def parse_arguments():
info = 'Checks mutations to see what strand they are reported on and for unmapped mutations.'
parser = argparse.ArgumentParser(description=info)
# logging arguments
parser.add_argument('-ll', '--log-level',
type=str,
action='store',
default='',
help='Write a log file (--log-level=DEBUG for debug mode, '
'--log-level=INFO for info mode)')
parser.add_argument('-l', '--log',
type=str,
action='store',
default='stdout',
help='Path to log file. (Default: stdout)')
parser.add_argument('-v', '--verbose',
action='store_true',
default=False,
help='Flag for more verbose log output')
# program arguments
help_str = 'Human genome FASTA file'
parser.add_argument('-f', '--fasta',
type=str, required=True,
help=help_str)
help_str = 'Text file specifying mutations in the format required for permutation test'
parser.add_argument('-m', '--mutations',
type=str, required=True,
help=help_str)
help_str = 'BED file of reference transcripts'
parser.add_argument('-b', '--bed',
type=str, required=True,
help=help_str)
help_str = 'Save mutations that could not be found on the reference transcript'
parser.add_argument('-u', '--unmapped',
type=str, required=True,
help=help_str)
args = parser.parse_args()
# handle logging
if args.log_level or args.log:
if args.log:
log_file = args.log
else:
log_file = '' # auto-name the log file
else:
log_file = os.devnull
log_level = args.log_level
utils.start_logging(log_file=log_file,
log_level=log_level,
verbose=args.verbose) # start logging
return vars(args)
def parse_arguments():
info = 'Extracts gene sequences from a genomic FASTA file'
parser = argparse.ArgumentParser(description=info)
# logging arguments
parser.add_argument('-ll', '--log-level',
type=str,
action='store',
default='',
help='Write a log file (--log-level=DEBUG for debug mode, '
'--log-level=INFO for info mode)')
parser.add_argument('-l', '--log',
type=str,
action='store',
default='',
help='Path to log file. (accepts stdout)')
parser.add_argument('-v', '--verbose',
action='store_true',
default=False,
help='Flag for more verbose log output')
# program arguments
help_str = 'Human genome FASTA file'
parser.add_argument('-i', '--input',
type=str, required=True,
help=help_str)
help_str = 'BED file annotation of genes'
parser.add_argument('-b', '--bed',
type=str, required=True,
help=help_str)
help_str = 'Output a single FASTA file with gene sequences'
parser.add_argument('-o', '--output',
type=str, required=True,
help=help_str)
args = parser.parse_args()
# handle logging
if args.log_level or args.log:
if args.log:
log_file = args.log
else:
log_file = '' # auto-name the log file
else:
log_file = os.devnull
log_level = args.log_level
utils.start_logging(log_file=log_file,
log_level=log_level,
verbose=args.verbose) # start logging
# log user entered command
logger.info('Command: {0}'.format(' '.join(sys.argv)))
return vars(args)
def parse_arguments():
# make a parser
info = 'Performs a randomization-based test on the oncogene and TSG score'
parser = argparse.ArgumentParser(description=info)
# logging arguments
parser.add_argument(
'-ll',
'--log-level',
type=str,
action='store',
default='',
help='Write a log file (--log-level=DEBUG for debug mode, '
'--log-level=INFO for info mode)')
parser.add_argument('-l',
'--log',
type=str,
action='store',
default='',
help='Path to log file. (accepts "stdout")')
parser.add_argument('-v',
'--verbose',
action='store_true',
default=False,
help='Flag for more verbose log output')
# program arguments
help_str = 'gene FASTA file from extract_gene_seq.py script'
parser.add_argument('-i',
'--input',
type=str,
required=True,
help=help_str)
help_str = 'DNA mutations file'
parser.add_argument('-m',
'--mutations',
type=str,
required=True,
help=help_str)
help_str = 'BED file annotation of genes'
parser.add_argument('-b', '--bed', type=str, required=True, help=help_str)
help_str = 'Directory containing score information in pickle files (Default: None).'
parser.add_argument('-s',
'--score-dir',
type=str,
default=None,
help=help_str)
help_str = 'Directory containing neighbor graph information in pickle files (Default: None).'
parser.add_argument('-ng',
'--neighbor-graph-dir',
type=str,
default=None,
help=help_str)
help_str = ('Number of processes to use. 0 indicates using a single '
'process without using a multiprocessing pool '
'(more means Faster, default: 0).')
parser.add_argument('-p',
'--processes',
type=int,
default=0,
help=help_str)
help_str = ('Number of iterations for null model. p-value precision '
'increases with more iterations, however this will also '
'increase the run time (Default: 10000).')
parser.add_argument('-n',
'--num-iterations',
type=int,
default=10000,
help=help_str)
help_str = (
'Number of iterations more significant then the observed statistic '
'to stop further computations. This decreases compute time spent in resolving '
'p-values for non-significant genes. (Default: 1000).')
parser.add_argument('-sc',
'--stop-criteria',
type=int,
default=1000,
help=help_str)
help_str = (
'Kind of permutation test to perform ("oncogene" or "tsg"). "position-based" permutation '
'test is intended to find oncogenes using position based statistics. '
'The "deleterious" permutation test is intended to find tumor '
'suppressor genes. (Default: oncogene)')
parser.add_argument('-k',
'--kind',
type=str,
default='oncogene',
help=help_str)
help_str = (
'Number of DNA bases to use as context. 0 indicates no context. '
'1 indicates only use the mutated base. 1.5 indicates using '
'the base context used in CHASM '
'(http://wiki.chasmsoftware.org/index.php/CHASM_Overview). '
'2 indicates using the mutated base and the upstream base. '
'3 indicates using the mutated base and both the upstream '
'and downstream bases. (Default: 1.5)')
parser.add_argument('-c',
'--context',
type=float,
default=1.5,
help=help_str)
help_str = (
'Use mutations that are not mapped to the the single reference '
'transcript for a gene specified in the bed file indicated by '
'the -b option.')
parser.add_argument('-u',
'--use-unmapped',
action='store_true',
default=False,
help=help_str)
help_str = (
'Path to the genome fasta file. Required if --use-unmapped flag '
'is used. (Default: None)')
parser.add_argument('-g', '--genome', type=str, default='', help=help_str)
help_str = ('Only keep unique mutations for each tumor sample.'
'Mutations reproted from heterogeneous sources may contain'
' duplicates, e.g. a tumor sample was sequenced twice.')
parser.add_argument('--unique',
action='store_true',
default=False,
help=help_str)
help_str = ('Minimum number of mutations at a position for it to be '
'considered a recurrently mutated position (Default: 3).')
parser.add_argument('-r',
'--recurrent',
type=int,
default=3,
help=help_str)
help_str = ('Fraction of total mutations in a gene. This define the '
'minimumm number of mutations for a position to be defined '
'as recurrently mutated (Defaul: .02).')
parser.add_argument('-f',
'--fraction',
type=float,
default=.02,
help=help_str)
help_str = (
'Perform tsg permutation test if gene has '
'at least a user specified number of deleterious mutations (default: 1)'
)
parser.add_argument('-d',
'--deleterious',
type=int,
default=1,
help=help_str)
help_str = ('Maximum TSG score to allow gene to be tested for oncogene '
'permutation test. Values greater than one indicate all '
'genes will be tested (Default: 1.01).')
parser.add_argument('-t',
'--tsg-score',
type=float,
default=1.01,
help=help_str)
help_str = ('Deleterious mutation pseudo-count for null distribution '
'statistics. (Default: 0)')
parser.add_argument('-dp',
'--deleterious-pseudo-count',
type=int,
default=0,
help=help_str)
help_str = (
'Recurrent missense mutation pseudo-count for null distribution '
'statistics. (Default: 0)')
parser.add_argument('-rp',
'--recurrent-pseudo-count',
type=int,
default=0,
help=help_str)
help_str = ('Specify the seed for the pseudo random number generator. '
'By default, the seed is randomly chosen based. The seed will '
'be used for the permutation test monte carlo simulations.')
parser.add_argument('-seed',
'--seed',
type=int,
default=None,
help=help_str)
help_str = 'Output of probabilistic 20/20 results'
parser.add_argument('-o',
'--output',
type=str,
required=True,
help=help_str)
args = parser.parse_args()
# handle logging
if args.log_level or args.log:
if args.log:
log_file = args.log
else:
log_file = '' # auto-name the log file
else:
log_file = os.devnull
log_level = args.log_level
utils.start_logging(log_file=log_file,
log_level=log_level,
verbose=args.verbose) # start logging
opts = vars(args)
if opts['use_unmapped'] and not opts['genome']:
print('You must specify a genome fasta with -g if you set the '
'--use-unmapped flag to true.')
sys.exit(1)
# log user entered command
logger.info('Command: {0}'.format(' '.join(sys.argv)))
return opts
def parse_arguments():
# make a parser
info = 'Performs a statistical test for oncogene, TSG, or driver gene'
parent_parser = argparse.ArgumentParser(description=info)
# logging arguments
parent_parser.add_argument(
'-ll',
'--log-level',
type=str,
action='store',
default='',
help='Write a log file (--log-level=DEBUG for debug mode, '
'--log-level=INFO for info mode)')
parent_parser.add_argument('-l',
'--log',
type=str,
action='store',
default='stdout',
help='Path to log file. (accepts "stdout")')
parent_parser.add_argument('-v',
'--verbose',
action='store_true',
default=False,
help='Flag for more verbose log output')
# add subparsers
subparsers = parent_parser.add_subparsers(title='Driver Gene Type',
dest='kind')
parser_og = subparsers.add_parser(
'oncogene',
help='Find statistically significant oncogene-like genes.',
description='Find statsitically significant oncogene-like genes. '
'Evaluates clustering of missense mutations and high in '
'silico pathogenicity scores for missense mutations.')
help_info = 'Find statistically significant Tumor Suppressor-like genes.'
parser_tsg = subparsers.add_parser(
'tsg',
help=help_info,
description=help_info + ' Evaluates for a higher proportion '
'of inactivating mutations than expected.')
#parser_protein = subparsers.add_parser('protein', help='Find statistically significant '
#'3D clustering in genes based on protein structure.')
# program arguments
for i, parser in enumerate([parser_og, parser_tsg]):
# group of parameters
major_parser = parser.add_argument_group(title='Major options')
advance_parser = parser.add_argument_group(title='Advanced options')
# set the CLI params
help_str = 'gene FASTA file from extract_gene_seq.py script'
major_parser.add_argument('-i',
'--input',
type=str,
required=True,
help=help_str)
help_str = (
'DNA mutations file (MAF file). Columns can be in any order, '
'but should contain the correct column header names.')
major_parser.add_argument('-m',
'--mutations',
type=str,
required=True,
help=help_str)
help_str = 'BED file annotation of genes'
major_parser.add_argument('-b',
'--bed',
type=str,
required=True,
help=help_str)
help_str = (
'Number of processes to use for parallelization. 0 indicates using a single '
'process without using a multiprocessing pool '
'(more means Faster, default: 0).')
major_parser.add_argument('-p',
'--processes',
type=int,
default=0,
help=help_str)
help_str = ('Number of iterations for null model. p-value precision '
'increases with more iterations, however this will also '
'increase the run time (Default: 100,000).')
major_parser.add_argument('-n',
'--num-iterations',
type=int,
default=100000,
help=help_str)
help_str = (
'Number of iterations more significant then the observed statistic '
'to stop further computations. This decreases compute time spent in resolving '
'p-values for non-significant genes. (Default: 1000).')
advance_parser.add_argument('-sc',
'--stop-criteria',
type=int,
default=1000,
help=help_str)
help_str = (
'Number of DNA bases to use as context. 0 indicates no context. '
'1 indicates only use the mutated base. 1.5 indicates using '
'the base context used in CHASM '
'(http://wiki.chasmsoftware.org/index.php/CHASM_Overview). '
'2 indicates using the mutated base and the upstream base. '
'3 indicates using the mutated base and both the upstream '
'and downstream bases. (Default: 1.5)')
major_parser.add_argument('-c',
'--context',
type=float,
default=1.5,
help=help_str)
if i == 0:
help_str = 'Directory containing VEST score information in pickle files (Default: None).'
major_parser.add_argument('-s',
'--score-dir',
type=str,
default=None,
help=help_str)
help_str = (
'Minimum number of mutations at a position for it to be '
'considered a recurrently mutated position (Default: 3).')
advance_parser.add_argument('-r',
'--recurrent',
type=int,
default=3,
help=help_str)
help_str = (
'Fraction of total mutations in a gene. This define the '
'minimumm number of mutations for a position to be defined '
'as recurrently mutated (Defaul: .02).')
advance_parser.add_argument('-f',
'--fraction',
type=float,
default=.02,
help=help_str)
elif i == 1:
help_str = (
'Perform tsg randomization-based test if gene has '
'at least a user specified number of deleterious mutations (default: 1)'
)
advance_parser.add_argument('-d',
'--deleterious',
type=int,
default=1,
help=help_str)
elif i == 2:
help_str = 'Directory containing codon neighbor graph information in pickle files (Default: None).'
major_parser.add_argument('-ng',
'--neighbor-graph-dir',
type=str,
required=True,
help=help_str)
help_str = (
'Minimum number of mutations at a position for it to be '
'considered a recurrently mutated position (Default: 3).')
advance_parser.add_argument('-r',
'--recurrent',
type=int,
default=3,
help=help_str)
help_str = (
'Fraction of total mutations in a gene. This define the '
'minimumm number of mutations for a position to be defined '
'as recurrently mutated (Defaul: .02).')
advance_parser.add_argument('-f',
'--fraction',
type=float,
default=.02,
help=help_str)
help_str = ('Only keep unique mutations for each tumor sample. '
'Mutations reported from heterogeneous sources may contain'
' duplicates, e.g. a tumor sample was sequenced twice.')
advance_parser.add_argument('--unique',
action='store_true',
default=False,
help=help_str)
help_str = (
'Use mutations that are not mapped to the the single reference '
'transcript for a gene specified in the bed file indicated by '
'the -b option.')
advance_parser.add_argument('-u',
'--use-unmapped',
action='store_true',
default=False,
help=help_str)
help_str = (
'Path to the genome fasta file. Required if --use-unmapped flag '
'is used. (Default: None)')
advance_parser.add_argument('-g',
'--genome',
type=str,
default='',
help=help_str)
help_str = ('Specify the seed for the pseudo random number generator. '
'By default, the seed is randomly chosen. The seed will '
'be used for the monte carlo simulations (Default: 101).')
advance_parser.add_argument('-seed',
'--seed',
type=int,
default=101,
help=help_str)
help_str = 'Output text file of probabilistic 20/20 results'
major_parser.add_argument('-o',
'--output',
type=str,
required=True,
help=help_str)
args = parent_parser.parse_args()
# handle logging
if args.log_level or args.log:
if args.log:
log_file = args.log
else:
log_file = '' # auto-name the log file
else:
log_file = os.devnull
log_level = args.log_level
utils.start_logging(log_file=log_file,
log_level=log_level,
verbose=args.verbose) # start logging
opts = vars(args)
if opts['use_unmapped'] and not opts['genome']:
print('You must specify a genome fasta with -g if you set the '
'--use-unmapped flag to true.')
sys.exit(1)
# log user entered command
logger.info('Version: {0}'.format(prob2020.__version__))
logger.info('Command: {0}'.format(' '.join(sys.argv)))
return opts
def parse_arguments():
# make a parser
info = 'Simulates the non-silent mutation ratio by randomly permuting mutations'
parser = argparse.ArgumentParser(description=info)
# logging arguments
parser.add_argument(
'-ll',
'--log-level',
type=str,
action='store',
default='',
help='Write a log file (--log-level=DEBUG for debug mode, '
'--log-level=INFO for info mode)')
parser.add_argument('-l',
'--log',
type=str,
action='store',
default='',
help='Path to log file. (accepts "stdout")')
# program arguments
help_str = 'gene FASTA file from extract_gene_seq.py script'
parser.add_argument('-i',
'--input',
type=str,
required=True,
help=help_str)
help_str = 'DNA mutations file'
parser.add_argument('-m',
'--mutations',
type=str,
required=True,
help=help_str)
help_str = 'BED file annotation of genes'
parser.add_argument('-b', '--bed', type=str, required=True, help=help_str)
help_str = ('Number of processes to use. 0 indicates using a single '
'process without using a multiprocessing pool '
'(more means Faster, default: 0).')
parser.add_argument('-p',
'--processes',
type=int,
default=0,
help=help_str)
help_str = ('Number of permutations for null model. p-value precision '
'increases with more permutations (Default: 10000).')
parser.add_argument('-n',
'--num-permutations',
type=int,
default=10000,
help=help_str)
help_str = (
'Number of DNA bases to use as context. 0 indicates no context. '
'1 indicates only use the mutated base. 1.5 indicates using '
'the base context used in CHASM '
'(http://wiki.chasmsoftware.org/index.php/CHASM_Overview). '
'2 indicates using the mutated base and the upstream base. '
'3 indicates using the mutated base and both the upstream '
'and downstream bases. (Default: 1.5)')
parser.add_argument('-c',
'--context',
type=float,
default=1.5,
help=help_str)
help_str = 'Directory containing score information in pickle files (Default: None).'
parser.add_argument('-s',
'--score-dir',
type=str,
default=None,
help=help_str)
help_str = 'Report counts for observed mutations stratified by the tumor sample'
parser.add_argument('-bs',
'--by-sample',
action='store_true',
help=help_str)
help_str = (
'Use mutations that are not mapped to the the single reference '
'transcript for a gene specified in the bed file indicated by '
'the -b option.')
parser.add_argument('-u',
'--use-unmapped',
action='store_true',
default=False,
help=help_str)
help_str = (
'Path to the genome fasta file. Required if --use-unmapped flag '
'is used. (Default: None)')
parser.add_argument('-g', '--genome', type=str, default='', help=help_str)
help_str = 'Output text file of observed results (optional).'
parser.add_argument('-oo',
'--observed-output',
type=str,
default=None,
help=help_str)
help_str = 'Output text file of simulation results'
parser.add_argument('-o',
'--output',
type=str,
required=True,
help=help_str)
args = parser.parse_args()
# handle logging
if args.log_level or args.log:
if args.log:
log_file = args.log
else:
log_file = '' # auto-name the log file
else:
log_file = os.devnull
log_level = args.log_level
utils.start_logging(log_file=log_file,
log_level=log_level) # start logging
opts = vars(args)
if opts['use_unmapped'] and not opts['genome']:
print('You must specify a genome fasta with -g if you set the '
'--use-unmapped flag to true.')
sys.exit(1)
# log user entered command
logger.info('Command: {0}'.format(' '.join(sys.argv)))
return opts
def parse_arguments():
info = 'Checks mutations to see what strand they are reported on and for unmapped mutations.'
parser = argparse.ArgumentParser(description=info)
# logging arguments
parser.add_argument(
'-ll',
'--log-level',
type=str,
action='store',
default='',
help='Write a log file (--log-level=DEBUG for debug mode, '
'--log-level=INFO for info mode)')
parser.add_argument('-l',
'--log',
type=str,
action='store',
default='stdout',
help='Path to log file. (Default: stdout)')
parser.add_argument('-v',
'--verbose',
action='store_true',
default=False,
help='Flag for more verbose log output')
# program arguments
help_str = 'Human genome FASTA file'
parser.add_argument('-f',
'--fasta',
type=str,
required=True,
help=help_str)
help_str = 'Text file specifying mutations in the format required for permutation test'
parser.add_argument('-m',
'--mutations',
type=str,
required=True,
help=help_str)
help_str = 'BED file of reference transcripts'
parser.add_argument('-b', '--bed', type=str, required=True, help=help_str)
help_str = 'Save mutations that could not be found on the reference transcript'
parser.add_argument('-u',
'--unmapped',
type=str,
required=True,
help=help_str)
args = parser.parse_args()
# handle logging
if args.log_level or args.log:
if args.log:
log_file = args.log
else:
log_file = '' # auto-name the log file
else:
log_file = os.devnull
log_level = args.log_level
utils.start_logging(log_file=log_file,
log_level=log_level,
verbose=args.verbose) # start logging
return vars(args)
def parse_arguments():
# make a parser
info = 'Either simulates or summarizes observed mutation data.'
parser = argparse.ArgumentParser(description=info)
# logging arguments
parser.add_argument(
'-ll',
'--log-level',
type=str,
action='store',
default='',
help='Write a log file (--log-level=DEBUG for debug mode, '
'--log-level=INFO for info mode)')
parser.add_argument('-l',
'--log',
type=str,
action='store',
default='stdout',
help='Path to log file. (accepts "stdout")')
parser.add_argument('-v',
'--verbose',
action='store_true',
default=False,
help='Flag for more verbose log output')
# program arguments
help_str = 'gene FASTA file from extract_gene_seq script'
parser.add_argument('-i',
'--input',
type=str,
required=True,
help=help_str)
help_str = 'DNA mutations file (MAF file)'
parser.add_argument('-m',
'--mutations',
type=str,
required=True,
help=help_str)
help_str = 'BED file annotation of genes'
parser.add_argument('-b', '--bed', type=str, required=True, help=help_str)
help_str = (
'Directory containing pre-compute score information in '
'for VEST and evolutionary conservation in pickle format (Default: None).'
)
parser.add_argument('-s',
'--score-dir',
type=str,
default=None,
help=help_str)
help_str = ('Number of processes to use. 0 indicates using a single '
'process without using a multiprocessing pool '
'(more means Faster, default: 0).')
parser.add_argument('-p',
'--processes',
type=int,
default=0,
help=help_str)
help_str = (
'Number of iterations for null model simulations. If zero is '
'specified then output represents a result from actually observed mutations (provided by -m parameter), '
'otherwise results will be from simulated mutations. (Default: 0).')
parser.add_argument('-n',
'--num-iterations',
type=int,
default=0,
help=help_str)
help_str = (
'Number of DNA bases to use as context. 0 indicates no context. '
'1 indicates only use the mutated base. 1.5 indicates using '
'the base context used in CHASM '
'(http://wiki.chasmsoftware.org/index.php/CHASM_Overview). '
'2 indicates using the mutated base and the upstream base. '
'3 indicates using the mutated base and both the upstream '
'and downstream bases. (Default: 1.5)')
parser.add_argument('-c',
'--context',
type=float,
default=1.5,
help=help_str)
parser_grouper = parser.add_mutually_exclusive_group(required=True)
parser_grouper.add_argument('--summary',
action='store_true',
help='Flag for saving results as summarized '
'features used (Default: True).')
parser_grouper.add_argument('--maf',
action='store_true',
help='Flag for saving results in MAF format '
'(Default: False).')
help_str = (
'Use mutations that are not mapped to the the single reference '
'transcript for a gene specified in the bed file indicated by '
'the -b option.')
parser.add_argument('-u',
'--use-unmapped',
action='store_true',
default=False,
help=help_str)
help_str = (
'Path to the genome fasta file. Required if --use-unmapped flag '
'is used. (Default: None)')
parser.add_argument('-g', '--genome', type=str, default='', help=help_str)
help_str = ('Minimum number of mutations at a position for it to be '
'considered a recurrently mutated position (Default: 3).')
parser.add_argument('-r',
'--recurrent',
type=int,
default=3,
help=help_str)
help_str = ('Fraction of total mutations in a gene. This define the '
'minimumm number of mutations for a position to be defined '
'as recurrently mutated (Default: .02).')
parser.add_argument('-f',
'--fraction',
type=float,
default=.02,
help=help_str)
help_str = ('Only keep unique mutations for each tumor sample.'
'Mutations reproted from heterogeneous sources may contain'
' duplicates, e.g. a tumor sample was sequenced twice.')
parser.add_argument('--unique',
action='store_true',
default=False,
help=help_str)
help_str = ('Specify the seed for the pseudo random number generator. '
'By default, the seed is randomly chosen based. The seed will '
'be used for the monte carlo simulations (Default: 101).')
parser.add_argument('-seed',
'--seed',
type=int,
default=101,
help=help_str)
help_str = 'Output text file of results'
parser.add_argument('-o',
'--output',
type=str,
required=True,
help=help_str)
args = parser.parse_args()
# handle logging
if args.log_level or args.log:
if args.log:
log_file = args.log
else:
log_file = '' # auto-name the log file
else:
log_file = os.devnull
log_level = args.log_level
utils.start_logging(log_file=log_file,
log_level=log_level,
verbose=args.verbose) # start logging
opts = vars(args)
if opts['use_unmapped'] and not opts['genome']:
print('You must specify a genome fasta with -g if you set the '
'--use-unmapped flag to true.')
sys.exit(1)
# log user entered command
logger.info('Command: {0}'.format(' '.join(sys.argv)))
return opts
def parse_arguments():
# make a parser
info = 'Simulates the non-silent mutation ratio by randomly permuting mutations'
parser = argparse.ArgumentParser(description=info)
# logging arguments
parser.add_argument('-ll', '--log-level',
type=str,
action='store',
default='',
help='Write a log file (--log-level=DEBUG for debug mode, '
'--log-level=INFO for info mode)')
parser.add_argument('-l', '--log',
type=str,
action='store',
default='',
help='Path to log file. (accepts "stdout")')
# program arguments
help_str = 'gene FASTA file from extract_gene_seq.py script'
parser.add_argument('-i', '--input',
type=str, required=True,
help=help_str)
help_str = 'DNA mutations file'
parser.add_argument('-m', '--mutations',
type=str, required=True,
help=help_str)
help_str = 'BED file annotation of genes'
parser.add_argument('-b', '--bed',
type=str, required=True,
help=help_str)
help_str = ('Number of processes to use. 0 indicates using a single '
'process without using a multiprocessing pool '
'(more means Faster, default: 0).')
parser.add_argument('-p', '--processes',
type=int, default=0,
help=help_str)
help_str = ('Number of permutations for null model. p-value precision '
'increases with more permutations (Default: 10000).')
parser.add_argument('-n', '--num-permutations',
type=int, default=10000,
help=help_str)
help_str = ('Number of DNA bases to use as context. 0 indicates no context. '
'1 indicates only use the mutated base. 1.5 indicates using '
'the base context used in CHASM '
'(http://wiki.chasmsoftware.org/index.php/CHASM_Overview). '
'2 indicates using the mutated base and the upstream base. '
'3 indicates using the mutated base and both the upstream '
'and downstream bases. (Default: 1.5)')
parser.add_argument('-c', '--context',
type=float, default=1.5,
help=help_str)
help_str = 'Directory containing score information in pickle files (Default: None).'
parser.add_argument('-s', '--score-dir',
type=str, default=None,
help=help_str)
help_str = 'Report counts for observed mutations stratified by the tumor sample'
parser.add_argument('-bs', '--by-sample',
action='store_true',
help=help_str)
help_str = ('Use mutations that are not mapped to the the single reference '
'transcript for a gene specified in the bed file indicated by '
'the -b option.')
parser.add_argument('-u', '--use-unmapped',
action='store_true',
default=False,
help=help_str)
help_str = ('Path to the genome fasta file. Required if --use-unmapped flag '
'is used. (Default: None)')
parser.add_argument('-g', '--genome',
type=str, default='',
help=help_str)
help_str = 'Output text file of observed results (optional).'
parser.add_argument('-oo', '--observed-output',
type=str, default=None,
help=help_str)
help_str = 'Output text file of simulation results'
parser.add_argument('-o', '--output',
type=str, required=True,
help=help_str)
args = parser.parse_args()
# handle logging
if args.log_level or args.log:
if args.log:
log_file = args.log
else:
log_file = '' # auto-name the log file
else:
log_file = os.devnull
log_level = args.log_level
utils.start_logging(log_file=log_file,
log_level=log_level) # start logging
opts = vars(args)
if opts['use_unmapped'] and not opts['genome']:
print('You must specify a genome fasta with -g if you set the '
'--use-unmapped flag to true.')
sys.exit(1)
# log user entered command
logger.info('Command: {0}'.format(' '.join(sys.argv)))
return opts
def parse_arguments():
# make a parser
info = 'Performs a randomization-based test on the oncogene and TSG score'
parser = argparse.ArgumentParser(description=info)
# logging arguments
parser.add_argument('-ll', '--log-level',
type=str,
action='store',
default='',
help='Write a log file (--log-level=DEBUG for debug mode, '
'--log-level=INFO for info mode)')
parser.add_argument('-l', '--log',
type=str,
action='store',
default='',
help='Path to log file. (accepts "stdout")')
parser.add_argument('-v', '--verbose',
action='store_true',
default=False,
help='Flag for more verbose log output')
# program arguments
help_str = 'gene FASTA file from extract_gene_seq.py script'
parser.add_argument('-i', '--input',
type=str, required=True,
help=help_str)
help_str = 'DNA mutations file'
parser.add_argument('-m', '--mutations',
type=str, required=True,
help=help_str)
help_str = 'BED file annotation of genes'
parser.add_argument('-b', '--bed',
type=str, required=True,
help=help_str)
help_str = 'Directory containing score information in pickle files (Default: None).'
parser.add_argument('-s', '--score-dir',
type=str, default=None,
help=help_str)
help_str = 'Directory containing neighbor graph information in pickle files (Default: None).'
parser.add_argument('-ng', '--neighbor-graph-dir',
type=str, default=None,
help=help_str)
help_str = ('Number of processes to use. 0 indicates using a single '
'process without using a multiprocessing pool '
'(more means Faster, default: 0).')
parser.add_argument('-p', '--processes',
type=int, default=0,
help=help_str)
help_str = ('Number of iterations for null model. p-value precision '
'increases with more iterations, however this will also '
'increase the run time (Default: 10000).')
parser.add_argument('-n', '--num-iterations',
type=int, default=10000,
help=help_str)
help_str = ('Number of iterations more significant then the observed statistic '
'to stop further computations. This decreases compute time spent in resolving '
'p-values for non-significant genes. (Default: 1000).')
parser.add_argument('-sc', '--stop-criteria',
type=int, default=1000,
help=help_str)
help_str = ('Kind of permutation test to perform ("oncogene" or "tsg"). "position-based" permutation '
'test is intended to find oncogenes using position based statistics. '
'The "deleterious" permutation test is intended to find tumor '
'suppressor genes. (Default: oncogene)')
parser.add_argument('-k', '--kind',
type=str, default='oncogene',
help=help_str)
help_str = ('Number of DNA bases to use as context. 0 indicates no context. '
'1 indicates only use the mutated base. 1.5 indicates using '
'the base context used in CHASM '
'(http://wiki.chasmsoftware.org/index.php/CHASM_Overview). '
'2 indicates using the mutated base and the upstream base. '
'3 indicates using the mutated base and both the upstream '
'and downstream bases. (Default: 1.5)')
parser.add_argument('-c', '--context',
type=float, default=1.5,
help=help_str)
help_str = ('Use mutations that are not mapped to the the single reference '
'transcript for a gene specified in the bed file indicated by '
'the -b option.')
parser.add_argument('-u', '--use-unmapped',
action='store_true',
default=False,
help=help_str)
help_str = ('Path to the genome fasta file. Required if --use-unmapped flag '
'is used. (Default: None)')
parser.add_argument('-g', '--genome',
type=str, default='',
help=help_str)
help_str = ('Only keep unique mutations for each tumor sample.'
'Mutations reproted from heterogeneous sources may contain'
' duplicates, e.g. a tumor sample was sequenced twice.')
parser.add_argument('--unique',
action='store_true',
default=False,
help=help_str)
help_str = ('Minimum number of mutations at a position for it to be '
'considered a recurrently mutated position (Default: 3).')
parser.add_argument('-r', '--recurrent',
type=int, default=3,
help=help_str)
help_str = ('Fraction of total mutations in a gene. This define the '
'minimumm number of mutations for a position to be defined '
'as recurrently mutated (Defaul: .02).')
parser.add_argument('-f', '--fraction',
type=float, default=.02,
help=help_str)
help_str = ('Perform tsg permutation test if gene has '
'at least a user specified number of deleterious mutations (default: 1)')
parser.add_argument('-d', '--deleterious',
type=int, default=1,
help=help_str)
help_str = ('Maximum TSG score to allow gene to be tested for oncogene '
'permutation test. Values greater than one indicate all '
'genes will be tested (Default: 1.01).')
parser.add_argument('-t', '--tsg-score',
type=float, default=1.01,
help=help_str)
help_str = ('Deleterious mutation pseudo-count for null distribution '
'statistics. (Default: 0)')
parser.add_argument('-dp', '--deleterious-pseudo-count',
type=int, default=0,
help=help_str)
help_str = ('Recurrent missense mutation pseudo-count for null distribution '
'statistics. (Default: 0)')
parser.add_argument('-rp', '--recurrent-pseudo-count',
type=int, default=0,
help=help_str)
help_str = ('Specify the seed for the pseudo random number generator. '
'By default, the seed is randomly chosen based. The seed will '
'be used for the permutation test monte carlo simulations.')
parser.add_argument('-seed', '--seed',
type=int, default=None,
help=help_str)
help_str = 'Output of probabilistic 20/20 results'
parser.add_argument('-o', '--output',
type=str, required=True,
help=help_str)
args = parser.parse_args()
# handle logging
if args.log_level or args.log:
if args.log:
log_file = args.log
else:
log_file = '' # auto-name the log file
else:
log_file = os.devnull
log_level = args.log_level
utils.start_logging(log_file=log_file,
log_level=log_level,
verbose=args.verbose) # start logging
opts = vars(args)
if opts['use_unmapped'] and not opts['genome']:
print('You must specify a genome fasta with -g if you set the '
'--use-unmapped flag to true.')
sys.exit(1)
# log user entered command
logger.info('Command: {0}'.format(' '.join(sys.argv)))
return opts
def parse_arguments():
# make a parser
info = 'Performs a statistical test for oncogene, TSG, or driver gene'
parent_parser = argparse.ArgumentParser(description=info)
# logging arguments
parent_parser.add_argument('-ll', '--log-level',
type=str,
action='store',
default='',
help='Write a log file (--log-level=DEBUG for debug mode, '
'--log-level=INFO for info mode)')
parent_parser.add_argument('-l', '--log',
type=str,
action='store',
default='stdout',
help='Path to log file. (accepts "stdout")')
parent_parser.add_argument('-v', '--verbose',
action='store_true',
default=False,
help='Flag for more verbose log output')
# add subparsers
subparsers = parent_parser.add_subparsers(title='Driver Gene Type', dest='kind')
parser_og = subparsers.add_parser('oncogene',
help='Find statistically significant oncogene-like genes.',
description='Find statsitically significant oncogene-like genes. '
'Evaluates clustering of missense mutations and high in '
'silico pathogenicity scores for missense mutations.')
help_info = 'Find statistically significant Tumor Suppressor-like genes.'
parser_tsg = subparsers.add_parser('tsg',
help=help_info,
description=help_info + ' Evaluates for a higher proportion '
'of inactivating mutations than expected.')
help_info = 'Find codons with significant clustering of missense mutations in sequence.'
parser_hotmaps = subparsers.add_parser('hotmaps1d',
help=help_info,
description=help_info + ' Evaluates for a higher ammount of '
'clustering of missense mutations.')
#parser_protein = subparsers.add_parser('protein', help='Find statistically significant '
#'3D clustering in genes based on protein structure.')
# program arguments
for i, parser in enumerate([parser_og, parser_tsg, parser_hotmaps]):
# group of parameters
major_parser = parser.add_argument_group(title='Major options')
advance_parser = parser.add_argument_group(title='Advanced options')
# set the CLI params
help_str = 'gene FASTA file from extract_gene_seq.py script'
major_parser.add_argument('-i', '--input',
type=str, required=True,
help=help_str)
help_str = ('DNA mutations file (MAF file). Columns can be in any order, '
'but should contain the correct column header names.')
major_parser.add_argument('-m', '--mutations',
type=str, required=True,
help=help_str)
help_str = 'BED file annotation of genes'
major_parser.add_argument('-b', '--bed',
type=str, required=True,
help=help_str)
help_str = ('Number of processes to use for parallelization. 0 indicates using a single '
'process without using a multiprocessing pool '
'(more means Faster, default: 0).')
major_parser.add_argument('-p', '--processes',
type=int, default=0,
help=help_str)
help_str = ('Number of iterations for null model. p-value precision '
'increases with more iterations, however this will also '
'increase the run time (Default: 100,000).')
major_parser.add_argument('-n', '--num-iterations',
type=int, default=100000,
help=help_str)
help_str = ('Number of iterations more significant then the observed statistic '
'to stop further computations. This decreases compute time spent in resolving '
'p-values for non-significant genes. (Default: 1000).')
advance_parser.add_argument('-sc', '--stop-criteria',
type=int, default=1000,
help=help_str)
help_str = ('Number of DNA bases to use as context. 0 indicates no context. '
'1 indicates only use the mutated base. 1.5 indicates using '
'the base context used in CHASM '
'(http://wiki.chasmsoftware.org/index.php/CHASM_Overview). '
'2 indicates using the mutated base and the upstream base. '
'3 indicates using the mutated base and both the upstream '
'and downstream bases. (Default: 1.5)')
major_parser.add_argument('-c', '--context',
type=float, default=1.5,
help=help_str)
if i == 0:
help_str = 'Directory containing VEST score information in pickle files (Default: None).'
major_parser.add_argument('-s', '--score-dir',
type=str, default=None,
help=help_str)
help_str = ('Minimum number of mutations at a position for it to be '
'considered a recurrently mutated position (Default: 3).')
advance_parser.add_argument('-r', '--recurrent',
type=int, default=3,
help=help_str)
help_str = ('Fraction of total mutations in a gene. This define the '
'minimumm number of mutations for a position to be defined '
'as recurrently mutated (Defaul: .02).')
advance_parser.add_argument('-f', '--fraction',
type=float, default=.02,
help=help_str)
elif i == 1:
help_str = ('Perform tsg randomization-based test if gene has '
'at least a user specified number of deleterious mutations (default: 1)')
advance_parser.add_argument('-d', '--deleterious',
type=int, default=1,
help=help_str)
elif i == 2:
help_str = ('Sequence window size for HotMAPS 1D algorithm '
'by number of codons (Default: 3)')
advance_parser.add_argument('-w', '--window',
type=str, default='3',
help=help_str)
help_str = ('Flag for reporting index (row number, starts at zero) in associated mutation file')
advance_parser.add_argument('-r', '--report-index',
action='store_true', default=False,
help=help_str)
help_str = ('Path to directory to save empirical null distribution')
advance_parser.add_argument('-nd', '--null-distr-dir',
type=str,
help=help_str)
elif i == 3:
help_str = 'Directory containing codon neighbor graph information in pickle files (Default: None).'
major_parser.add_argument('-ng', '--neighbor-graph-dir',
type=str, required=True,
help=help_str)
help_str = ('Minimum number of mutations at a position for it to be '
'considered a recurrently mutated position (Default: 3).')
advance_parser.add_argument('-r', '--recurrent',
type=int, default=3,
help=help_str)
help_str = ('Fraction of total mutations in a gene. This define the '
'minimumm number of mutations for a position to be defined '
'as recurrently mutated (Default: .02).')
advance_parser.add_argument('-f', '--fraction',
type=float, default=.02,
help=help_str)
help_str = ('Only keep unique mutations for each tumor sample. '
'Mutations reported from heterogeneous sources may contain'
' duplicates, e.g. a tumor sample was sequenced twice.')
advance_parser.add_argument('--unique',
action='store_true',
default=False,
help=help_str)
help_str = ('Use mutations that are not mapped to the the single reference '
'transcript for a gene specified in the bed file indicated by '
'the -b option.')
advance_parser.add_argument('-u', '--use-unmapped',
action='store_true',
default=False,
help=help_str)
help_str = ('Path to the genome fasta file. Required if --use-unmapped flag '
'is used. (Default: None)')
advance_parser.add_argument('-g', '--genome',
type=str, default='',
help=help_str)
help_str = ('Specify the seed for the pseudo random number generator. '
'By default, the seed is randomly chosen. The seed will '
'be used for the monte carlo simulations (Default: 101).')
advance_parser.add_argument('-seed', '--seed',
type=int, default=101,
help=help_str)
help_str = 'Output text file of probabilistic 20/20 results'
major_parser.add_argument('-o', '--output',
type=str, required=True,
help=help_str)
args = parent_parser.parse_args()
# handle logging
if args.log_level or args.log:
if args.log:
log_file = args.log
else:
log_file = '' # auto-name the log file
else:
log_file = os.devnull
log_level = args.log_level
utils.start_logging(log_file=log_file,
log_level=log_level,
verbose=args.verbose) # start logging
opts = vars(args)
if opts['use_unmapped'] and not opts['genome']:
print('You must specify a genome fasta with -g if you set the '
'--use-unmapped flag to true.')
sys.exit(1)
# log user entered command
logger.info('Version: {0}'.format(prob2020.__version__))
logger.info('Command: {0}'.format(' '.join(sys.argv)))
return opts
