def main(opts, mut_df=None, frameshift_df=None):
# hack to index the FASTA file
gene_fa = pysam.Fastafile(opts['input'])
gene_fa.close()
# Get Mutations
if mut_df is None:
mut_df = pd.read_csv(opts['mutations'], sep='\t')
orig_num_mut = len(mut_df)
# rename columns to fit my internal column names
rename_dict = {
'Hugo_Symbol': 'Gene',
'Tumor_Sample_Barcode': 'Tumor_Sample',
'Tumor_Seq_Allele2': 'Tumor_Allele'
}
mut_df.rename(columns=rename_dict, inplace=True)
# drop rows with missing info
na_cols = ['Gene', 'Tumor_Allele', 'Start_Position', 'Chromosome']
mut_df = mut_df.dropna(subset=na_cols)
logger.info('Kept {0} mutations after droping mutations with missing '
'information (Droped: {1})'.format(len(mut_df),
orig_num_mut - len(mut_df)))
# count frameshifts
if opts['kind'] == 'tsg':
if frameshift_df is None:
# read in mutations
if mut_df is None:
mut_df = pd.read_csv(opts['mutations'], sep='\t')
# count number of frameshifts
frameshift_df = cf.count_frameshift_total(mut_df, opts['bed'],
opts['use_unmapped'])
# calculate the proportion of inactivating
#num_inact = len(mut_df[mut_df['Variant_Classification'].isin(utils.variant_inactivating)])
#num_non_inact = len(mut_df[mut_df['Variant_Classification'].isin(utils.variant_non_inactivating)])
num_fs = len(mut_df[mut_df['Variant_Classification'].isin(
utils.variant_frameshift)])
num_all = len(mut_df[mut_df['Variant_Classification'].isin(
utils.all_variants)])
#p_inactivating = float(num_inact) / (num_inact + num_non_inact)
p_inactivating = float(num_fs) / num_all
# select valid single nucleotide variants only
mut_df = utils._fix_mutation_df(mut_df, opts['unique'])
# log random number seed choice if provided
if opts['seed'] is not None:
logger.info('Pseudo Random Number Generator Seed: {0}'.format(
opts['seed']))
# read BED file
bed_dict = utils.read_bed(opts['bed'])
# Perform BH p-value adjustment and tidy up data for output
if opts['kind'] == 'oncogene':
permutation_result = multiprocess_permutation(bed_dict, mut_df, opts)
permutation_df = pr.handle_oncogene_results(permutation_result,
opts['num_iterations'])
elif opts['kind'] == 'tsg':
permutation_result = multiprocess_permutation(bed_dict, mut_df, opts,
frameshift_df,
p_inactivating)
permutation_df = pr.handle_tsg_results(permutation_result)
elif opts['kind'] == 'hotmaps1d':
permutation_result = multiprocess_permutation(bed_dict, mut_df, opts)
#frameshift_df, p_inactivating)
permutation_df = pr.handle_hotmaps_results(permutation_result)
elif opts['kind'] == 'protein':
permutation_result = multiprocess_permutation(bed_dict, mut_df, opts)
permutation_df = pr.handle_protein_results(permutation_result)
elif opts['kind'] == 'effect':
permutation_result = multiprocess_permutation(bed_dict, mut_df, opts)
permutation_df = pr.handle_effect_results(permutation_result)
# save output
if opts['output']:
permutation_df.to_csv(opts['output'], sep='\t', index=False)
return permutation_df
def main(opts, mut_df=None, frameshift_df=None):
# hack to index the FASTA file
gene_fa = pysam.Fastafile(opts['input'])
gene_fa.close()
# Get Mutations
if mut_df is None:
mut_df = pd.read_csv(opts['mutations'], sep='\t')
orig_num_mut = len(mut_df)
# rename columns to fit my internal column names
rename_dict = {
'Hugo_Symbol': 'Gene',
'Tumor_Sample_Barcode': 'Tumor_Sample',
'Tumor_Seq_Allele2' : 'Tumor_Allele'
}
mut_df.rename(columns=rename_dict, inplace=True)
# drop rows with missing info
na_cols = ['Gene', 'Tumor_Allele', 'Start_Position', 'Chromosome']
mut_df = mut_df.dropna(subset=na_cols)
logger.info('Kept {0} mutations after droping mutations with missing '
'information (Droped: {1})'.format(len(mut_df), orig_num_mut - len(mut_df)))
# count frameshifts
if opts['kind'] == 'tsg':
if frameshift_df is None:
# read in mutations
if mut_df is None:
mut_df = pd.read_csv(opts['mutations'], sep='\t')
# count number of frameshifts
frameshift_df = cf.count_frameshift_total(mut_df, opts['bed'],
opts['use_unmapped'])
# calculate the proportion of inactivating
#num_inact = len(mut_df[mut_df['Variant_Classification'].isin(utils.variant_inactivating)])
#num_non_inact = len(mut_df[mut_df['Variant_Classification'].isin(utils.variant_non_inactivating)])
num_fs = len(mut_df[mut_df['Variant_Classification'].isin(utils.variant_frameshift)])
num_all = len(mut_df[mut_df['Variant_Classification'].isin(utils.all_variants)])
#p_inactivating = float(num_inact) / (num_inact + num_non_inact)
p_inactivating = float(num_fs) / num_all
# select valid single nucleotide variants only
mut_df = utils._fix_mutation_df(mut_df, opts['unique'])
# log random number seed choice if provided
if opts['seed'] is not None:
logger.info('Pseudo Random Number Generator Seed: {0}'.format(opts['seed']))
# read BED file
bed_dict = utils.read_bed(opts['bed'])
# Perform BH p-value adjustment and tidy up data for output
if opts['kind'] == 'oncogene':
permutation_result = multiprocess_permutation(bed_dict, mut_df, opts)
permutation_df = pr.handle_oncogene_results(permutation_result,
opts['num_iterations'])
elif opts['kind'] == 'tsg':
permutation_result = multiprocess_permutation(bed_dict, mut_df, opts,
frameshift_df, p_inactivating)
permutation_df = pr.handle_tsg_results(permutation_result)
elif opts['kind'] == 'hotmaps1d':
permutation_result = multiprocess_permutation(bed_dict, mut_df, opts)
#frameshift_df, p_inactivating)
permutation_df = pr.handle_hotmaps_results(permutation_result)
elif opts['kind'] == 'protein':
permutation_result = multiprocess_permutation(bed_dict, mut_df, opts)
permutation_df = pr.handle_protein_results(permutation_result)
elif opts['kind'] == 'effect':
permutation_result = multiprocess_permutation(bed_dict, mut_df, opts)
permutation_df = pr.handle_effect_results(permutation_result)
# save output
if opts['output']:
permutation_df.to_csv(opts['output'], sep='\t', index=False)
return permutation_df