temporary fix to remove drug compounds from drug_smiles.tsv that have no smiles string

ymahlich · ymahlich · commit dcabaea28fb0 · 2025-02-05T12:00:11.000-08:00
diff --git a/scripts/prepare_data_for_improve.py b/scripts/prepare_data_for_improve.py
@@ -402,6 +402,7 @@ def process_datasets(args):
         columns={'improve_drug_id': 'improve_chem_id'},
         inplace=True,
         )
+    out_df = out_df.dropna(how='any',axis=0)
 
     outfile_path = args.WORKDIR.joinpath(
         "data_out",

Original file line number	Diff line number	Diff line change
`@@ -402,6 +402,7 @@ def process_datasets(args):`
`402`	`402`	`columns={'improve_drug_id': 'improve_chem_id'},`
`403`	`403`	`inplace=True,`
`404`	`404`	`)`
	`405`	`+ out_df = out_df.dropna(how='any',axis=0)`
`405`	`406`
`406`	`407`	`outfile_path = args.WORKDIR.joinpath(`
`407`	`408`	`"data_out",`