def main_cosmic(options):
"""Main function used to process COSMIC data."""
# get configs
in_opts = _utils.get_input_config('classifier')
out_opts = _utils.get_output_config('features')
count_opts = _utils.get_output_config('feature_matrix')
# result_opts = _utils.get_input_config('result')
db_cfg = _utils.get_db_config('2020plus')
# get mutations
conn = sqlite3.connect(db_cfg['db'])
sql = ("SELECT Gene, Protein_Change as AminoAcid, "
" DNA_Change as Nucleotide, "
" Variant_Classification, "
" Tumor_Sample, Tumor_Type "
"FROM mutations")
mut_df = psql.frame_query(sql, con=conn)
conn.close()
# get features for classification
all_features = futils.generate_features(mut_df, options)
# save features to text file
cols = all_features.columns.tolist()
new_order = ['gene'] + cols[:cols.index('gene')] + cols[cols.index('gene')+1:]
all_features = all_features[new_order] # make the gene name the first column
out_path = _utils.save_dir + in_opts['gene_features'] if not options['output'] else options['output']
all_features.to_csv(out_path, sep='\t', index=False)
def main_cosmic(options):
"""Main function used to process COSMIC data."""
# get configs
in_opts = _utils.get_input_config('classifier')
out_opts = _utils.get_output_config('features')
count_opts = _utils.get_output_config('feature_matrix')
# result_opts = _utils.get_input_config('result')
db_cfg = _utils.get_db_config('2020plus')
# get mutations
conn = sqlite3.connect(db_cfg['db'])
sql = ("SELECT Gene, Protein_Change as AminoAcid, "
" DNA_Change as Nucleotide, "
" Variant_Classification, "
" Tumor_Sample, Tumor_Type "
"FROM mutations")
mut_df = psql.frame_query(sql, con=conn)
conn.close()
# get features for classification
all_features = futils.generate_features(mut_df, options)
# save features to text file
cols = all_features.columns.tolist()
new_order = ['gene'
] + cols[:cols.index('gene')] + cols[cols.index('gene') + 1:]
all_features = all_features[
new_order] # make the gene name the first column
out_path = _utils.save_dir + in_opts['gene_features'] if not options[
'output'] else options['output']
all_features.to_csv(out_path, sep='\t', index=False)
def main(db_path):
db_opts = _utils.get_db_config('2020plus')
out_db = db_opts['db']
out_db = db_path if db_path else out_db
# drop table if exists
# _utils.drop_table('mutation', out_db, kind='sqlite')
cols_of_interest = [
'Gene', 'Tumor_Sample', 'Tumor_Type', 'Chromosome', 'Start_Position',
'End_Position', 'Variant_Classification', 'Reference_Allele',
'Tumor_Allele', 'Protein_Change', 'DNA_Change'
]
data_type = [
'TEXT', 'TEXT', 'TEXT', 'TEXT', 'INT', 'INT', 'TEXT', 'TEXT', 'TEXT',
'TEXT', 'TEXT'
]
_utils.create_empty_table('mutation', out_db, cols_of_interest, data_type)
conn = sqlite3.connect(out_db) # open connection
cur = conn.cursor()
#col_info_list = [' '.join(x) for x in zip(cols_of_interest, data_type)]
#col_info_str = ', '.join(col_info_list)
#sql = "CREATE TABLE mutation({0});".format(col_info_str)
#cur.execute(sql)
#conn.commit()
maf_mutation_cols = ['Gene_Symbol'] + cols_of_interest[1:-1]
sql = ("INSERT INTO mutation ({0}) "
" SELECT {1}"
" FROM maf_mutation".format(', '.join(cols_of_interest[:-1]),
', '.join(maf_mutation_cols)))
cur.execute(sql)
conn.commit()
cols_of_interest = cols_of_interest[:-5] + cols_of_interest[-2:] + [
'Variant_Classification'
]
cosmic_col_list = [
'Gene', 'SampleName', 'PrimaryTissue', 'hg19chrom', 'hg19start',
'hg19end', 'AminoAcid', 'Nucleotide', 'Variant_Classification'
]
mut_cols = ', '.join(cols_of_interest)
cosmic_cols = ', '.join(cosmic_col_list)
sql = ("INSERT INTO mutation({0}) "
" SELECT {1} "
" FROM cosmic_mutation cm"
" WHERE cm.SampleName NOT IN ("
" SELECT DISTINCT(m.Tumor_Sample) "
" FROM mutation m "
" ) ".format(mut_cols, cosmic_cols))
cur.execute(sql)
conn.commit()
sql = ("UPDATE mutation SET DNA_Change='c.?'" "WHERE DNA_CHANGE IS NULL")
cur.execute(sql)
conn.commit()
conn.close()
def main(hypermutator_count, mut_path, db_path, no_cosmic_flag, opts):
"""Concatenates all the mutation data from tab delmited files in
the cosmic directory. Next, saves the results to a sqlite db.
Parameters
----------
hypermutator_count : int
remove samples with too many mutations
mut_path : str
Either path to directory containing contents of COSMIC's
genes.tgz file or decompressed CosmicMutantExport.tsv.
If empty string, just use path from config file.
db_path : str
path to save sqlite database. If string is empty,
use path from config.
no_cosmic_flag : bool
indicates not to use cosmic mutations
"""
# get input/output configurations
in_opts = _utils.get_input_config('input')
cosmic_path = in_opts['cosmic_path']
out_opts = _utils.get_output_config('gene_tsv')
out_path = out_opts['gene_tsv']
cnv_path = out_opts['cnv_tsv']
db_opts = _utils.get_db_config('2020plus')
out_db = db_opts['db']
# check if user specifies non standard db path
out_db = db_path if db_path else out_db
# save info into a txt file and sqlite3 database
if not no_cosmic_flag:
cosmic_path = mut_path if mut_path else cosmic_path
if os.path.isdir(cosmic_path):
# concatenate all gene files
concatenate_genes(out_path, cosmic_path)
# save database
save_db(hypermutator_count,
out_path,
out_db,
is_genes_tgz=True,
only_genome_wide=opts['only_genome_wide'],
use_unknown_status=opts['use_unknown_status'])
elif os.path.isfile(cosmic_path):
# save database
save_db(hypermutator_count,
cosmic_path,
out_db,
is_genes_tgz=False,
only_genome_wide=opts['only_genome_wide'],
use_unknown_status=opts['use_unknown_status'])
else:
raise ValueError('Please specify a vlid path to COSMIC data')
else:
# create an empty table if cosmic not wanted
create_empty_cosmic_mutation_table(out_db)
def main(maf_path, db_path, hypermutator_count):
# get db info
db_opts = _utils.get_db_config('2020plus')
out_db = db_opts['db']
out_db = db_path if db_path else out_db
# update databse maf_mutation table
if maf_path:
# add to database if they specify a MAF file
save_db(maf_path, out_db, hypermutator_count)
else:
# else just create an empty maf_mutation table
create_empty_maf_mutation_table(out_db)
def main(maf_path, db_path, hypermutator_count):
# get db info
db_opts = _utils.get_db_config('2020plus')
out_db = db_opts['db']
out_db = db_path if db_path else out_db
# update databse maf_mutation table
if maf_path:
# add to database if they specify a MAF file
save_db(maf_path, out_db, hypermutator_count)
else:
# else just create an empty maf_mutation table
create_empty_maf_mutation_table(out_db)
def wrapper_retrieve_gene_features(opts):
"""Wrapper arround the retrieve_gene_features function in the
features module.
Parameters
----------
opts : dict
command line options
Returns
-------
additional_features : pd.DataFrame
"""
# get additional features
db_cfg = _utils.get_db_config('2020plus')
conn = sqlite3.connect(db_cfg['db'])
additional_features = retrieve_gene_features(conn, opts, get_entropy=False)
conn.close()
return additional_features
def wrapper_retrieve_gene_features(opts):
"""Wrapper arround the retrieve_gene_features function in the
features module.
Parameters
----------
opts : dict
command line options
Returns
-------
additional_features : pd.DataFrame
"""
# get additional features
db_cfg = _utils.get_db_config('2020plus')
conn = sqlite3.connect(db_cfg['db'])
additional_features = retrieve_gene_features(conn, opts, get_entropy=False)
conn.close()
return additional_features
def main(db_path):
# get config files
in_opts = _utils.get_input_config('input')
db_opts = _utils.get_db_config('2020plus')
# get absolute path for cosmic data
cosmic_path = os.path.join(_utils.proj_dir, in_opts['cosmic_path'])
# get data for gene_features table
logger.info('Processing features for gene_features table ...')
if os.path.isdir(cosmic_path):
gene_length = recursive_gene_length(in_opts['fasta_dir'])
genes, lengths = zip(*gene_length.items())
gene_length_df = pd.DataFrame({'gene': genes, 'gene length': lengths})
else:
gene_length_df = pd.read_csv(cosmic_path, sep='\t')
gene_length_df = gene_length_df[['Gene name', 'Gene CDS length']]
gene_length_df = gene_length_df.rename(columns={
'Gene name': 'gene',
'Gene CDS length': 'gene length'
})
gene_length_df.drop_duplicates(cols=['gene'], inplace=True)
# merge in data from mutsig and biogrid
mutsigcv_feature_path = os.path.join(_utils.proj_dir,
in_opts['mutsigcv_features'])
df = pd.read_csv(mutsigcv_feature_path, sep='\t')
df = pd.merge(gene_length_df, df, how='left',
on='gene') # merge the data frames
biogrid_path = os.path.join(_utils.proj_dir, 'data/biogrid_stats.txt')
biogrid_df = pd.read_csv(biogrid_path, sep='\t')
df = pd.merge(df, biogrid_df, how='left', on='gene')
# path to database
db_path = db_path if db_path else db_opts['db']
logger.info('Finished processing features for gene_features table.')
# save database
save_db(df, db_path)
def main(db_path):
# get config files
in_opts = _utils.get_input_config('input')
db_opts = _utils.get_db_config('2020plus')
# get absolute path for cosmic data
cosmic_path = os.path.join(_utils.proj_dir, in_opts['cosmic_path'])
# get data for gene_features table
logger.info('Processing features for gene_features table ...')
if os.path.isdir(cosmic_path):
gene_length = recursive_gene_length(in_opts['fasta_dir'])
genes, lengths = zip(*gene_length.items())
gene_length_df = pd.DataFrame({'gene': genes, 'gene length': lengths})
else:
gene_length_df = pd.read_csv(cosmic_path, sep='\t')
gene_length_df = gene_length_df[['Gene name', 'Gene CDS length']]
gene_length_df = gene_length_df.rename(columns={'Gene name': 'gene',
'Gene CDS length': 'gene length'})
gene_length_df.drop_duplicates(cols=['gene'], inplace=True)
# merge in data from mutsig and biogrid
mutsigcv_feature_path = os.path.join(_utils.proj_dir, in_opts['mutsigcv_features'])
df = pd.read_csv(mutsigcv_feature_path, sep='\t')
df = pd.merge(gene_length_df, df, how='left', on='gene') # merge the data frames
biogrid_path = os.path.join(_utils.proj_dir, 'data/biogrid_stats.txt')
biogrid_df = pd.read_csv(biogrid_path, sep='\t')
df = pd.merge(df, biogrid_df, how='left', on='gene')
# path to database
db_path = db_path if db_path else db_opts['db']
logger.info('Finished processing features for gene_features table.')
# save database
save_db(df, db_path)