def tolerance_pass(line, headlist, yaml_commands):
lineList = line.rstrip("\n").split("\t")
tiering_cmds = yaml_commands[yaml_keys.kModules][yaml_keys.kTiering]
tolerance_zscore_colHeaders = yaml_utils.convertColumns(tiering_cmds[yaml_keys.kTToleranceZScoreCols], yaml_commands)
tolerance_zscore_cutoff = tiering_cmds[yaml_keys.kTToleranceZScoreCutoff]
for zscore_col_header in tolerance_zscore_colHeaders:
zscores = lineList[headlist.index(zscore_col_header)].split(yaml_utils.get_dataset_defaults(yaml_commands)[yaml_keys.kDMultimatchDelimiter]) # our delimiter
for zscore in zscores:
if(zscore != '' and float(zscore) > float(tolerance_zscore_cutoff)):
return True
#else
return False
def is_rare(templine, freq_thresh, bp_indexlist, yaml_commands):
#debug
# print 'bp_indexlist: ' + str(bp_indexlist)
multimatch_delimiter = yaml_utils.get_dataset_defaults(yaml_commands)[yaml_keys.kDMultimatchDelimiter]
templinelist = templine.split("\t")
rare_flag = 1 # rare
for i in bp_indexlist:
if templinelist[i] != "":
templinelistElts = templinelist[i].split(multimatch_delimiter)
# should throw an exception if templinelist[i] isn't a float
#debug
# print 'templinelist[{i}]: '.format(i=i) + str(float(templinelist[i]))
# print 'freq thresh: ' + str(float(freq_thresh))
for elt in templinelistElts:
if(float(elt) > float(freq_thresh)):
rare_flag = 0 # not rare
return rare_flag
def tolerance_pass(line, headlist, yaml_commands):
lineList = line.rstrip("\n").split("\t")
tiering_cmds = yaml_commands[yaml_keys.kModules][yaml_keys.kTiering]
tolerance_zscore_colHeaders = yaml_utils.convertColumns(
tiering_cmds[yaml_keys.kTToleranceZScoreCols], yaml_commands)
tolerance_zscore_cutoff = tiering_cmds[yaml_keys.kTToleranceZScoreCutoff]
for zscore_col_header in tolerance_zscore_colHeaders:
zscores = lineList[headlist.index(zscore_col_header)].split(
yaml_utils.get_dataset_defaults(yaml_commands)[
yaml_keys.kDMultimatchDelimiter]) # our delimiter
for zscore in zscores:
if (zscore != ''
and float(zscore) > float(tolerance_zscore_cutoff)):
return True
#else
return False
def is_rare(templine, freq_thresh, bp_indexlist, yaml_commands):
#debug
# print 'bp_indexlist: ' + str(bp_indexlist)
multimatch_delimiter = yaml_utils.get_dataset_defaults(yaml_commands)[
yaml_keys.kDMultimatchDelimiter]
templinelist = templine.split("\t")
rare_flag = 1 # rare
for i in bp_indexlist:
if templinelist[i] != "":
templinelistElts = templinelist[i].split(multimatch_delimiter)
# should throw an exception if templinelist[i] isn't a float
#debug
# print 'templinelist[{i}]: '.format(i=i) + str(float(templinelist[i]))
# print 'freq thresh: ' + str(float(freq_thresh))
for elt in templinelistElts:
if (float(elt) > float(freq_thresh)):
rare_flag = 0 # not rare
return rare_flag
def is_rare(templine, freq_thresh, bp_indexlist, yaml_commands):
logger = logging.getLogger(__name__)
logger.debug('bp_indexlist: ' + str(bp_indexlist))
multimatch_delimiter = yaml_utils.get_dataset_defaults(yaml_commands)[
yaml_keys.kDMultimatchDelimiter]
templinelist = templine.split("\t")
rare_flag = 0 # not rare
#note the logic has been changed so that we only keep a variant if there is proof that it is rare
for i in bp_indexlist:
if templinelist[i] != "":
templinelistElts = templinelist[i].split(multimatch_delimiter)
# should throw an exception if templinelist[i] isn't a float
logger.debug('templinelist[{i}]: '.format(i=i) +
str(float(templinelist[i])))
logger.debug('freq thresh: ' + str(float(freq_thresh)))
for elt in templinelistElts:
if (float(elt) < float(freq_thresh)):
rare_flag = 1 # rare
return rare_flag
parser.add_argument('--tab_file', help='.tab file to be expanded')
parser.add_argument(
'--out_suffix',
default='.tsv',
help=
'suffix for output file (stored in same location as input file), e.g. ".tsv"'
)
parser.add_argument('--config_modules',
help='path to modules configuration file (YAML)')
parser.add_argument('--config_datasets',
help='path to datasets configuration file (YAML)')
args = parser.parse_args()
config_yaml = yaml_utils.parse_yaml_input_files(args.config_datasets,
args.config_modules)
modules_yaml = config_yaml[yaml_keys.kModules]
# modules_yaml = yaml_utils.parse_yaml(args.config_modules)
# datasets_yaml = yaml_utils.parse_yaml(args.config_datasets)
bed_delimiter = modules_yaml[yaml_keys.kAnnotation][
yaml_keys.kABedInternalDelimiter]
bed_multimatch_internal_delimiter = modules_yaml[yaml_keys.kAnnotation][
yaml_keys.kABedMultimatchInternalDelimiter]
# for now, just using the default delimiter. Later, check if there's a specific delimiter for a given dataset and use that instead.
dataset_multimatch_delimiter = yaml_utils.get_dataset_defaults(
config_yaml)[yaml_keys.kDMultimatchDelimiter]
expandBED(args.tab_file, bed_multimatch_internal_delimiter, bed_delimiter,
dataset_multimatch_delimiter, args.out_suffix)
flc = fl.split(bed_delimiter)
lineContents.extend(flc)
out_file.write("\t".join(lineContents) + "\n")
return out_file_path
##### MAIN CODE ####
if __name__ == '__main__':
# parse commandline args.
parser = argparse.ArgumentParser(description = 'IntersectBed Expander')
parser.add_argument('--tab_file', help='.tab file to be expanded')
parser.add_argument('--out_suffix', default='.tsv', help='suffix for output file (stored in same location as input file), e.g. ".tsv"')
parser.add_argument('--config_modules', help='path to modules configuration file (YAML)')
parser.add_argument('--config_datasets', help='path to datasets configuration file (YAML)')
args = parser.parse_args()
config_yaml = yaml_utils.parse_yaml_input_files(args.config_datasets, args.config_modules)
modules_yaml = config_yaml[yaml_keys.kModules]
# modules_yaml = yaml_utils.parse_yaml(args.config_modules)
# datasets_yaml = yaml_utils.parse_yaml(args.config_datasets)
bed_delimiter = modules_yaml[yaml_keys.kAnnotation][yaml_keys.kABedInternalDelimiter]
bed_multimatch_internal_delimiter = modules_yaml[yaml_keys.kAnnotation][yaml_keys.kABedMultimatchInternalDelimiter]
# for now, just using the default delimiter. Later, check if there's a specific delimiter for a given dataset and use that instead.
dataset_multimatch_delimiter = yaml_utils.get_dataset_defaults(config_yaml)[yaml_keys.kDMultimatchDelimiter]
expandBED(args.tab_file, bed_multimatch_internal_delimiter, bed_delimiter, dataset_multimatch_delimiter, args.out_suffix)