m_name = '.'.join(m_name.split('.')[:-1]) + '_tstlvl' + str(lvl)
res['method'] = m_name
res = res[~res.test_var_alleles.str.contains('nan')]
res.to_csv(os.path.join(output_dir, m_name + '.csv'), index=False)
res['var_id'] = res['test_var_id']
res_u = res[~res.var_id.duplicated()]
res_u.reset_index(inplace=True)
res_u.ix[:, 'pred_labels'] = (res_u['pred_prob'] > prob_cutoff).astype(int)
#res_u = res_u[res_u.pred_labels == 1]
#outp_tsv = os.path.join(output_dir, m_name + '.tsv')
outp_tsv = os.path.join(output_dir, child_id + '.tsv')
func.writePredAsVcf(res_u, outp_tsv, min_DP=min_DP)
script_dir = os.path.dirname(os.path.realpath(sys.argv[0]))
cmd = ' '.join(
[os.path.join(script_dir, 'vcf2table.sh'), outp_tsv, script_dir, child_id])
print(cmd)
func.runInShell(cmd)
summarizeVariants.summarizeMutations(
os.path.join(output_dir, child_id + '-ann-onePline.tsv'),
os.path.join(output_dir, 'denovo'), config_file)
#cmd = ' '.join([os.path.join(script_dir, 'work', 'summarizeMutations.py'),
# os.path.join(output_dir, child_id + '-ann-onePline.tsv'),
# os.path.join(output_dir, 'denovo'),
# config_file])
#func.runInShell(cmd)
# work/summarizeMutations.py /mnt/xfs1/home/asalomatov/projects/spark/feature_sets/hc/trio003.p1_642940-ann-onePline.tsv /mnt/xfs1/home/asalomatov/projects/spark/feature_sets/hc/denovo cfg_spark.yml
dnvo = pandas.read_csv(input_file)
dnvo.ix[:, 'pred_labels'] = (dnvo['pred_prob'] > prob_cutoff).astype(int)
dnvo = dnvo[dnvo.pred_labels == 1]
dnvo.reset_index(inplace=True)
if dnvo.empty:
sys.exit('No mutations at score %s' % prob_cutoff)
tmp_dir = tempfile.mkdtemp()
print(tmp_dir)
input_file_bn = os.path.splitext(os.path.basename(input_file))[0]
outp_tsv = os.path.join(tmp_dir, input_file_bn + '.tsv')
print(outp_tsv)
func.writePredAsVcf(dnvo, outp_tsv, min_DP=min_DP)
script_name = os.path.join(os.path.dirname(os.path.realpath(sys.argv[0])),
'vcf2table.sh')
#script_name = os.path.abspath(pkg_resources.resource_filename('variants',
# 'vcf2table.sh'))
cmd = ' '.join([
script_name, outp_tsv,
os.path.dirname(script_name), input_file_bn, targ_bed, incl_make
])
print(cmd)
func.runInShell(cmd)
vn = summarizeVariants.summarizeMutations(
os.path.join(tmp_dir, input_file_bn + '-ann.vcf.onePline.tsv'),
os.path.join(tmp_dir, input_file_bn + '-vep.tsv'), input_file_bn,
output_dir, config_file)
if rm_tmp == 'yes':
cmd = 'rm -rf %s' % tmp_dir
func.runInShell(cmd)
dnvo.reset_index(inplace=True)
if dnvo.empty:
sys.exit('No mutations at score %s' % prob_cutoff)
tmp_dir = tempfile.mkdtemp()
print(tmp_dir)
input_file_bn = os.path.splitext(os.path.basename(input_file))[0]
outp_tsv = os.path.join(tmp_dir, input_file_bn + '.tsv')
print(outp_tsv)
func.writePredAsVcf(dnvo, outp_tsv, min_DP=min_DP)
# script_name = os.path.basename(os.path.realpath(sys.argv[0]))
script_name = os.path.abspath(pkg_resources.resource_filename('variants',
'vcf2table.sh'))
cmd = ' '.join([script_name,
outp_tsv,
os.path.dirname(script_name),
input_file_bn,
targ_bed])
print(cmd)
func.runInShell(cmd)
vn = summarizeVariants.summarizeMutations(
os.path.join(tmp_dir,
input_file_bn +
'-ann-onePline.tsv'),
input_file_bn,
output_dir,
config_file)
if rm_tmp == 'yes':
cmd = 'rm -rf %s' % tmp_dir
func.runInShell(cmd)
res.to_csv(os.path.join(output_dir, m_name + '.csv'), index=False)
res['var_id'] = res['test_var_id']
res_u = res[~res.var_id.duplicated()]
res_u.reset_index(inplace=True)
res_u.ix[:, 'pred_labels'] = (res_u['pred_prob'] > prob_cutoff).astype(int)
#res_u = res_u[res_u.pred_labels == 1]
#outp_tsv = os.path.join(output_dir, m_name + '.tsv')
outp_tsv = os.path.join(output_dir, child_id + '.tsv')
func.writePredAsVcf(res_u, outp_tsv, min_DP=min_DP)
script_dir = os.path.dirname(os.path.realpath(sys.argv[0]))
cmd = ' '.join([os.path.join(script_dir, 'vcf2table.sh'),
outp_tsv,
script_dir,
child_id])
print(cmd)
func.runInShell(cmd)
summarizeVariants.summarizeMutations(os.path.join(output_dir, child_id + '-ann-onePline.tsv'),
os.path.join(output_dir, 'denovo'),
config_file)
#cmd = ' '.join([os.path.join(script_dir, 'work', 'summarizeMutations.py'),
# os.path.join(output_dir, child_id + '-ann-onePline.tsv'),
# os.path.join(output_dir, 'denovo'),
# config_file])
#func.runInShell(cmd)
# work/summarizeMutations.py /mnt/xfs1/home/asalomatov/projects/spark/feature_sets/hc/trio003.p1_642940-ann-onePline.tsv /mnt/xfs1/home/asalomatov/projects/spark/feature_sets/hc/denovo cfg_spark.yml