added fix to eperiemnts

Author: sgosline

build/broad_sanger/03a-nci60Drugs.py

@@ -19,9 +19,6 @@
 conc_data = 'https://wiki.nci.nih.gov/download/attachments/147193864/DOSERESP.zip?version=11&modificationDate=1712351454136&api=v2'
 
 
-
-
-
 def main():    
     parser = argparse.ArgumentParser()
     parser.add_argument('--test',action='store_true',default=False,help='Test script by sampling 100 chemicals')
@@ -51,7 +48,7 @@ def main():
         arr = set(pubchems['CID'])
 
     print("Querying pubchem from CIDs")
-    pr.update_dataframe_and_write_tsv(arr,opts.output,'/tmp/ignore_chems.txt',batch_size=400,isname=False)
+    pr.update_dataframe_and_write_tsv(arr,opts.output,'/tmp/ignore_chems.txt',batch_size=400,isname=False,time_limit=10*60*60)
 
     ##then make sure to paste `nsc` in front of all nsc idds
     res = pl.read_csv(opts.output,separator='\t')

build/broad_sanger/04-drug_dosage_and_curves.py

@@ -12,6 +12,7 @@
 
 import os
 import argparse
+import pandas as pd
 
 parser = argparse.ArgumentParser()
 parser.add_argument('--curSampleFile',dest='samplefile',default=None,help='DepMap sample file')
@@ -45,7 +46,12 @@
     os.system('/opt/venv/bin/python fit_curve.py --input '+a+' --output '+a)
 
 ###step 4c concatenate all files
+outfiles = [a for a in os.listdir("./") if ".0" in a]
+final_file = []
+for of in outfiles:
+    final_file.append(pd.read_csv(of,sep='\t'))
 
-os.system('cat *.0 > /tmp/broad_sanger_experiments.tsv')
+pd.concat(final_file).to_csv('/tmp/broad_sanger_experiments.tsv',index=False,sep='\t')
+#os.system('cat *.0 > /tmp/broad_sanger_experiments.tsv')
 #os.system('gzip -f /tmp/experiments.tsv')
 

build/utils/pubchem_retrieval.py

@@ -150,9 +150,9 @@ def timeout_handler(signum, frame):
     should_continue = False
 
 # Call this function from other scripts. 
-def update_dataframe_and_write_tsv(unique_names, output_filename="drugs.tsv",ignore_chems="ignore_chems.txt", batch_size=1,isname=True):
+def update_dataframe_and_write_tsv(unique_names, output_filename="drugs.tsv",ignore_chems="ignore_chems.txt", batch_size=1,isname=True,time_limit=5*60*60):
     global should_continue, existing_synonyms, existing_pubchemids
-    time_limit=5*60*60 # 5 hours
+    #time_limit=5*60*60 # 5 hours
     signal.signal(signal.SIGALRM, timeout_handler)
     signal.alarm(time_limit)
     print('starting with '+str(len(unique_names))+' drug names/ids')