def n_atoms(gro_in):
if (type(gro_in) == str):
if (not ot.checkfile(os.getcwd(), gro_in)):
print('ERROR (n_atoms): checkfile() failed for args \"'+os.getcwd()+\
'\" and \"'+gro_in+'\"')
sys.exit(1)
gro_mem = gio.put_grofile_in_memory(gro_in)
nat = int(gro_mem[1][0])
del gro_mem
return nat
elif (type(gro_in) == list):
nat_list = []
for file in gro_in:
if (not ot.checkfile(os.getcwd(), file)):
print('ERROR (n_atoms): checkfile() failed for args \"'+os.getcwd()+\
'\" and \"'+file+'\"')
sys.exit(1)
gro_mem = gio.put_grofile_in_memory(file)
nat = int(gro_mem[1][0])
del gro_mem
nat_list.append(nat)
return nat_list
def to_gro(pdb_in):
if (type(pdb_in) == str):
if (not ot.checkfile(os.getcwd(), pdb_in)):
print('ERROR (to_gro): checkfile() failed for args \"'+os.getcwd()+\
'\" and \"'+pdb_in+'\"')
sys.exit(1)
gro_out = re.sub('.pdb', '.gro', pdb_in)
ifacelist = ['-f ' + pdb_in, '-o ' + gro_out]
gmx.g_editconf(ifacelist, log='editconf.err')
del ifacelist
return gro_out
elif (type(pdb_in) == list):
gro_out_list = []
for file in pdb_in:
if (not ot.checkfile(os.getcwd(), file)):
print('ERROR (to_gro): checkfile() failed for args \"'+os.getcwd()+\
'\" and \"'+file+'\"')
sys.exit(1)
gro_out = re.sub('.pdb', '.gro', file)
ifacelist = ['-f ' + file, '-o ' + gro_out]
gmx.g_editconf(ifacelist, log='editconf.err')
del ifacelist
gro_out_list.append(gro_out)
return gro_out_list
def do_fg2cg(pdbfile, pair):
pdbase = pdbfile.split('.pdb')[0]
# file parsing and conversion
ListChains = []
if (ot.checkfile(os.getcwd(), pdbfile)):
splitpdb = 1
ListChains = env.a2f.run(pdbfile, splitpdb)
else:
print('ERROR: checkfile() failed for args \"'+os.getcwd()+\
'\" and \"'+pdbfile+'\"')
sys.exit(1)
# First make CG structures of AA chains:
FastaLs = []
for file in os.listdir(os.getcwd()):
if (re.search('fasta', file)):
FastaLs.append(file)
DictIsChainAA = {}
for c in ListChains:
IsAA = False
for file in FastaLs:
if (re.search('_' + c + '.[0-9].fasta', file)):
IsAA = True
if (IsAA):
DictIsChainAA[c] = 'AASequence'
else:
DictIsChainAA[c] = 'NonProtein'
PdbLs = []
for file in os.listdir(os.getcwd()):
if (re.search('[0-9].pdb', file)):
PdbLs.append(file)
os.system('ls -lfh ' + file)
print("Found pdb files", PdbLs)
FgStructFiles = []
CgStructFiles = []
FgFastaFiles = []
FgDsspFiles = []
FgSsdFiles = []
CgItpFiles = []
for key, value in DictIsChainAA.items(): # Changed iteritems() to items()
if (value == 'AASequence'):
FgPdbs = []
CgPdbs = []
FgFastas = []
FgDssps = []
FgSsds = []
CgItps = []
for file in PdbLs:
if (re.search('_' + key + '.[0-9].pdb', file)):
FgPdbs.append(file)
FgFastas.append(re.sub('.pdb', '.fasta', file))
FgStructFiles.extend(FgPdbs)
FgFastaFiles.extend(FgFastas)
for file in FgPdbs:
CgPdbs.extend(finegrained2coarsegrained([file]))
FgDssps.extend(pdbt.pdb2dssp([file]))
for file in FgDssps:
FgSsds.extend(dssp2ssd([file]))
DictFastaSsd = {}
for file in FgSsds:
FastaFile = re.sub('.ssd', '.fasta', file)
DictFastaSsd[FastaFile] = file
CgItps.extend(to_itp(DictFastaSsd))
CgStructFiles.extend(CgPdbs)
FgDsspFiles.extend(FgDssps)
FgSsdFiles.extend(FgSsds)
CgItpFiles.extend(CgItps)
elif (value == 'NonProtein'):
FgPdbs = []
CgPdbs = []
CgItps = []
for file in PdbLs:
if (re.search('_' + key + '.[0-9].pdb', file)):
FgPdbs.append(file)
CgPdbs.append(Fg2Cg_NonProtein(file))
# print(FgStructFiles
# print(CgStructFiles
# print(FgFastaFiles
# print(FgDsspFiles
# print(FgSsdFiles
# print(CgItpFiles
fgpair = pdbt.merge_pdbs(pdbase, pair)
fastapair = pdbt.merge_fastas(pdbase, pair)
for i in fgpair:
if (not ot.checkfile(os.getcwd(), i)):
print('ERROR: checkfile() failed for args \"'+os.getcwd()+\
'\" and \"'+i+'\"')
sys.exit(1)
cgpair = finegrained2coarsegrained(fgpair)
dssppair = pdbt.pdb2dssp(fgpair)
for i in dssppair:
if (not ot.checkfile(os.getcwd(), i)):
print('ERROR: checkfile() failed for args \"'+os.getcwd()+\
'\" and \"'+i+'\"')
sys.exit(1)
ssdpair = dssp2ssd(dssppair)
itppair = []
if (len(ssdpair) == len(fastapair)):
fastassddict = {}
i = 0
for fasta in fastapair:
fastassddict[fasta] = ssdpair[i]
i += 1
for fasta in fastassddict.keys(): # Changed iterkeys() to keys()
if (not ot.checkfile(os.getcwd(), fasta)):
print('ERROR: checkfile() failed for args \"'+os.getcwd()+\
'\" and \"'+fasta+'\"')
sys.exit(1)
for ssd in fastassddict.values(): # Changed itervalues() to values()
if (not ot.checkfile(os.getcwd(), ssd)):
print('ERROR: checkfile() failed for args \"'+os.getcwd()+\
'\" and \"'+ssd+'\"')
sys.exit(1)
itppair = to_itp(fastassddict)
# check if order of fastapair == order of itppair
# since dictionary order can be different from list order
for i in range(len(itppair)):
itpname = itppair[i]
itpbase = itpname.split('.')[0]
itpext = itpname.split('.')[1]
fastaname = fastapair[i]
fastabase = fastaname.split('.')[0]
if (not re.match(fastabase, itpbase)):
itppair[i] = fastabase + '.' + itpext
else:
print('ERROR: len(ssdpair)!=len(fastapair)')
sys.exit(1)
gro_cgpair = gio.to_gro(cgpair)
nat_cgpair = st.n_atoms(gro_cgpair)
nrs_cgpair = st.n_residues(gro_cgpair)
cggro_merged = pdbase + '_cg.gro'
gio.merge_gro(cggro_merged, gro_cgpair, nat_cgpair, nrs_cgpair)
# make indexfile
ifacelist = ['-f ' + cggro_merged, '-o ' + 'tmp.ndx']
gmx.g_make_ndx(ifacelist, stdin=['q'], log='make_ndx.err')
del ifacelist
ngroups = st.ngroups_in_ndx('tmp.ndx')
os.remove('tmp.ndx')
cgndx_merged = re.sub('.gro', '.ndx', cggro_merged)
ifacelist = ['-f ' + cggro_merged, '-o ' + cgndx_merged]
gmx.g_make_ndx(ifacelist,
stdin=gmx.gen_ndxUIlist(ngroups, gro_cgpair, nat_cgpair),
log='make_ndx.err')
del ifacelist
# stabilize the tertiary structure:
cg_stable_itppair = stabilize_tertiary_structure(cggro_merged,
cgndx_merged, itppair,
'backbone', nat_cgpair)
return cggro_merged, cgndx_merged, cg_stable_itppair, \
gro_cgpair, nat_cgpair, fgpair