Renamed All PDO/PDX Datasets. Modified all files that reference the datasets. This was hundreds of references so its possible I missed something or capitalization is off somewhere

Author: jjacobson95

…dderpdo/00_createBladderPDOSampleFile.py …ld/bladder/00_createBladderSampleFile.pycoderbuild/bladderpdo/00_createBladderPDOSampleFile.py renamed to coderbuild/bladder/00_createBladderSampleFile.py coderbuild/bladderpdo/00_createBladderPDOSampleFile.py renamed to coderbuild/bladder/00_createBladderSampleFile.py

@@ -39,7 +39,7 @@ def _parse_model_type(sample_id):
     return "unknown"
 
 #Generate Samples Data
-def get_bladder_pdo_samples(synLoginObject, maxval):
+def get_bladder_samples(synLoginObject, maxval):
 
 
     #Part 1: Get Data from Synapse
@@ -115,5 +115,5 @@ def get_bladder_pdo_samples(synLoginObject, maxval):
     else: 
         prev_max_improve_id = 0
 
-    bladder_pdo_samples = get_bladder_pdo_samples(synObject, prev_max_improve_id)
-    bladder_pdo_samples.to_csv("/tmp/bladderpdo_samples.csv", index=False)
+    bladder_samples = get_bladder_samples(synObject, prev_max_improve_id)
+    bladder_samples.to_csv("/tmp/bladder_samples.csv", index=False)

…dderpdo/01_createBladderPDOOmicsFiles.py …ld/bladder/01_createBladderOmicsFiles.pycoderbuild/bladderpdo/01_createBladderPDOOmicsFiles.py renamed to coderbuild/bladder/01_createBladderOmicsFiles.py coderbuild/bladderpdo/01_createBladderPDOOmicsFiles.py renamed to coderbuild/bladder/01_createBladderOmicsFiles.py

@@ -35,7 +35,7 @@ def get_copy_call(a):
 
 def normalise_id(s):
     """
-    Make GEO sample IDs line up with 'other_id' in bladderpdo_samples.csv.
+    Make GEO sample IDs line up with 'other_id' in bladder_samples.csv.
     """
     if pd.isna(s):
         return s
@@ -48,10 +48,10 @@ def normalise_id(s):
 
 
 
-def get_bladder_pdo_transcriptomics(GEO_id_link_table, samples, genes):
+def get_bladder_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)
+    bladder_url ='https://ftp.ncbi.nlm.nih.gov/geo/series/GSE103nnn/GSE103990/suppl/GSE103990_Normalized_counts.txt.gz'
+    transcriptomic_txt = wget.download(bladder_url)
     transcriptomics = pd.read_csv(transcriptomic_txt, compression='gzip', sep="\t")
     subprocess.call (["/usr/bin/Rscript", "--vanilla", "obtainGSMidLink.R"])
 
@@ -92,7 +92,7 @@ def get_bladder_pdo_transcriptomics(GEO_id_link_table, samples, genes):
 
     return final_tx
 
-def get_bladder_pdo_mutations(synObject, samples, genes):
+def get_bladder_mutations(synObject, samples, genes):
     print(samples.head)
     mutations = synObject.get("syn64765525")
     mutations_df = pd.read_csv(mutations.path, sep='\t')
@@ -111,7 +111,7 @@ def get_bladder_pdo_mutations(synObject, samples, genes):
     final_mutations = final_mutations[final_mutations["entrez_id"] != 0]
     return final_mutations
 
-def get_bladder_pdo_copynumber(synObject, samples, genes):
+def get_bladder_copynumber(synObject, samples, genes):
     segfile = synObject.get("syn64765499")
     segfile_df = pd.read_csv(segfile.path, sep='\t')
 
@@ -161,10 +161,10 @@ def get_bladder_pdo_copynumber(synObject, samples, genes):
     samples = pd.read_csv(args.samples)
 
     if args.expression:
-        get_bladder_pdo_transcriptomics(args.geolink, samples, genes).to_csv("/tmp/bladderpdo_transcriptomics.csv", index=False)
+        get_bladder_transcriptomics(args.geolink, samples, genes).to_csv("/tmp/bladder_transcriptomics.csv", index=False)
 
     if args.mutation:
-        get_bladder_pdo_mutations(synObject, samples, genes).to_csv('/tmp/bladderpdo_mutations.csv', index=False)
+        get_bladder_mutations(synObject, samples, genes).to_csv('/tmp/bladder_mutations.csv', index=False)
 
     if args.copy:
-        get_bladder_pdo_copynumber(synObject, samples, genes).to_csv("/tmp/bladderpdo_copy_number.csv", index=False)
+        get_bladder_copynumber(synObject, samples, genes).to_csv("/tmp/bladder_copy_number.csv", index=False)

…adderpdo/02_createBladderPDODrugsFile.py …ild/bladder/02_createBladderDrugsFile.pycoderbuild/bladderpdo/02_createBladderPDODrugsFile.py renamed to coderbuild/bladder/02_createBladderDrugsFile.py coderbuild/bladderpdo/02_createBladderPDODrugsFile.py renamed to coderbuild/bladder/02_createBladderDrugsFile.py

@@ -9,7 +9,7 @@
 from pubchem_retrieval import update_dataframe_and_write_tsv
 
 
-def create_bladder_pdo_drugs_file(synObject, prevDrugFilepath, outputPath):
+def create_bladder_drugs_file(synObject, prevDrugFilepath, outputPath):
     bladder_dir = synObject.get('syn64765430')
     filenames = list(synObject.getChildren(parent='syn64765430', includeTypes=['file']))
 
@@ -22,10 +22,10 @@ def create_bladder_pdo_drugs_file(synObject, prevDrugFilepath, outputPath):
     raw_names = [str(n) for n in bladder_drugs['drugNames'].dropna().unique() if str(n).strip()]
 
     if not raw_names:
-        print("No bladderPDO drug names extracted; exiting.")
+        print("No bladder drug names extracted; exiting.")
         return
 
-    print(f"BladderPDO raw drug names: {raw_names}")
+    print(f"bladder raw drug names: {raw_names}")
 
     #New pubchem call
     update_dataframe_and_write_tsv(
@@ -53,4 +53,4 @@ def create_bladder_pdo_drugs_file(synObject, prevDrugFilepath, outputPath):
         previousDrugs = args.prevDrugFilePath
     else:
         previousDrugs = None
-    create_bladder_pdo_drugs_file(synObject, previousDrugs, args.outputPath)
+    create_bladder_drugs_file(synObject, previousDrugs, args.outputPath)

…pdo/03_createBladderPDOExperimentFile.py …ladder/03_createBladderExperimentFile.pycoderbuild/bladderpdo/03_createBladderPDOExperimentFile.py renamed to coderbuild/bladder/03_createBladderExperimentFile.py coderbuild/bladderpdo/03_createBladderPDOExperimentFile.py renamed to coderbuild/bladder/03_createBladderExperimentFile.py

@@ -3,7 +3,7 @@
 import argparse
 
 
-def get_bladder_pdo_experiments(synObject, samples, drugs):
+def get_bladder_experiments(synObject, samples, drugs):
     # get list of syn id info
     files = list(synObject.getChildren(parent='syn64765430', includeTypes=['file']))
     # load sample sheet and format _ to .
@@ -58,7 +58,7 @@ def get_bladder_pdo_experiments(synObject, samples, drugs):
     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')
+    parser.add_argument('-o', '--output', default = '/tmp/bladder_doserep.tsv',help='Output file to be read into curve fitting code')
 
     args = parser.parse_args()
     print("Logging into Synapse")
@@ -67,6 +67,6 @@ def get_bladder_pdo_experiments(synObject, samples, drugs):
     drug_df = pd.read_csv(args.drugfile, sep='\t')
     samples_df = pd.read_csv(args.curSampleFile)
 
-    doseresponse_data = get_bladder_pdo_experiments(synObject, samples_df, drug_df)
+    doseresponse_data = get_bladder_experiments(synObject, samples_df, drug_df)
     doseresponse_data.to_csv(args.output, sep='\t')
 

…uild/bladderpdo/CNV-segfile-annotation.R …erbuild/bladder/CNV-segfile-annotation.Rcoderbuild/bladderpdo/CNV-segfile-annotation.R renamed to coderbuild/bladder/CNV-segfile-annotation.R coderbuild/bladderpdo/CNV-segfile-annotation.R renamed to coderbuild/bladder/CNV-segfile-annotation.R

@@ -20,30 +20,30 @@ For these data, we had complete drug dose-response data to recalculate curves, a
 
 ### First sample and omics steps are the same, by hand locally or in full coderbuild process
 ```
-python3 00_createBladderPDOSampleFile.py --token $SYNAPSE_AUTH_TOKEN -p prevSamples
+python3 00_createbladderSampleFile.py --token $SYNAPSE_AUTH_TOKEN -p prevSamples
 
 # for mutation data (-m)
-python3 01_createBladderPDOOmicsFiles.py --token $SYNAPSE_AUTH_TOKEN -s curSamples -g genes.csv -m
+python3 01_createbladderOmicsFiles.py --token $SYNAPSE_AUTH_TOKEN -s curSamples -g genes.csv -m
 # for expressiondata (-e)
-python3 01_createBladderPDOOmicsFiles.py --token $SYNAPSE_AUTH_TOKEN -s curSamples -g genes.csv -e
+python3 01_createbladderOmicsFiles.py --token $SYNAPSE_AUTH_TOKEN -s curSamples -g genes.csv -e
 # for copynumber (-c)
-python3 01_createBladderPDOOmicsFiles.py --token $SYNAPSE_AUTH_TOKEN -s curSamples -g genes.csv -c
+python3 01_createbladderOmicsFiles.py --token $SYNAPSE_AUTH_TOKEN -s curSamples -g genes.csv -c
 ```
 
 ### For drug and experiment steps, command depends on location of helper scripts
 ```
 # for running locally (from coderbuild directory):
-python3 -m bladderpdo.02_createBladderPDODrugsFile --token $SYNAPSE_AUTH_TOKEN -d prevDrugFilePath -o ./bladderpdo/bladderpdo_drugs.tsv
+python3 -m bladder.02_createbladderDrugsFile --token $SYNAPSE_AUTH_TOKEN -d prevDrugFilePath -o ./bladder/bladder_drugs.tsv
 # for running in Docker as part of full build
-python3 02_createBladderPDODrugsFile.py --token $SYNAPSE_AUTH_TOKEN -d prevDrugFilePath -o /tmp/bladderpdo_drugs.tsv
+python3 02_createbladderDrugsFile.py --token $SYNAPSE_AUTH_TOKEN -d prevDrugFilePath -o /tmp/bladder_drugs.tsv
 
 # for running locally (from coderbuild directory): 
-python3 utils/build_drug_desc.py --drugtable ./bladderpdo/bladderpdo_drugs.tsv --desctable ./bladderpdo/bladderpdo_drug_descriptors.tsv.gz
+python3 utils/build_drug_desc.py --drugtable ./bladder/bladder_drugs.tsv --desctable ./bladder/bladder_drug_descriptors.tsv.gz
 # for running in docker as part of full build
-python3 build_drug_desc.py --drugtable /tmp/bladderpdo_drugs.tsv --desctable /tmp/bladderpdo_drug_descriptors.tsv.gz
+python3 build_drug_desc.py --drugtable /tmp/bladder_drugs.tsv --desctable /tmp/bladder_drug_descriptors.tsv.gz
 
 
-python3 03_createBladderPDOExperimentFile.py --token $SYNAPSE_AUTH_TOKEN --drugfile curDrugFile --curSampleFile curSampleFile --output /tmp/bladderpdo_doserep.tsv
+python3 03_createbladderExperimentFile.py --token $SYNAPSE_AUTH_TOKEN --drugfile curDrugFile --curSampleFile curSampleFile --output /tmp/bladder_doserep.tsv
 
-python3 fit_curve.py --input /tmp/bladderpdo_doserep.tsv --output /tmp/bladderpdo_experiments.tsv
+python3 fit_curve.py --input /tmp/bladder_doserep.tsv --output /tmp/bladder_experiments.tsv
 ```

coderbuild/bladderpdo/README.md coderbuild/bladder/README.mdcoderbuild/bladderpdo/README.md renamed to coderbuild/bladder/README.md

@@ -6,9 +6,9 @@ trap 'echo "Error on or near line $LINENO while executing: $BASH_COMMAND"; exit
 echo "Running script with token and drugFile $1"
 # for running locally (from build directory):
 #python3 -m bladderpdo.02_createBladderPDODrugsFile --token $SYNAPSE_AUTH_TOKEN -d $1 -o ./bladderpdo/bladderpdo_drugs.tsv
-python3 02_createBladderPDODrugsFile.py --token $SYNAPSE_AUTH_TOKEN -d $1 -o /tmp/bladderpdo_drugs.tsv
+python3 02_createBladderDrugsFile.py --token $SYNAPSE_AUTH_TOKEN -d $1 -o /tmp/bladder_drugs.tsv
 
 echo "Running build_drug_desc.py..."
 #for running locally: 
 #python3 utils/build_drug_desc.py --drugtable ./bladderpdo/bladderpdo_drugs.tsv --desctable ./bladderpdo/bladderpdo_drug_descriptors.tsv.gz
-python3 build_drug_desc.py --drugtable /tmp/bladderpdo_drugs.tsv --desctable /tmp/bladderpdo_drug_descriptors.tsv.gz
+python3 build_drug_desc.py --drugtable /tmp/bladder_drugs.tsv --desctable /tmp/bladder_drug_descriptors.tsv.gz

coderbuild/bladderpdo/build_drugs.sh coderbuild/bladder/build_drugs.shcoderbuild/bladderpdo/build_drugs.sh renamed to coderbuild/bladder/build_drugs.sh

@@ -0,0 +1,11 @@
+#!/bin/bash
+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"
+python3 03_createBladderExperimentFile.py --token $SYNAPSE_AUTH_TOKEN --drugfile $2 --curSampleFile $1 --output /tmp/bladder_doserep.tsv
+
+python3 fit_curve.py --input /tmp/bladder_doserep.tsv --output /tmp/bladder_experiments.tsv
+rm /tmp/bladder_doserep.tsv
+mv /tmp/bladder_experiments.tsv.0 /tmp/bladder_experiments.tsv

coderbuild/bladder/build_exp.sh

@@ -0,0 +1,12 @@
+#!/bin/bash
+set -euo pipefail
+
+trap 'echo "Error on or near line $LINENO while executing: $BASH_COMMAND"; exit 1' ERR
+
+echo "Running script with token, curSamples $2, and genes $1."
+# for mutation data (-m)
+python3 01_createBladderOmicsFiles.py --token $SYNAPSE_AUTH_TOKEN -s $2 -g $1 -m
+# for expressiondata (-e)
+python3 01_createBladderOmicsFiles.py --token $SYNAPSE_AUTH_TOKEN -s $2 -g $1 -e
+# for copynumber
+python3 01_createBladderOmicsFiles.py --token $SYNAPSE_AUTH_TOKEN -s $2 -g $1 -c

coderbuild/bladder/build_omics.sh

@@ -0,0 +1,7 @@
+#!/bin/bash
+set -euo pipefail
+
+trap 'echo "Error on or near line $LINENO while executing: $BASH_COMMAND"; exit 1' ERR
+
+echo "Running 00_createBladderSampleFile.py with token and previous sample file $1"
+python3 00_createBladderSampleFile.py --token $SYNAPSE_AUTH_TOKEN -p $1