Mercurial > repos > bgruening > get_pubchem
comparison get_pubchem_as_smiles.py @ 0:cd19c3fab3a6 draft
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/data_source/get_pubchem commit aed18d7d09e332efe57d00b33c2b8249abefaedb
| author | bgruening |
|---|---|
| date | Wed, 22 May 2019 07:44:03 -0400 |
| parents | |
| children |
comparison
equal
deleted
inserted
replaced
| -1:000000000000 | 0:cd19c3fab3a6 |
|---|---|
| 1 #!/usr/bin/env python | |
| 2 | |
| 3 __author__ = 'Bjoern Gruening' | |
| 4 __version__ = '0.1' | |
| 5 __date__ = '2012' | |
| 6 __license__ = 'GLP3+' | |
| 7 | |
| 8 import ftplib | |
| 9 import os, sys | |
| 10 import argparse | |
| 11 import subprocess | |
| 12 from multiprocessing import Pool | |
| 13 import tempfile | |
| 14 import shutil | |
| 15 | |
| 16 | |
| 17 def main(output, processors = 4): | |
| 18 output_handle = open(output,'w+') | |
| 19 | |
| 20 td = tempfile.mkdtemp() | |
| 21 ftp = ftplib.FTP('ftp.ncbi.nih.gov') | |
| 22 ftp.login() | |
| 23 ftp.cwd('/pubchem/Compound/CURRENT-Full/SDF/') | |
| 24 filelist = ftp.nlst() | |
| 25 | |
| 26 pool = Pool(processes = processors) | |
| 27 filenames = zip(filelist, [td]*len(filelist)) | |
| 28 result = pool.map_async(fetch_convert, filenames) | |
| 29 result.get() | |
| 30 | |
| 31 for filename in os.listdir(td): | |
| 32 path = os.path.join(td, filename) | |
| 33 shutil.copyfileobj(open(path, 'rb'), output_handle) | |
| 34 | |
| 35 output_handle.close() | |
| 36 shutil.rmtree(td) | |
| 37 | |
| 38 def fetch_convert(args): | |
| 39 (filename, td) = args | |
| 40 tmp_name = os.path.join( td, filename) | |
| 41 subprocess.call( ['wget', '-O', tmp_name, os.path.join('ftp://ftp.ncbi.nih.gov/pubchem/Compound/CURRENT-Full/SDF/', filename)] ) | |
| 42 output = os.path.join(td, filename) + '.smi' | |
| 43 subprocess.call(["obabel", "-isdf", tmp_name, "-ocan", '-O', output]) | |
| 44 os.remove(tmp_name) | |
| 45 | |
| 46 | |
| 47 if __name__ == '__main__': | |
| 48 parser = argparse.ArgumentParser(description='Download the whole PubChem and converts it to canonical SMILES on the fly.') | |
| 49 parser.add_argument("-o", "--output", dest="output", | |
| 50 required=True, | |
| 51 help="Path to the output file.") | |
| 52 parser.add_argument("-p", "--processors", dest="processors", | |
| 53 type=int, default=10, | |
| 54 help="How many processors you want to use.") | |
| 55 | |
| 56 options = parser.parse_args() | |
| 57 main( options.output, options.processors ) | |
| 58 |