def pdb():
"""Get PDB content of selection.
.. image:: ../../rna_tools/utils/PyMOL4RNA/doc/pdb.png"""
tmpfn = '/tmp/pymol_get_pdb.pdb'
cmd.save(tmpfn, '(sele)')
s = RNAStructure(tmpfn)
for l in s.lines:
print(l)
# get version
version = os.path.basename(os.path.dirname(
os.path.abspath(__file__))), get_version(__file__)
version = version[1].strip()
# get parser and arguments
parser = get_parser()
args = parser.parse_args()
# quick fix for one files vs file-s
if list == type(args.file) and len(args.file) == 1:
args.file = args.file[0]
if args.report:
s = RNAStructure(args.file)
print(s.get_report)
print(s.get_preview())
print(s.get_info_chains())
if args.clean:
s = RNAStructure(args.file)
s.decap_gtp()
s.std_resn()
s.remove_hydrogen()
s.remove_ion()
s.remove_water()
s.renum_atoms()
s.fix_O_in_UC()
s.fix_op_atoms()
# print s.get_preview()
def run(self, pdb_file, numSteps, verbose=False):
"""Compute SimRNA energy for a single file
Arguments:
* pdb_file = path to a PDB file
* numSteps, number of SimRNA steps
Output:
* global energy as a floating point number
"""
self.log('Running program')
self.log('input - pdb_file: %s' % pdb_file)
#copyfile(pdb_file, self.sandbox_dir + os.sep + 'query.pdb')
s = RNAStructure(pdb_file)
s.get_rnapuzzle_ready()
s.write(self.sandbox_dir + os.sep + 'query.pdb', False)
try:
old_pwd = os.getcwd()
except OSError:
old_pwd = None
os.chdir(self.sandbox_dir)
if verbose: print('simrna::', self.sandbox_dir)
# This is the place why you run SimRNA (self.src_bin)
# you can add options like '-c', '~/tmp/config'
# following flags mean:
# -n 0 = 0 steps of simulation
# -R 0 = set random seed to a constant,
# results should be the same every time
if run_command(
self.src_bin,
[
'-p', self.sandbox_dir + os.sep + 'query.pdb', '-n',
str(numSteps), '-R', '0'
], # 16000
stderr_file=self.sandbox_dir + os.sep + 'output.txt'):
self.log('Run failed', 'error')
# the place where I read the output file (stderr_file) of SimRNA
f = open(self.sandbox_dir + os.sep + 'output.txt')
stderr = f.read()
f.close()
self.log('STDERR:\n' + stderr, 'debug')
if old_pwd:
os.chdir(old_pwd)
return -1
if old_pwd:
os.chdir(old_pwd)
self.log('Run finished')
# parse output
scores = []
f = open(self.sandbox_dir + os.sep + 'output.txt')
lines_temp = f.read().split('\n')
lines = lines_temp
if verbose: print('simrna::', '\n'.join(lines))
# the output is dicombosed into score
total_enrg = [l for l in lines
if 'Total energy of system' in l][-1].split(' ')[-1]
bb = [l for l in lines
if 'Base-Base interactions energy' in l][-1].split(' ')[-1]
ss = [l for l in lines if 'where: short stacking energy' in l
][-1].strip().split(' ')[-1]
bbc = [l for l in lines if 'Base-Backbone interact. energy' in l
][-1].strip().split(' ')[-1]
lge = [l for l in lines
if 'Local geometry energy' in l][-1].strip().split(' ')[-1]
bcp = [l for l in lines
if "bonds (distance) C4'-P" in l][-1].strip().split(' ')[-1]
bpc = [l for l in lines
if "bonds (distance) P-C4'" in l][-1].strip().split(' ')[-1]
fa = [l for l in lines
if "flat angles C4'-P-C4'" in l][-1].strip().split(' ')[-1]
fa2 = [l for l in lines
if "flat angles P-C4'-P" in l][-1].strip().split(' ')[-1]
tor = [l for l in lines
if "tors. eta vs tors. theta" in l][-1].strip().split(' ')[-1]
lim = '' # empty at the moment '' # [l for l in lines if "limit. sphere exceed penalty:" in l][-1].strip().split(' ')[-1]
cc = [l for l in lines
if "current chain energy:" in l][-1].strip().split(' ')[-1]
scores += [numSteps] + [total_enrg] + [bb] + [ss] + [bbc] + [lge] + [
bcp
] + [bpc] + [fa] + [fa2] + [tor] + [lim] + [cc]
f.close()
if verbose: print(' simrna::steps:', numSteps)
#s = '\t'.join(scores)
#if verbose: print ' simrna::scores:', s
#return s
return scores
#!/usr/bin/env python
import sys
from rna_tools.rna_tools_lib import RNAStructure
if __name__ == '__main__':
files = sys.argv[1:]
if not files:
print('rna_pdb_merge_into_one.py test_in/*.pdb')
sys.exit(1)
c = 1
for f in files:
s = RNAStructure(f)
print("MODEL " + str(c))
print(s.get_text(add_end=False))
print('ENDMDL')
c += 1
print('END')
nmdp += l
if verbose: print(nmdp)
with open(mdp_out, 'w') as f:
f.write(nmdp)
def get_parser():
parser = argparse.ArgumentParser(
description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
#parser.add_argument('-', "--", help="", default="")
parser.add_argument("-v", "--verbose",
action="store_true", help="be verbose")
parser.add_argument("file", help="", default="")
return parser
# main
if __name__ == '__main__':
#fn = 'test_data/decoy0165_amb_clx.pdb'
fn = 'test_data/1duq.pdb'
fn = 'test_data/1duq_rpr.pdb'
# format_score_mdp('out.txt', '', '')
# print(open('out.txt').read())
from rna_tools.rna_tools_lib import RNAStructure
r = RNAStructure(fn)
for i in r.get_all_chain_ids():
chain = r.get_chain(i)
nchain = make_rna_gromacs_ready(chain)
print(nchain).strip()
def get_rmsd_to(self,
other_rnamodel,
way="",
triple_mode=False,
save=True):
"""Calc rmsd P-atom based rmsd to other rna model"""
sup = Bio.PDB.Superimposer()
if way == 'backbone+sugar':
self.atoms_for_rmsd = []
for a in self.atoms:
if a.name in "P,OP1,OP2,C5',O5',C4',O4',C3',O3',C2',O2',C1'".split(
','):
self.atoms_for_rmsd.append(a)
if args.debug: print('atoms_for_rmsd', len(self.atoms_for_rmsd))
other_atoms_for_rmsd = []
for a in other_rnamodel.atoms:
if a.name in "P,OP1,OP2,C5',O5',C4',O4',C3',O3',C2',O2',C1'".split(
','):
other_atoms_for_rmsd.append(a)
if args.debug:
print('other_atoms_for_rmsd', len(other_atoms_for_rmsd))
else:
self.atoms_for_rmsd = self.atoms
other_atoms_for_rmsd = other_rnamodel.atoms
if triple_mode:
def chunks(lst, n):
"""Yield successive n-sized chunks from lst.
https://stackoverflow.com/questions/312443/how-do-you-split-a-list-into-evenly-sized-chunks
"""
for i in range(0, len(lst), n):
yield lst[i:i + n]
rmsd_min = 10000 # ugly
import itertools
per = list(itertools.permutations([0, 1, 2]))
lst = list(chunks(other_atoms_for_rmsd, 12))
sup_min = None
for p in per:
patoms = []
for i in p: # p=(1, 2, 3)
patoms.extend(lst[i])
#print(self.atoms_for_rmsd)
## print('patoms')
## for a in patoms:
## print(a, a.get_parent().get_id())
## print('self.atoms_for_rmsd')
## for a in self.atoms_for_rmsd:
## print(a, a.get_parent().get_id())
#sup.set_atoms(patoms, self.atoms_for_rmsd)
sup.set_atoms(self.atoms_for_rmsd, patoms)
rms = round(sup.rms, 3)
rt = None
seq = ''
for a in patoms:
r = a.get_parent()
if r != rt:
rt = r
seq += r.get_resname().strip()
if rms < rmsd_min:
rmsd_min = rms
sup_min = copy.copy(sup)
suffix = seq
p_min = p
seq_min = seq
if args.debug:
print(p, '', [i + 1 for i in p], end=' ')
print(seq, 'seq_min:', seq_min, rms)
index = [0, 0, 0]
index[0] = p_min.index(0)
index[1] = p_min.index(1)
index[2] = p_min.index(2)
# ugly re-set 123 to crazy id ! + 100, so this will
# fill up 1 2 3 for the second for
rs = other_rnamodel.struc[0].get_residues()
for i, r in enumerate(rs):
r.id = (' ', index[i] + 153, ' ') # ugly, some random offset
for i, r in enumerate(other_rnamodel.struc[0].get_residues()):
r.id = (' ', index[i] + 1, ' ')
if args.debug: print(r)
io = Bio.PDB.PDBIO()
sup_min.apply(other_rnamodel.struc.get_atoms())
# if args.debug: print(p_min, [i + 1 for i in p_min])
io.set_structure(other_rnamodel.struc)
fout = other_rnamodel.fpath.replace('.pdb',
'_aligned' + suffix + '.pdb')
# if args.debug: print(fout)
io.save(fout)
# ugly set chain to A
set_chain_for_struc(fout, 'A', save_file_inplace=True)
# and now run this to sort into 1 2 3
r = RNAStructure(fout)
remarks = r.get_remarks_text()
r1 = r.get_res_text('A', 1)
r2 = r.get_res_text('A', 2)
r3 = r.get_res_text('A', 3)
with open(fout, 'w') as f:
f.write(remarks)
f.write(r1)
f.write(r2)
f.write(r3)
r.reload()
r.get_rnapuzzle_ready()
r.write()
return str(rmsd_min) + ',' + seq_min
else:
sup.set_atoms(self.atoms_for_rmsd, other_atoms_for_rmsd)
rms = round(sup.rms, 2)
if save:
## io = Bio.PDB.PDBIO()
## sup.apply(self.struc.get_atoms())
## io.set_structure(self.struc)
## io.save("aligned.pdb")
io = Bio.PDB.PDBIO()
sup.apply(other_rnamodel.struc.get_atoms())
io.set_structure(other_rnamodel.struc)
io.save(
other_rnamodel.fpath.replace('.pdb',
'_' + args.suffix + '.pdb'))
return rms
def get_rmsd_to(self,
other_rnamodel,
way="",
triple_mode=False,
save=True,
tseq=''):
"""Calc rmsd P-atom based rmsd to other rna model
sugar now 10 atoms ;-) """
sup = Bio.PDB.Superimposer()
if way in ['c1', 'backbone+sugar', 'sugar']:
if way == 'c1':
atomslist = ["C1'"] # ,"C2'","O4'"] #, "C2'"]
elif way == 'sugar':
atomslist = "C5',O5',C4',O4',C3',O3',C2',O2',C1'".split(',')
elif way == 'backbone+sugar':
atomslist = "P,OP1,OP2,C5',O5',C4',O4',C3',O3',C2',O2',C1'".split(
',')
self.atoms_for_rmsd = []
for a in self.atoms:
nt = a.get_parent().get_resname().strip()
if nt in ['G', 'A']:
atomslistx = atomslist + ['N9']
if nt in ['C', 'U']:
atomslistx = atomslist + ['N1']
if a.name in atomslistx:
self.atoms_for_rmsd.append(a)
if args.debug: print('atoms_for_rmsd', len(self.atoms_for_rmsd))
other_atoms_for_rmsd = []
for a in other_rnamodel.atoms:
nt = a.get_parent().get_resname().strip()
if nt in ['G', 'A']:
atomslistx = atomslist + ['N9']
if nt in ['C', 'U']:
atomslistx = atomslist + ['N1']
if a.name in atomslistx:
other_atoms_for_rmsd.append(a)
if args.debug:
print('other_atoms_for_rmsd', len(other_atoms_for_rmsd))
elif way == 'c1+Nx':
self.atoms_for_rmsd = []
for a in self.atoms:
nt = a.get_parent().get_resname().strip() # G
if nt in ['G', 'A']:
atomslist = ["C1'", 'N9'] # , 'N1']
if nt in ['C', 'U']:
atomslist = ["C1'", 'N1'] # , 'N1']
if a.name in atomslist:
self.atoms_for_rmsd.append(a)
if args.debug: print('atoms_for_rmsd', len(self.atoms_for_rmsd))
other_atoms_for_rmsd = []
for a in other_rnamodel.atoms:
nt = a.get_parent().get_resname().strip() # G
if nt in ['G', 'A']:
atomslist = ["C1'", 'N9'] # , 'N1']
if nt in ['C', 'U']:
atomslist = ["C1'", 'N1'] # , 'N1']
if a.name in atomslist:
other_atoms_for_rmsd.append(a)
if args.debug:
print('other_atoms_for_rmsd', len(other_atoms_for_rmsd))
else:
self.atoms_for_rmsd = self.atoms
other_atoms_for_rmsd = other_rnamodel.atoms
# calc rmsd #
if not tseq:
tseq = ''
rt = None
for a in self.atoms_for_rmsd:
r = a.get_parent()
if r != rt:
rt = r
tseq += r.get_resname().strip()
if triple_mode:
def chunks(lst, n):
"""Yield successive n-sized chunks from lst.
https://stackoverflow.com/questions/312443/how-do-you-split-a-list-into-evenly-sized-chunks
"""
for i in range(0, len(lst), n):
yield lst[i:i + n]
rmsd_min = 10000 # ugly
import itertools
# ok, for different residues now it's a problem
per = list(
itertools.permutations([0, 1, 2])
) # [(0, 1, 2), (0, 2, 1), (1, 0, 2), (1, 2, 0), (2, 0, 1), (2, 1, 0)]
lst = list(
chunks(other_atoms_for_rmsd,
int(len(other_atoms_for_rmsd) /
3))) # for 1 atom, this will be 1 x 3 [3 residues]
# so so len is 3 atoms so / by 3 to get how many atoms per residue
print(lst)
sup_min = None
seq_min = 'not yet obtained, rmsd rejected!'
p_min = None
rms = -1
for p in per:
patoms = []
for i in p: # p=(1, 2, 3)
patoms.extend(lst[i])
#print(self.atoms_for_rmsd)
## print('patoms')
## for a in patoms:
## print(a, a.get_parent().get_id())
## print('self.atoms_for_rmsd')
## for a in self.atoms_for_rmsd:
## print(a, a.get_parent().get_id())
#sup.set_atoms(patoms, self.atoms_for_rmsd)
rt = None
seq = ''
for a in patoms:
r = a.get_parent()
if r != rt:
rt = r
seq += r.get_resname().strip()
ic(tseq.lower(), seq.lower(), other_rnamodel.fpath)
# dont' even calc rmsd if the curr seq and tseq are not the same
if tseq.lower() == seq.lower(): # only if seq is the same
print(self.atoms_for_rmsd)
print(patoms)
print(len(self.atoms_for_rmsd), len(patoms))
for a, b in zip(self.atoms_for_rmsd, patoms):
print(a,
a.get_parent().id,
a.get_parent().get_resname(),
b.get_parent().id,
b.get_parent().get_resname())
print(len(self.atoms_for_rmsd), len(patoms))
try:
sup.set_atoms(self.atoms_for_rmsd, patoms)
except:
pass
rms = round(sup.rms, 2)
if rms < rmsd_min:
rmsd_min = rms
sup_min = copy.copy(sup)
suffix = seq
p_min = p
seq_min = seq
if args.debug: 'set new rmsd_min', rmsd_min
if args.debug:
print(p, '', [i + 1 for i in p], end=' ')
print(seq, 'seq_min: ' + seq_min, rms)
if p_min: # found target sequence
# what is this? ;-)
index = [0, 0, 0]
index[0] = p_min.index(0)
index[1] = p_min.index(1)
index[2] = p_min.index(2)
# ugly re-set 123 to crazy id ! + 100, so this will
# fill up 1 2 3 for the second for
rs = other_rnamodel.struc[0].get_residues()
for i, r in enumerate(rs):
r.id = (' ', index[i] + 253, ' '
) # ugly, some random offset
for i, r in enumerate(other_rnamodel.struc[0].get_residues()):
r.id = (' ', index[i] + 1, ' ')
if args.debug: print('r', r)
io = Bio.PDB.PDBIO()
sup_min.apply(other_rnamodel.struc.get_atoms())
# if args.debug: print(p_min, [i + 1 for i in p_min])
io.set_structure(other_rnamodel.struc)
args.save_here = True
if args.save_here and save:
folder = os.path.basename(
self.fpath.replace(
'.pdb', '_' + args.folder_prefix + '_aligned'))
# print(f)
try:
os.mkdir(folder)
except:
pass
fout = folder + os.sep + "{:1.2f}".format(
rmsd_min) + '-' + os.path.basename(
other_rnamodel.fpath
) #.replace('.pdb', '-' + str(rms) + '.pdb'))
#_s' + suffix + '.pdb'))
else:
fout = other_rnamodel.fpath.replace(
'.pdb', '_aligned.pdb') #_s' + suffix + '.pdb')
if args.debug: print(fout)
if save:
io.save(fout)
# ugly set chain to A
set_chain_for_struc(fout, 'A', save_file_inplace=True)
# and now run this to sort into 1 2 3
r = RNAStructure(fout)
remarks = r.get_remarks_text()
r1 = r.get_res_text('A', 1)
r2 = r.get_res_text('A', 2)
r3 = r.get_res_text('A', 3)
with open(fout, 'w') as f:
f.write(remarks)
f.write(r1)
f.write(r2)
f.write(r3)
r.reload()
r.get_rnapuzzle_ready()
if rmsd_min < 1: # !!!!!!!!!!!! ugly
r.write()
return str(rmsd_min
) # + ',s' + seq_min + ',' + os.path.basename(fout)
else:
# check if number of the same atoms #
# if not the same then return -1 #
# print(len(self.atoms_for_rmsd), len(other_atoms_for_rmsd))
if len(self.atoms_for_rmsd) != len(other_atoms_for_rmsd):
return -1
sup.set_atoms(self.atoms_for_rmsd, other_atoms_for_rmsd)
rms = round(sup.rms, 2)
if save:
## io = Bio.PDB.PDBIO()
## sup.apply(self.struc.get_atoms())
## io.set_structure(self.struc)
## io.save("aligned.pdb")
io = Bio.PDB.PDBIO()
sup.apply(other_rnamodel.struc.get_atoms())
io.set_structure(other_rnamodel.struc)
args.save_here = True
if args.save_here and save:
f = os.path.basename(self.fpath.replace('.pdb', '_aligned'))
# print(f)
try:
os.mkdir(f)
except:
pass
# fout = f + os.sep + os.path.basename(other_rnamodel.fpath.replace('.pdb', '_aligned_s' + suffix + '.pdb'))
fout = f + os.sep + os.path.basename(
other_rnamodel.fpath) #.replace('.pdb', '_aligned'))
else:
fout = other_rnamodel.fpath.replace('.pdb', '_aligned.pdb')
if save:
io.save(fout)
return rms
if __name__ == '__main__':
# get version
version = os.path.basename(os.path.dirname(os.path.abspath(__file__))), get_version(__file__)
version = version[1].strip()
# get parser and arguments
parser = get_parser()
args = parser.parse_args()
# quick fix for one files vs file-s
if list == type(args.file) and len(args.file) == 1:
args.file = args.file[0]
if args.report:
s = RNAStructure(args.file)
print(s.get_report)
print(s.get_preview())
print(s.get_info_chains())
if args.clean:
s = RNAStructure(args.file)
s.decap_gtp()
s.std_resn()
s.remove_hydrogen()
s.remove_ion()
s.remove_water()
s.renum_atoms()
s.fix_O_in_UC()
s.fix_op_atoms()
# print s.get_preview()
#!/usr/bin/env python
import sys
from rna_tools.rna_tools_lib import RNAStructure
if __name__ == '__main__':
files = sys.argv[1:]
if not files:
print('rna_pdb_merge_into_one.py test_in/*.pdb')
sys.exit(1)
c = 1
for f in files:
s = RNAStructure(f)
print("MODEL " + str(c))
print(s.get_text(add_end=False))
print('ENDMDL')
c += 1
print('END')
description=__doc__,
formatter_class=argparse.RawDescriptionHelpFormatter)
#parser.add_argument('-', "--", help="", default="")
parser.add_argument("-v",
"--verbose",
action="store_true",
help="be verbose")
parser.add_argument("file", help="", default="") # nargs='+')
parser.add_argument("insert", help="", default="") # nargs='+')
parser.add_argument("--output",
help="by default <file>_rpl.pdb",
default="") # nargs='+')
return parser
if __name__ == '__main__':
parser = get_parser()
args = parser.parse_args()
f1 = args.file
f2 = args.insert
r1 = RNAStructure(f1)
r2 = RNAStructure(f2)
t = replace_atoms(f1, f2)
if not args.output:
with open(args.file.replace('.pdb', '_rpl.pdb'), 'w') as f:
f.write(t)