def prody_anm(pdb, **kwargs):
"""Perform ANM calculations for *pdb*.
"""
for key in DEFAULTS:
if not key in kwargs:
kwargs[key] = DEFAULTS[key]
from os.path import isdir, join
outdir = kwargs.get('outdir')
if not isdir(outdir):
raise IOError('{0} is not a valid path'.format(repr(outdir)))
import numpy as np
import prody
LOGGER = prody.LOGGER
selstr = kwargs.get('select')
prefix = kwargs.get('prefix')
cutoff = kwargs.get('cutoff')
gamma = kwargs.get('gamma')
nmodes = kwargs.get('nmodes')
selstr = kwargs.get('select')
model = kwargs.get('model')
pdb = prody.parsePDB(pdb, model=model)
if prefix == '_anm':
prefix = pdb.getTitle() + '_anm'
select = pdb.select(selstr)
if select is None:
LOGGER.warn('Selection {0} did not match any atoms.'
.format(repr(selstr)))
return
LOGGER.info('{0} atoms will be used for ANM calculations.'
.format(len(select)))
anm = prody.ANM(pdb.getTitle())
anm.buildHessian(select, cutoff, gamma)
anm.calcModes(nmodes)
LOGGER.info('Writing numerical output.')
if kwargs.get('outnpz'):
prody.saveModel(anm, join(outdir, prefix))
prody.writeNMD(join(outdir, prefix + '.nmd'), anm, select)
extend = kwargs.get('extend')
if extend:
if extend == 'all':
extended = prody.extendModel(anm, select, pdb)
else:
extended = prody.extendModel(anm, select, select | pdb.bb)
prody.writeNMD(join(outdir, prefix + '_extended_' +
extend + '.nmd'), *extended)
outall = kwargs.get('outall')
delim = kwargs.get('numdelim')
ext = kwargs.get('numext')
format = kwargs.get('numformat')
if outall or kwargs.get('outeig'):
prody.writeArray(join(outdir, prefix + '_evectors'+ext),
anm.getArray(), delimiter=delim, format=format)
prody.writeArray(join(outdir, prefix + '_evalues'+ext),
anm.getEigvals(), delimiter=delim, format=format)
if outall or kwargs.get('outbeta'):
from prody.utilities import openFile
fout = openFile(prefix + '_beta.txt', 'w', folder=outdir)
fout.write('{0[0]:1s} {0[1]:4s} {0[2]:4s} {0[3]:5s} {0[4]:5s}\n'
.format(['C', 'RES', '####', 'Exp.', 'The.']))
for data in zip(select.getChids(), select.getResnames(),
select.getResnums(), select.getBetas(),
prody.calcTempFactors(anm, select)):
fout.write('{0[0]:1s} {0[1]:4s} {0[2]:4d} {0[3]:5.2f} {0[4]:5.2f}\n'
.format(data))
fout.close()
if outall or kwargs.get('outcov'):
prody.writeArray(join(outdir, prefix + '_covariance' + ext),
anm.getCovariance(), delimiter=delim, format=format)
if outall or kwargs.get('outcc') or kwargs.get('outhm'):
cc = prody.calcCrossCorr(anm)
if outall or kwargs.get('outcc'):
prody.writeArray(join(outdir, prefix +
'_cross-correlations' + ext),
cc, delimiter=delim, format=format)
if outall or kwargs.get('outhm'):
prody.writeHeatmap(join(outdir, prefix + '_cross-correlations.hm'),
cc, resnum=select.getResnums(),
xlabel='Residue', ylabel='Residue',
title=anm.getTitle() + ' cross-correlations')
if outall or kwargs.get('hessian'):
prody.writeArray(join(outdir, prefix + '_hessian'+ext),
anm.getHessian(), delimiter=delim, format=format)
if outall or kwargs.get('kirchhoff'):
prody.writeArray(join(outdir, prefix + '_kirchhoff'+ext),
anm.getKirchhoff(), delimiter=delim, format=format)
if outall or kwargs.get('outsf'):
prody.writeArray(join(outdir, prefix + '_sqflucts'+ext),
prody.calcSqFlucts(anm), delimiter=delim,
format=format)
figall = kwargs.get('figall')
cc = kwargs.get('figcc')
sf = kwargs.get('figsf')
bf = kwargs.get('figbeta')
cm = kwargs.get('figcmap')
if figall or cc or sf or bf or cm:
try:
import matplotlib.pyplot as plt
except ImportError:
LOGGER.warning('Matplotlib could not be imported. '
'Figures are not saved.')
else:
prody.SETTINGS['auto_show'] = False
LOGGER.info('Saving graphical output.')
format = kwargs.get('figformat')
width = kwargs.get('figwidth')
height = kwargs.get('figheight')
dpi = kwargs.get('figdpi')
format = format.lower()
if figall or cc:
plt.figure(figsize=(width, height))
prody.showCrossCorr(anm)
plt.savefig(join(outdir, prefix + '_cc.'+format),
dpi=dpi, format=format)
plt.close('all')
if figall or cm:
plt.figure(figsize=(width, height))
prody.showContactMap(anm)
plt.savefig(join(outdir, prefix + '_cm.'+format),
dpi=dpi, format=format)
plt.close('all')
if figall or sf:
plt.figure(figsize=(width, height))
prody.showSqFlucts(anm)
plt.savefig(join(outdir, prefix + '_sf.'+format),
dpi=dpi, format=format)
plt.close('all')
if figall or bf:
plt.figure(figsize=(width, height))
bexp = select.getBetas()
bcal = prody.calcTempFactors(anm, select)
plt.plot(bexp, label='Experimental')
plt.plot(bcal, label=('Theoretical (R={0:.2f})'
.format(np.corrcoef(bcal, bexp)[0,1])))
plt.legend(prop={'size': 10})
plt.xlabel('Node index')
plt.ylabel('Experimental B-factors')
plt.title(pdb.getTitle() + ' B-factors')
plt.savefig(join(outdir, prefix + '_bf.'+format),
dpi=dpi, format=format)
plt.close('all')
def prody_pca(coords, **kwargs):
"""Perform PCA calculations for PDB or DCD format *coords* file.
"""
for key in DEFAULTS:
if not key in kwargs:
kwargs[key] = DEFAULTS[key]
from os.path import isdir, splitext, join
outdir = kwargs.get('outdir')
if not isdir(outdir):
raise IOError('{0} is not a valid path'.format(repr(outdir)))
import prody
LOGGER = prody.LOGGER
prefix = kwargs.get('prefix')
nmodes = kwargs.get('nmodes')
selstr = kwargs.get('select')
ext = splitext(coords)[1].lower()
if ext == '.gz':
ext = splitext(coords[:-3])[1].lower()
if ext == '.dcd':
pdb = kwargs.get('psf') or kwargs.get('pdb')
if pdb:
if splitext(pdb)[1].lower() == '.psf':
pdb = prody.parsePSF(pdb)
else:
pdb = prody.parsePDB(pdb)
dcd = prody.DCDFile(coords)
if prefix == '_pca' or prefix == '_eda':
prefix = dcd.getTitle() + prefix
if len(dcd) < 2:
raise ValueError('DCD file must have multiple frames')
if pdb:
if pdb.numAtoms() == dcd.numAtoms():
select = pdb.select(selstr)
dcd.setAtoms(select)
LOGGER.info('{0} atoms are selected for calculations.'
.format(len(select)))
else:
select = pdb.select(selstr)
if select.numAtoms() != dcd.numAtoms():
raise ValueError('number of selected atoms ({0}) does '
'not match number of atoms in the DCD '
'file ({1})'.format(select.numAtoms(),
dcd.numAtoms()))
if pdb.numCoordsets():
dcd.setCoords(select.getCoords())
else:
select = prody.AtomGroup()
select.setCoords(dcd.getCoords())
pca = prody.PCA(dcd.getTitle())
if len(dcd) > 1000:
pca.buildCovariance(dcd, aligned=kwargs.get('aligned'))
pca.calcModes(nmodes)
ensemble = dcd
else:
ensemble = dcd[:]
if not kwargs.get('aligned'):
ensemble.iterpose()
pca.performSVD(ensemble)
else:
pdb = prody.parsePDB(coords)
if pdb.numCoordsets() < 2:
raise ValueError('PDB file must contain multiple models')
if prefix == '_pca' or prefix == '_eda':
prefix = pdb.getTitle() + prefix
select = pdb.select(selstr)
LOGGER.info('{0} atoms are selected for calculations.'
.format(len(select)))
if select is None:
raise ValueError('selection {0} do not match any atoms'
.format(repr(selstr)))
LOGGER.info('{0} atoms will be used for PCA calculations.'
.format(len(select)))
ensemble = prody.Ensemble(select)
pca = prody.PCA(pdb.getTitle())
if not kwargs.get('aligned'):
ensemble.iterpose()
pca.performSVD(ensemble)
LOGGER.info('Writing numerical output.')
if kwargs.get('outnpz'):
prody.saveModel(pca, join(outdir, prefix))
prody.writeNMD(join(outdir, prefix + '.nmd'), pca[:nmodes], select)
extend = kwargs.get('extend')
if extend:
if pdb:
if extend == 'all':
extended = prody.extendModel(pca[:nmodes], select, pdb)
else:
extended = prody.extendModel(pca[:nmodes], select,
select | pdb.bb)
prody.writeNMD(join(outdir, prefix + '_extended_' +
extend + '.nmd'), *extended)
else:
prody.LOGGER.warn('Model could not be extended, provide a PDB or '
'PSF file.')
outall = kwargs.get('outall')
delim = kwargs.get('numdelim')
ext = kwargs.get('numext')
format = kwargs.get('numformat')
if outall or kwargs.get('outeig'):
prody.writeArray(join(outdir, prefix + '_evectors'+ext),
pca.getArray(), delimiter=delim, format=format)
prody.writeArray(join(outdir, prefix + '_evalues'+ext),
pca.getEigvals(), delimiter=delim, format=format)
if outall or kwargs.get('outcov'):
prody.writeArray(join(outdir, prefix + '_covariance'+ext),
pca.getCovariance(), delimiter=delim, format=format)
if outall or kwargs.get('outcc') or kwargs.get('outhm'):
cc = prody.calcCrossCorr(pca)
if outall or kwargs.get('outcc'):
prody.writeArray(join(outdir, prefix + '_cross-correlations' +
ext), cc, delimiter=delim, format=format)
if outall or kwargs.get('outhm'):
resnums = select.getResnums()
hmargs = {} if resnums is None else {'resnums': resnums}
prody.writeHeatmap(join(outdir, prefix + '_cross-correlations.hm'),
cc, xlabel='Residue', ylabel='Residue',
title=pca.getTitle() + ' cross-correlations',
**hmargs)
if outall or kwargs.get('outsf'):
prody.writeArray(join(outdir, prefix + '_sqfluct'+ext),
prody.calcSqFlucts(pca), delimiter=delim,
format=format)
if outall or kwargs.get('outproj'):
prody.writeArray(join(outdir, prefix + '_proj'+ext),
prody.calcProjection(ensemble, pca), delimiter=delim,
format=format)
figall = kwargs.get('figall')
cc = kwargs.get('figcc')
sf = kwargs.get('figsf')
sp = kwargs.get('figproj')
if figall or cc or sf or sp:
try:
import matplotlib.pyplot as plt
except ImportError:
LOGGER.warning('Matplotlib could not be imported. '
'Figures are not saved.')
else:
prody.SETTINGS['auto_show'] = False
LOGGER.info('Saving graphical output.')
format = kwargs.get('figformat')
width = kwargs.get('figwidth')
height = kwargs.get('figheight')
dpi = kwargs.get('figdpi')
format = format.lower()
if figall or cc:
plt.figure(figsize=(width, height))
prody.showCrossCorr(pca)
plt.savefig(join(outdir, prefix + '_cc.'+format),
dpi=dpi, format=format)
plt.close('all')
if figall or sf:
plt.figure(figsize=(width, height))
prody.showSqFlucts(pca)
plt.savefig(join(outdir, prefix + '_sf.'+format),
dpi=dpi, format=format)
plt.close('all')
if figall or sp:
indices = []
for item in sp.split():
try:
if '-' in item:
item = item.split('-')
if len(item) == 2:
indices.append(list(range(int(item[0])-1,
int(item[1]))))
elif ',' in item:
indices.append([int(i)-1 for i in item.split(',')])
else:
indices.append(int(item)-1)
except:
pass
for index in indices:
plt.figure(figsize=(width, height))
prody.showProjection(ensemble, pca[index])
if isinstance(index, int):
index = [index]
index = [str(i+1) for i in index]
plt.savefig(join(outdir, prefix + '_proj_' +
'_'.join(index) + '.' + format),
dpi=dpi, format=format)
plt.close('all')
def prody_pca(coords, **kwargs):
"""Perform PCA calculations for PDB or DCD format *coords* file.
"""
for key in DEFAULTS:
if not key in kwargs:
kwargs[key] = DEFAULTS[key]
from os.path import isdir, splitext, join
outdir = kwargs.get('outdir')
if not isdir(outdir):
raise IOError('{0} is not a valid path'.format(repr(outdir)))
import prody
LOGGER = prody.LOGGER
prefix = kwargs.get('prefix')
nmodes = kwargs.get('nmodes')
selstr = kwargs.get('select')
quiet = kwargs.pop('quiet', False)
altloc = kwargs.get('altloc')
ext = splitext(coords)[1].lower()
if ext == '.gz':
ext = splitext(coords[:-3])[1].lower()
if ext == '.dcd':
pdb = kwargs.get('psf') or kwargs.get('pdb')
if pdb:
if splitext(pdb)[1].lower() == '.psf':
pdb = prody.parsePSF(pdb)
else:
pdb = prody.parsePDB(pdb, altlocs=altlocs)
dcd = prody.DCDFile(coords)
if prefix == '_pca' or prefix == '_eda':
prefix = dcd.getTitle() + prefix
if len(dcd) < 2:
raise ValueError('DCD file must have multiple frames')
if pdb:
if pdb.numAtoms() == dcd.numAtoms():
select = pdb.select(selstr)
dcd.setAtoms(select)
LOGGER.info('{0} atoms are selected for calculations.'.format(
len(select)))
else:
select = pdb.select(selstr)
if select.numAtoms() != dcd.numAtoms():
raise ValueError('number of selected atoms ({0}) does '
'not match number of atoms in the DCD '
'file ({1})'.format(
select.numAtoms(), dcd.numAtoms()))
if pdb.numCoordsets():
dcd.setCoords(select.getCoords())
else:
select = prody.AtomGroup()
select.setCoords(dcd.getCoords())
pca = prody.PCA(dcd.getTitle())
nproc = kwargs.get('nproc')
if nproc:
try:
from threadpoolctl import threadpool_limits
except ImportError:
raise ImportError(
'Please install threadpoolctl to control threads')
with threadpool_limits(limits=nproc, user_api="blas"):
if len(dcd) > 1000:
pca.buildCovariance(dcd,
aligned=kwargs.get('aligned'),
quiet=quiet)
pca.calcModes(nmodes)
ensemble = dcd
else:
ensemble = dcd[:]
if not kwargs.get('aligned'):
ensemble.iterpose(quiet=quiet)
pca.performSVD(ensemble)
nmodes = pca.numModes()
else:
if len(dcd) > 1000:
pca.buildCovariance(dcd,
aligned=kwargs.get('aligned'),
quiet=quiet)
pca.calcModes(nmodes)
ensemble = dcd
else:
ensemble = dcd[:]
if not kwargs.get('aligned'):
ensemble.iterpose(quiet=quiet)
pca.performSVD(ensemble)
nmodes = pca.numModes()
else:
pdb = prody.parsePDB(coords)
if pdb.numCoordsets() < 2:
raise ValueError('PDB file must contain multiple models')
if prefix == '_pca' or prefix == '_eda':
prefix = pdb.getTitle() + prefix
select = pdb.select(selstr)
LOGGER.info('{0} atoms are selected for calculations.'.format(
len(select)))
if select is None:
raise ValueError('selection {0} do not match any atoms'.format(
repr(selstr)))
LOGGER.info('{0} atoms will be used for PCA calculations.'.format(
len(select)))
ensemble = prody.Ensemble(select)
pca = prody.PCA(pdb.getTitle())
if not kwargs.get('aligned'):
ensemble.iterpose()
nproc = kwargs.get('nproc')
if nproc:
try:
from threadpoolctl import threadpool_limits
except ImportError:
raise ImportError(
'Please install threadpoolctl to control threads')
with threadpool_limits(limits=nproc, user_api="blas"):
pca.performSVD(ensemble)
else:
pca.performSVD(ensemble)
LOGGER.info('Writing numerical output.')
if kwargs.get('outnpz'):
prody.saveModel(pca, join(outdir, prefix))
if kwargs.get('outscipion'):
prody.writeScipionModes(outdir, pca)
prody.writeNMD(join(outdir, prefix + '.nmd'), pca[:nmodes], select)
extend = kwargs.get('extend')
if extend:
if pdb:
if extend == 'all':
extended = prody.extendModel(pca[:nmodes], select, pdb)
else:
extended = prody.extendModel(pca[:nmodes], select,
select | pdb.bb)
prody.writeNMD(
join(outdir, prefix + '_extended_' + extend + '.nmd'),
*extended)
else:
prody.LOGGER.warn('Model could not be extended, provide a PDB or '
'PSF file.')
outall = kwargs.get('outall')
delim = kwargs.get('numdelim')
ext = kwargs.get('numext')
format = kwargs.get('numformat')
if outall or kwargs.get('outeig'):
prody.writeArray(join(outdir, prefix + '_evectors' + ext),
pca.getArray(),
delimiter=delim,
format=format)
prody.writeArray(join(outdir, prefix + '_evalues' + ext),
pca.getEigvals(),
delimiter=delim,
format=format)
if outall or kwargs.get('outcov'):
prody.writeArray(join(outdir, prefix + '_covariance' + ext),
pca.getCovariance(),
delimiter=delim,
format=format)
if outall or kwargs.get('outcc') or kwargs.get('outhm'):
cc = prody.calcCrossCorr(pca)
if outall or kwargs.get('outcc'):
prody.writeArray(join(outdir,
prefix + '_cross-correlations' + ext),
cc,
delimiter=delim,
format=format)
if outall or kwargs.get('outhm'):
resnums = select.getResnums()
hmargs = {} if resnums is None else {'resnums': resnums}
prody.writeHeatmap(join(outdir, prefix + '_cross-correlations.hm'),
cc,
xlabel='Residue',
ylabel='Residue',
title=pca.getTitle() + ' cross-correlations',
**hmargs)
if outall or kwargs.get('outsf'):
prody.writeArray(join(outdir, prefix + '_sqfluct' + ext),
prody.calcSqFlucts(pca),
delimiter=delim,
format=format)
if outall or kwargs.get('outproj'):
prody.writeArray(join(outdir, prefix + '_proj' + ext),
prody.calcProjection(ensemble, pca),
delimiter=delim,
format=format)
figall = kwargs.get('figall')
cc = kwargs.get('figcc')
sf = kwargs.get('figsf')
sp = kwargs.get('figproj')
if figall or cc or sf or sp:
try:
import matplotlib.pyplot as plt
except ImportError:
LOGGER.warning('Matplotlib could not be imported. '
'Figures are not saved.')
else:
prody.SETTINGS['auto_show'] = False
LOGGER.info('Saving graphical output.')
format = kwargs.get('figformat')
width = kwargs.get('figwidth')
height = kwargs.get('figheight')
dpi = kwargs.get('figdpi')
format = format.lower()
if figall or cc:
plt.figure(figsize=(width, height))
prody.showCrossCorr(pca)
plt.savefig(join(outdir, prefix + '_cc.' + format),
dpi=dpi,
format=format)
plt.close('all')
if figall or sf:
plt.figure(figsize=(width, height))
prody.showSqFlucts(pca)
plt.savefig(join(outdir, prefix + '_sf.' + format),
dpi=dpi,
format=format)
plt.close('all')
if figall or sp:
indices = []
for item in sp.split():
try:
if '-' in item:
item = item.split('-')
if len(item) == 2:
indices.append(
list(range(int(item[0]) - 1,
int(item[1]))))
elif ',' in item:
indices.append(
[int(i) - 1 for i in item.split(',')])
else:
indices.append(int(item) - 1)
except:
pass
for index in indices:
plt.figure(figsize=(width, height))
prody.showProjection(ensemble, pca[index])
if isinstance(index, Integral):
index = [index]
index = [str(i + 1) for i in index]
plt.savefig(join(
outdir,
prefix + '_proj_' + '_'.join(index) + '.' + format),
dpi=dpi,
format=format)
plt.close('all')
def evol_coevol(msa, **kwargs):
from numpy import arange
import prody
from prody import parseMSA, buildMutinfoMatrix, showMutinfoMatrix
from prody import applyMutinfoCorr, calcShannonEntropy
from prody import writeArray, LOGGER, applyMutinfoNorm, writeHeatmap
from os.path import splitext
prefix = kwargs.get('prefix')
if prefix is None:
prefix, _ = splitext(msa)
if _.lower() == '.gz':
prefix, _ = splitext(prefix)
prefix += '_mutinfo'
msa = parseMSA(msa)
mutinfo = buildMutinfoMatrix(msa, **kwargs)
numformat = kwargs.get('numformat', '%12g')
heatmap = kwargs.get('heatmap', False)
#writeArray(prefix + '.txt', mutinfo, format=numformat)
if heatmap:
hmargs = {
'xlabel': 'Residue', 'ylabel': 'Residue',
'xorigin': 1, 'xstep': 1,
'residue': arange(msa.numResidues())}
todo = [(None, None)]
norm = kwargs.get('normalization', [])
corr = kwargs.get('correction', [])
if norm is not None:
if 'joint' in norm:
todo.append(('norm', 'joint'))
for which in norm:
if which == 'join': continue
todo.append(('norm', which))
if corr is not None:
for which in corr:
todo.append(('corr', which))
entropy = None
for what, which in todo:
if what is None:
matrix = mutinfo
suffix = ''
tuffix = ' Mutual Information'
elif which == 'joint':
LOGGER.info('Applying {0} normalization.'.format(repr(which)))
matrix = buildMutinfoMatrix(msa, norm=True, **kwargs)
suffix = '_norm_joint'
tuffix = ' MI - Normalization: ' + which
elif what == 'norm':
LOGGER.info('Applying {0} normalization.'.format(repr(which)))
if entropy is None:
entropy = calcShannonEntropy(msa, **kwargs)
matrix = applyMutinfoNorm(mutinfo, entropy, norm=which)
suffix = '_norm_' + which
tuffix = ' MI - Normalization: ' + which
else:
LOGGER.info('Applying {0} correction.'.format(repr(which)))
matrix = applyMutinfoCorr(mutinfo, which)
suffix = '_corr_' + which
tuffix = ' MI - Correction: ' + which
writeArray(prefix + suffix + '.txt',
matrix, format=kwargs.get('numformat', '%12g'))
if heatmap:
writeHeatmap(prefix + suffix + '.hm', matrix,
title = msa.getTitle() + tuffix, **hmargs)
if kwargs.get('figcoevol'):
try:
import matplotlib.pyplot as plt
except ImportError:
LOGGER.warn('Matplotlib could not be imported, '
'figures are not saved.')
else:
cmin = kwargs.get('cmin', matrix.min())
cmax = kwargs.get('cmax', matrix.max())
prody.SETTINGS['auto_show'] = False
width = kwargs.get('figwidth', 8)
height = kwargs.get('figheight', 6)
xlabel = kwargs.get('xlabel')
title = kwargs.get('title')
figure = plt.figure(figsize=(width, height))
show = showMutinfoMatrix(matrix, msa=msa, clim=(cmin, cmax),
xlabel=xlabel, title=title)
format = kwargs.get('figformat', 'pdf')
figure.savefig(prefix + suffix + '.' + format, format=format,
dpi=kwargs.get('figdpi', 300))
def prody_anm(pdb, **kwargs):
"""Perform ANM calculations for *pdb*.
"""
for key in DEFAULTS:
if not key in kwargs:
kwargs[key] = DEFAULTS[key]
from os.path import isdir, join
outdir = kwargs.get('outdir')
if not isdir(outdir):
raise IOError('{0} is not a valid path'.format(repr(outdir)))
import numpy as np
import prody
LOGGER = prody.LOGGER
selstr = kwargs.get('select')
prefix = kwargs.get('prefix')
cutoff = kwargs.get('cutoff')
gamma = kwargs.get('gamma')
nmodes = kwargs.get('nmodes')
selstr = kwargs.get('select')
model = kwargs.get('model')
pdb = prody.parsePDB(pdb, model=model)
if prefix == '_anm':
prefix = pdb.getTitle() + '_anm'
select = pdb.select(selstr)
if select is None:
LOGGER.warn('Selection {0} did not match any atoms.'.format(
repr(selstr)))
return
LOGGER.info('{0} atoms will be used for ANM calculations.'.format(
len(select)))
anm = prody.ANM(pdb.getTitle())
anm.buildHessian(select, cutoff, gamma)
anm.calcModes(nmodes)
LOGGER.info('Writing numerical output.')
if kwargs.get('outnpz'):
prody.saveModel(anm, join(outdir, prefix))
prody.writeNMD(join(outdir, prefix + '.nmd'), anm, select)
extend = kwargs.get('extend')
if extend:
if extend == 'all':
extended = prody.extendModel(anm, select, pdb)
else:
extended = prody.extendModel(anm, select, select | pdb.bb)
prody.writeNMD(join(outdir, prefix + '_extended_' + extend + '.nmd'),
*extended)
outall = kwargs.get('outall')
delim = kwargs.get('numdelim')
ext = kwargs.get('numext')
format = kwargs.get('numformat')
if outall or kwargs.get('outeig'):
prody.writeArray(join(outdir, prefix + '_evectors' + ext),
anm.getArray(),
delimiter=delim,
format=format)
prody.writeArray(join(outdir, prefix + '_evalues' + ext),
anm.getEigvals(),
delimiter=delim,
format=format)
if outall or kwargs.get('outbeta'):
from prody.utilities import openFile
fout = openFile(prefix + '_beta.txt', 'w', folder=outdir)
fout.write(
'{0[0]:1s} {0[1]:4s} {0[2]:4s} {0[3]:5s} {0[4]:5s}\n'.format(
['C', 'RES', '####', 'Exp.', 'The.']))
for data in zip(select.getChids(), select.getResnames(),
select.getResnums(), select.getBetas(),
prody.calcTempFactors(anm, select)):
fout.write(
'{0[0]:1s} {0[1]:4s} {0[2]:4d} {0[3]:5.2f} {0[4]:5.2f}\n'.
format(data))
fout.close()
if outall or kwargs.get('outcov'):
prody.writeArray(join(outdir, prefix + '_covariance' + ext),
anm.getCovariance(),
delimiter=delim,
format=format)
if outall or kwargs.get('outcc') or kwargs.get('outhm'):
cc = prody.calcCrossCorr(anm)
if outall or kwargs.get('outcc'):
prody.writeArray(join(outdir,
prefix + '_cross-correlations' + ext),
cc,
delimiter=delim,
format=format)
if outall or kwargs.get('outhm'):
prody.writeHeatmap(join(outdir, prefix + '_cross-correlations.hm'),
cc,
resnum=select.getResnums(),
xlabel='Residue',
ylabel='Residue',
title=anm.getTitle() + ' cross-correlations')
if outall or kwargs.get('hessian'):
prody.writeArray(join(outdir, prefix + '_hessian' + ext),
anm.getHessian(),
delimiter=delim,
format=format)
if outall or kwargs.get('kirchhoff'):
prody.writeArray(join(outdir, prefix + '_kirchhoff' + ext),
anm.getKirchhoff(),
delimiter=delim,
format=format)
if outall or kwargs.get('outsf'):
prody.writeArray(join(outdir, prefix + '_sqflucts' + ext),
prody.calcSqFlucts(anm),
delimiter=delim,
format=format)
figall = kwargs.get('figall')
cc = kwargs.get('figcc')
sf = kwargs.get('figsf')
bf = kwargs.get('figbeta')
cm = kwargs.get('figcmap')
if figall or cc or sf or bf or cm:
try:
import matplotlib.pyplot as plt
except ImportError:
LOGGER.warning('Matplotlib could not be imported. '
'Figures are not saved.')
else:
prody.SETTINGS['auto_show'] = False
LOGGER.info('Saving graphical output.')
format = kwargs.get('figformat')
width = kwargs.get('figwidth')
height = kwargs.get('figheight')
dpi = kwargs.get('figdpi')
format = format.lower()
if figall or cc:
plt.figure(figsize=(width, height))
prody.showCrossCorr(anm)
plt.savefig(join(outdir, prefix + '_cc.' + format),
dpi=dpi,
format=format)
plt.close('all')
if figall or cm:
plt.figure(figsize=(width, height))
prody.showContactMap(anm)
plt.savefig(join(outdir, prefix + '_cm.' + format),
dpi=dpi,
format=format)
plt.close('all')
if figall or sf:
plt.figure(figsize=(width, height))
prody.showSqFlucts(anm)
plt.savefig(join(outdir, prefix + '_sf.' + format),
dpi=dpi,
format=format)
plt.close('all')
if figall or bf:
plt.figure(figsize=(width, height))
bexp = select.getBetas()
bcal = prody.calcTempFactors(anm, select)
plt.plot(bexp, label='Experimental')
plt.plot(bcal,
label=('Theoretical (R={0:.2f})'.format(
np.corrcoef(bcal, bexp)[0, 1])))
plt.legend(prop={'size': 10})
plt.xlabel('Node index')
plt.ylabel('Experimental B-factors')
plt.title(pdb.getTitle() + ' B-factors')
plt.savefig(join(outdir, prefix + '_bf.' + format),
dpi=dpi,
format=format)
plt.close('all')
def prody_gnm(pdb, **kwargs):
"""Perform GNM calculations for *pdb*.
"""
for key in DEFAULTS:
if not key in kwargs:
kwargs[key] = DEFAULTS[key]
from os.path import isdir, splitext, join
outdir = kwargs.get("outdir")
if not isdir(outdir):
raise IOError("{0} is not a valid path".format(repr(outdir)))
import numpy as np
import prody
LOGGER = prody.LOGGER
selstr = kwargs.get("select")
prefix = kwargs.get("prefix")
cutoff = kwargs.get("cutoff")
gamma = kwargs.get("gamma")
nmodes = kwargs.get("nmodes")
selstr = kwargs.get("select")
model = kwargs.get("model")
pdb = prody.parsePDB(pdb, model=model)
if prefix == "_gnm":
prefix = pdb.getTitle() + "_gnm"
select = pdb.select(selstr)
if select is None:
raise ValueError("selection {0} do not match any atoms".format(repr(selstr)))
LOGGER.info("{0} atoms will be used for GNM calculations.".format(len(select)))
gnm = prody.GNM(pdb.getTitle())
gnm.buildKirchhoff(select, cutoff, gamma)
gnm.calcModes(nmodes)
LOGGER.info("Writing numerical output.")
if kwargs.get("outnpz"):
prody.saveModel(gnm, join(outdir, prefix))
prody.writeNMD(join(outdir, prefix + ".nmd"), gnm, select)
extend = kwargs.get("extend")
if extend:
if extend == "all":
extended = prody.extendModel(gnm, select, pdb)
else:
extended = prody.extendModel(gnm, select, select | pdb.bb)
prody.writeNMD(join(outdir, prefix + "_extended_" + extend + ".nmd"), *extended)
outall = kwargs.get("outall")
delim = kwargs.get("numdelim")
ext = kwargs.get("numext")
format = kwargs.get("numformat")
if outall or kwargs.get("outeig"):
prody.writeArray(join(outdir, prefix + "_evectors" + ext), gnm.getArray(), delimiter=delim, format=format)
prody.writeArray(join(outdir, prefix + "_evalues" + ext), gnm.getEigvals(), delimiter=delim, format=format)
if outall or kwargs.get("outbeta"):
from prody.utilities import openFile
fout = openFile(prefix + "_beta.txt", "w", folder=outdir)
fout.write("{0[0]:1s} {0[1]:4s} {0[2]:4s} {0[3]:5s} {0[4]:5s}\n".format(["C", "RES", "####", "Exp.", "The."]))
for data in zip(
select.getChids(),
select.getResnames(),
select.getResnums(),
select.getBetas(),
prody.calcTempFactors(gnm, select),
):
fout.write("{0[0]:1s} {0[1]:4s} {0[2]:4d} {0[3]:5.2f} {0[4]:5.2f}\n".format(data))
fout.close()
if outall or kwargs.get("outcov"):
prody.writeArray(
join(outdir, prefix + "_covariance" + ext), gnm.getCovariance(), delimiter=delim, format=format
)
if outall or kwargs.get("outcc") or kwargs.get("outhm"):
cc = prody.calcCrossCorr(gnm)
if outall or kwargs.get("outcc"):
prody.writeArray(join(outdir, prefix + "_cross-correlations" + ext), cc, delimiter=delim, format=format)
if outall or kwargs.get("outhm"):
prody.writeHeatmap(
join(outdir, prefix + "_cross-correlations.hm"),
cc,
resnum=select.getResnums(),
xlabel="Residue",
ylabel="Residue",
title=gnm.getTitle() + " cross-correlations",
)
if outall or kwargs.get("kirchhoff"):
prody.writeArray(join(outdir, prefix + "_kirchhoff" + ext), gnm.getKirchhoff(), delimiter=delim, format=format)
if outall or kwargs.get("outsf"):
prody.writeArray(
join(outdir, prefix + "_sqfluct" + ext), prody.calcSqFlucts(gnm), delimiter=delim, format=format
)
figall = kwargs.get("figall")
cc = kwargs.get("figcc")
sf = kwargs.get("figsf")
bf = kwargs.get("figbeta")
cm = kwargs.get("figcmap")
modes = kwargs.get("figmode")
if figall or cc or sf or bf or cm or modes:
try:
import matplotlib.pyplot as plt
except ImportError:
LOGGER.warning("Matplotlib could not be imported. " "Figures are not saved.")
else:
prody.SETTINGS["auto_show"] = False
LOGGER.info("Saving graphical output.")
format = kwargs.get("figformat")
width = kwargs.get("figwidth")
height = kwargs.get("figheight")
dpi = kwargs.get("figdpi")
format = format.lower()
if figall or cc:
plt.figure(figsize=(width, height))
prody.showCrossCorr(gnm)
plt.savefig(join(outdir, prefix + "_cc." + format), dpi=dpi, format=format)
plt.close("all")
if figall or cm:
plt.figure(figsize=(width, height))
prody.showContactMap(gnm)
plt.savefig(join(outdir, prefix + "_cm." + format), dpi=dpi, format=format)
plt.close("all")
if figall or sf:
plt.figure(figsize=(width, height))
prody.showSqFlucts(gnm)
plt.savefig(join(outdir, prefix + "_sf." + format), dpi=dpi, format=format)
plt.close("all")
if figall or bf:
plt.figure(figsize=(width, height))
bexp = select.getBetas()
bcal = prody.calcTempFactors(gnm, select)
plt.plot(bexp, label="Experimental")
plt.plot(bcal, label=("Theoretical (corr coef = {0:.2f})".format(np.corrcoef(bcal, bexp)[0, 1])))
plt.legend(prop={"size": 10})
plt.xlabel("Node index")
plt.ylabel("Experimental B-factors")
plt.title(pdb.getTitle() + " B-factors")
plt.savefig(join(outdir, prefix + "_bf." + format), dpi=dpi, format=format)
plt.close("all")
if modes:
indices = []
items = modes.split()
items = sum([item.split(",") for item in items], [])
for item in items:
try:
item = item.split("-")
if len(item) == 1:
indices.append(int(item[0]) - 1)
elif len(item) == 2:
indices.extend(range(int(item[0]) - 1, int(item[1])))
except:
pass
for index in indices:
try:
mode = gnm[index]
except:
pass
else:
plt.figure(figsize=(width, height))
prody.showMode(mode)
plt.grid()
plt.savefig(
join(outdir, prefix + "_mode_" + str(mode.getIndex() + 1) + "." + format),
dpi=dpi,
format=format,
)
plt.close("all")
def prody_gnm(pdb, **kwargs):
"""Perform GNM calculations for *pdb*.
"""
for key in DEFAULTS:
if not key in kwargs:
kwargs[key] = DEFAULTS[key]
from os.path import isdir, splitext, join
outdir = kwargs.get('outdir')
if not isdir(outdir):
raise IOError('{0} is not a valid path'.format(repr(outdir)))
import numpy as np
import prody
LOGGER = prody.LOGGER
selstr = kwargs.get('select')
prefix = kwargs.get('prefix')
cutoff = kwargs.get('cutoff')
gamma = kwargs.get('gamma')
nmodes = kwargs.get('nmodes')
selstr = kwargs.get('select')
model = kwargs.get('model')
altloc = kwargs.get('altloc')
zeros = kwargs.get('zeros')
pdb = prody.parsePDB(pdb, model=model, altloc=altloc)
if prefix == '_gnm':
prefix = pdb.getTitle() + '_gnm'
select = pdb.select(selstr)
if select is None:
raise ValueError('selection {0} do not match any atoms'.format(
repr(selstr)))
LOGGER.info('{0} atoms will be used for GNM calculations.'.format(
len(select)))
gnm = prody.GNM(pdb.getTitle())
nproc = kwargs.get('nproc')
if nproc:
try:
from threadpoolctl import threadpool_limits
except ImportError:
raise ImportError(
'Please install threadpoolctl to control threads')
with threadpool_limits(limits=nproc, user_api="blas"):
gnm.buildKirchhoff(select, cutoff, gamma)
gnm.calcModes(nmodes, zeros=zeros)
else:
gnm.buildKirchhoff(select, cutoff, gamma)
gnm.calcModes(nmodes, zeros=zeros)
LOGGER.info('Writing numerical output.')
if kwargs.get('outnpz'):
prody.saveModel(gnm, join(outdir, prefix))
if kwargs.get('outscipion'):
prody.writeScipionModes(outdir, gnm)
prody.writeNMD(join(outdir, prefix + '.nmd'), gnm, select)
extend = kwargs.get('extend')
if extend:
if extend == 'all':
extended = prody.extendModel(gnm, select, pdb)
else:
extended = prody.extendModel(gnm, select, select | pdb.bb)
prody.writeNMD(join(outdir, prefix + '_extended_' + extend + '.nmd'),
*extended)
outall = kwargs.get('outall')
delim = kwargs.get('numdelim')
ext = kwargs.get('numext')
format = kwargs.get('numformat')
if outall or kwargs.get('outeig'):
prody.writeArray(join(outdir, prefix + '_evectors' + ext),
gnm.getArray(),
delimiter=delim,
format=format)
prody.writeArray(join(outdir, prefix + '_evalues' + ext),
gnm.getEigvals(),
delimiter=delim,
format=format)
if outall or kwargs.get('outbeta'):
from prody.utilities import openFile
fout = openFile(prefix + '_beta' + ext, 'w', folder=outdir)
fout.write(
'{0[0]:1s} {0[1]:4s} {0[2]:4s} {0[3]:5s} {0[4]:5s}\n'.format(
['C', 'RES', '####', 'Exp.', 'The.']))
for data in zip(select.getChids(), select.getResnames(),
select.getResnums(), select.getBetas(),
prody.calcTempFactors(gnm, select)):
fout.write(
'{0[0]:1s} {0[1]:4s} {0[2]:4d} {0[3]:5.2f} {0[4]:5.2f}\n'.
format(data))
fout.close()
if outall or kwargs.get('outcov'):
prody.writeArray(join(outdir, prefix + '_covariance' + ext),
gnm.getCovariance(),
delimiter=delim,
format=format)
if outall or kwargs.get('outcc') or kwargs.get('outhm'):
cc = prody.calcCrossCorr(gnm)
if outall or kwargs.get('outcc'):
prody.writeArray(join(outdir,
prefix + '_cross-correlations' + ext),
cc,
delimiter=delim,
format=format)
if outall or kwargs.get('outhm'):
prody.writeHeatmap(join(outdir, prefix + '_cross-correlations.hm'),
cc,
resnum=select.getResnums(),
xlabel='Residue',
ylabel='Residue',
title=gnm.getTitle() + ' cross-correlations')
if outall or kwargs.get('kirchhoff'):
prody.writeArray(join(outdir, prefix + '_kirchhoff' + ext),
gnm.getKirchhoff(),
delimiter=delim,
format=format)
if outall or kwargs.get('outsf'):
prody.writeArray(join(outdir, prefix + '_sqfluct' + ext),
prody.calcSqFlucts(gnm),
delimiter=delim,
format=format)
figall = kwargs.get('figall')
cc = kwargs.get('figcc')
sf = kwargs.get('figsf')
bf = kwargs.get('figbeta')
cm = kwargs.get('figcmap')
modes = kwargs.get('figmode')
if figall or cc or sf or bf or cm or modes:
try:
import matplotlib.pyplot as plt
except ImportError:
LOGGER.warning('Matplotlib could not be imported. '
'Figures are not saved.')
else:
prody.SETTINGS['auto_show'] = False
LOGGER.info('Saving graphical output.')
format = kwargs.get('figformat')
width = kwargs.get('figwidth')
height = kwargs.get('figheight')
dpi = kwargs.get('figdpi')
format = format.lower()
if figall or cc:
plt.figure(figsize=(width, height))
prody.showCrossCorr(gnm)
plt.savefig(join(outdir, prefix + '_cc.' + format),
dpi=dpi,
format=format)
plt.close('all')
if figall or cm:
plt.figure(figsize=(width, height))
prody.showContactMap(gnm)
plt.savefig(join(outdir, prefix + '_cm.' + format),
dpi=dpi,
format=format)
plt.close('all')
if figall or sf:
plt.figure(figsize=(width, height))
prody.showSqFlucts(gnm)
plt.savefig(join(outdir, prefix + '_sf.' + format),
dpi=dpi,
format=format)
plt.close('all')
if figall or bf:
plt.figure(figsize=(width, height))
bexp = select.getBetas()
bcal = prody.calcTempFactors(gnm, select)
plt.plot(bexp, label='Experimental')
plt.plot(bcal,
label=('Theoretical (corr coef = {0:.2f})'.format(
np.corrcoef(bcal, bexp)[0, 1])))
plt.legend(prop={'size': 10})
plt.xlabel('Node index')
plt.ylabel('Experimental B-factors')
plt.title(pdb.getTitle() + ' B-factors')
plt.savefig(join(outdir, prefix + '_bf.' + format),
dpi=dpi,
format=format)
plt.close('all')
if modes:
indices = []
items = modes.split()
items = sum([item.split(',') for item in items], [])
for item in items:
try:
item = item.split('-')
if len(item) == 1:
indices.append(int(item[0]) - 1)
elif len(item) == 2:
indices.extend(
list(range(int(item[0]) - 1, int(item[1]))))
except:
pass
for index in indices:
try:
mode = gnm[index]
except:
pass
else:
plt.figure(figsize=(width, height))
prody.showMode(mode)
plt.grid()
plt.savefig(join(
outdir, prefix + '_mode_' +
str(mode.getIndex() + 1) + '.' + format),
dpi=dpi,
format=format)
plt.close('all')