def dbsearch(rundir, args, globs):
cwd = os.getcwd()
flag = False
obab = 'obabel'
if args.gui:
from molSimplify.Classes.mWidgets import mQDialogErr
from molSimplify.Classes.mWidgets import mQDialogWarn
from molSimplify.Classes.mWidgets import mQDialogInf
### in any case do similarity search over indexed db ###
outf = args.dbfname if args.dbfname else 'simres.smi' # output file
### convert to SMILES/SMARTS if file
if not args.dbbase:
if args.gui:
qqb = mQDialogWarn('Warning', "No database file found within " + globs.chemdbdir + '. Search not possible.')
qqb.setParent(args.gui.DBWindow)
print "No database file found within " + globs.chemdbdir + '. Search not possible.'
return True
# if args.dbsim:
# print('similarity searching')
# if '.smi' in args.dbsim:
# if glob.glob(args.dbsim):
# f = open(args.dbsim,'r')
# smistr = f.read()
# f.close()
# else:
# print 'File '+args.dbsim+' not existing. Check your input.'
# print 'Similarity search terminating..'
# return True
# elif ('.mol' in args.dbsim or '.xyz' in args.dbsim):
# if glob.glob(args.dbsim):
# ftype = args.dbsim.split('.')[-1]
# obConversion = openbabel.OBConversion()
# obConversion.SetInFormat(ftype)
# OBMol = openbabel.OBMol()
# obConversion.ReadFile(OBMol,args.dbsim)
# smistr = pybel.write("smi")
# else:
# print 'File '+args.dbsim+' not existing. Check your input.'
# print 'Similarity search terminating..'
# return True
# else:
# smistr = args.dbsim
# print smistr
if args.dbsmarts:
if '.smi' in args.dbsmarts:
if glob.glob(args.dbsmarts):
f = open(args.dbsmarts, 'r')
smistr = f.read()
f.close()
else:
print 'File ' + args.dbsmarts + ' does not exist. Check your input.'
print 'Substructure search terminating..'
return 1
elif ('.mol' in args.dbsmarts or '.xyz' in args.dbsmarts):
if glob.glob(args.dbsmarts):
ftype = args.dbsmarts.split('.')[-1]
smistr = pymol.write("smi")
else:
print 'File ' + args.dbsmarts + ' does not exist. Check your input.'
print 'Substructure search terminating..'
return True
else:
smistr = args.dbsmarts
elif args.dbhuman:
smistr = []
denticity = args.dbvdent if args.dbvdent else '1'
coordatoms = args.dbvconns if args.dbvconns else 'N'
hyb = args.dbvhyb if args.dbvhyb else '3'
nlinks = args.dbvlinks if args.dbvlinks else '2'
monod = ['1', 'mono', 'Mono', 'monodentate', 'Monodentate']
bid = ['2', 'bi', 'Bi', 'bidentate', 'Bidentate']
if args.debug:
print('dbhuman conversion')
print('dbhuman coordatoms ' + str(coordatoms))
print('dbhuman nlinks ' + str(nlinks))
print('dbhuman hyb ' + str(hyb))
if denticity in monod:
smistr = '[#' + str(amassdict[coordatoms[0]][1]) + '^' + hyb[0] + ';!+]'
elif denticity in bid:
smistr = '[#' + str(amassdict[coordatoms[0]][1]) + '^' + hyb[0] + ';!+]'
for i in range(int(nlinks)):
smistr = smistr + '[#6;R0]'
print(coordatoms, hyb)
smistr = smistr + '[#' + str(amassdict[coordatoms[1]][1]) + '^' + hyb[1] + ';!+]'
print('setting smistr from dbhuman ' + smistr)
# else:
## get database
# [dbsdf,dbfs] = setupdb(args.dbbase)
## convert to smiles and print to output
# if globs.osx:
# cmd = "/usr/local/bin/obabel "+dbsdf+" -f0 -l100 -o"+outf[-3:]+" -O "+outf
# else:
# cmd = obab+" "+dbsdf+" -f0 -l100 -o"+outf[-3:]+" -O "+outf
# t = mybash(cmd)
# os.rename(outf,args.rundir+'/'+outf)
# print t
# return False
### parse filters
squery = checkscr(args)
if args.debug:
print("squery is " + str(squery))
if args.dbmaxsmartsmatches:
plugin_path = plugin_defs()
shutil.copy(plugin_path, 'plugindefines.txt')
cmd = "sed -i '/nsmartsmatches/!b;n;c" + smistr + "' " + 'plugindefines.txt'
mybash(cmd)
### run substructure search ###
nmols = '10000' if not args.dbnsearch else args.dbnsearch
finger = 'FP2' if not args.dbfinger else args.dbfinger
if int(nmols) > 3000 and args.gui:
qqb = mQDialogInf('Warning', "Database search is going to take a few minutes. Please wait..OK?")
qqb.setParent(args.gui.DBWindow)
if args.dbsmarts or args.dbhuman or args.dbsim:
outputf, flag = getsimilar(smistr, nmols, args.dbbase, finger, squery, args)
try:
shutil.copy('simres.smi', outf)
except:
pass
if args.debug:
print('after similarity search, outf is ' + str(outputf))
if flag:
if args.gui:
qqb = mQDialogWarn('Warning', "No matches found in search..")
qqb.setParent(args.gui.DBWindow)
print "No matches found in search.."
return True
# strip metals and clean-up, remove duplicates etc
# print('mb ' + str(mybash('cat '+outf)))
if args.dbsmarts or args.dbhuman:
print('Stripping salts and removing duplicates')
print('number of smiles strings BEFORE salt stripping: ' + mybash("cat " + outf + '| wc -l'))
flag = stripsalts(outf)
print('number of smiles strings AFTER salt stripping: ' + mybash("cat " + outf + '| wc -l'))
# print('flag from salt stripping: ' + str(flag))
print('number of smiles strings BEFORE unique: ' + mybash("cat " + outf + '| wc -l'))
cmd = obab + " -ismi " + outf + " -osmi -O " + outf + " --unique"
# print('running:' + str(cmd))
shutil.copy(outf, 'afterstrippingsalts.smi')
t = mybash(cmd)
print('number of smiles strings AFTER unique: ' + mybash("cat " + outf + '| wc -l'))
# print 't (ret from bash) is '+ str(t)
# filter results containing elements that aren't allowed
if args.dballowedels:
if args.dballowedels == 'organic': # HCNO only
allowedels = ['H', 'C', 'N', 'O']
elif args.dballowedels == 'organohalides':
allowedels = ['H', 'C', 'N', 'O', 'F', 'Cl', 'Br', 'I']
elif args.dballowedels == 'common':
allowedels = ['H', 'C', 'N', 'O', 'F', 'Cl', 'Br', 'I', 'P', 'S']
else:
allowedels = args.dballowedels
print('number of smiles strings BEFORE element filter: ' + mybash("cat " + outf + '| wc -l'))
checkels(outf, allowedels)
print('number of smiles strings AFTER element filter unique: ' + mybash("cat " + outf + '| wc -l'))
shutil.copy(outf, 'afterfilteringels.smi')
# check if defined connection atoms
if args.dbcatoms:
catoms = [int(a) for a in args.dbcatoms]
else:
catoms = [1]
# do pattern matching
nres = 50 if not args.dbresults else int(args.dbresults)
if args.dbsmarts or args.dbhuman:
print('number of smiles strings BEFORE SMARTS filter: ' + mybash("cat " + outf + '| wc -l'))
flag = matchsmarts(smistr, outf, catoms, args)
print('number of smiles strings AFTER SMARTS filter: ' + mybash("cat " + outf + '| wc -l'))
if args.debug:
print('outf is ' + str(outf))
### maximal dissimilarity search
if args.dbdissim:
dissim(outf, int(args.dbdissim))
if args.rundir:
print('writing output to ' + str(args.rundir) + '/' + str(outf) + '\n')
os.rename(outf, args.rundir + '/' + outf)
else:
print('writing output to ' + str(cwd) + '/' + str(outf) + '\n')
# os.chdir(cwd)
return False
def dbsearch(rundir, args, globs):
cwd = os.getcwd()
flag = False
obab = 'obabel'
if args.gui:
from molSimplify.Classes.mWidgets import mQDialogWarn
from molSimplify.Classes.mWidgets import mQDialogInf
### in any case do similarity search over indexed db ###
outf = args.dbfname if args.dbfname else 'simres.smi' # output file
# convert to SMILES/SMARTS if file
if not args.dbbase:
if args.gui:
qqb = mQDialogWarn(
'Warning', "No database file found within " + globs.chemdbdir +
'. Search not possible.')
qqb.setParent(args.gui.DBWindow)
print(("No database file found within " + globs.chemdbdir +
'. Search not possible.'))
return True
# if args.dbsim:
# print('similarity searching')
# if '.smi' in args.dbsim:
# if glob.glob(args.dbsim):
# f = open(args.dbsim,'r')
# smistr = f.read()
# f.close()
# else:
# print 'File '+args.dbsim+' not existing. Check your input.'
# print 'Similarity search terminating..'
# return True
# elif ('.mol' in args.dbsim or '.xyz' in args.dbsim):
# if glob.glob(args.dbsim):
# ftype = args.dbsim.split('.')[-1]
# obConversion = openbabel.OBConversion()
# obConversion.SetInFormat(ftype)
# OBMol = openbabel.OBMol()
# obConversion.ReadFile(OBMol,args.dbsim)
# smistr = pybel.write("smi")
# else:
# print 'File '+args.dbsim+' not existing. Check your input.'
# print 'Similarity search terminating..'
# return True
# else:
# smistr = args.dbsim
# print smistr
if args.dbsmarts:
if '.smi' in args.dbsmarts:
if glob.glob(args.dbsmarts):
f = open(args.dbsmarts, 'r')
smistr = f.read()
f.close()
else:
print(('File ' + args.dbsmarts +
' does not exist. Check your input.'))
print('Substructure search terminating..')
return 1
elif ('.mol' in args.dbsmarts or '.xyz' in args.dbsmarts):
if glob.glob(args.dbsmarts):
ftype = args.dbsmarts.split('.')[-1]
smistr = pymol.write("smi")
else:
print(('File ' + args.dbsmarts +
' does not exist. Check your input.'))
print('Substructure search terminating..')
return True
else:
smistr = args.dbsmarts
elif args.dbhuman:
smistr = []
denticity = args.dbvdent if args.dbvdent else '1'
coordatoms = args.dbvconns if args.dbvconns else 'N'
hyb = args.dbvhyb if args.dbvhyb else '3'
nlinks = args.dbvlinks if args.dbvlinks else '2'
monod = ['1', 'mono', 'Mono', 'monodentate', 'Monodentate']
bid = ['2', 'bi', 'Bi', 'bidentate', 'Bidentate']
if args.debug:
print('dbhuman conversion')
print(('dbhuman coordatoms ' + str(coordatoms)))
print(('dbhuman nlinks ' + str(nlinks)))
print(('dbhuman hyb ' + str(hyb)))
if denticity in monod:
smistr = '[#' + str(
amassdict[coordatoms[0]][1]) + '^' + hyb[0] + ';!+]'
elif denticity in bid:
smistr = '[#' + str(
amassdict[coordatoms[0]][1]) + '^' + hyb[0] + ';!+]'
for i in range(int(nlinks)):
smistr = smistr + '[#6;R0]'
print((coordatoms, hyb))
smistr = smistr + \
'[#' + str(amassdict[coordatoms[1]][1]) + '^' + hyb[1] + ';!+]'
print(('setting smistr from dbhuman ' + smistr))
# else:
# get database
# [dbsdf,dbfs] = setupdb(args.dbbase)
# convert to smiles and print to output
# if globs.osx:
# cmd = "/usr/local/bin/obabel "+dbsdf+" -f0 -l100 -o"+outf[-3:]+" -O "+outf
# else:
# cmd = obab+" "+dbsdf+" -f0 -l100 -o"+outf[-3:]+" -O "+outf
# t = mybash(cmd)
# os.rename(outf,args.rundir+'/'+outf)
# print t
# return False
# parse filters
squery = checkscr(args)
if args.debug:
print(("squery is " + str(squery)))
if args.dbmaxsmartsmatches:
plugin_path = plugin_defs()
shutil.copy(plugin_path, 'plugindefines.txt')
cmd = "sed -i '/nsmartsmatches/!b;n;c" + smistr + "' " + 'plugindefines.txt'
mybash(cmd)
### run substructure search ###
nmols = '10000' if not args.dbnsearch else args.dbnsearch
finger = 'FP2' if not args.dbfinger else args.dbfinger
if int(nmols) > 3000 and args.gui:
qqb = mQDialogInf(
'Warning',
"Database search is going to take a few minutes. Please wait..OK?")
qqb.setParent(args.gui.DBWindow)
if args.dbsmarts or args.dbhuman or args.dbsim:
outputf, flag = getsimilar(smistr, nmols, args.dbbase, finger, squery,
args)
try:
shutil.copy('simres.smi', outf)
except:
pass
if args.debug:
print(('after similarity search, outf is ' + str(outputf)))
if flag:
if args.gui:
qqb = mQDialogWarn('Warning', "No matches found in search..")
qqb.setParent(args.gui.DBWindow)
print("No matches found in search..")
return True
# strip metals and clean-up, remove duplicates etc
# print('mb ' + str(mybash('cat '+outf)))
if args.dbsmarts or args.dbhuman:
print('Stripping salts and removing duplicates')
print(('number of smiles strings BEFORE salt stripping: ' +
mybash("cat " + outf + '| wc -l')))
flag = stripsalts(outf)
print(('number of smiles strings AFTER salt stripping: ' +
mybash("cat " + outf + '| wc -l')))
# print('flag from salt stripping: ' + str(flag))
print(('number of smiles strings BEFORE unique: ' +
mybash("cat " + outf + '| wc -l')))
cmd = obab + " -ismi " + outf + " -osmi -O " + outf + " --unique"
# print('running:' + str(cmd))
shutil.copy(outf, 'afterstrippingsalts.smi')
t = mybash(cmd)
print(('number of smiles strings AFTER unique: ' +
mybash("cat " + outf + '| wc -l')))
# print 't (ret from bash) is '+ str(t)
# filter results containing elements that aren't allowed
if args.dballowedels:
if args.dballowedels == 'organic': # HCNO only
allowedels = ['H', 'C', 'N', 'O']
elif args.dballowedels == 'organohalides':
allowedels = ['H', 'C', 'N', 'O', 'F', 'Cl', 'Br', 'I']
elif args.dballowedels == 'common':
allowedels = ['H', 'C', 'N', 'O', 'F', 'Cl', 'Br', 'I', 'P', 'S']
else:
allowedels = args.dballowedels
print(('number of smiles strings BEFORE element filter: ' +
mybash("cat " + outf + '| wc -l')))
checkels(outf, allowedels)
print(('number of smiles strings AFTER element filter unique: ' +
mybash("cat " + outf + '| wc -l')))
shutil.copy(outf, 'afterfilteringels.smi')
# check if defined connection atoms
if args.dbcatoms:
catoms = [int(a) for a in args.dbcatoms]
else:
catoms = [1]
# do pattern matching
nres = 50 if not args.dbresults else int(args.dbresults)
if args.dbsmarts or args.dbhuman:
print(('number of smiles strings BEFORE SMARTS filter: ' +
mybash("cat " + outf + '| wc -l')))
flag = matchsmarts(smistr, outf, catoms, args)
print(('number of smiles strings AFTER SMARTS filter: ' +
mybash("cat " + outf + '| wc -l')))
if args.debug:
print(('outf is ' + str(outf)))
# maximal dissimilarity search
if args.dbdissim:
dissim(outf, int(args.dbdissim))
if args.rundir:
print(
('writing output to ' + str(args.rundir) + '/' + str(outf) + '\n'))
os.rename(outf, args.rundir + '/' + outf)
else:
print(('writing output to ' + str(cwd) + '/' + str(outf) + '\n'))
# os.chdir(cwd)
return False
def postproc(rundir, args, globs):
globs = globalvars()
if args.gui:
from molSimplify.Classes.mWidgets import mQDialogInf
choice = mQDialogInf(
'Post processing',
'Parsing the results will take a while..Please be patient. Start?')
choice.setParent(args.gui.pWindow)
# locate output files
pdir = args.postdir if args.postdir else globs.rundir
cmd = "find '" + pdir + "' -name *out"
t = mybash(cmd)
resf = t.splitlines()
logfile = pdir + "/post.log"
if not os.path.isdir(pdir):
print(('\nSpecified directory ' + pdir + ' does not exist..\n\n'))
if args.gui:
args.gui.iWtxt.setText('\nSpecified directory ' + pdir +
' does not exist.\n\n' +
args.gui.iWtxt.toPlainText())
return
flog = open(logfile, 'a')
flog.write('\n\n\n##### Date: ' + time.strftime('%m/%d/%Y %H:%M') +
'#####\n\n')
# run summary report
if args.pres:
print('\nGetting runs summary..\n\n')
flog.write('\nGetting runs summary..\n\n')
if args.gui:
args.gui.iWtxt.setText('\nGetting runs summary..\n\n' +
args.gui.iWtxt.toPlainText())
terapost(resf, pdir, args.gui, flog)
gampost(resf, pdir, args.gui, flog)
# run nbo analysis
if args.pnbo:
print('\nGetting NBO summary..\n\n')
flog.write('\nGetting NBO summary..\n\n')
if args.gui:
args.gui.iWtxt.setText('\nGetting NBO summary..\n\n' +
args.gui.iWtxt.toPlainText())
nbopost(resf, pdir, args.gui, flog)
# locate molden files
cmd = "find " + "'" + pdir + "'" + " -name *molden"
t = mybash(cmd)
molf = t.splitlines()
# parse molecular orbitals
if args.porbinfo:
print('\nGetting MO information..\n\n')
flog.write('\nGetting MO information..\n\n')
if args.gui:
args.gui.iWtxt.setText('\nGetting MO information..\n\n' +
args.gui.iWtxt.toPlainText())
if not os.path.isdir(pdir + '/MO_files'):
os.mkdir(pdir + '/MO_files')
moldpost(molf, pdir, args.gui, flog)
# calculate delocalization indices
if args.pdeloc:
print('\nCalculating delocalization indices..\n\n')
flog.write('\nCalculating delocalization indices..\n\n')
if args.gui:
args.gui.iWtxt.setText(
'\nCalculating delocalization indices..\n\n' +
args.gui.iWtxt.toPlainText())
if not os.path.isdir(pdir + '/Deloc_files'):
os.mkdir(pdir + '/Deloc_files')
deloc(molf, pdir, args.gui, flog)
# calculate charges
if args.pcharge:
print('\nCalculating charges..\n\n')
flog.write('\nCalculating charges..\n\n')
if args.gui:
args.gui.iWtxt.setText('\nCalculating charges..\n\n' +
args.gui.iWtxt.toPlainText())
if not os.path.isdir(pdir + '/Charge_files'):
os.mkdir(pdir + '/Charge_files')
getcharges(molf, pdir, args.gui, flog)
# parse wavefunction
if args.pwfninfo:
print('\nCalculating wavefunction properties..\n\n')
flog.write('\nCalculating wavefunction properties..\n\n')
if args.gui:
args.gui.iWtxt.setText(
'\nCalculating wavefunction properties..\n\n' +
args.gui.iWtxt.toPlainText())
if not os.path.isdir(pdir + '/Wfn_files'):
os.mkdir(pdir + '/Wfn_files')
if not os.path.isdir(pdir + '/Cube_files'):
os.mkdir(pdir + '/Cube_files')
getcubes(molf, pdir, args.gui, flog)
getwfnprops(molf, pdir, args.gui, flog)
if not args.pgencubes and os.path.isdir(pdir + '/Cube_files'):
shutil.rmtree(pdir + '/Cube_files')
# generate cube files
if args.pgencubes:
print('\nGenerating cube files..\n\n')
flog.write('\nGenerating cube files..\n\n')
if args.gui:
args.gui.iWtxt.setText('\nGenerating cube files..\n\n' +
args.gui.iWtxt.toPlainText())
if not os.path.isdir(pdir + '/Cube_files'):
os.mkdir(pdir + '/Cube_files')
getcubes(molf, pdir, args.gui, flog)
flog.close()