File: do_smiles.py

package info (click to toggle)
rdkit 202503.6-3
  • links: PTS, VCS
  • area: main
  • in suites: sid
  • size: 222,000 kB
  • sloc: cpp: 411,111; python: 78,482; ansic: 26,181; java: 8,285; javascript: 4,404; sql: 2,393; yacc: 1,626; lex: 1,267; cs: 1,090; makefile: 581; xml: 229; fortran: 183; sh: 121
file content (38 lines) | stat: -rwxr-xr-x 742 bytes parent folder | download | duplicates (4)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
import re

splitExpr = re.compile('[\t ]')

from rdkit import Chem


def runit(fName):
  inLines = open(fName, 'r').readlines()
  nFailed = 0
  nPassed = 0
  nTried = 0
  for line in inLines:
    if len(line):
      smi = splitExpr.split(line)[1]
      if smi[-1] == '\n':
        smi = smi[:-1]
      if smi[-1] == '\r':
        smi = smi[:-1]
      nTried += 1
      m = Chem.MolFromSmiles(smi)
      if m:
        nPassed += 1
      else:
        print('\t%s failed' % repr(smi))
        print('\tline: %s' % (repr(line)))
        nFailed += 1
      m = None
  print('%d of %d passed' % (nPassed, nTried))


if __name__ == '__main__':
  import sys
  fName = 'ntp_smiles.txt'
  if len(sys.argv) > 1:
    fName = sys.argv[1]

  runit(fName)