successful docker build

Author: RubyFore

build/bladderpdo/01_createBladderPDOOmicsFiles.py

@@ -38,7 +38,7 @@ def get_bladder_pdo_transcriptomics(GEO_id_link_table, samples, genes):
     bladderpdo_url ='https://ftp.ncbi.nlm.nih.gov/geo/series/GSE103nnn/GSE103990/suppl/GSE103990_Normalized_counts.txt.gz'
     transcriptomic_txt = wget.download(bladderpdo_url)
     transcriptomics = pd.read_csv(transcriptomic_txt, compression='gzip', sep="\t")
-    subprocess.call (["/usr/local/bin/Rscript", "--vanilla", "obtainGSMidLink.R"])
+    subprocess.call (["/usr/bin/Rscript", "--vanilla", "obtainGSMidLink.R"])
 
     GEO_ids_link = pd.read_csv("./gsmlinkDf.csv")
     fpkm_totals = transcriptomics.iloc[:, 1:43].sum()
@@ -85,7 +85,7 @@ def get_bladder_pdo_copynumber(synObject, samples, genes):
     segfile_df = pd.read_csv(segfile.path, sep='\t')
 
     segfile_df.to_csv("bladder_segfile.csv")
-    subprocess.call (["/usr/local/bin/Rscript", "--vanilla", "CNV-segfile-annotation.R", "bladder_segfile.csv", "bladder_annotated_segfile.csv"])
+    subprocess.call (["/usr/bin/Rscript", "--vanilla", "CNV-segfile-annotation.R", "bladder_segfile.csv", "bladder_annotated_segfile.csv"])
     copynumber = pd.read_csv("bladder_annotated_segfile.csv")
     copynumber['copy_number'] = np.exp2(copynumber['score'].div(2))*2
     copynumber['copy_call'] = [get_copy_call(a) for a in copynumber['copy_number']]

build/bladderpdo/02_createBladderPDODrugsFile.py

@@ -4,9 +4,9 @@
 import argparse
 import os
 # for testing locally
-from utils.pubchem_retrieval import update_dataframe_and_write_tsv
+#from utils.pubchem_retrieval import update_dataframe_and_write_tsv
 # for building in docker
-#from pubchem_retrieval import update_dataframe_and_write_tsv
+from pubchem_retrieval import update_dataframe_and_write_tsv
 
 
 def create_bladder_pdo_drugs_file(synObject, prevDrugFilepath, outputPath):
@@ -39,12 +39,16 @@ def create_bladder_pdo_drugs_file(synObject, prevDrugFilepath, outputPath):
 if __name__ == "__main__":
 
     parser = argparse.ArgumentParser(description="This script handles downloading, processing and formatting of drug data files for the Lee Bladder PDO project")
-    parser.add_argument('-d', '--prevDrugFilePath', help='Path to a previous drug file for sarcpdo', default = None)
+    parser.add_argument('-d', '--prevDrugFilePath', help='Path to a previous drug file for sarcpdo', nargs="?", default = None)
     parser.add_argument('-o', '--outputPath', help='Output path for updated sarcpdo drug file', default = "/tmp/sarcpdo_drugs.tsv") 
     parser.add_argument('-t', '--token', help='Synapse token')
 
     args = parser.parse_args()
     print("Logging into Synapse")
     PAT = args.token
     synObject = synapseclient.login(authToken=PAT)
-    create_bladder_pdo_drugs_file(synObject, args.prevDrugFilePath, args.outputPath)
+    if args.prevDrugFilePath:
+        previousDrugs = args.prevDrugFilePath
+    else:
+        previousDrugs = None
+    create_bladder_pdo_drugs_file(synObject, previousDrugs, args.outputPath)

build/bladderpdo/03_createBladderPDOExperimentFile.py

@@ -1,13 +1,14 @@
 import synapseclient
 import pandas as pd
+import argparse
 
 
 def get_bladder_pdo_experiments(synObject, samples, drugs):
     # get list of syn id info
-    files = list(syn.getChildren(parent='syn64765430', includeTypes=['file']))
+    files = list(synObject.getChildren(parent='syn64765430', includeTypes=['file']))
     # load sample sheet and format _ to .
     # load conversion table and remove trailing _T
-    conversion_table = syn.get(files[50]['id'])
+    conversion_table = synObject.get(files[50]['id'])
     conversion_table_df = pd.read_excel(conversion_table.path, header=None)
     conversion_table_df[2] = conversion_table_df[1].str.rsplit("_", expand=True)[0]#.replace(".", "_")
     conversion_table_df[3] = conversion_table_df[2].str.replace(".", "_")
@@ -17,7 +18,7 @@ def get_bladder_pdo_experiments(synObject, samples, drugs):
     drug_df = pd.DataFrame()
     # for each drug, 
     for i in range(len(files)-4):
-        drug_table_syn =syn.get(files[i]['id'])
+        drug_table_syn =synObject.get(files[i]['id'])
         drug_table = pd.read_csv(drug_table_syn.path, sep="\t")
     # melt
     # link to conversion table
@@ -54,7 +55,7 @@ def get_bladder_pdo_experiments(synObject, samples, drugs):
 
 if __name__ == "__main__": 
     parser = argparse.ArgumentParser()
-    parser.add_argument('-t' '--token', help='Synapse authentication token')
+    parser.add_argument('-t', '--token', help='Synapse authentication token')
     parser.add_argument('-s', '--curSampleFile', help='Sample mapping file for bladder pdo samples')
     parser.add_argument('-d', '--drugfile', help='Drug mapping file for bladder pdo samples')
     parser.add_argument('-o', '--output', default = '/tmp/bladderpdo_doserep.tsv',help='Output file to be read into curve fitting code')

build/bladderpdo/build_exp.sh

@@ -4,6 +4,6 @@ set -euo pipefail
 trap 'echo "Error on or near line $LINENO while executing: $BASH_COMMAND"; exit 1' ERR
 
 echo "Running 04-drug_dosage_and_curves.py with drugfile $2 and curSampleFile $1"
-python 03_createBladderPDOExperimentFile.py --token $SYNAPSE_AUTH_TOKEN --drugfile $2 --curSampleFile $1 --output /tmp/bladderpdo_doserep.tsv
+python3 03_createBladderPDOExperimentFile.py --token $SYNAPSE_AUTH_TOKEN --drugfile $2 --curSampleFile $1 --output /tmp/bladderpdo_doserep.tsv
 
-python fit_curve.py --input /tmp/bladderpdo_doserep.tsv --output /tmp/bladderpdo_doserep.tsv
+python3 fit_curve.py --input /tmp/bladderpdo_doserep.tsv --output /tmp/bladderpdo_doserep.tsv

build/bladderpdo/requirements.txt

@@ -7,10 +7,10 @@ scikit-learn
 mordredcommunity
 rdkit
 wget
-gzip
-subprocess
-math
+#gzip
+#subproce
+#math
 tqdm
-itertools
+#itertools
 scipy
-multiprocessing
+openpyxl

build/docker/Dockerfile.bladderpdo

@@ -1,46 +1,63 @@
 FROM r-base:4.4.1
-ENV DEBIAN_FRONTEND=noninteractive
-RUN apt-get update  --fix-missing
-#RUN apt-get install -y --fix-missing --allow-unauthenticated build-essential libpq-dev python3.10 python3-pip python3-setuptools python3-dev python3-venv libcurl4-openssl-dev libxml2-dev libglpk-dev
-
-# RUN apt-get install -y --fix-missing --allow-unauthenticated build-essential python3-pip python3-setuptools python3-dev python3-venv libcurl4-openssl-dev libglpk-dev libxml2-dev libpq-dev
 
-RUN apt-get install -y --fix-missing --allow-unauthenticated \
-    build-essential \
-    python3-pip \
-    python3-setuptools \
-    python3-dev \
-    python3-venv \
-    libcurl4-openssl-dev \
-    libglpk-dev \
-    libxml2-dev \
-    libpq-dev \
-    ca-certificates
-
-RUN python3 -m venv /opt/venv
-RUN /opt/venv/bin/pip3 install --upgrade pip
+ENV DEBIAN_FRONTEND=noninteractive
 
+# Update package list and install required packages
+RUN apt-get update && \
+    apt-get install -y build-essential wget curl libcurl4-openssl-dev libxml2-dev \
+    zlib1g-dev libssl-dev libbz2-dev libreadline-dev libsqlite3-dev libffi-dev
+
+# Download and compile Python 3.10 with shared library support
+RUN wget https://www.python.org/ftp/python/3.10.12/Python-3.10.12.tgz && \
+    tar -xf Python-3.10.12.tgz && \
+    cd Python-3.10.12 && \
+    ./configure --enable-optimizations --enable-shared && \
+    make -j$(nproc) && \
+    make altinstall && \
+    cd .. && \
+    rm -rf Python-3.10.12.tgz Python-3.10.12
+
+# Set Python 3.10 as default
+RUN ln -s /usr/local/bin/python3.10 /usr/bin/python3 && \
+    ln -s /usr/local/bin/pip3.10 /usr/bin/pip3
+
+# Update library paths for Python shared library
+RUN echo "/usr/local/lib" >> /etc/ld.so.conf.d/python3.10.conf && ldconfig
+
+# Create a Python virtual environment
+#RUN python3 -m venv /opt/venv
+#RUN /opt/venv/bin/pip install --upgrade pip
+
+# Set environment variables for reticulate
+#ENV RETICULATE_PYTHON="/opt/venv/bin/python3"
+ENV PYTHONPATH=/app#"${PYTHONPATH}:/app"
+WORKDIR /app
 
-# Set MPLCONFIGDIR to a writable directory
+# Set MPLCONFIGDIR to a writable directory and create it.
 ENV MPLCONFIGDIR=/app/tmp/matplotlib
 RUN mkdir -p /app/tmp/matplotlib
 
 
-ENV PYTHONPATH "${PYTHONPATH}:/app"
-WORKDIR /app
+ADD build/bladderpdo/requirements.R .
+# installing r libraries
+RUN Rscript requirements.R
 
-ADD build/broad_sanger/obtainGSMidLink.R.R ./
-ADD build/broad_sanger/CNV-segfile-annotation.R ./
-ADD build/broad_sanger/*py ./
-ADD build/broad_sanger/*sh ./
 
-ADD build/utils/* ./
 
+# installing python libraries
 ADD build/bladderpdo/requirements.txt .
-ADD build/bladderpdo/exp_requirements.r .
+#RUN /opt/venv/bin/pip3 install -r requirements.txt
+RUN pip3 install -r requirements.txt
 
-# installing r libraries
-RUN Rscript exp_requirements.r
+RUN python3 --version
+RUN which Rscript
+
+#ENV PATH="/opt/venv/bin:$PATH"
+
+ADD build/bladderpdo/obtainGSMidLink.R ./
+ADD build/bladderpdo/CNV-segfile-annotation.R ./
+ADD build/bladderpdo/*py ./
+ADD build/bladderpdo/*sh ./
+
+ADD build/utils/* ./
 
-# installing python libraries
-RUN /opt/venv/bin/pip3 install -r requirements.txt

build/docker/docker-compose.yml

@@ -71,7 +71,7 @@ services:
     platform: linux/amd64
     image: cptac:latest
 
-   bladderpdo:
+  bladderpdo:
     build:
       context: ../../
       dockerfile: build/docker/Dockerfile.bladderpdo