def evol_conserv(msa, **kwargs):
import prody
from prody import parseMSA, calcShannonEntropy, showShannonEntropy
from prody import writeArray
from os.path import splitext
prefix = kwargs.get('prefix')
if prefix is None:
prefix, _ = splitext(msa)
if _.lower() == '.gz':
prefix, _ = splitext(prefix)
prefix += '_conserv'
msa = parseMSA(msa)
entropy = calcShannonEntropy(msa, **kwargs)
writeArray(prefix + '.txt',
entropy, format=kwargs.get('numformat', '%12g'))
if kwargs.get('figent'):
try:
import matplotlib.pyplot as plt
except ImportError:
LOGGER.warn('Matplotlib could not be imported, '
'figures are not saved.')
else:
prody.SETTINGS['auto_show'] = False
width = kwargs.get('figwidth', 8)
height = kwargs.get('figheight', 6)
figargs = kwargs.get('figargs', ())
figure = plt.figure(figsize=(width, height))
show = showShannonEntropy(entropy, msa=msa, *figargs)
format = kwargs.get('figformat', 'pdf')
figure.savefig(prefix + '.' + format, format=format,
dpi=kwargs.get('figdpi', 300))
def evol_occupancy(msa, **kwargs):
from numpy import arange
import prody
from prody import parseMSA, calcMSAOccupancy, showMSAOccupancy, writeArray
from os.path import splitext
prefix = kwargs.get('prefix')
if prefix is None:
prefix, _ = splitext(msa)
if _.lower() == '.gz':
prefix, _ = splitext(prefix)
prefix += '_occupancy'
msa = parseMSA(msa)
numformat = kwargs.get('numformat', '%12g')
occupancy, suffix = [], []
occaxis = kwargs.get('occaxis', 'row')
if occaxis == 'both':
suffix = ['_row', '_col']
occupancy.append(calcMSAOccupancy(msa, occ='row'))
occupancy.append(calcMSAOccupancy(msa, occ='col'))
else:
suffix = '_' + occaxis
occupancy.append(calcMSAOccupancy(msa, occ=occaxis))
for i, occ in enumerate(occupancy):
writeArray((prefix + suffix[i] + '.txt'), occ, format=numformat)
for i, occ in enumerate(occupancy):
if kwargs.get('figocc'):
try:
import matplotlib.pyplot as plt
except ImportError:
LOGGER.warn('Matplotlib could not be imported, '
'figures are not saved.')
else:
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))
label = kwargs.get('label')
show = showMSAOccupancy(msa=msa,
occ=occ,
label=label,
xlabel=xlabel,
title=title)
format = kwargs.get('figformat', 'pdf')
figure.savefig(prefix + suffix[i] + '.' + format,
format=format,
dpi=kwargs.get('figdpi', 300))
def evol_occupancy(msa, **kwargs):
from numpy import arange
import prody
from prody import parseMSA, calcMSAOccupancy, showMSAOccupancy, writeArray
from os.path import splitext
prefix = kwargs.get('prefix')
if prefix is None:
prefix, _ = splitext(msa)
if _.lower() == '.gz':
prefix, _ = splitext(prefix)
prefix += '_occupancy'
msa = parseMSA(msa)
numformat = kwargs.get('numformat', '%12g')
occupancy , suffix = [], []
occaxis = kwargs.get('occaxis', 'row')
if occaxis == 'both':
suffix = ['_row', '_col']
occupancy.append(calcMSAOccupancy(msa, occ='row'))
occupancy.append(calcMSAOccupancy(msa, occ='col'))
else:
suffix = '_' + occaxis
occupancy.append(calcMSAOccupancy(msa, occ=occaxis))
for i, occ in enumerate(occupancy):
writeArray((prefix + suffix[i] + '.txt'), occ, format=numformat)
for i, occ in enumerate(occupancy):
if kwargs.get('figocc'):
try:
import matplotlib.pyplot as plt
except ImportError:
LOGGER.warn('Matplotlib could not be imported, '
'figures are not saved.')
else:
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))
label = kwargs.get('label')
show = showMSAOccupancy(msa=msa, occ=occ, label=label,
xlabel=xlabel, title=title)
format = kwargs.get('figformat', 'pdf')
figure.savefig(prefix + suffix[i] + '.' + format, format=format,
dpi=kwargs.get('figdpi', 300))
def evol_conserv(msa, **kwargs):
import prody
from prody import parseMSA, calcShannonEntropy, showShannonEntropy
from prody import writeArray
from os.path import splitext
prefix = kwargs.get('prefix')
if prefix is None:
prefix, _ = splitext(msa)
if _.lower() == '.gz':
prefix, _ = splitext(prefix)
prefix += '_conserv'
msa = parseMSA(msa)
entropy = calcShannonEntropy(msa, **kwargs)
writeArray(prefix + '.txt',
entropy,
format=kwargs.get('numformat', '%12g'))
if kwargs.get('figent'):
try:
import matplotlib.pyplot as plt
except ImportError:
LOGGER.warn('Matplotlib could not be imported, '
'figures are not saved.')
else:
prody.SETTINGS['auto_show'] = False
width = kwargs.get('figwidth', 8)
height = kwargs.get('figheight', 6)
figargs = kwargs.get('figargs', ())
figure = plt.figure(figsize=(width, height))
show = showShannonEntropy(entropy, msa=msa, *figargs)
format = kwargs.get('figformat', 'pdf')
figure.savefig(prefix + '.' + format,
format=format,
dpi=kwargs.get('figdpi', 300))
def prody_pca(opt):
"""Perform PCA calculations based on command line arguments."""
outdir = opt.outdir
if not os.path.isdir(outdir):
opt.subparser.error('{0:s} is not a valid path'.format(outdir))
import prody
LOGGER = prody.LOGGER
coords = opt.coords
prefix = opt.prefix
nmodes, selstr = opt.nmodes, opt.select
if os.path.splitext(coords)[1].lower() == '.dcd':
ag = opt.psf or opt.pdb
if ag:
if os.path.splitext(ag)[1].lower() == '.psf':
ag = prody.parsePSF(ag)
else:
ag = prody.parsePDB(ag)
dcd = prody.DCDFile(opt.coords)
if len(dcd) < 2:
opt.subparser("DCD file must contain multiple frames.")
if ag:
dcd.setAtomGroup(ag)
select = dcd.select(selstr)
LOGGER.info('{0:d} atoms are selected for calculations.'
.format(len(select)))
else:
select = prody.AtomGroup()
select.setCoords(dcd.getCoords())
pca = prody.PCA(dcd.getTitle())
if len(dcd) > 1000:
pca.buildCovariance(dcd)
pca.calcModes(dcd)
else:
pca.performSVD(dcd[:])
else:
pdb = prody.parsePDB(opt.coords)
if pdb.numCoordsets() < 2:
opt.subparser("PDB file must contain multiple models.")
if prefix == '_pca':
prefix = pdb.getTitle() + '_pca'
select = pdb.select(selstr)
LOGGER.info('{0:d} atoms are selected for calculations.'
.format(len(select)))
if select is None:
opt.subparser('Selection "{0:s}" do not match any atoms.'
.format(selstr))
LOGGER.info('{0:d} atoms will be used for PCA calculations.'
.format(len(select)))
ensemble = prody.Ensemble(select)
pca = prody.PCA(pdb.getTitle())
ensemble.iterpose()
pca.performSVD(ensemble)
LOGGER.info('Writing numerical output.')
if opt.npz:
prody.saveModel(pca)
prody.writeNMD(os.path.join(outdir, prefix + '.nmd'), pca[:nmodes], select)
outall = opt.all
delim, ext, format = opt.delim, opt.ext, opt.numformat
if outall or opt.eigen:
prody.writeArray(os.path.join(outdir, prefix + '_evectors'+ext),
pca.getArray(), delimiter=delim, format=format)
prody.writeArray(os.path.join(outdir, prefix + '_evalues'+ext),
pca.getEigenvalues(), delimiter=delim, format=format)
if outall or opt.covar:
prody.writeArray(os.path.join(outdir, prefix + '_covariance'+ext),
pca.getCovariance(), delimiter=delim, format=format)
if outall or opt.ccorr:
prody.writeArray(os.path.join(outdir, prefix + '_cross-correlations' +
ext), prody.calcCrossCorr(pca),
delimiter=delim, format=format)
if outall or opt.sqflucts:
prody.writeArray(os.path.join(outdir, prefix + '_sqfluct'+ext),
prody.calcSqFlucts(pca), delimiter=delim,
format=format)
if outall or opt.proj:
prody.writeArray(os.path.join(outdir, prefix + '_proj'+ext),
prody.calcProjection(ensemble, pca), delimiter=delim,
format=format)
figall, cc, sf, sp = opt.figures, opt.cc, opt.sf, opt.sp
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:
LOGGER.info('Saving graphical output.')
format, width, height, dpi = \
opt.figformat, opt.width, opt.height, opt.dpi
format = format.lower()
if figall or cc:
plt.figure(figsize=(width, height))
prody.showCrossCorr(pca)
plt.savefig(os.path.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(os.path.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(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(os.path.join(outdir, prefix + '_proj_' +
'_'.join(index) + '.' + format),
dpi=dpi, format=format)
plt.close('all')
def prody_anm(opt):
"""Perform ANM calculations based on command line arguments."""
outdir = opt.outdir
if not os.path.isdir(outdir):
opt.subparser.error('{0:s} is not a valid path'.format(outdir))
import numpy as np
import prody
LOGGER = prody.LOGGER
pdb = opt.pdb
prefix = opt.prefix
cutoff, gamma = opt.cutoff, opt.gamma,
nmodes, selstr, model = opt.nmodes, opt.select, opt.model
pdb = prody.parsePDB(pdb, model=model)
if prefix == '_anm':
prefix = pdb.getTitle() + '_anm'
select = pdb.select(selstr)
if select is None:
opt.subparser('Selection "{0:s}" do not match any atoms.'
.format(selstr))
LOGGER.info('{0:d} 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 opt.npz:
prody.saveModel(anm)
prody.writeNMD(os.path.join(outdir, prefix + '.nmd'), anm, select)
outall = opt.all
delim, ext, format = opt.delim, opt.ext, opt.numformat
if outall or opt.eigen:
prody.writeArray(os.path.join(outdir, prefix + '_evectors'+ext),
anm.getArray(), delimiter=delim, format=format)
prody.writeArray(os.path.join(outdir, prefix + '_evalues'+ext),
anm.getEigenvalues(), delimiter=delim, format=format)
if outall or opt.beta:
fout = prody.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 opt.covar:
prody.writeArray(os.path.join(outdir, prefix + '_covariance'+ext),
anm.getCovariance(), delimiter=delim, format=format)
if outall or opt.ccorr:
prody.writeArray(os.path.join(outdir, prefix + '_cross-correlations'
+ ext),
prody.calcCrossCorr(anm), delimiter=delim,
format=format)
if outall or opt.hessian:
prody.writeArray(os.path.join(outdir, prefix + '_hessian'+ext),
anm.getHessian(), delimiter=delim, format=format)
if outall or opt.kirchhoff:
prody.writeArray(os.path.join(outdir, prefix + '_kirchhoff'+ext),
anm.getKirchhoff(), delimiter=delim, format=format)
if outall or opt.sqflucts:
prody.writeArray(os.path.join(outdir, prefix + '_sqflucts'+ext),
prody.calcSqFlucts(anm), delimiter=delim,
format=format)
figall, cc, sf, bf, cm = opt.figures, opt.cc, opt.sf, opt.bf, opt.cm
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:
LOGGER.info('Saving graphical output.')
format, width, height, dpi = \
opt.figformat, opt.width, opt.height, opt.dpi
format = format.lower()
if figall or cc:
plt.figure(figsize=(width, height))
prody.showCrossCorr(anm)
plt.savefig(os.path.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(os.path.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(os.path.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(os.path.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 corepagecalculation(pdbfilename, selatom, noma1, nummodes, gamcut, cut1, gam2, cut2, showresults, smodes, snmd, smodel, scollec, massnomass, sample1, modeens, confens, rmsdens, traverse1, modetra, steptra, rmsdtra, modelnumber, caanm, cagnm, nohanm, nohgnm, allanm, allgnm, bbanm, bbgnm, scanm, scgnm, nmdfolder, modesfolder, collectivityfolder, modelnewname, nmdnewname, modesnewname, modesendname, collectivitynewname, collectivityendname, samplenewname, traversenewname, crosscorr=0, corrfolder='', corrname='', corrend='', compmode01='7', compmode02='15', sqflucts=0, sqfluctsfolder='', sqfluctsname='', sqfluctsend='', separatevar1='0', temfac=0, temfacfolder='', temfacname='', temfacend='', fracovar=0, fraconame='', fracoend='', ovlap=0, ovlapfold='', ovlapname='', ovlapend='', ovlaptab=0, ovlaptabname='', ovlaptabend='', comppdbfilename=''):
# modelnumber
import prody
import time
import os
import Tkinter
root=Tkinter.Tk()
root.title('Info')
onlypage=Tkinter.Frame(root)
onlypage.pack(side='top')
Tkinter.Label(onlypage,text='File: '+pdbfilename).grid(row=0,column=0,sticky='w')
Tkinter.Label(onlypage,text='Atoms: '+selatom).grid(row=1,column=0,sticky='w')
Tkinter.Label(onlypage,text='Analysis: '+noma1).grid(row=2,column=0,sticky='w')
path=os.path.join(os.path.expanduser('~'),'.noma/')
fin = open(path+'savefile.txt','r')
global savedfile
savedfile=fin.readlines()
fin.close()
i=0
a=len(savedfile)
while i<a:
savedfile[i]=savedfile[i][:-1]
i+=1
if gamcut=='0':
Tkinter.Label(onlypage,text='Gamma: r^'+savedfile[91]).grid(row=3,column=0,sticky='w')
Tkinter.Label(onlypage,text='Cutoff: '+cut1).grid(row=4,column=0,sticky='w')
elif gamcut=='1':
Tkinter.Label(onlypage,text='Gamma: '+gam2).grid(row=3,column=0,sticky='w')
Tkinter.Label(onlypage,text='Cutoff: '+cut2).grid(row=4,column=0,sticky='w')
find = 0 #
while find < len(pdbfilename): #
if pdbfilename[-(find+1):-find] == '/': #
bgn = len(pdbfilename)-find #
break #
else: # helps in the
find +=1 # saving of files
try: #
float(bgn) #
except (NameError): #
bgn = 0 #
find = 0 #
while bgn+find<len(pdbfilename): #
if pdbfilename[bgn+find:bgn+find+1] == '.': #
end = len(pdbfilename)-(bgn+find) #
break #
else: #
find +=1 #
try: #
name = pdbfilename[bgn:-end] #
except (NameError): #
name = pdbfilename[bgn:len(pdbfilename)] # name of the file
bgn = pdbfilename[:bgn] # path for file
mytimeis = time.asctime(time.localtime(time.time()))
start = time.time()
try:
p38 = prody.parsePDB(pdbfilename,model=int(modelnumber))
except:
import tkMessageBox
tkMessageBox.askokcancel("File Error","""This is not the correct path or name. Try entering /some/path/nameoffile.pdb
If you need help finding the path, open a new terminal and enter:
find -name 'filename.pdb' use the output as the pdb input
If this doesn't work, make sure the file is in PDB format.""")
p38 = prody.parsePDB(pdbfilename)
print 'Submitted: '+pdbfilename+' at '+mytimeis
Tkinter.Label(onlypage,text='Submitted at: '+mytimeis).grid(row=5,column=0,sticky='w')
root.update()
if selatom == "C-alpha" and noma1 == "Gaussian Normal Mode":
folder = cagnm+'/'
pro = p38.select('protein and name CA') # selects only carbon alpahs
elif selatom == "C-alpha" and noma1 == "Anisotropic Normal Mode":
folder = caanm+'/'
pro = p38.select('protein and name CA')
elif selatom == "Heavy" and noma1 == "Gaussian Normal Mode":
folder = nohgnm+'/'
pro = p38.select('protein and not name "[1-9]?H.*"') # gets rid of all Hydrogens
elif selatom == "Heavy" and noma1 == "Anisotropic Normal Mode":
folder = nohanm+'/'
pro = p38.select('protein and not name "[1-9]?H.*"')
elif selatom == "All" and noma1 == "Gaussian Normal Mode":
folder = allgnm+'/'
pro = p38.select('protein')
elif selatom == "All" and noma1 == "Anisotropic Normal Mode":
folder = allanm+'/'
pro = p38.select('protein')
elif selatom == "Backbone" and noma1 == "Gaussian Normal Mode":
folder = bbgnm+'/'
pro = p38.select('protein and name CA C O N H') # selects backbone
elif selatom == "Backbone" and noma1 == "Anisotropic Normal Mode":
folder = bbanm+'/'
pro = p38.select('protein and name CA C O N H') # selects backbone
elif selatom == "Sidechain" and noma1 == "Gaussian Normal Mode":
folder = scgnm+'/'
pro = p38.select('protein and not name CA C O N H') # selects sidechain
elif selatom == "Sidechain" and noma1 == "Anisotropic Normal Mode":
folder = scanm+'/'
pro = p38.select('protein and not name CA C O N H') # selects sidechain
try: #
open(bgn+folder) # creates the folders
except (IOError): # where the files will
try: # be saved only if they
os.makedirs(bgn+folder) # are not there
except (OSError): #
mer = 0 #
if noma1 == "Gaussian Normal Mode":
print 'Building the Kirchhoff matrix'
Tkinter.Label(onlypage,text='Building Kirchhoff').grid(row=6,column=0,sticky='w')
root.update()
anm = prody.GNM(name)###
if gamcut=='0':
anm.buildKirchhoff(pro,cutoff=float(cut1),gamma=gammaDistanceDependent)###
anm.setKirchhoff(anm.getKirchhoff())
elif gamcut=='1':
anm.buildKirchhoff(pro,cutoff=float(cut2),gamma=float(gam2))###
brat = 2
elif noma1 == "Anisotropic Normal Mode":
print 'Building the Hessian matrix'
Tkinter.Label(onlypage,text='Building Hessian').grid(row=6,column=0,sticky='w')
root.update()
anm = prody.ANM(name)###
if gamcut=='0':
anm.buildHessian(pro,cutoff=float(cut1),gamma=gammaDistanceDependent)###
anm.setHessian(anm.getHessian())###
elif gamcut=='1':
anm.buildHessian(pro,cutoff=float(cut2),gamma=float(gam2))###
brat = 7
print 'Calculating modes'
Tkinter.Label(onlypage,text='Calculating modes').grid(row=7,column=0,sticky='w')
root.update()
anm.calcModes(int(nummodes),zeros = True)###
numatom=anm.numAtoms()###
eigval=anm.getEigvals()###
atomname=pro.getNames()###
if smodel==1:
if brat==2:
modelfilename=bgn+folder+name+modelnewname+'.gnm.npz'
elif brat==7:
modelfilename=bgn+folder+name+modelnewname+'.anm.npz'
print 'Saving Model'
Tkinter.Label(onlypage,text='Saving Model').grid(row=8,column=0,sticky='w')
root.update()
try:
prody.saveModel(anm,bgn+folder+name+modelnewname,True)###
except:
print 'Matrix not saved due to size'
Tkinter.Label(onlypage,text='Matrix not saved').grid(row=8,column=0,sticky='w')
root.update()
prody.saveModel(anm,bgn+folder+name+modelnewname)###
if snmd==1:
print 'Saving NMD'
Tkinter.Label(onlypage,text='Saving NMD').grid(row=9,column=0,sticky='w')
root.update()
try: #
os.makedirs(bgn+folder+nmdfolder+'/') #
except (OSError): #
mer = 0 #
prody.writeNMD(bgn+folder+nmdfolder+'/'+name+nmdnewname+'.nmd',anm[:len(eigval)],pro)### # this can be viewed in VMD
if smodes==1:
print 'Saving Modes'
Tkinter.Label(onlypage,text='Saving Modes').grid(row=10,column=0,sticky='w')
root.update()
try: #
os.makedirs(bgn+folder+modesfolder+'/') #
except (OSError): #
mer = 0 #
modefile = bgn+folder+modesfolder+'/'+name+modesnewname+'.'+modesendname
fout = open(modefile,'w')
mer = 0
while mer< len(eigval):
slowest_mode = anm[mer]###
r = slowest_mode.getEigvec()###
p = slowest_mode.getEigval()###
tq = 0
tt = 0
ttt = 1
tttt = 2
fout.write('MODE {0:3d} {1:15e}'.format(mer+1,p))
fout.write("""
-------------------------------------------------
""")
if noma1 == "Gaussian Normal Mode":
while tq < numatom:
fout.write("""{0:4s}{1:15e}
""".format(atomname[tq],r[tq]))
tq +=1
elif noma1 == "Anisotropic Normal Mode":
while tt < numatom*3:
fout.write("""{0:4s}{1:15e}{2:15e}{3:15e}
""".format(atomname[tq],r[tt],r[ttt],r[tttt]))
tq+=1
tt +=3
ttt+=3
tttt+=3
mer +=1
fout.close()
if showresults=='1':
os.system('/usr/bin/gnome-open '+modefile)
if scollec==1:
print 'Saving collectivity'
Tkinter.Label(onlypage,text='Saving collectivity').grid(row=11,column=0,sticky='w')
root.update()
try: #
os.makedirs(bgn+folder+collectivityfolder+'/') #
except (OSError): #
mer = 0 #
mer = 0
xx = [0]*(numatom) # sets the array to zero and other initial conditions
i = 0
aa = 0
no = 0
var3 = 0
sss = [0]*(len(eigval))
while mer< len(eigval):
slowest_mode = anm[mer]###
r = slowest_mode.getEigvec()###
p = slowest_mode.getEigval()###
a = 0
tt = 0
ttt = 1
tttt = 2
while a < numatom:
atom = atomname[a]
mass = 0
while mass < 2:
if atom[mass] == "N": # all nitrogen
m = 14.0067
break
elif atom[mass] == 'H': # all hydrogen
m = 1.00794
break
elif atom[mass] == "C" : # all carbon
m = 12.0107
break
elif atom[mass] == "O" : # all oxygen
m = 15.9994
break
elif atom[mass] == 'S': # all sulfur
m = 32.065
break
elif atom[mass] == 'P' : # all phosphorus
m = 30.973762
break
else:
if mass == 0:
mass +=1
try:
atom[mass]
except (IndexError):
m = 1
if no == 0:
print 'Enter atom '+atom+' in to the system. Its mass was set to 1 in this simulation.'
no +=1
break
else:
m = 1
if no == 0:
print 'Enter atom '+atom+' in to the system. Its mass was set to 1 in this simulation'
no +=1
break
if len(r)/numatom == 3:
xx[i] = (r[tt]**2 + r[ttt]**2 + r[tttt]**2)/m
i +=1
tt +=3
ttt+=3
tttt+=3
else:
xx[i] = (r[tt]**2)/m
i +=1
tt +=1
a +=1
var3 = 0
j = 0
loop = 1
while loop == 1:
if sum(xx) == 0: # need this because you can't divide by 0
loop = 0
elif j <(numatom):
var1 = xx[j]/sum(xx)
if var1 == 0:
var2 = 0
elif var1 != 0:
from math import log # this means natural log
var2 = var1* log(var1)
var3 += var2
j +=1
else:
from math import exp
k = exp(-var3)/numatom
sss[aa] = k, aa+1
aa +=1
mer +=1
loop = 0
i = 0
xx = [0]*(numatom) # goes through all this until the big loop is done
a = 0
k=[0]*(len(eigval))
while a < len(eigval):
k[a]=prody.calcCollectivity(anm[a]),a+1
a +=1
collectivefile = bgn+folder+collectivityfolder+'/'+name+collectivitynewname+'.'+collectivityendname
fout = open(collectivefile,'w')
if massnomass=='0':
fout.write('MODE COLLECTIVITY(mass)')
fout.write("""
---------------------------
""")
for h in sorted(sss,reverse=True):
fout.write(str(h)[-3:-1]+' '+str(h)[1:19]+"""
""")
fout.write("""
MODE COLLECTIVITY(without mass)""")
fout.write("""
---------------------------
""")
for hh in sorted(k,reverse=True):
fout.write(str(hh)[-3:-1]+' '+str(hh)[1:19]+"""
""")
elif massnomass=='1':
fout.write('MODE COLLECTIVITY(without mass)')
fout.write("""
---------------------------
""")
for hh in sorted(k,reverse=True):
fout.write(str(hh)[-3:-1]+' '+str(hh)[1:19]+"""
""")
fout.write("""
MODE COLLECTIVITY(mass)""")
fout.write("""
---------------------------
""")
for h in sorted(sss,reverse=True):
fout.write(str(h)[-3:-1]+' '+str(h)[1:19]+"""
""")
fout.close()
if showresults=='1':
os.system('/usr/bin/gnome-open '+collectivefile)
fin = open(collectivefile,'r')
lst = fin.readlines()
hi0 = 2
looop = 1
prut=0
secoll=0
thicoll=0
while looop == 1:
fine = lst[hi0]
if int(fine[0:2]) >= brat:
if prut==0:
prut=fine[0:2]
elif secoll==0:
secoll=fine[0:2]
elif thicoll==0:
thicoll=fine[0:2]
else:
foucoll=fine[0:2]
looop = 0
else:
hi0 +=1
mostcollective= "Mode "+prut+" is the most collective."
Tkinter.Label(onlypage,text='Mode '+prut+' is the most collective').grid(row=12,column=0,sticky='w')
root.update()
print mostcollective
fin.close()
if sample1 == 1:
print 'Saving sample file'
Tkinter.Label(onlypage,text='Saving sample file').grid(row=13,column=0,sticky='w')
root.update()
a = modeens+' '
b = [0]*(len(a)+1)
i = 0
j = 0
b1 = 0
while i < len(a):
if a[i:i+1] ==' ' or a[i:i+1]==',':
try:
b[b1]=int(a[j:i])-1
except:
if '1c' in a[j:i]:
b[b1]=int(prut)-1
elif '2c' in a[j:i]:
b[b1]=int(prut)-1
b1 +=1
b[b1]=int(secoll)-1
elif '3c' in a[j:i]:
b[b1]=int(prut)-1
b1 +=1
b[b1]=int(secoll)-1
b1 +=1
b[b1]=int(thicoll)-1
elif '4c' in a[j:i]:
b[b1]=int(prut)-1
b1 +=1
b[b1]=int(secoll)-1
b1 +=1
b[b1]=int(thicoll)-1
b1+=1
b[b1]=int(foucoll)-1
j = i+1
i +=1
b1 +=1
else:
i +=1
del b[b1:]
ensemble = prody.sampleModes(anm[b],pro, n_confs=int(confens), rmsd =float(rmsdens))
p38ens=pro.copy()
p38ens.delCoordset(0)
p38ens.addCoordset(ensemble.getCoordsets())
prody.writePDB(bgn+folder+name+samplenewname+'.pdb',p38ens)
if traverse1 ==1:
print 'Saving traverse file'
Tkinter.Label(onlypage,text='Saving traverse file').grid(row=14,column=0,sticky='w')
root.update()
if modetra=='c':
modefortra=int(prut)-1
else:
modefortra=int(modetra)-1
trajectory=prody.traverseMode(anm[modefortra],pro,n_steps=int(steptra),rmsd=float(rmsdtra))
prody.calcRMSD(trajectory).round(2)
p38traj=pro.copy()
p38traj.delCoordset(0)
p38traj.addCoordset(trajectory.getCoordsets())
prody.writePDB(bgn+folder+name+'_mode'+str(modefortra+1)+traversenewname+'.pdb',p38traj)
if crosscorr==1:
print 'Saving cross correlation'
Tkinter.Label(onlypage,text='Saving cross-correlation').grid(row=15,column=0,sticky='w')
root.update()
try: #
os.makedirs(bgn+folder+corrfolder+'/') #
except (OSError): #
mer = 0
i=int(compmode01)
while i <= int(compmode02):
x=i-1
correlationdataname=bgn+folder+corrfolder+'/'+name+corrname+'_mode'+str(x+1)+'.'+corrend
prody.writeArray(correlationdataname,prody.calcCrossCorr(anm[x]),'%.18e')
print correlationdataname
i+=1
##
if sqflucts==1:
print 'Saving square fluctuation'
Tkinter.Label(onlypage,text='Saving square fluctuation').grid(row=16,column=0,sticky='w')
root.update()
try: #
os.makedirs(bgn+folder+sqfluctsfolder+'/') #
except (OSError): #
mer = 0
i=int(compmode01)
while i < int(compmode02):
yelp = i-1
sqfluctdataname = bgn+folder+sqfluctsfolder+'/'+name+sqfluctsname+'_mode'+str(yelp+1)+'.'+sqfluctsend
fout = open(sqfluctdataname,'w')
if separatevar1=='0':
a = 0
while a < numatom:
fout.write(str(a))
fout.write(""" """)
fout.write(str(prody.calcSqFlucts(anm[yelp])[a]))
fout.write("""
""")
a +=1
elif separatevar1=='1':
a=0
while a <numatom:
firstresnum=int(p38.getResnums()[0:1][0])
origiresnum=int(p38.getResnums()[0:1][0])
while firstresnum<(int(numatom*1.0/p38.numChains())+origiresnum):
fout.write(str(firstresnum))
fout.write('\t')
fout.write(str(prody.calcSqFlucts(anm[yelp])[a]))
fout.write('\n')
a+=1
firstresnum+=1
fout.write('&\n')
fout.close()
print sqfluctdataname
i+=1
if temfac==1:
print 'Saving temperature factors'
Tkinter.Label(onlypage,text='Saving temperature factors').grid(row=17,column=0,sticky='w')
root.update()
try: #
os.makedirs(bgn+folder+temfacfolder+'/') #
except (OSError): #
mer = 0
fin=open(pdbfilename,'r')
d = [None]*len(atomname)
e = 0
for line in fin:
pair = line.split()
if 'ATOM ' in line and e < len(atomname):
if str(pair[2]) == str(atomname[e]):
d[e]=str(pair[1])
e+=1
else:
e+=0
else:
continue
fin.close()
sqf = prody.calcSqFlucts(anm)
x = sqf/((sqf**2).sum()**.5)
y = prody.calcTempFactors(anm,pro)
a = 0
tempfactorsdataname =bgn+folder+temfacfolder+'/'+name+temfacname+'.'+temfacend
fout=open(tempfactorsdataname,'w')
fout.write("""Atom Residue TempFactor TempFactor with exp beta
""")
while a < numatom:
fout.write("""{0:4s} {1:4d} {2:15f} {3:15f}
""".format(d[a],a+1,x[a],y[a]))
a +=1
fout.close()
print tempfactorsdataname
if fracovar==1:
try:
import matplotlib.pyplot as plt
print 'Saving Fraction of Variance'
Tkinter.Label(onlypage,text='Saving Fraction of Variance').grid(row=18,column=0,sticky='w')
root.update()
try: #
os.makedirs(bgn+folder+modesfolder+'/') #
except (OSError): #
mer = 0 #
plt.figure(figsize = (5,4))
prody.showFractVars(anm)
prody.showCumulFractVars(anm)
fracvardataname =bgn+folder+modesfolder+'/'+name+fraconame+'.'+fracoend
plt.savefig(fracvardataname)
print fracvardataname
if showresults=='1':
os.system('/usr/bin/gnome-open '+fracvardataname)
except:
print 'Error: Fraction of Variance'
Tkinter.Label(onlypage,text='Error: Fraction of Variance').grid(row=18,column=0,sticky='w')
root.update()
mer=0
if ovlap==1 or ovlaptab==1:
try:
import matplotlib.pyplot as plt
print 'Saving Overlap'
Tkinter.Label(onlypage,text='Saving Overlap').grid(row=19,column=0,sticky='w')
root.update()
Tkinter.Label(onlypage,text='Comparison: '+comppdbfilename).grid(row=20,column=0,sticky='w')
##
find = 0
while find < len(comppdbfilename):
if comppdbfilename[-(find+1):-find] == '/':
bgn1 = len(comppdbfilename)-find
break
else:
find +=1
try:
float(bgn1)
except (NameError):
bgn1 = 0
find = 0
while bgn1+find<len(comppdbfilename):
if comppdbfilename[bgn1+find:bgn1+find+1] == '.':
end1 = len(comppdbfilename)-(bgn1+find)
break
else:
find +=1
try:
name1 = comppdbfilename[bgn1:-end1]
except (NameError):
name1 = comppdbfilename[bgn1:len(comppdbfilename)]
bgn1 = comppdbfilename[:bgn1]
p381 = prody.parsePDB(comppdbfilename,model=int(modelnumber))
if selatom == "C-alpha" and noma1 == "Gaussian Normal Mode":
pro1 = p381.select('protein and name CA')
elif selatom == "C-alpha" and noma1 == "Anisotropic Normal Mode":
pro1 = p381.select('protein and name CA')
elif selatom == "Heavy" and noma1 == "Gaussian Normal Mode":
pro1 = p381.select('protein and not name "[1-9]?H.*"')
elif selatom == "Heavy" and noma1 == "Anisotropic Normal Mode":
pro1 = p381.select('protein and not name "[1-9]?H.*"')
elif selatom == "All" and noma1 == "Gaussian Normal Mode":
pro1 = p381.select('protein')
elif selatom == "All" and noma1 == "Anisotropic Normal Mode":
pro1 = p381.select('protein')
elif selatom == "Backbone" and noma1 == "Gaussian Normal Mode":
pro1 = p381.select('protein and name CA C O N H')
elif selatom == "Backbone" and noma1 == "Anisotropic Normal Mode":
pro1 = p381.select('protein and name CA C O N H')
elif selatom == "Sidechain" and noma1 == "Gaussian Normal Mode":
pro1 = p381.select('protein and not name CA C O N H')
elif selatom == "Sidechain" and noma1 == "Anisotropic Normal Mode":
pro1 = p381.select('protein and not name CA C O N H')
if noma1 == "Gaussian Normal Mode":
print 'Building the Kirchhoff matrix'
Tkinter.Label(onlypage,text='Building Kirchhoff').grid(row=21,column=0,sticky='w')
root.update()
anm1 = prody.GNM(name1)
if gamcut=='0':
anm1.buildKirchhoff(pro1,cutoff=float(cut1),gamma=gammaDistanceDependent)
anm1.setKirchhoff(anm1.getKirchhoff())
elif gamcut=='1':
anm1.buildKirchhoff(pro1,cutoff=float(cut2),gamma=float(gam2))
brat = 2
elif noma1 == "Anisotropic Normal Mode":
print 'Building the Hessian matrix'
Tkinter.Label(onlypage,text='Building Hessian').grid(row=21,column=0,sticky='w')
root.update()
anm1 = prody.ANM(name1)
if gamcut=='0':
anm1.buildHessian(pro1,cutoff=float(cut1),gamma=gammaDistanceDependent)
anm1.setHessian(anm1.getHessian())
elif gamcut=='1':
anm1.buildHessian(pro1,cutoff=float(cut2),gamma=float(gam2))
brat = 7
print 'Calculating modes'
Tkinter.Label(onlypage,text='Calculating modes').grid(row=22,column=0,sticky='w')
root.update()
anm1.calcModes(int(nummodes),zeros = True)
##
try:
os.makedirs(bgn+folder+ovlapfold+'/')
except (OSError):
mer = 0
if ovlap==1:
i=int(compmode01)
while i < int(compmode02):
a = i-1
plt.figure(figsize=(5,4))
prody.showCumulOverlap(anm[a],anm1)
prody.showOverlap(anm[a],anm1)
plt.title('Overlap with Mode '+str(a+1)+' from '+name)
plt.xlabel(name1+' mode index')
overlapname = bgn+folder+ovlapfold+'/'+name+'_'+name1+ovlapname+'_mode'+str(a+1)+'.'+ovlapend
plt.savefig(overlapname)
print overlapname
i+=1
if ovlaptab==1:
plt.figure(figsize=(5,4))
prody.showOverlapTable(anm1,anm)
plt.xlim(int(compmode01)-1,int(compmode02))
plt.ylim(int(compmode01)-1,int(compmode02))
plt.title(name1+' vs '+name+' Overlap')
plt.ylabel(name1)
plt.xlabel(name)
overlapname = bgn+folder+ovlapfold+'/'+name+'_'+name1+ovlaptabname+'.'+ovlaptabend
plt.savefig(overlapname)
print overlapname
except:
mer=0
root.destroy()
mynewtimeis = float(time.time()-start)
if mynewtimeis <= 60.00:
timeittook= "The calculations took %.2f s."%(mynewtimeis)
elif mynewtimeis > 60.00 and mynewtimeis <= 3600.00:
timeittook= "The calculations took %.2f min."%((mynewtimeis/60.00))
else:
timeittook= "The calculations took %.2f hrs."%((mynewtimeis/3600.00))
print timeittook
if smodel==1 and scollec==1:
return (timeittook,modelfilename,str(int(prut)))
elif scollec==1:
return (timeittook,'nofile',str(int(prut)))
elif smodel==1:
return (timeittook,modelfilename,'nocoll')
else:
return (timeittook,'nofile','nocoll')
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')
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')
def align():
global wd
ans = wd + '/challengedata/answers'
if os.path.isdir(
ans) == False: #if the answers directory isnt formed make it
os.mkdir(wd + '/challengedata/answers')
rddir = wd + '/challengedata/rdkit-scripts'
if os.path.isdir(rddir) == False:
a = 'git clone https://github.com/dkoes/rdkit-scripts'
os.system(a)
data = os.listdir(wd + '/challengedata')
for x in (data): #for each weeks data
if x == "readme.txt" or x == "latest.txt" or x == "answers" or x == "rdkit-scripts" or x == 'PDBfiles' or x == 'visual.txt':
pass
else:
toDir = wd + '/challengedata/answers/' + x
if os.path.isdir(
toDir
) == False: #if the path to answers dir doesnt exist
os.mkdir(toDir) #make directory
dock = os.listdir(wd + '/challengedata/' + x)
for y in (dock):
a = str(os.getcwd() + '/answers/' + x + '/' + y +
'/lmcss_docked.sdf')
if y == 'readme.txt' or y == 'new_release_structure_sequence_canonical.tsv' or y == 'new_release_structure_nonpolymer.tsv' or y == 'new_release_crystallization_pH.tsv' or y == 'new_release_structure_sequence.tsv':
pass
elif (os.path.isfile(a) == True):
pass
else:
input = os.listdir(wd + '/challengedata/' + x + '/' +
y)
for z in (input):
if z.startswith("LMCSS") and z.endswith(".pdb"):
if (z.endswith("lig.pdb")):
pass
else:
id = z.strip('.pdb')
sts = str("grep ATOM " + z +
" > lmcss_rec.pdb"
) #creates receptor .pdb file
cd = wd + '/challengedata'
os.chdir(
cd + '/' + x + '/' +
y) #change directory to week/ligand
os.system(
sts
) #runs and creates receptor .pbd file
os.chdir(cd) #back to challenge directory
input = os.listdir(
cd + '/' + x + '/' + y
) #lists files inside ligand in certain week
for z in (input):
if z.endswith(
".smi"
): # changes .smi -> lig.sdf
cd = str(os.getcwd())
sts = str(" " + cd + '/' + x +
'/' + y + '/' + z +
" lig.sdf --maxconfs 1")
os.chdir(cd + '/' + x + '/' + y)
os.system(
cd +
'/rdkit-scripts/rdconf.py' +
sts)
os.chdir(cd)
for z in (input): # runs smina
if z.endswith("lig.pdb"):
sts = str(
"smina -r lmcss_rec.pdb -l lig.sdf --autobox_ligand "
+ z + " -o " + id +
"_docked.sdf")
cd = str(
os.getcwd()) #lignad directory
os.chdir(cd + '/' + x + '/' + y)
#os.system(sts)
sts = str(
"smina -r lmcss_rec.pdb -l lig.sdf --autobox_ligand "
+ z + " -o lmcss_docked.sdf")
cd = str(
os.getcwd()) #lignad directory
os.chdir(cd + '/' + x + '/' + y)
os.system(sts)
os.chdir(cd)
cur = str(os.getcwd() + '/answers/' + x +
'/' + y)
if (os.path.isdir(cur) == True):
os.chdir(cd + '/' + x + '/' + y)
os.getcwd() ##
input = os.listdir(cd + '/' + x + '/' +
y)
for i in (input):
if i.endswith(
".txt"
) and i != "center.txt" and i != "visual.txt":
f = open(i)
lines = f.readlines()
ligand = lines[2].strip(
'ligand, ')
ligand = ligand.replace(
'\n', '')
ligand = str(ligand)
#gets the ligand from txt file
if i.endswith("lig.pdb"):
#see if pdb exists
prody.fetchPDB(y)
proteinPDB = prody.parsePDB(y)
ourPDB = prody.parsePDB(
'lmcss_rec.pdb')
a, b, seqid, overlap = prody.matchChains(
proteinPDB, ourPDB)[0]
b, protein_sp = prody.superpose(
b, a, weights=None)
b.select(ligand +
'_ligand.pdb')
sts = str("obrms -f " + i +
' ' + id +
"_docked.sdf")
#run obrms
# parse results and output to the visualization txt file
os.system(sts)
f = open('visual.txt', 'ab+')
f.write(x + ' smina ' + y +
'\n')
f.close
curdir = str(cd + '/' + x +
'/' + y + '/' +
id +
'_docked.sdf')
print(input) ##
for i in (input):
if i.endswith("lig.pdb"):
#see if pdb exists
protein = prody.fetchPDB(y)
#NEED NUMPY ARRAY
prody.writeArray(
'lmcss_docked_array.sdf',
array)
prody.superpose(
'lmcss_docked.sdf',
protein,
weights=None)
sts = str("obrms -f " + i +
" lmcss_docked.sdf")
#run obrms
# parse results and output to the visualization txt file
os.system(sts)
os.chdir(wd +
'/challengedata/')
f = open('visual.txt', 'ab+')
f.write(x + ' smina ' + y +
'\n')
f.close
curdir = str(
cd + '/' + x + '/' + y +
'/lmcss_docked.sdf')
todir = str(cd + '/answers/' +
x + '/' + y + '/')
shutil.copy(curdir, todir)
print(curdir)
break
os.chdir(wd)
else:
os.mkdir(cur)
os.chdir(cd + '/' + x + '/' + y)
input = os.listdir(cd + '/' + x + '/' +
y)
for i in (input):
if i.endswith(
".txt"
) and i != "center.txt" and i != "visual.txt":
f = open(i)
lines = f.readlines()
ligand = lines[2].strip(
"ligand, ")
ligand = ligand.replace(
'\n', '')
ligand = str(ligand)
#gets ligand from txt file
if i.endswith("lig.pdb"):
prody.fetchPDB(y)
proteinPDB = prody.parsePDB(y)
ourPDB = prody.parsePDB(
'lmcss_rec.pdb')
prody.matchChains(
proteinPDB, ourPDB)
protein_sp = prody.superpose(
ourPDB,
proteinPDB,
weights=None)
protein_sp.select(
ligand + '_ligand.pdb')
sts = str("obrms -f " + i +
' ' + id +
"_docked.sdf")
os.system(sts)
f = open('visual.txt', 'ab+')
f.write(x + ' smina ' + y +
'\n')
f.close
curdir = str(cd + '/' + x +
'/' + y + '/' +
id +
'_docked.sdf')
if i.endswith("lig.pdb"):
protein = prody.fetchPDB(y)
prody.writeArray(
'lmcss_docked_array.sdf',
array)
prody.superpose(
'lmcss_docked.sdf',
protein,
weights=None)
sts = str("obrms -f " + i +
" lmcss_docked.sdf")
os.system(sts)
os.chdir(wd +
'/challengedata/')
f = open('visual.txt', 'ab+')
f.write(x + ' smina ' + y +
'\n')
f.close
curdir = str(
cd + '/' + x + '/' + y +
'/lmcss_docked.sdf')
todir = str(cd + '/answers/' +
x + '/' + y + '/')
shutil.copy(curdir, todir)
print(curdir)
break
os.chdir(wd)