changed name of columns that were being searched in filtered.maf inpu…

…t file for tag_by_variant_classification.
msk-access · Sep 26, 2024 · 2d06597 · 2d06597
1 parent e807105
commit 2d06597
Show file tree

Hide file tree

Showing 3 changed files with 11 additions and 11 deletions.
diff --git a/postprocessing_variant_calls/maf/helper.py b/postprocessing_variant_calls/maf/helper.py
@@ -727,12 +727,12 @@ def tag_traceback(self, cols, tagging):
 
     def tag_by_variant_classification(self, output_dir, ref_lst):
         maf = add_dummy_columns(self.data_frame, MAF_DUMMY_COLUMNS)
-
+        
         # start tagging the input MAF with the 5 categories
 
         def is_exonic_or_silent(row, ref_lst):
             exonic_result = IS_EXONIC_CLASS(
-                row.Hugo_Symbol, row.Variant_Classification, row.vcf_pos
+                row.Hugo_Symbol, row.Variant_Classification, row.Start_Position
             )
             if exonic_result:
                 if row.Transcript_ID in ref_lst:

diff --git a/postprocessing_variant_calls/maf/tag/tag_constants.py b/postprocessing_variant_calls/maf/tag/tag_constants.py
@@ -525,13 +525,13 @@
         # ("Start_Position", "Start"),
         # ("Reference_Allele", "Ref"),
         # ("Tumor_Seq_Allele2", "Alt"),
-        ("vcf_pos", "Start"),
-        ("VCF_REF", "Ref"),
-        ("VCF_ALT", "Alt"),
+        ("Start_Position", "Start_Position"),
+        ("Reference_Allele", "Reference_Allele"),
+        ("Tumor_Seq_Allele2", "Tumor_Seq_Allele2"),
         ("Variant_Classification", "VariantClass"),
         ("Hugo_Symbol", "Gene"),
         ("Call_Confidence", "Call_Confidence"),
-        ("EXON", "Exon"),
+        ("Exon_Number", "Exon_Number"),
         ("Transcript_ID", "TranscriptID"),
         ("Comments", "Comments"),
         ("HGVSc", "cDNAchange"),

diff --git a/postprocessing_variant_calls/maf/tag/tag_process.py b/postprocessing_variant_calls/maf/tag/tag_process.py
@@ -384,7 +384,6 @@ def format_var(variant):
             columns = map(lambda x: getattr(variant, x), MAF_TSV_COL_MAP.keys())
             return "\t".join(map(str, columns)) + "\n"
         except AttributeError:
-            return
             missing_columns = set(MAF_TSV_COL_MAP.keys()) - set(
                 filter(lambda x: not x.startswith("_"), dir(variant))
             )
@@ -413,7 +412,7 @@ def reformat_tx(txID, tx_df):
 
     # start tagging by variant classification process
     final_maf = mafa.tag_by_variant_classification(output_dir, tx_isoform_lst)
-
+    
     # Create exonic, silent, and nonpanel files.
     file_names = [
         EXONIC_FILTERED,
@@ -438,13 +437,13 @@ def reformat_tx(txID, tx_df):
 
             # Reformat the row
             formatted_variant = format_var(variant)
-
+            
             # Determine which file(s) to write to based on the tag
             if "exonic" in tag:
                 variant_tuple = (
                     variant.Hugo_Symbol,
                     variant.Variant_Classification,
-                    variant.vcf_pos,
+                    variant.Start_Position,
                 )
                 transcript_id = reformat_tx(variant.Transcript_ID, tx_df)
 
@@ -456,13 +455,14 @@ def reformat_tx(txID, tx_df):
                     Chromosome=variant.Chromosome,
                     Variant_Classification=variant_tuple[1],  # VariantClass
                     Variant_Type=variant.Variant_Type,
-                    vcf_pos=variant_tuple[2],  # Start coordinate
+                    Start_Position=variant_tuple[2],  # Start coordinate
                     Tumor_Sample_Barcode=variant.Tumor_Sample_Barcode,
                     caller_Norm_Sample_Barcode=variant.caller_Norm_Sample_Barcode,
                     Transcript_ID=transcript_id,  # TranscriptID
                 )
                 formatted_exonic_variant_row = format_var(variant)
                 files[0].write(formatted_exonic_variant_row)
+
             if "silent" in tag:
                 files[1].write(formatted_variant)
             if "nonpanel_exonic" in tag: