Multiple input & output files?

Question

I'm trying to print out the measured distances for each .pdbqt file, and then write a new output file for each .pdbqt, using the original name of the .pdbqt file as the new .txt file name. Below is the script.

I'm using python3 & I'm trying to do this via Linux CLI.

from pymol import stored
stored.a, stored.b, stored.c, stored.d = [],[],[],[]
cmd.iterate_state(1, "r55_01///UNL`1/N*", "stored.a.append(ID)")
cmd.iterate_state(1, "r55_01///UNL`1/O*", "stored.b.append(ID)")
cmd.iterate_state(1, "r55_01//R/ASP`113/OD2", "stored.c.append(ID)")
cmd.iterate_state(1, "r55_01//R/ASN`312/ND2", "stored.d.append(ID)")

f=open("tt.txt", 'w')

for a in stored.a:
  for c in stored.c:
      d1=cmd.distance("id %s" % a, "id %s" % c,cutoff=5)
      f.write("%s D113 %s\n" % (a,d1))
      print(d1)

for b in stored.b:
  for d in stored.d:
      d2 = cmd.distance("id %s" % b, "id %s" % d, cutoff=5)
      f.write("%s N312 %s\n" % (b,d2))
      print(d2)

f.close()

My folder looks something like this

.
├── dst6.txt
├── sp
│   ├── r55_01.pdbqt
│   ├── r55_02.pdbqt
│   ├── r55_03.pdbqt
│   ├── r55_04.pdbqt
│   ├── r55_05.pdbqt
│   ├── r55_06.pdbqt
│   ├── r55_07.pdbqt
│   ├── r55_08.pdbqt
│   ├── r55_09.pdbqt
│   ├── r55_10.pdbqt
│   ├── r56_01.pdbqt
│   ├── r56_02.pdbqt
│   ├── r56_03.pdbqt
│   ├── r56_04.pdbqt
│   ├── r56_05.pdbqt
│   ├── r56_06.pdbqt
│   ├── r56_07.pdbqt
│   ├── r56_08.pdbqt
│   ├── r56_09.pdbqt
│   └── r56_10.pdbqt
└── t6.py

THANKS IN ADVANCE!!

Answer 1

You made the hardest work, you were not far to achieve what you wanted ;)

This script.py should work after you made it executable (in a terminal type: chmod u+x script.py), just type ./script.py in your terminal in your working directory (so here you should be in your "sp" directory). Note that I got inspired by: https://www.biostars.org/p/42474/ to know how to launch pymol within the script and also that I would personally not use pymol for doing this kind of analysis/data extraction from a pdb/pdbqt file but rather use a dedicated analysis package (there are plenty like MDanalysis). I personally use pymol (pymol script) for visualization purpose.

#!/usr/bin/env python


import __main__
__main__.pymol_argv = ['pymol', '-qc']  # Quiet and no GUI

from pymol import stored
import pymol, os

pymol.finish_launching()

#put what you've done into a function
def myfunc(file):
    spath = os.path.abspath(file)
    sname = spath.split('/')[-1].split('.')[0]

    pymol.cmd.load(spath, sname)

    stored.a, stored.b, stored.c, stored.d = [], [], [], []
    pymol.cmd.iterate_state(1, "%s///UNL`1/N*" % sname, "stored.a.append(ID)")
    pymol.cmd.iterate_state(1, "%s///UNL`1/O*" % sname, "stored.b.append(ID)")
    pymol.cmd.iterate_state(1, "%s//R/ASP`113/OD2" % sname, "stored.c.append(ID)")
    pymol.cmd.iterate_state(1, "%s//R/ASN`312/ND2" % sname, "stored.d.append(ID)")

    f = open('%s.txt' % sname, 'w')

    for a in stored.a:
        for c in stored.c:
            d1 = pymol.cmd.distance("id %s" % a, "id %s" % c, cutoff=5)
            f.write("%s D113 %s\n" % (a, d1))
            print(d1)

    for b in stored.b:
        for d in stored.d:
            d2 = pymol.cmd.distance("id %s" % b, "id %s" % d, cutoff=5)
            f.write("%s N312 %s\n" % (b, d2))
            print(d2)

    f.close()


mypdbqt = os.popen('ls *.pdbqt').read().split()

for i in mypdbqt:
    myfunc(i)

pymol.cmd.quit()