Hi
Using the cookbook code as basis (apologies if I should have posted in
the corresponding topic), I've put together a script to generate
conformers for my smiles library. Works like a charm too, aside from the
fact that after 10-20 hours, I'm out of RAM and swap (the memory
consumption seems to be accumulating with each iteration). I'd
appreciate any hints for getting this resolved (any other ones as well).
Thanks a lot,
Adam
====the code====
max_workers = 16
def generateconformations(m, n, name=''):
m = Chem.AddHs(m)
ids=AllChem.EmbedMultipleConfs(m, numConfs=n, pruneRmsThresh=0.5,
randomSeed=1)
etable=[] ## Gathers conformer energies
for id in ids:
ff = AllChem.UFFGetMoleculeForceField(m, confId=id)
ff.Minimize()
etable.append(ff.CalcEnergy())
return PropertyMol(m), list(ids), etable, name
input_dir, output_dir = sys.argv[1:3]
n = 75 ## Conformer number
os.chdir(input_dir)
for ifile in glob.glob('*.s*'):
raw_file = open(ifile, 'r') ## To get back molecule name later on
ofile = os.path.join(output_dir, 'conf_' + ifile)
if 'smiles' in ifile:
suppl = Chem.SmilesMolSupplier(ifile, titleLine=False,
delimiter='\t')
ofile = ofile.replace('.smiles', '.sdf')
sdfinput = False
if not os.path.isfile(ofile):
writer = Chem.SDWriter(ofile)
print 'Processing %s' %os.path.abspath(ifile),
datetime.datetime.now()
if sdfinput == False:
with futures.ProcessPoolExecutor(max_workers=max_workers)
as executor:
# Submit a set of asynchronous jobs
jobs = []
for mol in suppl:
if mol:
raw_line = raw_file.readline().split()[1] ##
extracting molecule name from the olriginal ifile
job = executor.submit(generateconformations,
mol, n, raw_line) ## returns molecules and associated ids / untill here
the conformers cannot be pickled
jobs.append(job)
for job in jobs:
mol, ids, etable, name = job.result()
mol.SetProp("_Name", name) ## Restoring lost property
mine = min(etable) ## Lowest conformer energy
for i in ids:
if etable[i] > mine + 20: ## Conformers with
energies greater then min+20 will not be written
ids.remove(i)
for i in ids:
for j in ids:
if i != j:
if AllChem.GetConformerRMS(mol, i, j) <
0.5: ## 0.5 A threshold for keeping conformers
ids.remove(j)
for id in ids:
writer.write(mol, confId=id)
writer.close()
else:
print "%s exists, skipping" % ofile
===========
------------------------------------------------------------------------------
Monitor 25 network devices or servers for free with OpManager!
OpManager is web-based network management software that monitors
network devices and physical & virtual servers, alerts via email & sms
for fault. Monitor 25 devices for free with no restriction. Download now
http://ad.doubleclick.net/ddm/clk/292181274;119417398;o
_______________________________________________
Rdkit-discuss mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/rdkit-discuss
