Add base annotation files

Update example_clinical.oncokb.txt

delete files

Add option to include descriptions

The added descriptions include the following
- GENE_SUMMARY
- VARIANT_SUMMARY
- TUMOR_TYPE_SUMMARY
- DIAGNOSTIC_SUMMARY
- PROGNOSTIC_SUMMARY

CnaAnnotator.py

@@ -20,7 +20,9 @@ def main(argv):
     if argv.help:
         log.info(
             '\n'
-            'CnaAnnotator.py -i <input CNA file> -o <output CNA file> [-p previous results] [-c <input clinical file>] [-s sample list filter] [-t <default tumor type>] [-u oncokb-base-url] [-b oncokb_api_bear_token] [-z annotate_gain_loss] [-f CNA file formt, gistic or individual]\n'
+            'CnaAnnotator.py -i <input CNA file> -o <output CNA file> [-p previous results] [-c <input clinical file>] '
+            '[-s sample list filter] [-t <default tumor type>] [-u oncokb-base-url] [-b oncokb_api_bear_token] '
+            '[-z annotate_gain_loss] [-f CNA file formt, gistic or individual] [-d include descriptions]\n'
             '  Input CNA file uses GISTIC output by default (https://docs.cbioportal.org/5.1-data-loading/data-loading/file-formats#data-file-1). You can also list copy number alteration individually by specifying -f=individual\n'
             '  Essential clinical columns:\n'
             '    SAMPLE_ID: sample ID\n'
@@ -57,7 +59,7 @@ def main(argv):
     validate_oncokb_token()
 
     log.info('annotating %s ...' % argv.input_file)
-    process_cna_data(argv.input_file, argv.output_file, argv.previous_result_file, argv.default_cancer_type, cancertypemap, argv.annotate_gain_loss, argv.cna_file_format.lower())
+    process_cna_data(argv.input_file, argv.output_file, argv.previous_result_file, argv.default_cancer_type, cancertypemap, argv.include_descriptions, argv.annotate_gain_loss, argv.cna_file_format.lower())
 
     log.info('done!')
 
@@ -75,6 +77,7 @@ def main(argv):
     parser.add_argument('-b', dest='oncokb_api_bearer_token', default='', type=str)
     parser.add_argument('-z', dest='annotate_gain_loss', action="store_true", default=False)
     parser.add_argument('-f', dest='cna_file_format', default=CNA_FILE_FORMAT_GISTIC)
+    parser.add_argument('-d', dest='include_descriptions', action="store_true", default=False)
     parser.set_defaults(func=main)
 
     args = parser.parse_args()

FusionAnnotator.py

@@ -20,7 +20,10 @@ def main(argv):
     if argv.help:
         log.info(
             '\n'
-            "FusionAnnotator.py -i <input Fusion file> -o <output Fusion file> [-p previous results] [-c <input clinical file>] [-s sample list filter] [-t <default tumor type>] [-u <oncokb api url>] [-b <oncokb api bear token>] [-r <structural variant name format, default: [A-Za-z\\d]+-[A-Za-z\\d]+>]\n"
+            "FusionAnnotator.py -i <input Fusion file> -o <output Fusion file> [-p previous results] "
+            "[-c <input clinical file>] [-s sample list filter] [-t <default tumor type>] [-u <oncokb api url>] "
+            "[-b <oncokb api bear token>] [-r <structural variant name format, default: [A-Za-z\\d]+-[A-Za-z\\d]+>] "
+            "[-d include descriptions]\n"
             '  Essential Fusion columns (case insensitive):\n'
             '    HUGO_SYMBOL: Hugo gene symbol\n'
             '    VARIANT_CLASSIFICATION: Translational effect of variant allele\n'
@@ -63,7 +66,7 @@ def main(argv):
     validate_oncokb_token()
 
     log.info('annotating %s ...' % argv.input_file)
-    process_fusion(argv.input_file, argv.output_file, argv.previous_result_file, argv.default_cancer_type, cancertypemap, argv.structural_variant_name_format)
+    process_fusion(argv.input_file, argv.output_file, argv.previous_result_file, argv.default_cancer_type, cancertypemap, argv.structural_variant_name_format, argv.include_descriptions)
 
     log.info('done!')
 
@@ -82,6 +85,7 @@ def main(argv):
     parser.add_argument('-v', dest='cancer_hotspots_base_url', default='', type=str)
     parser.add_argument('-b', dest='oncokb_api_bearer_token', default='', type=str)
     parser.add_argument('-r', dest='structural_variant_name_format', default=None, type=str)
+    parser.add_argument('-d', dest='include_descriptions', action="store_true", default=False)
     parser.set_defaults(func=main)
 
     args = parser.parse_args()

MafAnnotator.py

@@ -23,7 +23,8 @@ def main(argv):
         log.info(
             '\n'
             'MafAnnotator.py -i <input MAF file> -o <output MAF file> [-p previous results] [-c <input clinical file>] '
-            '[-s sample list filter] [-t <default tumor type>] [-u oncokb-base-url] [-b oncokb api bear token] [-a] [-q query type] [-r default reference genome]\n'
+            '[-s sample list filter] [-t <default tumor type>] [-u oncokb-base-url] [-b oncokb api bear token] [-a] '
+            '[-q query type] [-r default reference genome] [-d include descriptions]\n'
             'For definitions of the MAF format, please see https://docs.gdc.cancer.gov/Data/File_Formats/MAF_Format/\n\n'
             'Essential MAF columns for querying HGVSp_Short and HGVSp(case insensitive):\n'
             '    Hugo_Symbol: Hugo gene symbol\n'
@@ -111,7 +112,8 @@ def main(argv):
     validate_oncokb_token()
 
     processalterationevents(argv.input_file, argv.output_file, argv.previous_result_file, argv.default_cancer_type,
-                            cancertypemap, argv.annotate_hotspots, user_input_query_type, default_reference_genome)
+                            cancertypemap, argv.annotate_hotspots, user_input_query_type, default_reference_genome,
+                            argv.include_descriptions)
 
     log.info('done!')
 
@@ -131,6 +133,7 @@ def main(argv):
     parser.add_argument('-b', dest='oncokb_api_bearer_token', default='', type=str)
     parser.add_argument('-q', dest='query_type', default=None, type=str)
     parser.add_argument('-r', dest='default_reference_genome', default=None, type=str)
+    parser.add_argument('-d', dest='include_descriptions', action="store_true", default=False)
     parser.set_defaults(func=main)
 
     args = parser.parse_args()