def main(argv):
if argv.help:
log.info(
'\n'
'ClinicalDataAnnotator.py -i <input clinical file> -o <output clinical file> -a <annotated alteration files, separate by ,> [-s sample list filter]\n'
' Essential clinical columns:\n'
' SAMPLE_ID: sample ID')
sys.exit()
if argv.sample_ids_filter:
setsampleidsfileterfile(argv.sample_ids_filter)
annotated_alteration_files = re.split(',|, ',
argv.annotated_alteration_files)
if argv.input_file == '' or argv.output_file == '' or len(
annotated_alteration_files) == 0:
required_params = []
if argv.input_file == '':
required_params.append('-i')
if argv.output_file == '':
required_params.append('-o')
if len(annotated_alteration_files) == 0:
required_params.append('-a')
log.error('The parameter(s) ' + ', '.join(required_params) +
' can not be empty')
log.info('for help: python ClinicalDataAnnotator.py -h')
sys.exit(2)
log.info('annotating %s ...' % argv.input_file)
process_clinical_data(annotated_alteration_files, argv.input_file,
argv.output_file)
log.info('done!')
def main(argv):
params = {
"catogerycolumn": argv.catogery_column, # -c
"thresholdcat": argv.threshold_cat, # -n
}
if argv.help:
log.info(
'\n'
'OncoKBPlots.py -i <annotated clinical file> -o <output PDF file> [-c <categorization column, '
'e.g. CANCER_TYPE>] [-s sample list filter] [-n threshold of # samples in a category] [-l comma separated levels to include]\n'
' Essential clinical columns:\n'
' SAMPLE_ID: sample ID\n'
' HIGHEST_LEVEL: Highest OncoKB levels\n'
' Supported levels (-l): \n'
' LEVEL_1,LEVEL_2,LEVEL_3A,LEVEL_3B,LEVEL_4,ONCOGENIC,VUS')
sys.exit()
if argv.input_file == '' or argv.output_file == '':
required_params = []
if argv.input_file == '':
required_params.append('-i')
if argv.output_file == '':
required_params.append('-o')
log.error('The parameter(s) ' + ', '.join(required_params) +
' can not be empty')
log.info('for help: python OncoKBPlots.py -h')
sys.exit(2)
if argv.sample_ids_filter:
setsampleidsfileterfile(argv.sample_ids_filter)
if argv.levels:
params["levels"] = re.split(',', argv.levels)
log.info('annotating %s ...' % argv.input_file)
fig, (ax1, ax2, ax3) = plt.subplots(3, 1)
plotclinicalactionability(ax1, argv.input_file, argv.output_file, params)
# ax.yaxis.grid(linestyle="dotted", color="lightgray") # horizontal lines
# plt.margins(0.01)
plotclinicalactionability(ax1, args.input_file, args.output_file, params)
plotimplications(ax2, 'HIGHEST_DX_LEVEL', 'OncoKB Diagnostic Implications',
dxLevels, args.input_file, argv.output_file, params)
plotimplications(ax3, 'HIGHEST_PX_LEVEL', 'OncoKB Prognostic Implications',
pxLevels, args.input_file, argv.output_file, params)
plt.subplots_adjust(left=0.2, bottom=0.3)
plt.gcf().text(0.90,
0.1,
"Generated by OncoKB\n[Chakravarty et al., JCO PO 2017]",
fontsize=6,
horizontalalignment='right',
verticalalignment='bottom')
fig.tight_layout()
fig.savefig(argv.output_file, bbox_inches='tight')
log.info('done!')
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"
' Essential Fusion columns (case insensitive):\n'
' HUGO_SYMBOL: Hugo gene symbol\n'
' VARIANT_CLASSIFICATION: Translational effect of variant allele\n'
' TUMOR_SAMPLE_BARCODE: sample ID\n'
' FUSION: amino acid change, e.g. "TMPRSS2-ERG"\n'
' Essential clinical columns:\n'
' SAMPLE_ID: sample ID\n'
' ONCOTREE_CODE: tumor type code from oncotree (oncotree.mskcc.org)\n'
' Cancer type will be assigned based on the following priority:\n'
' 1) ONCOTREE_CODE in clinical data file\n'
' 2) ONCOTREE_CODE exist in Fusion\n'
' 3) default tumor type (-t)\n'
' Default OncoKB base url is https://www.oncokb.org')
sys.exit()
if argv.input_file == '' or argv.output_file == '' or argv.oncokb_api_bearer_token == '':
required_params = []
if argv.input_file == '':
required_params.append('-i')
if argv.output_file == '':
required_params.append('-o')
if argv.oncokb_api_bearer_token == '':
required_params.append('-b')
log.error('The parameter(s) ' + ', '.join(required_params) +
' can not be empty')
log.info('for help: python FusionAnnotator.py -h')
sys.exit(2)
if argv.sample_ids_filter:
setsampleidsfileterfile(argv.sample_ids_filter)
if argv.cancer_hotspots_base_url:
setcancerhotspotsbaseurl(argv.cancer_hotspots_base_url)
if argv.oncokb_api_url:
setoncokbbaseurl(argv.oncokb_api_url)
setoncokbapitoken(argv.oncokb_api_bearer_token)
cancertypemap = {}
if argv.input_clinical_file:
readCancerTypes(argv.input_clinical_file, cancertypemap)
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)
log.info('done!')
def main(argv):
if argv.help:
log.info(
'\n'
'StructuralVariantAnnotator.py -i <input structural variant file> -o <output structural variant 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>]\n'
' Essential structural variant columns (case insensitive):\n'
' GENEA: Hugo gene symbol for gene A\n'
' GENEB: Hugo gene symbol for gene B\n'
' SV_TYPE: Structural variant type. Available values: DELETION, TRANSLOCATION, DUPLICATION, INSERTION, INVERSION, FUSION, UNKNOWN. Other type will be converted to UNKNOWN\n'
' TUMOR_SAMPLE_BARCODE: sample ID\n'
' Essential clinical columns:\n'
' SAMPLE_ID: sample ID\n'
' ONCOTREE_CODE: tumor type code from oncotree (oncotree.mskcc.org)\n'
' Cancer type will be assigned based on the following priority:\n'
' 1) ONCOTREE_CODE in clinical data file\n'
' 2) ONCOTREE_CODE exist in structural variant\n'
' 3) default tumor type (-t)\n'
' Default OncoKB base url is https://www.oncokb.org')
sys.exit()
if argv.input_file == '' or argv.output_file == '' or argv.oncokb_api_bearer_token == '':
required_params = []
if argv.input_file == '':
required_params.append('-i')
if argv.output_file == '':
required_params.append('-o')
if argv.oncokb_api_bearer_token == '':
required_params.append('-b')
log.error('The parameter(s) ' + ', '.join(required_params) +
' can not be empty')
log.info('for help: python StructuralVariantAnnotator.py -h')
sys.exit(2)
if argv.sample_ids_filter:
setsampleidsfileterfile(argv.sample_ids_filter)
if argv.cancer_hotspots_base_url:
setcancerhotspotsbaseurl(argv.cancer_hotspots_base_url)
if argv.oncokb_api_url:
setoncokbbaseurl(argv.oncokb_api_url)
setoncokbapitoken(argv.oncokb_api_bearer_token)
cancertypemap = {}
if argv.input_clinical_file:
readCancerTypes(argv.input_clinical_file, cancertypemap)
validate_oncokb_token()
log.info('annotating %s ...' % argv.input_file)
process_sv(argv.input_file, argv.output_file, argv.previous_result_file,
argv.default_cancer_type, cancertypemap)
log.info('done!')
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'
' 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'
' Cancer type will be assigned based on the following priority:\n'
' 1) ONCOTREE_CODE in clinical data file\n'
' 2) ONCOTREE_CODE exist in MAF\n'
' 3) default tumor type (-t)\n'
' We do not annotate Gain and Loss by default, add -z to include the analysis. See https://github.com/oncokb/oncokb-annotator/issues/51 for more information.\n'
' Default OncoKB base url is https://www.oncokb.org')
sys.exit()
if argv.input_file == '' or argv.output_file == '' or argv.oncokb_api_bearer_token == '':
required_params = []
if argv.input_file == '':
required_params.append('-i')
if argv.output_file == '':
required_params.append('-o')
if argv.oncokb_api_bearer_token == '':
required_params.append('-b')
log.error('The parameter(s) ' + ', '.join(required_params) +
' can not be empty')
log.info('for help: python CnaAnnotator.py -h')
sys.exit(2)
if argv.sample_ids_filter:
setsampleidsfileterfile(argv.sample_ids_filter)
if argv.oncokb_api_url:
setoncokbbaseurl(argv.oncokb_api_url)
setoncokbapitoken(argv.oncokb_api_bearer_token)
cancertypemap = {}
if argv.input_clinical_file:
readCancerTypes(argv.input_clinical_file, cancertypemap)
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())
log.info('done!')
def main(argv):
if argv.help:
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'
'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'
' Tumor_Sample_Barcode: sample ID\n'
' HGVSp(query type: HGVSp): protein change in HGVSp format\n'
' HGVSp_Short(query type: HGVSp_Short): protein change in HGVSp format using 1-letter amino-acid codes\n'
'Essential MAF columns for querying HGVSg(case insensitive):\n'
' Tumor_Sample_Barcode: sample ID\n'
' HGVSg: Genomic change in HGVSg format\n'
'Essential MAF columns for querying genomic change(case insensitive):\n'
' Tumor_Sample_Barcode: sample ID\n'
' Chromosome: Chromosome number\n'
' Start_Position: Mutation start coordinate\n'
' End_Position: Mutation end coordinate\n'
' Reference_Allele: The plus strand reference allele at this position\n'
' Tumor_Seq_Allele1: Primary data genotype for tumor sequencing (discovery) allele\n'
' Tumor_Seq_Allele2: Tumor sequencing (discovery) allele 2\n'
'Essential clinical columns:\n'
' SAMPLE_ID: sample ID\n'
' ONCOTREE_CODE: tumor type code from oncotree (http://oncotree.mskcc.org)\n'
'Cancer type will be assigned based on the following priority:\n'
' 1) ONCOTREE_CODE in clinical data file\n'
' 2) ONCOTREE_CODE exist in MAF\n'
' 3) default tumor type (-t)\n'
'Query type only allows the following values (case-insensitive):\n'
' - HGVSp_Short\n'
' It reads from column HGVSp_Short or Alteration\n'
' - HGVSp\n'
' It reads from column HGVSp or Alteration\n'
' - HGVSg\n'
' It reads from column HGVSg or Alteration\n'
' - Genomic_Change\n'
' It reads from columns Chromosome, Start_Position, End_Position, Reference_Allele, Tumor_Seq_Allele1 and Tumor_Seq_Allele2 \n'
'Reference Genome only allows the following values(case-insensitive):\n'
' - GRCh37\n'
' GRCh38\n'
'Default OncoKB base url is https://www.oncokb.org.\n'
)
sys.exit()
if argv.input_file == '' or argv.output_file == '' or argv.oncokb_api_bearer_token == '':
required_params = []
if argv.input_file == '':
required_params.append('-i')
if argv.output_file == '':
required_params.append('-o')
if argv.oncokb_api_bearer_token == '':
required_params.append('-b')
log.error('The parameter(s) ' + ', '.join(required_params) + ' can not be empty')
log.info('For help: python MafAnnotator.py -h')
sys.exit(2)
if argv.sample_ids_filter:
setsampleidsfileterfile(argv.sample_ids_filter)
if argv.cancer_hotspots_base_url:
setcancerhotspotsbaseurl(argv.cancer_hotspots_base_url)
if argv.oncokb_api_url:
setoncokbbaseurl(argv.oncokb_api_url)
setoncokbapitoken(argv.oncokb_api_bearer_token)
cancertypemap = {}
if argv.input_clinical_file:
readCancerTypes(argv.input_clinical_file, cancertypemap)
log.info('annotating %s ...' % argv.input_file)
user_input_query_type = None
if argv.query_type is not None:
try:
user_input_query_type = QueryType[argv.query_type.upper()]
except KeyError:
log.error(
'Query type is not acceptable. Only the following allows(case insensitive): HGVSp_Short, HGVSp, HGVSg, Genomic_Change')
raise
default_reference_genome = None
if argv.default_reference_genome is not None:
try:
default_reference_genome = ReferenceGenome[argv.default_reference_genome.upper()]
except KeyError:
log.error(
'Reference genome is not acceptable. Only the following allows(case insensitive): GRCh37, GRCh38')
raise
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)
log.info('done!')