/install_platypus.sh
+RUN bash /gatk_modified/conda_install_for_gatk/install_picard.sh
+
+ENTRYPOINT [ "/bin/bash" ]
+# sudo docker build . -f Dockerfile -t astrabert/silly-gat-kay:latest -t astrabert/silly-gat-kay:0.1.0

v0.3.0/Dockerfile

@@ -0,0 +1,11 @@
+FROM astrabert/silly-gat-kay:latest
+
+WORKDIR /gatk_modified
+
+COPY ./shell/installations/conda_install_for_gatk /gatk_modified/conda_install_for_gatk
+
+RUN bash /gatk_modified/conda_install_for_gatk/install_python_deps.sh
+
+ENTRYPOINT [ "/bin/bash" ]
+
+# sudo docker build . -f Dockerfile -t astrabert/silly-gat-kay:latest -t astrabert/silly-gat-kay:0.3.0

v0.4.0/Dockerfile

@@ -0,0 +1,11 @@
+FROM astrabert/silly-gat-kay:latest
+
+WORKDIR /gatk_modified
+
+COPY ./shell/installations/conda_install_for_gatk /gatk_modified/conda_install_for_gatk
+
+RUN bash /gatk_modified/conda_install_for_gatk/install_cmake.sh
+
+ENTRYPOINT [ "/bin/bash" ]
+
+# sudo docker build . -f Dockerfile.gatk -t astrabert/silly-gat-kay:latest -t astrabert/silly-gat-kay:0.4.0

v0.5.0/Dockerfile

@@ -0,0 +1,11 @@
+FROM astrabert/silly-gat-kay:latest
+
+WORKDIR /gatk_modified
+
+COPY ./shell/installations/conda_install_for_gatk /gatk_modified/conda_install_for_gatk
+
+RUN bash /gatk_modified/conda_install_for_gatk/install_poolfstat.sh
+
+ENTRYPOINT [ "/bin/bash" ]
+
+# sudo docker build . -f Dockerfile -t astrabert/silly-gat-kay:latest -t astrabert/silly-gat-kay:0.5.0