output_file.write('\t'.join(output) + '\n')
# Enough?
num_processed += 1
if limit and num_processed >= limit:
break
return num_processed
if __name__ == '__main__':
parser = argparse.ArgumentParser('Vendor Compound Standardiser (Enamine)')
parser.add_argument('vendor_dir',
help='The Enamine vendor directory,'
' containing the ".gz" files to be processed.')
parser.add_argument('vendor_prefix',
help='The Enamine vendor file prefix,'
' i.e. "June2018". Only files with this prefix'
' in the vendor directory will be processed')
parser.add_argument('output', help='The output directory')
parser.add_argument('--output-is-prefix',
action='store_true',
help='Use the output as filename prefix rather than'
' a directory. This is useful in nextflow'
' workflows')
parser.add_argument('-l',
'--limit',
type=int,
default=0,
num_vendor_molecule_failures += 1
traceback.print_exc()
# Enough?
num_processed += 1
if limit and num_processed >= limit:
break
return num_processed
if __name__ == '__main__':
parser = argparse.ArgumentParser('Vendor Compound Standardiser (SDF)')
parser.add_argument('vendor_dir',
help='The SDF vendor directory,'
' containing the ".gz" files to be processed.')
parser.add_argument('vendor_prefix',
help='The SDF vendor file prefix,'
' i.e. "iis_smiles". Only files with this prefix'
' in the vendor directory will be processed')
parser.add_argument('output', help='The output directory')
parser.add_argument(
'--id-field',
help=
'Name of the field for the compound ID. If not specified the title line is used'
)
parser.add_argument('--prefix',
required=True,
help='Prefix for the compound ID')
output_file.write('\t'.join(output) + '\n')
# Enough?
num_processed += 1
if limit and num_processed >= limit:
break
return num_processed
if __name__ == '__main__':
parser = argparse.ArgumentParser('Vendor Compound Standardiser (ChEMBL)')
parser.add_argument(
'--input',
'-i',
help='The ChEMBL chembl_*.sdf.gz file to be processed.')
parser.add_argument('--output', '-o', help='The output directory')
parser.add_argument('--output-is-prefix',
action='store_true',
help='Use the output as filename prefix rather than'
' a directory. This is useful in nextflow'
' workflows')
parser.add_argument('--limit',
'-l',
type=int,
default=0,
help='Limit processing to the first N molecules,'
' process all otherwise')
args = parser.parse_args()
# Write the standardised data
output = [
smiles, smiles, smiles, '0',
'%s%s' % (compound_prefix, line_num)
]
output_file.write('\t'.join(output) + '\n')
lines_processed += 1
return lines_processed
if __name__ == '__main__':
parser = argparse.ArgumentParser('Exclusion Standardiser')
parser.add_argument('exclusion_file',
help='The file of exclusions.'
' A ".gz" of excluded SMILES strings.')
parser.add_argument('output',
help='The output directory, where'
' the standard file will be written')
args = parser.parse_args()
# Open the file we'll write the standardised data set to.
# A text, tab-separated file.
output_filename = os.path.join(args.output,
'{}.gz'.format(output_filename))
logger.info('Writing %s...', output_filename)
num_processed = 0
with gzip.open(output_filename, 'wt') as output_gzip_file:
