def soap_score():
import modeller
from modeller.scripts import complete_pdb
from modeller import soap_protein_od
env = modeller.environ()
env.libs.topology.read(file='$(LIB)/top_heav.lib')
env.libs.parameters.read(file='$(LIB)/par.lib')
# Set up SOAP-Protein-OD scoring (we create the scorer once and keep it
# around, since reading in the potential from disk can take a long time).
sp = soap_protein_od.Scorer()
out = open('SnapList.txt', 'w')
cnt = 0
files = [
i for i in glob.glob('pm.pdb*.pdb') if 'pm.pdb.B10010002.pdb' not in i
]
for fil in files:
try:
cnt += 1
# Read a model previously generated by Modeller's automodel class
mdl = complete_pdb(env, fil)
# Select all atoms
atmsel = modeller.selection(mdl)
# Assess with the above Scorer
try:
score = atmsel.assess(sp)
out.write(fil + '\t' + str(score) + '\n')
except modeller.ModellerError:
print("The SOAP-Protein-OD library file is not included "
"with MODELLER.")
print("Please get it from https://salilab.org/SOAP/.")
# Was 'except: pass' but this will hide genuine errors. Replace with
# a more specific list of exceptions (and test)
except:
raise
out.close()
def calc_score(self,runnumber,reportstatus=True):
"""Methods to benchmark the statistical potential, run on current directory"""
ddbfile='pdbs'+str(runnumber)
tmpdir=scratchdir
bm=self.bm
env = environ()
if self.atompairclustering and self.decomposition:
dnlist=pir(ddbfile).get_codelist()
idist=self.calc_individual_sp(ddbfile,dnlist,'apdecompscore')
np.save(str(runnumber)+'.score.npy',idist)
if reportstatus:
report_job_runstatus(self.runpath, True, runnumber, '.score.npy',inputname='runme.py')
return idist
elif self.atompairclustering:
dnlist=pir(ddbfile).get_codelist()
idist=self.calc_individual_sp(ddbfile,dnlist,'apscore')
np.save(str(runnumber)+'.score.npy',idist)
if reportstatus:
report_job_runstatus(self.runpath, True, runnumber, '.score.npy',inputname='runme.py')
return idist
elif self.decomposition:
dnlist=pir(ddbfile).get_codelist()
idist=self.calc_individual_sp(ddbfile,dnlist,'decompscore')
np.save(str(runnumber)+'.score.npy',idist)
if reportstatus:
report_job_runstatus(self.runpath, True, runnumber, '.score.npy',inputname='runme.py')
return idist
if self.features=='soap_loop':
from modeller import soap_loop
pair = soap_loop.Scorer()
env.edat.sphere_stdv=-1
env.edat.contact_shell=6
env.edat.dynamic_sphere=False
env.edat.energy_terms.append(pair)
elif self.features=='soap_pep':
from modeller import soap_peptide
pair = soap_peptide.Scorer('soap_pep.hdf5')
env.edat.sphere_stdv=-1
env.edat.contact_shell=6
env.edat.dynamic_sphere=False
env.edat.energy_terms.append(pair)
elif self.features=='soap_pp':
from modeller import soap_pp
atom = soap_pp.AtomScorer()
pair = soap_pp.PairScorer()
env.edat.sphere_stdv=-1
env.edat.contact_shell=15
env.edat.dynamic_sphere=False
env.edat.energy_terms.append(atom)
env.edat.energy_terms.append(pair)
elif self.features=='soap_protein_od':
from modeller import soap_protein_od
pair = soap_protein_od.Scorer()
env.edat.sphere_stdv=-1
env.edat.contact_shell=7
env.edat.dynamic_sphere=False
env.edat.energy_terms.append(pair)
features=self.features
mdtfile=self.ssppath+'.hdf5'
print 'Benchmarking: '+ ddbfile
log.minimal()
io=env.io
mlib=mdt.Library(env)
mlib.bond_classes.read('${LIB}/bndgrp.lib')
featurelist=feature(self.features,mlib).get_featurelist()
if self.pdbset!='Otherpot':
m=mdt.Table(mlib,features=featurelist,shape=[-1]*len(featurelist))
print mdtfile
m.read_hdf5(mdtfile)
a=alignment(env)
f=modfile.File(self.runpath+ddbfile,'r')
csmin, csmax,kcut, kcut1, bs,bsm, errsv,ssp=decode_genmethod(bm)
fp=0;
tn=0;
xp=0
scorestr=''
aln=alignment(env)
tmml=[]
fdl=[]
while aln.read_one(f):
tn=tn+1
try:
sr=0;
alncode=aln[0].code
codelist=alncode.split('.')
spdbdir=runenv.ddbdir+codelist[0]+'/'+codelist[1]+'/'
if self.features in ['firedock','zrank','rdock','dfire','epad','rosetta','plop','posescore','rankscore']:
naln=aln
fd=spdbdir
if len(fdl)==0 or fd!=fdl[-1]:
fdl.append(fd)
tmml.append([])
if self.features in ['dfire','epad']:
if not os.path.isfile('.'.join(alncode.split('.')[:2])+'.seq'):
aln.write(file='.'.join(alncode.split('.')[:2])+'.seq', alignment_format='FASTA')
tmml[-1].append(alncode)
else:
tmml[-1].append(alncode)
else:
errcount=1
while errcount<10:
try:
fd,naln=self.get_pdbfile(spdbdir,codelist,alncode,env,aln,tmpdir)
io.atom_files_directory=[fd]
if self.features=='dope' or self.features.startswith('soap'):
score=self.calc_special_score(env,fd,naln)
else:
sr=m.open_alignment(naln,io=io)
score=sr.sum(chain_span_range=(-csmax,-csmin,csmin,csmax),residue_span_range=(-kcut1,-kcut,kcut,kcut1),bond_span_range=(bs,bsm),disulfide=ssp)
print score
scorestr=scorestr+'>'+aln[0].code+' score: '+str(score)+'\n'
fp+=1
print alncode
break
except Exception,e:
time.sleep(0.1)
print open(os.path.join(tmpdir,alncode+'.pdb')).read()
print os.system('rm -f '+os.path.join(tmpdir,'*'))
errcount+=1
if errcount>=10:
raise e
except Exception,e:
traceback.print_exc()
xp=1
if re.search('fork failure',str(e)):
raise Exception('fork failure, quiting')
else:
if not self.test:
raise e
aln=0
aln=alignment(env)
import os
import sys
from modeller import *
from modeller.scripts import complete_pdb
from modeller import soap_protein_od
import os.path
log.verbose() # request verbose output
env = environ()
env.libs.topology.read(file='$(LIB)/top_heav.lib') # read topology
env.libs.parameters.read(file='$(LIB)/par.lib') # read parameters
# Set up SOAP-Protein-OD scoring (note: if assessing multiple models, it is
# best to create 'sp' just once and keep it around, since reading in the
# potential from disk can take a long time).
sp = soap_protein_od.Scorer()
# only calculate for single chains, because ga341 and dope only calculate first chains
models = [
'model_dimer.pdb', 'model_locked_dimer.pdb', 'model_fragment_dimer.pdb'
]
templates = ['template_dimer_all.pdb', 'template_fragment_dimer_all.pdb']
files = models + templates
for f in files:
if (not os.path.isfile(f)):
continue
print("; FILE " + f)
# read model file
mdl = complete_pdb(env, f)