def isConverged(TrajDir, PdbName, TempSet = 300, OutFile = None):
if OutFile is None: OutFile = os.path.abspath('./rmsd_convergence.png')
import cgprotein as lib, measure as m
TempFile = os.path.join(TrajDir, 'temps.txt')
Temps = np.loadtxt(TempFile)
Ind = np.argmin(abs(Temps - TempSet))
TrajTemp = Temps[Ind]
Traj = os.path.join(TrajDir, 'prot_%s.%3.2f.lammpstrj.gz' % (PdbName, TrajTemp))
NativePdb = parseNative(PdbName)
LammpsREMDLog = os.path.join(TrajDir, 'prot_%slammps.log' % PdbName)
calc = lib.Compute(TrajFn = Traj, NativePdb = NativePdb, Temp = TrajTemp)
rmsd = calc.RMSD_frame()
avgrmsd = rmsd.mean()
stdrmsd = np.std(rmsd, ddof = 1)
avgerr = stdrmsd / avgrmsd
avgerr *= 100.
m.NBins = 50 ; m.NBlocks = 4 ; m.Normalize = True
rmsdhist = m.makeHist(rmsd)
Walk = np.loadtxt(LammpsREMDLog, skiprows = 3)[:, 1:]
fig = plt.figure(facecolor = 'w', edgecolor = 'w', figsize = (8, 4))
ax1 = fig.add_subplot(2,2,1)
ax2 = fig.add_subplot(2,2,2)
ax3 = fig.add_subplot(2,2,3)
ax1.plot(rmsd, lw = 1, color = 'blue', label = 'fluct from mean = %3.2f %%' % avgerr)
ax1.axhline(avgrmsd, ls = '--', color = 'black', lw = 2)
ax1.legend(loc = 'best')
ax2.errorbar(rmsdhist[0], rmsdhist[1], yerr = rmsdhist[2], color = 'black', lw = 2, marker = 'o', markersize = 5)
ax2.set_xlabel(r'$RMSD (\AA)$') ; ax2.set_ylabel('distribution')
for i, T in enumerate(Temps):
x = Walk[:,i]
y = np.array([Temps[int(k)] for k in x])
m.NBins = len(Temps) ; m.NBlocks = 1; m.Normalize = False
walkhist = m.makeHist(y)
ax3.plot(walkhist[0], walkhist[1], lw = 2, label = 'Replica: %d' % i)
ax3.legend(loc = 'best', fontsize = 5)
ax3.set_xlabel('Temp (K)') ; ax3.set_ylabel('distribution')
fig.tight_layout()
plt.savefig(OutFile)
return
else:
TempSet = None
TrajFn = None
# output locations
OutPrefix = os.path.join(OutDir, Prefix)
if not os.path.isdir(OutDir): os.system('mkdir -p %s' % OutDir)
print '\n'
print 'ANALYZING POLYPEPTIDE'
print '====================='
# compute object
print '\nCreating Compute object'
calc = lib.Compute(NativePdb=NativePdb,
TrajFn=TrajFn,
Temp=TempSet,
Prefix=OutPrefix)
# replica object
print '\nCreating Replica object'
rep = lib.Replica(NativePdb=NativePdb,
TrajPrefix=TrajPrefix,
Prefix=OutPrefix,
TempSet=TempSet,
OrderParams=['U', 'Rg', 'RMSD', 'HScore', 'BScore'],
NStepsProd=NStepsProd,
NStepsSwap=NStepsSwap,
WriteFreq=WriteFreq)
def Cluster():
# extract AA and CG paths
print 'Setting ouput locations'
AAPrefix = OutPrefix + '_AA'
CGPrefix = OutPrefix + '_CG'
OutDir = os.path.dirname(OutPrefix)
if not os.path.isdir(OutDir): os.mkdir(OutDir)
# nativepdb w.r.t all calculations are done
NativePdb = os.path.expanduser('~/Go/%s_AA/topclust.pdb' % polymer)
if not os.path.isfile(NativePdb):
raise IOError('AA top cluster struct missing.')
# global compute and replica objects for AA and CG
print 'Creating global Compute objects for AA and CG'
c_AA = lib.Compute(NativePdb = NativePdb, Prefix = AAPrefix)
c_CG = lib.Compute(NativePdb = NativePdb, Prefix = CGPrefix)
# global replica objects for AA
print 'Creating global Replica objects for AA'
fAA = utils.parseAA(polymer)
if not fAA['hasReplica']:
print 'Error: Not enough data to create AA Replica object'
r_AA = None
else:
r_AA = lib.Replica(NativePdb = NativePdb, Prefix = AAPrefix,
TrajPrefix = os.path.join(fAA['MasterDir'], 'Lammps', polymer))
# global replica objects for CG
print 'Creating global Replica objects for CG'
fCG = utils.parseCG(polymer)
TempSet = float(sys.argv[5])
hasPseudoGLY = int(sys.argv[6]) if len(sys.argv) > 6 else False
# get Traj
if not os.path.isdir(OutDir): os.system('mkdir -p %s' % OutDir)
OutPrefix = os.path.join(OutDir, Prefix)
TrajPrefix = os.path.join(TrajDir, Prefix)
TrajFn = FMT['TRAJ'] % (TrajPrefix, TempSet)
# fancy intro
print 'ANALYSING MULTI-PROTEIN FOR %s at %3.2f K' % (Prefix, TempSet)
print '----------------------------------------------------------------'
# set up Compute object
print 'Creating Compute object'
calc = cg.Compute(NativePdb = NativePdb, TrajFn = TrajFn, Temp = TempSet, Prefix = OutPrefix, hasPseudoGLY = hasPseudoGLY)
# cluster the room temp traj
print 'Clustering trajectory'
calc.Cluster()
# top-cluster contact analysis
Trj = pickleTraj(TrajFn)
BoxL = Trj.FrameData['BoxL']
ClustPdb = FMT['CLUSTPDB'] % (calc.Prefix, calc.Temp)
p = cg.ProteinNCOS(ClustPdb, Model = 1)
# top cluster contact map
print 'Calculating contact map for top cluster'
cmap, cdist = p.GetResContacts(BoxL = BoxL)
picklename = FMT['RESCONTACTS'] % (calc.Prefix + '_topclust', calc.Temp)
NativePdb = {'ala_spc': 'ideal_helix.pdb', 'ala15': 'ideal_helix.pdb', 'leu15': 'ideal_helix.pdb', 'val15': hairpin_pdb}
fig = plt.figure(figsize = (22, 15), facecolor = 'w', edgecolor = 'w')
ind = 1
gs = gridspec.GridSpec(3,4)
for i, fftype in enumerate(fftypes):
print '-------- %s --------' % fftype
# get native Ramachandran angles
pNative = cg.ProteinNCOS(NativePdb[fftype])
PhiNative, PsiNative = pNative.GetPhiPsi(RamaType = 'Generic')
PhiNative, PsiNative = cg.TrimDihedrals(PhiNative, PsiNative, ResNums = range(NRes))
PhiNative *= (180 / np.pi)
PsiNative *= (180 / np.pi)
# create compute object
calc = cg.Compute(NativePdb = NativePdb[fftype], TrajFn = Traj[fftype], Temp = Temp[fftype], Prefix = fftype)
# get cluster ramachandran angle probabilities
calc.RamaChandran()
RamaPickle = utils.FMT['RAMA'] % (fftype, Temp[fftype])
with open(RamaPickle, 'r') as of: data = pickle.load(of)['Generic']
(x,y), ramahist, err = data[-1]
x *= (180 / np.pi)
y *= (180 / np.pi)
pmf = -np.log(ramahist)
pmf = pmf.clip(min = -5, max = 5)
# get cluster contact maps
NativeCM, TrajCM = calc.CompareContactMap()
# get fraction of native contacts
#!/usr/bin/env python
import numpy as np
import utils, cgprotein
polymers = ['ala15', 'leu15', 'val15']
for p in polymers:
dict_AA = utils.parseAA(PolyPrefix = p)
nativepdb = dict_AA['Pdb']
trajfn = dict_AA['Traj']
Temp = dict_AA['Temp']
calc = cgprotein.Compute(NativePdb = nativepdb, TrajFn = trajfn, Temp = Temp, Prefix = p)
nativeco, cohist = calc.CompareCO()
avgco = np.sum(cohist[0] * cohist[1]) / np.sum(cohist[1])
print 'Polymer: %s, Native CO: %g, TrajAvg CO: %g' % (p, nativeco, avgco)