Merge pull request #1 from DLBPointon/patch-1

Patch 1

PTL2/Dockerfile

@@ -0,0 +1,47 @@
+FROM python:3.8.20-bullseye
+RUN apt-get update -y && apt-get upgrade -y && \
+    apt-get install git wget ncbi-blast+-legacy mafft build-essential vim -y
+
+# PhyloToL installation
+# Tested on: RUN git clone -b patch-1 https://github.com/DLBPointon/EukPhylo.git
+# Will work on below container after PR merge
+
+RUN git clone -b Docker https://github.com/Katzlab/EukPhylo.git
+
+# IQ-TREE installation
+RUN wget https://github.com/Cibiv/IQ-TREE/releases/download/v1.6.12/iqtree-1.6.12-Linux.tar.gz && \
+    tar xzf iqtree-1.6.12-Linux.tar.gz && \
+    mv iqtree-1.6.12-Linux/ /usr/local/iqtree && \
+    ln -s /usr/local/iqtree/bin/iqtree /usr/local/bin/iqtree
+
+# Install python dependencies
+RUN pip install biopython==1.75 ete3==3.1.2 tqdm==4.66.4 six==1.17.0
+
+# VSEARCH installation
+RUN wget https://github.com/torognes/vsearch/releases/download/v2.21.0/vsearch-2.21.0-linux-aarch64.tar.gz && \
+    tar xzf vsearch-2.21.0-linux-aarch64.tar.gz && \
+    mv vsearch-2.21.0-linux-aarch64 /usr/local/vsearch && \
+    ln -s /usr/local/vsearch/bin/vsearch /usr/local/bin/vsearch
+
+# Guidance installation
+RUN mkdir guidance && \
+    wget https://taux.evolseq.net/guidance/static/download/guidance.v2.02.tar.gz && \
+    tar -xzvf guidance.v2.02.tar.gz -C guidance --no-same-owner && \
+    cd guidance/guidance.v2.02 && make
+
+# Install pre-compiled version of Trimal 1.5.0
+RUN wget https://github.com/inab/trimal/releases/download/v1.5.0/trimAl_Linux_x86-64.zip && \
+    unzip trimAl_Linux_x86-64.zip && \
+    mv trimAl_Linux_x86-64 /usr/local/trimal
+
+# Clean the container
+RUN rm -rf iqtree-1.6.12-Linux.tar.gz vsearch-2.21.0-linux-aarch64.tar.gz guidance.v2.02.tar.gz trimAl_Linux_x86-64.zip
+
+# Add executables to path
+ENV PATH="$PATH:/iqtree/bin/iqtree:/usr/local/vsearch/bin/vsearch:/usr/local/trimal/trimal:/usr/local/bin"
+
+# Change executable permissions on wrapper script
+RUN ["chmod", "+x", "/EukPhylo/PTL2/run_eukphylo.sh"]
+
+# Change entrypoint on execution of the container
+ENTRYPOINT ["bash","/EukPhylo/PTL2/run_eukphylo.sh"]

PTL2/run_eukphylo.sh

@@ -6,10 +6,17 @@
 ## EukPhylo Wiki (https://github.com/Katzlab/EukPhylo/wiki/EukPhylo-Part-2:-MSAs,-trees,-and-contamination-loop).
 ## These run commands can also be copied and run in the terminal / command line separately, without a shell script.
 
-
+parent='/EukPhylo/PTL2'
+out_dir='/Output_data'
+in_dir='/Input_data'
 
 ## EXAMPLE RUN COMMANDS BELOW
 
 # A simple run of part 2, starting from ReadyToGo files and running through tree building
-python3 Scripts/eukphylo.py --start raw --end trees --gf_list listofOGs.txt --taxon_list taxon_list.txt --data Input_folder --output Output_folder > Output.out
-
+python3 ${parent}/Scripts/eukphylo.py \
+    --start raw \
+    --end trees \
+    --gf_list ${parent}listofOGs.txt \
+    --taxon_list ${parent}taxon_list.txt \
+    --data ${in_dir} \
+    --output ${out_dir} > Output.out

README.md

@@ -1,4 +1,30 @@
-
 <img src="https://github.com/Katzlab/PhyloToL-6/blob/main/Other/Katzlab.png">
 
-**EukPhylo version 1.0** is an updated version of the PhyloToL pipeline from the [Katz Lab](https://www.science.smith.edu/katz-lab/) at Smith College. EukPhylo is a phylogenomic toolkit for processing transcriptomic and genomic data that includes novel phylogeny-informed contamination removal techniques. See our [Wiki](https://github.com/Katzlab/EukPhylo/wiki) for more information on installation and usage!
+> :warning: ** This is currently being dockerised! ** Use the container at your own peril!
+
+# **EukPhylo version 1.0** 
+EukPhylo is an updated version of the PhyloToL pipeline from the [Katz Lab](https://www.science.smith.edu/katz-lab/) at Smith College. EukPhylo is a phylogenomic toolkit for processing transcriptomic and genomic data that includes novel phylogeny-informed contamination removal techniques. See our [Wiki](https://github.com/Katzlab/EukPhylo/wiki) for more information on installation and usage!
+
+
+## Dockerfile
+
+The docker file can be executed with:
+
+```bash
+cd EukPhylo
+
+# Build the container
+docker build -f Dockerfile . --tag MyEuk:1
+
+# Get the container IMAGE_ID
+docker image list
+
+# Current command is:
+docker run -it \
+    --mount type=bind,src=$(pwd)/databases,dst=/Databases \
+    --mount type=bind,src=$(pwd)/input_data,dst=/Input_data \
+    --mount type=bind,src=$(pwd)/output_data,dst=/Output_data \
+    {IMAGE_ID}
+```
+
+After development, GitHub CICD workflows can be added to automatically build and release the dockerfile for the end user.