add additional r libraries for future plotting, organize.py now handles presence/absence of profile on user input and prepare command for running cosigt w/conda

Author: davidebolo1993

Dockerfile

@@ -63,9 +63,8 @@ ENV PATH="/root/.cargo/bin:${PATH}"
 RUN rustup update
 RUN cargo install --locked maturin
 
-#install numpy
-RUN pip3 install numpy \
-	pandas
+#install python libraries here
+#RUN pip3 install ...
 
 #ln python to python3 -not used right now but, who knows?
 RUN ln -s /usr/bin/python3 /usr/bin/python
@@ -161,14 +160,22 @@ RUN git clone https://github.com/davidebolo1993/cosigt.git \
 
 ENV PATH /opt:$PATH
 
-
 #R and R libs w/conda - adding should be easier
 
 RUN curl -LO https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh
 RUN bash Miniconda3-latest-Linux-x86_64.sh -p /miniconda -b
 RUN rm Miniconda3-latest-Linux-x86_64.sh
 ENV PATH=/miniconda/bin:${PATH}
 RUN conda update -y conda
-RUN conda create -y -n renv -c conda-forge r-base r-data.table=1.15.4 r-rjson=0.2.23 r-reshape2=1.4.4 r-nbclust=3.0.1 r-ggplot2=3.5.1 r-dendextend=1.18.1
+RUN conda create -y -n renv -c conda-forge -c bioconda \
+	r-base \
+	r-data.table=1.15.4 \
+	r-rjson=0.2.23 \
+	r-reshape2=1.4.4 \
+	r-nbclust=3.0.1 \
+	r-ggplot2=3.5.1 \
+	r-dendextend=1.18.1 \
+	r-gggenes=0.5.1 \
+	bioconductor-rtracklayer=1.62.0
 RUN echo "source activate renv" > ~/.bashrc
 ENV PATH /miniconda/envs/renv/bin:$PATH

cosigt_smk/workflow/envs/plot.yaml

@@ -0,0 +1,10 @@
+channels:
+ - conda-forge
+ - bioconda
+dependencies:
+  - r-data.table=1.15.4
+  - r-rjson=0.2.23
+  - r-ggplot2=3.5.1
+  - r-gggenes=0.5.1
+  - bioconductor-rtracklayer=1.62.0
+  - r-base

cosigt_smk/workflow/scripts/organize.py

@@ -127,6 +127,7 @@ def main():
 	additional.add_argument('--binds', help='additional paths to bind for singularity in /path/1,/path/2 format [/localscratch]', type=str, default='/localscratch')
 	additional.add_argument('--tmp', help='SINGULARITY TMPDIR [/tmp]', type=str, default='/tmp')	
 	additional.add_argument('--output', help='output folder [results]', metavar='FOLDER', default='results')
+	additional.add_argument('--profile', help='use profile. If "None", do not use profile and run on the local machine [config/slurm]', metavar='FOLDER', default='config/slurm')
 
 	metrics = parser.add_argument_group('Specify #threads, memory and time requirements')
 
@@ -160,6 +161,7 @@ def main():
 	metrics.add_argument('--wfmash_tmpdir', help='temporary directory - wfmash [working directory]',type=str, default=os.getcwd())
 
 	args = parser.parse_args()
+	args.profile=None if args.profile == 'None' else args.profile
 
 	#wd
 	wd=os.getcwd()
@@ -304,13 +306,38 @@ def main():
 
 	os.remove(out_yaml_tmp)
 
-	#write command
+	#write command - singularity
 	singpath=','.join(list(set([os.path.abspath(args.alignments),os.path.dirname(os.path.abspath(args.assemblies)), os.path.dirname(os.path.abspath(args.reference)),args.binds, os.path.abspath(args.pggb_tmpdir), os.path.abspath(args.wfmash_tmpdir)])))
-	command_out='SINGULARITY_TMPDIR=' + os.path.abspath(args.tmp) + ' snakemake --profile config/slurm --singularity-args "-B '+ singpath + ' -e" cosigt'
 
-	with open('snakemake.run.sh', 'w') as out:
+	if args.profile is not None:
+	
+		command_singularity_out='SINGULARITY_TMPDIR=' + os.path.abspath(args.tmp) + ' snakemake --profile ' + args.profile + ' --singularity-args "-B '+ singpath + ' -e" cosigt'
+	
+		with open('snakemake.singularity.profile.run.sh', 'w') as out:
+
+			out.write(command_singularity_out + '\n')
+
+		#write command - conda
+		command_conda_out='snakemake --profile ' + args.profile + ' --use-conda cosigt'
+
+		with open('snakemake.conda.profile.run.sh', 'w') as out:
+
+			out.write(command_conda_out + '\n')
+
+	else:
+
+		command_singularity_out='SINGULARITY_TMPDIR=' + os.path.abspath(args.tmp) + ' snakemake --singularity-args "-B '+ singpath + ' -e" cosigt'
+
+		with open('snakemake.singularity.run.sh', 'w') as out:
+
+			out.write(command_singularity_out + '\n')
+
+		#write command - conda
+		command_conda_out='snakemake --use-conda cosigt'
+
+		with open('snakemake.conda.run.sh', 'w') as out:
 
-		out.write(command_out + '\n')
+			out.write(command_conda_out + '\n')
 
 
 if __name__ == '__main__':