def prody_align(opt):
"""Align models in a PDB file or a PDB file onto others."""
import prody
LOGGER = prody.LOGGER
args = opt.pdb
if len(args) == 1:
pdb = args[0]
LOGGER.info('Aligning multiple models in: ' + pdb)
selstr, prefix, model = opt.select, opt.prefix, opt.model
pdb = prody.parsePDB(pdb)
pdbselect = pdb.select(selstr)
if pdbselect is None:
opt.subparser.error('Selection {0:s} do not match any atoms.'
.format(repr(selstr)))
LOGGER.info('{0:d} atoms will be used for alignment.'
.format(len(pdbselect)))
pdbselect.setACSIndex(model-1)
prody.printRMSD(pdbselect, msg='Before alignment ')
prody.alignCoordsets(pdbselect)
prody.printRMSD(pdbselect, msg='After alignment ')
if prefix == '':
prefix = pdb.getTitle() + '_aligned'
outfn = prefix + '.pdb'
LOGGER.info('Writing file: ' + outfn)
prody.writePDB(outfn, pdb)
else:
reffn = args.pop(0)
seqid=opt.seqid
overlap=opt.overlap
LOGGER.info('Aligning structures onto: ' + reffn)
ref = prody.parsePDB(reffn)
for arg in args:
if arg == reffn:
continue
if '_aligned.pdb' in arg:
continue
pdb = prody.parsePDB(arg)
result = prody.matchAlign(pdb, ref, seqid=seqid, overlap=overlap,
tarsel=opt.select, allcsets=True,
cslabel='Model', csincr=1)
if result:
outfn = pdb.getTitle() + '_aligned.pdb'
LOGGER.info('Writing file: ' + outfn)
prody.writePDB(outfn, pdb)
else:
LOGGER.warning('Failed to align ' + arg)
def prody_align(*pdbs, **kwargs):
"""Align models in a PDB file or multiple structures in separate PDB files.
By default, protein chains will be matched based on selected atoms and
alignment will be performed based on matching residues. If non-protein
atoms are selected and selected atoms match in multiple structures,
they will be used for alignment.
:arg pdbs: PDB identifier(s) or filename(s)
:arg select: atom selection string, default is :term:`calpha`,
see :ref:`selections`
:arg model: for NMR files, reference model index, default is ``1``
:arg seqid: percent sequence identity, default is ``90``
:arg overlap: percent sequence overlap, default is ``90``
:arg prefix: prefix for output file, default is PDB filename
:arg suffix: output filename suffix, default is :file:`_aligned`"""
from numpy import all
from prody import LOGGER, writePDB, parsePDB
from prody import alignCoordsets, printRMSD, matchAlign, superpose
selstr = kwargs.get('select', 'calpha')
suffix = kwargs.get('suffix', '_aligned')
if len(pdbs) == 1:
pdb = pdbs[0]
LOGGER.info('Aligning multiple models in: ' + pdb)
prefix = kwargs.get('prefix')
model = kwargs.get('model')
pdb = parsePDB(pdb)
pdbselect = pdb.select(selstr)
if pdbselect is None:
subparser = kwargs.get('subparser')
if subparser:
subparser.error('Selection {0} do not match any atoms.'.format(
repr(selstr)))
else:
raise ValueError('select does not match any atoms')
LOGGER.info('{0} atoms will be used for alignment.'.format(
len(pdbselect)))
pdbselect.setACSIndex(model - 1)
printRMSD(pdbselect, msg='Before alignment ')
alignCoordsets(pdbselect)
printRMSD(pdbselect, msg='After alignment ')
outfn = (prefix or pdb.getTitle()) + suffix + '.pdb'
LOGGER.info('Writing file: ' + outfn)
writePDB(outfn, pdb)
else:
pdbs = list(pdbs)
reffn = pdbs.pop(0)
seqid = kwargs.get('seqid')
overlap = kwargs.get('overlap')
LOGGER.info('Aligning structures onto: ' + reffn)
ref = parsePDB(reffn)
ref_sel = ref.select(selstr)
if ref_sel:
LOGGER.info('Selection {0} matched {1} atoms.'.format(
repr(selstr), len(ref_sel)))
else:
raise ValueError('selection {0} did not match any atoms'.format(
repr(selstr)))
match = True
if ref_sel.numAtoms('ca') < 2:
match = False
for arg in pdbs:
if arg == reffn:
continue
#if '_aligned.pdb' in arg:
# continue
LOGGER.info('Evaluating structure: ' + arg)
pdb = parsePDB(arg)
if match:
result = matchAlign(pdb,
ref,
seqid=seqid,
overlap=overlap,
tarsel=selstr,
allcsets=True,
cslabel='Model',
csincr=1)
if result:
outfn = pdb.getTitle() + suffix + '.pdb'
LOGGER.info('Writing file: ' + outfn)
writePDB(outfn, pdb)
continue
pdb_sel = pdb.select(selstr)
LOGGER.info('Selection {0} matched {1} atoms.'.format(
repr(selstr), len(pdb_sel)))
if (len(pdb_sel) == len(ref_sel)
and all(pdb_sel.getNames() == ref_sel.getNames())):
printRMSD(ref_sel, pdb_sel, msg='Before alignment ')
superpose(pdb_sel, ref_sel)
printRMSD(ref_sel, pdb_sel, msg='After alignment ')
outfn = pdb.getTitle() + suffix + '.pdb'
LOGGER.info('Writing file: ' + outfn)
writePDB(outfn, pdb)
else:
LOGGER.warn('Failed to align structure ' + arg + '.')
def prody_align(*pdbs, **kwargs):
"""Align models in a PDB file or multiple structures in separate PDB files.
By default, protein chains will be matched based on selected atoms and
alignment will be performed based on matching residues. If non-protein
atoms are selected and selected atoms match in multiple structures,
they will be used for alignment.
:arg pdbs: PDB identifier(s) or filename(s)
:arg select: atom selection string, default is :term:`calpha`,
see :ref:`selections`
:arg model: for NMR files, reference model index, default is ``1``
:arg seqid: percent sequence identity, default is ``90``
:arg overlap: percent sequence overlap, default is ``90``
:arg prefix: prefix for output file, default is PDB filename
:arg suffix: output filename suffix, default is :file:`_aligned`"""
from numpy import all
from prody import LOGGER, writePDB, parsePDB
from prody import alignCoordsets, printRMSD, matchAlign, superpose
selstr = kwargs.get('select', 'calpha')
suffix = kwargs.get('suffix', '_aligned')
if len(pdbs) == 1:
pdb = pdbs[0]
LOGGER.info('Aligning multiple models in: ' + pdb)
prefix = kwargs.get('prefix')
model = kwargs.get('model')
pdb = parsePDB(pdb)
pdbselect = pdb.select(selstr)
if pdbselect is None:
subparser = kwargs.get('subparser')
if subparser:
subparser.error('Selection {0} do not match any atoms.'
.format(repr(selstr)))
else:
raise ValueError('select does not match any atoms')
LOGGER.info('{0} atoms will be used for alignment.'
.format(len(pdbselect)))
pdbselect.setACSIndex(model-1)
printRMSD(pdbselect, msg='Before alignment ')
alignCoordsets(pdbselect)
printRMSD(pdbselect, msg='After alignment ')
outfn = (prefix or pdb.getTitle()) + suffix + '.pdb'
LOGGER.info('Writing file: ' + outfn)
writePDB(outfn, pdb)
else:
pdbs = list(pdbs)
reffn = pdbs.pop(0)
seqid = kwargs.get('seqid')
overlap = kwargs.get('overlap')
LOGGER.info('Aligning structures onto: ' + reffn)
ref = parsePDB(reffn)
ref_sel = ref.select(selstr)
if ref_sel:
LOGGER.info('Selection {0} matched {1} atoms.'
.format(repr(selstr), len(ref_sel)))
else:
raise ValueError('selection {0} did not match any atoms'
.format(repr(selstr)))
match = True
if ref_sel.numAtoms('ca') < 2:
match = False
for arg in pdbs:
if arg == reffn:
continue
#if '_aligned.pdb' in arg:
# continue
LOGGER.info('Evaluating structure: ' + arg)
pdb = parsePDB(arg)
if match:
result = matchAlign(pdb, ref, seqid=seqid, overlap=overlap,
tarsel=selstr, allcsets=True,
cslabel='Model', csincr=1)
if result:
outfn = pdb.getTitle() + suffix + '.pdb'
LOGGER.info('Writing file: ' + outfn)
writePDB(outfn, pdb)
continue
pdb_sel = pdb.select(selstr)
LOGGER.info('Selection {0} matched {1} atoms.'
.format(repr(selstr), len(pdb_sel)))
if (len(pdb_sel) == len(ref_sel) and
all(pdb_sel.getNames() == ref_sel.getNames())):
printRMSD(ref_sel, pdb_sel, msg='Before alignment ')
superpose(pdb_sel, ref_sel)
printRMSD(ref_sel, pdb_sel, msg='After alignment ')
outfn = pdb.getTitle() + suffix + '.pdb'
LOGGER.info('Writing file: ' + outfn)
writePDB(outfn, pdb)
else:
LOGGER.warn('Failed to align structure ' + arg + '.')