fixing issues

Author: alexandriai168

build/novartispdx/02-omics-novartispdx.py

@@ -113,7 +113,7 @@ def map_copy_number_novPDX(copy_number_data, improve_id_data, entrez_data):
     long_cn_df = pd.melt(copy_number_data, id_vars=['Sample'], value_vars=copy_number_data.columns[copy_number_data.columns != 'Sample'])
 
     # get entrez id's from Sample
-    entrez_cn_df = pd.merge(long_cn_df, entrez_data[['other_id','entrez_id']].drop_duplicates(), how = 'left', left_on= "Sample", right_on= "other_id")
+    entrez_cn_df = pd.merge(long_cn_df, entrez_data[['other_id','entrez_id']].drop_duplicates(), how = 'inner', left_on= "Sample", right_on= "other_id")
 
     # get copy call from value column (aka copy number)
     entrez_cn_df['copy_call'] = [get_copy_call(a) for a in entrez_cn_df['value']]

build/novartispdx/03-drugs-novartispdx.py

@@ -4,7 +4,7 @@
 import argparse
 import os
 # for testing locally
-from utils.pubchem_retrieval import update_dataframe_and_write_tsv
+from pubchem_retrieval import update_dataframe_and_write_tsv
 # for building in docker
 #from pubchem_retrieval import update_dataframe_and_write_tsv
 

build/novartispdx/build_drugs.sh

@@ -5,11 +5,11 @@ 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 03-drugs-novartispdx --token $SYNAPSE_AUTH_TOKEN -d $1 -o /tmp/novartispdx_drugs.tsv
+python3 03-drugs-novartispdx.py --token $SYNAPSE_AUTH_TOKEN -d $1 -o /tmp/novartispdx_drugs.tsv
 #python3 novar
 #python3 03-drugs-novartispdx.py --token $SYNAPSE_AUTH_TOKEN -d $1 -o /tmp/novartispdx_drugs.tsv
 
 echo "Running build_drug_desc.py..."
 #for running locally: 
-python3 utils/build_drug_desc.py --drugtable /tmp/novartispdx_drugs.tsv --desctable /tmp/novartispdx_drug_descriptors.tsv.gz
+python3 build_drug_desc.py --drugtable /tmp/novartispdx_drugs.tsv --desctable /tmp/novartispdx_drug_descriptors.tsv.gz
 #python3 build_drug_desc.py --drugtable /tmp/novartispdx_drugs.tsv --desctable /tmp/novartispdx_drug_descriptors.tsv.gz