Fix citation columns misalignment (#144)

CNA/Fusion annotation files are not aligned appropriately caused by #134
oncokb · Nov 29, 2021 · 78ece67 · 78ece67
1 parent 6c06049
commit 78ece67
Show file tree

Hide file tree

Showing 2 changed files with 16 additions and 9 deletions.
diff --git a/AnnotatorCore.py b/AnnotatorCore.py
@@ -661,21 +661,25 @@ def processsv(svdata, outfile, previousoutfile, defaultCancerType, cancerTypeMap
         outf.write("\t" + GENE_IN_ONCOKB_HEADER)
         outf.write("\t" + VARIANT_IN_ONCOKB_HEADER)
         outf.write("\tMUTATION_EFFECT")
+        outf.write("\tMUTATION_EFFECT_CITATIONS")
         outf.write("\tONCOGENIC")
         for l in levels:
             outf.write('\t' + l)
         outf.write("\tHIGHEST_LEVEL")
-        outf.write("\tCITATIONS")
+        outf.write("\tTX_CITATIONS")
 
         for l in dxLevels:
             outf.write('\t' + l)
         outf.write("\tHIGHEST_DX_LEVEL")
+        outf.write("\tDX_CITATIONS")
 
         for l in pxLevels:
             outf.write('\t' + l)
-        outf.write("\tHIGHEST_PX_LEVEL\n")
+        outf.write("\tHIGHEST_PX_LEVEL")
+        outf.write("\tPX_CITATIONS")
+        outf.write("\n")
 
-        newcols = ncols + 8 + len(levels) + len(dxLevels) + len(pxLevels)
+        newcols = ncols + 11 + len(levels) + len(dxLevels) + len(pxLevels)
 
         igene1 = geIndexOfHeader(headers, ['GENE1'])
         igene2 = geIndexOfHeader(headers, ['GENE2'])
@@ -767,21 +771,25 @@ def processcnagisticdata(cnafile, outfile, previousoutfile, defaultCancerType, c
         outf.write("\t"+GENE_IN_ONCOKB_HEADER)
         outf.write("\t"+VARIANT_IN_ONCOKB_HEADER)
         outf.write("\tMUTATION_EFFECT")
+        outf.write("\tMUTATION_EFFECT_CITATIONS")
         outf.write("\tONCOGENIC")
         for l in levels:
             outf.write('\t' + l)
         outf.write("\tHIGHEST_LEVEL")
-        outf.write("\tCITATIONS")
+        outf.write("\tTX_CITATIONS")
 
         for l in dxLevels:
             outf.write('\t' + l)
         outf.write("\tHIGHEST_DX_LEVEL")
+        outf.write("\tDX_CITATIONS")
 
         for l in pxLevels:
             outf.write('\t' + l)
-        outf.write("\tHIGHEST_PX_LEVEL\n")
+        outf.write("\tHIGHEST_PX_LEVEL")
+        outf.write("\tPX_CITATIONS")
+        outf.write("\n")
 
-        ncols = 12 + len(levels) + len(dxLevels) + len(pxLevels)
+        ncols = 15 + len(levels) + len(dxLevels) + len(pxLevels)
 
         i = 0
         rows = []

diff --git a/test_Annotation.py b/test_Annotation.py
@@ -281,9 +281,8 @@ def check_brca2_n3214i_without_cancertype(annotation):
     assert annotation[MUTATION_EFFECT_INDEX] == 'Likely Loss-of-function'
     assert annotation[ONCOGENIC_INDEX] == 'Likely Oncogenic'
     assert annotation[HIGHEST_LEVEL_INDEX] == 'LEVEL_1'
-    assert annotation[LEVEL_1_INDEX] == 'Olaparib,Olaparib+Bevacizumab,Rucaparib,Niraparib'
-    assert annotation[LEVEL_2_INDEX] == 'Talazoparib,Olaparib'
-    assert annotation[LEVEL_3A_INDEX] == 'Rucaparib,Olaparib'
+    assert annotation[LEVEL_1_INDEX] == 'Olaparib,Rucaparib,Olaparib+Bevacizumab,Niraparib'
+    assert annotation[LEVEL_3A_INDEX] == 'Olaparib,Rucaparib,Talazoparib'
 
 @pytest.mark.skipif(ONCOKB_API_TOKEN in (None, ''), reason="oncokb api token required")
 def test_duplicated_treatments():