def parse_arguments():
info = ('Uses BFS to connect hotspot residues into connected regions '
'within a structure.')
parser = argparse.ArgumentParser(description=info)
# program arguments
parser.add_argument('-i', '--input',
type=str, required=True,
help='Output file from hotspot.py which has p-values for residues')
parser.add_argument('-a', '--annotation-dir',
type=str, required=True,
help='Annotation directory from CRAVAT')
parser.add_argument('-p', '--pdb-info',
type=str, required=True,
help='PDB information file (contains paths to PDBs)')
parser.add_argument('-r', '--radius',
default=3.0,
type=float,
help='Sphere radius in angstroms for connecting link between two residues (Default: 10.0)')
parser.add_argument('-o', '--output',
default='output.txt',
type=str,
help='Output result file for hotspot regions')
parser.add_argument('-s', '--significance',
type=str, required=True,
help='File containing p-value thresholds for each tumour type')
# 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")')
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)
return opts
def parse_arguments():
info = 'Uses BFS to connect hotspot residues into connected regions.'
parser = argparse.ArgumentParser(description=info)
# program arguments
parser.add_argument('-m', '--multiple-testing',
type=str, required=True,
help='File that corrects for multiple testing')
parser.add_argument('-a', '--annotation-dir',
type=str, required=True,
help='Annotation directory from CRAVAT')
parser.add_argument('-p', '--pdb-info',
type=str, required=True,
help='PDB information file (contains paths to PDBs)')
parser.add_argument('-r', '--radius',
default=10.0,
type=float,
help='Sphere radius in angstroms for connecting link between two residues (Default: 10.0)')
parser.add_argument('-q', '--q-value',
default=.01,
type=float,
help='Q-value for FDR (Default: .01)')
parser.add_argument('-o', '--output',
default='output.txt',
type=str,
help='Output result file for hotspot regions')
# 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")')
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)
return opts
def parse_arguments():
info = 'Adds column for path to the correct PDB file'
parser = argparse.ArgumentParser(description=info)
parser.add_argument('-p', '--pdb-info',
type=str, required=True,
help='PDB Info file from mupit_modbase')
parser.add_argument('-o', '--output',
type=str, required=True,
help='Updated PDB info file with path to PDBs')
# 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")')
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
return vars(args)
def parse_arguments():
info = 'Uses BFS to connect hotspot residues into connected regions.'
parser = argparse.ArgumentParser(description=info)
# program arguments
parser.add_argument('-m',
'--multiple-testing',
type=str,
required=True,
help='File that corrects for multiple testing')
parser.add_argument('-a',
'--annotation-dir',
type=str,
required=True,
help='Annotation directory from CRAVAT')
parser.add_argument('-p',
'--pdb-info',
type=str,
required=True,
help='PDB information file (contains paths to PDBs)')
parser.add_argument(
'-r',
'--radius',
default=10.0,
type=float,
help=
'Sphere radius in angstroms for connecting link between two residues (Default: 10.0)'
)
parser.add_argument('-q',
'--q-value',
default=.01,
type=float,
help='Q-value for FDR (Default: .01)')
parser.add_argument('-o',
'--output',
default='output.txt',
type=str,
help='Output result file for hotspot regions')
# 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")')
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)
return opts
def parse_arguments():
info = 'Detects hotspot protein regions'
parser = argparse.ArgumentParser(description=info)
# program arguments
parser.add_argument('-m',
'--mutations',
type=str,
required=True,
help='Mutation counts for specific structures')
parser.add_argument('-a',
'--annotation',
type=str,
required=True,
help='Annotations about PDB')
parser.add_argument('-n',
'--num-simulations',
default=10000,
type=int,
help='Number of simulations (Default: 10000)')
parser.add_argument('-r',
'--radius',
default=10.0,
type=float,
help='Sphere radius in angstroms (Default: 10.0)')
parser.add_argument('-s',
'--seed',
default=101,
type=int,
help='Random number generator seed (Default: 101)')
parser.add_argument(
'-sc',
'--stop-criterion',
default=200,
type=int,
help='Number of simulations exceeding the maximum observed '
'residue before stopping. This speeds computation by spending '
'less time on non-significant structures. (Default: 200)')
parser.add_argument(
'-t',
'--tumor-type',
type=str,
default='EVERY',
help=
'Perform analysis for only specific tumor type (Default: "EVERY" = each tumor type)'
)
parser.add_argument(
'-e',
'--error-pdb',
type=str,
default=None,
help='File containing structures that have badly formated pdb files')
parser.add_argument('-o',
'--output',
default='output.txt',
type=str,
help='Output result file of hotspots')
# 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")')
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)
return opts
def parse_arguments():
info = 'Detects hotspot protein regions'
parser = argparse.ArgumentParser(description=info)
# program arguments
parser.add_argument('-m', '--mutations',
type=str, required=True,
help='Mutation counts for specific structures')
parser.add_argument('-a', '--annotation',
type=str, required=True,
help='Annotations about PDB')
parser.add_argument('-n', '--num-simulations',
default=10000,
type=int,
help='Number of simulations (Default: 10000)')
parser.add_argument('-r', '--radius',
default=10.0,
type=float,
help='Sphere radius in angstroms (Default: 10.0)')
parser.add_argument('-s', '--seed',
default=None,
type=int,
help='Random number generator seed (Default: automatic)')
parser.add_argument('-sc', '--stop-criterion',
default=200,
type=int,
help='Number of simulations exceeding the maximum observed '
'residue before stopping. This speeds computation by spending '
'less time on non-significant structures. (Default: 200)')
parser.add_argument('-t', '--tumor-type',
type=str, default='EVERY',
help='Perform analysis for only specific tumor type (Default: "EVERY" = each tumor type)')
parser.add_argument('-e', '--error-pdb',
type=str, default=None,
help='File containing structures that have badly formated pdb files')
parser.add_argument('-o', '--output',
default='output.txt',
type=str,
help='Output result file of hotspots')
# 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")')
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)
return opts
:param df:
:return:
'''
# First drop duplicated indexes
return df.groupby(df.index).first()
#TODO: Write unit test for this function
def merge_and_fill_gaps(df, left_column, right_column):
logging.info('filling holes')
pre_merge_zeros = count_empty_rows(df, column=left_column)
logging.debug(f'Rows with 0 or NaN prior to merge {pre_merge_zeros}')
df[left_column] = df.apply(lambda x: max(x[left_column], x[right_column]),
axis=1)
post_merge_zeros = count_empty_rows(df, column=left_column)
logging.debug(f'Rows with 0 or NaN post to merge {post_merge_zeros}')
return df
def count_empty_rows(df, column):
return (df[column].isna().sum()) + (df[column] == 0).sum()
if __name__ == '__main__':
start_logging(debug_to_console=True)
COMMON_REPLACEMENTS = {
'United States of America': 'USA',
'United States': 'US'
}
