added new scripts to pull data

Author: sgosline

build/build_dataset.py

@@ -124,7 +124,7 @@ def process_omics(executor, dataset, should_continue):
         'broad_sanger': ['copy_number', 'mutations', 'proteomics', 'transcriptomics'],
         'cptac': ['copy_number', 'mutations', 'proteomics', 'transcriptomics'],
         'hcmi': ['mutations', 'transcriptomics'],
-        'pancpdo': ['mutations', 'transcriptomics'],
+        'pancpdo': ['transcriptomics'],
         'mpnstpdx':['copy_number', 'mutations', 'proteomics', 'transcriptomics']
     }
 

build/pancpdo/02-getPancPDOData.py

@@ -576,9 +576,9 @@ def write_dataframe_to_csv(dataframe, outname):
     None
     """
     if('gz' in outname):
-        dataframe.to_pandas().to_csv(outname,compression='gzip',index=False)
+        dataframe.to_pandas().drop_duplicates().to_csv(outname,compression='gzip',index=False)
     else:
-        dataframe.to_pandas().to_csv(outname,index=False)
+        dataframe.to_pandas().drop_duplicates().to_csv(outname,index=False)
     return
 
 def main():
@@ -682,6 +682,7 @@ def main():
     print("Aligning to Schema")
     final_data = align_to_schema(combined_data,args.type,7500,args.samples)
     gc.collect()
+
     combined_data = None
 
     print(f"final data:\n{final_data}")

build/pancpdo/03-getPancPDODrugs.py

@@ -0,0 +1,21 @@
+import pandas as pd
+import os
+import argparse
+
+
+
+
+###figshare link:
+
+filelink='https://aacr.figshare.com/ndownloader/files/39996295'
+##get third tab and drugsa re listeda cross top
+
+def main():
+    parser = argparse.ArgumentParser(description='Download and match pancpdocdrugs')
+    parser.add_argument('-d', '--prevDrugFile')
+    parser.add_argument('-o', '--output', default = '/tmp/panpdc_drugs.tsv')
+
+    
+
+if __name__=='__main__':
+    main()

build/pancpdo/04-getPancPDOExperiments.py

@@ -0,0 +1,11 @@
+
+import os
+import pandas as pd
+import wget
+import argparse
+
+
+
+def main():
+    ##current AUC values are here: https://aacr.figshare.com/ndownloader/files/39996295 tabs 2 and 3
+    parser = argparse.ArgumentParser()