def test_traj_0():
aind = np.unique( np.random.randint( 22, size=4) )
stride = np.random.randint(1, 100 )
r_traj = get('Trajectories/trj0.lh5')
r_traj.restrict_atom_indices( aind )
r_traj['XYZList'] = r_traj['XYZList'][ ::stride ]
traj = Trajectory.load_from_lhdf(get('Trajectories/trj0.lh5', just_filename=True),
Stride=stride, AtomIndices=aind)
# make sure we loaded the right number of atoms
assert traj['XYZList'].shape[1] == len(aind)
for key in traj.keys():
if key in ['SerializerFilename'] :
continue
if key in ['IndexList']:
for row, r_row in zip( traj[key], r_traj[key] ):
eq(row, r_row)
elif key == 'XYZList':
eq(traj[key], r_traj[key])
else:
eq(traj[key], r_traj[key])
def get_project_object( traj_directory, conf_filename, out_filename=None ):
"""
This function constructs a msmbuilder.Project object
given a directory of trajectories saved as .lh5's.
Note that this is only really necessary when a script
like ConvertDataToLHDF.py converts the data but fails
to write out the ProjectInfo.yaml file.
This function can also be used to combine two projects
by copying and renaming the trajectories in a new
folder. Though, it's probably more efficient to just
do some bash stuff to cat the ProjectInfo.yaml's
together and rename the trajectories.
Inputs:
-------
1) traj_directory : directory to find the trajectories
2) conf_filename : file to find the conformation
3) out_filename [ None ] : if None, then this function
does not save the project file, but if given, the
function will save the project file and also
return the object
Outputs:
-------
project : msmbuilder.Project object corresponding to
your project.
"""
traj_paths = sorted( os.listdir( traj_directory ), key=keynat ) # relative to the traj_directory
traj_paths = [ os.path.join( traj_directory, filename ) for filename in traj_paths ] # relative to current directory
traj_lengths = []
for traj_filename in traj_paths: # Get the length of each trajectory
logger.info( traj_filename )
traj_lengths.append( Trajectory.load_from_lhdf( traj_filename, JustInspect=True )[0] )
# With JustInspect=True this just returns the shape of the XYZList
project = Project({'conf_filename': conf_filename,
'traj_lengths': traj_lengths,
'traj_paths': traj_paths,
'traj_errors': [None] * len(traj_paths),
'traj_converted_from': [ [None] ] * len(traj_paths) })
if out_filename is None:
return project
else:
project.save( out_filename )
logger.info('Saved project file to %s', out_filename)
return project
def test_traj_0():
aind = np.unique( np.random.randint( 22, size=4) )
stride = np.random.randint(1, 100 )
r_traj = Trajectory.load_from_lhdf( os.path.join( fixtures_dir(), 'trj0.lh5' ), Stride=1 )
r_traj.restrict_atom_indices( aind )
r_traj['XYZList'] = r_traj['XYZList'][ ::stride ]
traj = Trajectory.load_from_lhdf( os.path.join( fixtures_dir(), 'trj0.lh5' ), Stride = stride, AtomIndices = aind )
for key in traj.keys():
if key in ['SerializerFilename'] :
continue
if key in ['IndexList']:
for row, r_row in zip( traj[key], r_traj[key] ):
npt.assert_array_equal( row, r_row )
elif key == 'XYZList':
npt.assert_array_almost_equal( traj[key], r_traj[key])
else:
npt.assert_array_equal( traj[key], r_traj[key] )
def main(genfile):
dir=os.path.dirname(genfile)
traj=Trajectory.load_from_lhdf(genfile)
rmsd=numpy.loadtxt('%s.rmsd.dat' % genfile.split('.lh5')[0])
atom_pairs=numpy.loadtxt('./atompairs.dat', dtype=int)
names=numpy.loadtxt('./atompairs-map.txt', usecols=(2,), dtype=str)
indices=[i for i in atom_pairs]
for (ind, name) in zip(indices, names):
index1=numpy.zeros((1,2)) # here i just need to tell _dihedralcalc that we have one set of 4 coordinates
index1[0]=ind
pairmetric= metrics.AtomPairs(metric='euclidean', p=1, atom_pairs=index1)
distances=pairmetric.prepare_trajectory(traj)
pylab.figure()
pylab.scatter(rmsd, distances, label=name)
pylab.legend()
pylab.show()
numpy.savetxt('%s_%spair.dat' % (genfile.split('.lh5')[0], name), distances)
index1=numpy.zeros((1,4)) # here i just need to tell _dihedralcalc that we have one set of 4 coordinates
index1[0]=numpy.loadtxt('omega_indices.txt', dtype=int, ndmin=1)
index2=numpy.zeros((1,4)) # here i just need to tell _dihedralcalc that we have one set of 4 coordinates
index2[0]=numpy.loadtxt('phi_indices.txt', dtype=int, ndmin=1)
indices=[index1, index2]
names=['omega', 'phi']
for (ind, name) in zip(indices, names):
dihed=_dihedralcalc.compute_dihedrals(traj['XYZList'], ind, degrees=True)
dihed=[i[0] for i in dihed]
numpy.savetxt('%s_%s.dat' % (genfile.split('.lh5')[0], name), dihed)
atom_pairs=numpy.loadtxt('conformation_pairs.dat', dtype=int)
names=['oxos_dist', 'hydrophob_dist']
for (pair, name) in zip(atom_pairs, names):
index=numpy.zeros((1,2), dtype=int)
index[0]=pair
metric= metrics.AtomPairs(metric='euclidean', p=1, atom_pairs=index)
distances=metric.prepare_trajectory(traj)
distances=[i[0]*10 for i in distances]
pylab.figure()
pylab.scatter(rmsd, distances, label=name)
pylab.legend()
pylab.show()
numpy.savetxt('%s_pairs.dat' % genfile.split('.lh5')[0], distances)
def run( project, output, num_procs=1, chunk_size=50000, traj_fn='all' ):
pool = mp.Pool( num_procs )
dssp_assignments = []
if traj_fn.lower() == 'all':
for i in xrange( project.n_trajs ):
traj_dssp_assignments = []
N = project.traj_lengths[i]
j = 0
for trj_chunk in Trajectory.enum_chunks_from_lhdf( project.traj_filename( i ), ChunkSize=chunk_size ):
result = pool.map_async( analyze_conf, trj_chunk['XYZList'] )
result.wait()
traj_dssp_assignments.extend( result.get() )
j+=len(trj_chunk)
print "Trajectory %d: %d / %d" % (i, j, N)
dssp_assignments.append( traj_dssp_assignments )
else:
traj_dssp_assignments = []
N = Trajectory.load_from_lhdf(traj_fn, JustInspect=True)[0]
j = 0
for trj_chunk in Trajectory.enum_chunks_from_lhdf(traj_fn, ChunkSize=chunk_size):
result = pool.map_async(analyze_conf, trj_chunk['XYZList'])
result.wait()
traj_dssp_assignments.extend(result.get())
j+=len(trj_chunk)
print "Trajectory %s: %d / %d" % (traj_fn, j, N)
dssp_assignments.append(traj_dssp_assignments)
dssp_assignments = np.array( dssp_assignments )
np.save( output, dssp_assignments )
DEVNULL.close()
def main(coarse_val, orig_val, rcut):
data=dict()
data['coarse']=dict()
data['orig']=dict()
dirs=dict()
dirs['coarse']='./d%s' % coarse_val
dirs['orig']='./d%s' % orig_val
proj=Project.load_from('ProjectInfo.yaml')
types=['ass', 'rmsd', 'dist', 'gens']
for key in ['coarse', 'orig']:
for type in types:
if 'ass' in type:
ass=io.loadh('%s/Data/Assignments.h5' % dirs[key])
data[key][type]=ass['arr_0']
elif 'dist' in type:
ass=io.loadh('%s/Data/Assignments.h5.distances' % dirs[key])
data[key][type]=ass['arr_0']
elif 'rmsd' in type:
rmsd=numpy.loadtxt('%s/Gens.rmsd.dat' % dirs[key])
data[key][type]=rmsd
elif 'gens' in type:
gens=Trajectory.load_from_lhdf('%s/Gens.lh5' % dirs[key])
data[key][type]=gens
unboundmap=dict()
boundmap=dict()
#unboundstates=dict()
#unboundrmsd=dict()
# build map dict for orig to coarse unbound states, bound will stay same
newass=-1*numpy.ones(( data['orig']['ass'].shape[0], data['orig']['ass'].shape[1]), dtype=int)
for j in range(0, data['orig']['ass'].shape[0]):
for (n,i) in enumerate(data['orig']['ass'][j]):
# if unbound
if i != -1:
if data['orig']['rmsd'][i] > float(rcut):
state=data['coarse']['ass'][j][n]
newass[j][n]=state+10000
else:
newass[j][n]=i
count=0
unique=set(newass.flatten())
boundmap=dict()
unboundmap=dict()
for x in unique:
locations=numpy.where(newass==x)
newass[locations]=count
if x >= 10000:
unboundmap[count]=(x-10000)
else:
boundmap[count]=x
count+=1
io.saveh('%s/Coarsed_r%s_Assignments.h5' % (dirs['orig'], rcut), newass)
subdir='%s/Coarsed_r%s_gen/' % (dirs['orig'], rcut)
if not os.path.exists(subdir):
os.mkdir(subdir)
ohandle=open('%s/Coarsed%s_r%s_Gens.rmsd.dat' % (subdir, coarse_val, rcut), 'w')
b=data['orig']['gens']['XYZList'].shape[1]
c=data['orig']['gens']['XYZList'].shape[2]
dicts=[boundmap, unboundmap]
names=['bound', 'unbound']
labels=['orig', 'coarse']
total=len(boundmap.keys()) + len(unboundmap.keys())
structure=proj.empty_traj()
structure['XYZList']=numpy.zeros((total, b, c), dtype='float32')
count=0
for (name, label, mapdata) in zip( names, labels, dicts):
print "writing coarse gen %s out of %s pdbs" % (count, len(mapdata.keys()))
for i in sorted(mapdata.keys()):
macro=mapdata[i]
structure['XYZList'][count]=data[label]['gens']['XYZList'][macro]
ohandle.write('%s\t%s\t%s\n' % (name, count, data[label]['rmsd'][macro]))
print name, count
count+=1
structure.save_to_xtc('%s/Coarsed%s_r%s_Gens.xtc' % (subdir, coarse_val, rcut))
def main(modeldir, gensfile, write=False):
if not os.path.exists('%s/eig-states/' % modeldir):
os.mkdir('%s/eig-states/' % modeldir)
ohandle=open('%s/eig-states/eiginfo.txt' % modeldir, 'w')
project=Project.load_from('%s/ProjectInfo.yaml' % modeldir.split('Data')[0])
ass=io.loadh('%s/Assignments.Fixed.h5' % modeldir)
gens=Trajectory.load_from_lhdf(gensfile)
T=mmread('%s/tProb.mtx' % modeldir)
data=dict()
data['rmsd']=numpy.loadtxt('%s.rmsd.dat' % gensfile.split('.lh5')[0])
com=numpy.loadtxt('%s.vmd_com.dat' % gensfile.split('.lh5')[0], usecols=(1,))
data['com']=com[1:]
pops=numpy.loadtxt('%s/Populations.dat' % modeldir)
map=numpy.loadtxt('%s/Mapping.dat' % modeldir)
map_rmsd=[]
map_com=[]
for x in range(0, len(data['rmsd'])):
if map[x]!=-1:
map_com.append(data['com'][x])
map_rmsd.append(data['rmsd'][x])
map_com=numpy.array(map_com)
map_rmsd=numpy.array(map_rmsd)
T=mmread('%s/tProb.mtx' % modeldir)
eigs_m=msm_analysis.get_eigenvectors(T, 10)
cm=pylab.cm.get_cmap('RdYlBu_r') #blue will be negative components, red positive
print numpy.shape(eigs_m[1][:,1])
for i in range(0,1):
order=numpy.argsort(eigs_m[1][:,i])
if i==0:
maxes=[]
gen_maxes=[]
values=[]
ohandle.write('eig%s maxes\n' % i)
ohandle.write('state\tgenstate\tmagnitude\trmsd\tcom\n')
for n in order[::-1][:5]:
gen_maxes.append(numpy.where(map==n)[0])
maxes.append(n)
values.append(eigs_m[1][n,i])
ohandle.write('%s\t%s\t%s\t%s\t%s\n' % (n, numpy.where(map==n)[0], eigs_m[1][n,i], map_rmsd[n], map_com[n]))
print "maxes at ", maxes, values
maxes=numpy.array(maxes)
if write==True:
get_structure(modeldir, i, gen_maxes, maxes, gens, project, ass, type='max')
else:
maxes=[]
gen_maxes=[]
values=[]
ohandle.write('eig%s maxes\n' % i)
for n in order[::-1][:5]:
gen_maxes.append(numpy.where(map==n)[0])
maxes.append(n)
values.append(eigs_m[1][n,i])
ohandle.write('%s\t%s\t%s\t%s\t%s\n' % (n, numpy.where(map==n)[0], eigs_m[1][n,i], map_rmsd[n], map_com[n]))
print "maxes at ", maxes, values
order=numpy.argsort(eigs_m[1][:,i])
mins=[]
gen_mins=[]
values=[]
ohandle.write('eig%s mins\n' % i)
for n in order[:5]:
gen_mins.append(numpy.where(map==n)[0])
mins.append(n)
values.append(eigs_m[1][n,i])
ohandle.write('%s\t%s\t%s\t%s\t%s\n' % (n, numpy.where(map==n)[0], eigs_m[1][n,i], map_rmsd[n], map_com[n]))
print "mins at ", mins, values
if write==True:
get_structure(modeldir, i, gen_maxes, maxes, gens, project, ass, type='max')
get_structure(modeldir, i, gen_mins, mins, gens, project, ass, type='min')
pylab.scatter(map_com[order], map_rmsd[order], c=eigs_m[1][order,i], cmap=cm, s=1000*abs(eigs_m[1][order,i]), alpha=0.5)
print map_com[order][numpy.argmax(eigs_m[1][order,i])]
print eigs_m[1][order,i][1]
CB=pylab.colorbar()
l,b,w,h=pylab.gca().get_position().bounds
ll, bb, ww, hh=CB.ax.get_position().bounds
CB.ax.set_position([ll, b+0.1*h, ww, h*0.8])
CB.set_label('Eig%s Magnitudes' % i)
ylabel=pylab.ylabel('Ligand RMSD to Xtal ($\AA$)')
xlabel=pylab.xlabel(r'P Active Site - L COM Distance ($\AA$)')
pylab.legend(loc=8, frameon=False)
pylab.savefig('%s/2deigs%i_com_prmsd.png' %(modeldir, i),dpi=300)
usage = """Usage: python Cluster_Variance.py input_name num1
Try: python Cluster_Variance.py rgdf_nmev 100
"""
if len(sys.argv) < 2:
print usage
sys.exit(1)
input_name = sys.argv[1]
num1 = int(sys.argv[2])
input_numbers = [num1]
if __name__ == "__main__":
traj = Trajectory.load_from_lhdf('Trajectories/trj0.lh5')
#Load in all the pair data and add to dictionary#
def read_NOE_data(filename):
os.system('''cat %s | awk '{FS=" "}{print $3}' > atom1.txt'''%filename)
os.system('''cat %s | awk '{FS=" "}{print $4}' > atom2.txt'''%filename)
os.system('''cat %s | awk '{FS=" "}{print $8}' > pair_number.txt'''%filename)
peptide_data = {}
peptide_data['atom1'] = np.loadtxt('atom1.txt')
peptide_data['atom2'] = np.loadtxt('atom2.txt')
# Make sure that the pair_number tags start at 0
peptide_data['pair_number'] = np.loadtxt('pair_number.txt') - 1
return peptide_data
def analyzeTraj( trjFN ): print "Working on trajectory %s" % trjFN trj = Trajectory.load_from_lhdf(trjFN) return rg.calculate_rg(trj['XYZList'])
def main(dir):
t=Trajectory.load_from_lhdf('%s/Gens.lh5' % dir)
t.save_to_xtc('%s/Gens.xtc' % dir)
def main(coarse_val, orig_val, rcut):
data=dict()
data['coarse']=dict()
data['orig']=dict()
dirs=dict()
dirs['coarse']='./d%s' % coarse_val
dirs['orig']='./d%s' % orig_val
proj=Project.load_from('ProjectInfo.yaml')
types=['ass', 'rmsd', 'dist', 'gens']
for key in ['coarse', 'orig']:
for type in types:
if 'ass' in type:
ass=io.loadh('%s/Data/Assignments.h5' % dirs[key])
data[key][type]=ass['arr_0']
elif 'dist' in type:
ass=io.loadh('%s/Data/Assignments.h5.distances' % dirs[key])
data[key][type]=ass['arr_0']
elif 'rmsd' in type:
rmsd=numpy.loadtxt('%s/Gens.rmsd.dat' % dirs[key])
data[key][type]=rmsd
elif 'gens' in type:
gens=Trajectory.load_from_lhdf('%s/Gens.lh5' % dirs[key])
data[key][type]=gens
unboundmap=dict()
boundmap=dict()
# build map dict for orig to coarse unbound states, bound will stay same
unboundass=-1*numpy.ones(( data['orig']['ass'].shape[0], data['orig']['ass'].shape[1]), dtype=int)
newass=-1*numpy.ones(( data['orig']['ass'].shape[0], data['orig']['ass'].shape[1]), dtype=int)
newdist=-1*numpy.ones(( data['orig']['ass'].shape[0], data['orig']['ass'].shape[1]))
for j in range(0, data['orig']['ass'].shape[0]):
rmsd=numpy.loadtxt('Trajectories-metric/trj%s_lprmsd.dat' % j)
frames=numpy.where(data['orig']['ass'][j]!=-1)[0]
if len(rmsd)!=len(frames):
print "trajectory mismatch"
import pdb
pdb.set_trace()
for (n,i) in enumerate(data['orig']['ass'][j]):
# if unbound
if i != -1:
#if data['orig']['rmsd'][i] > float(rcut):
if rmsd[n] > float(rcut):
newstate=data['coarse']['ass'][j][n]
if data['coarse']['rmsd'][newstate] < float(rcut):
newass[j][n]=i
newdist[j][n]=data['orig']['dist'][j][n]
else:
unboundass[j][n]=newstate
newdist[j][n]=data['coarse']['dist'][j][n]
else:
newass[j][n]=i
newdist[j][n]=data['orig']['dist'][j][n]
count=0
unique=sorted(set(newass.flatten()))
newass, boundmap, count=remap_ass(newass, newass, unique, count)
unique=sorted(set(unboundass.flatten()))
newass, unboundmap, count=remap_ass(unboundass, newass, unique, count)
io.saveh('%s/Coarsed_r%s_d%s_Assignments.h5' % (dirs['orig'], rcut, coarse_val), newass)
io.saveh('%s/Coarsed_r%s_d%s_Assignments.distances.h5' % (dirs['orig'], rcut, coarse_val), newdist)
subdir='%s/Coarsed_r%s_gen/' % (dirs['orig'], rcut)
if not os.path.exists(subdir):
os.mkdir(subdir)
ohandle=open('%s/Coarsed%s_r%s_Gens.rmsd.dat' % (subdir, coarse_val, rcut), 'w')
b=data['orig']['gens']['XYZList'].shape[1]
c=data['orig']['gens']['XYZList'].shape[2]
dicts=[boundmap, unboundmap]
names=['bound', 'unbound']
labels=['orig', 'coarse']
total=len(boundmap.keys()) + len(unboundmap.keys())
structure=proj.empty_traj()
structure['XYZList']=numpy.zeros((total, b, c), dtype='float32')
count=0
for (name, label, mapdata) in zip( names, labels, dicts):
print "writing coarse gen %s out of %s pdbs" % (count, len(mapdata.keys()))
for i in sorted(mapdata.keys()):
macro=mapdata[i]
structure['XYZList'][count]=data[label]['gens']['XYZList'][macro]
ohandle.write('%s\t%s\t%s\n' % (name, count, data[label]['rmsd'][macro]))
print name, count
count+=1
otraj='%s/Coarsed%s_r%s_Gens.xtc' % (subdir, coarse_val, rcut)
if os.path.exists(otraj):
os.remove(otraj)
structure.save_to_xtc('%s/Coarsed%s_r%s_Gens.xtc' % (subdir, coarse_val, rcut))
