def distmatrix(uni,idxs,chosenselections,co,mindist=False, mindist_mode=None, type1char='p',type2char='n'):
numframes = uni.trajectory.numframes
final_percmat = np.zeros((len(chosenselections),len(chosenselections)))
log.info("Distance matrix will be %dx%d (%d elements)" % (len(idxs),len(idxs),len(idxs)**2))
a=1
distmats=[]
if mindist:
P = []
N = []
Pidxs = []
Nidxs = []
Psizes = []
Nsizes = []
for i in range(len(idxs)):
if idxs[i][3][-1] == type1char:
P.append(chosenselections[i])
Pidxs.append(idxs[i])
Psizes.append(len(chosenselections[i]))
elif idxs[i][3][-1] == type2char:
N.append(chosenselections[i])
Nidxs.append(idxs[i])
Nsizes.append(len(chosenselections[i]))
else:
raise
Nsizes = np.array(Nsizes, dtype=np.int)
Psizes = np.array(Psizes, dtype=np.int)
if mindist_mode == "diff":
sets = [(P,N)]
sets_idxs = [(Pidxs,Nidxs)]
sets_sizes = [(Psizes,Nsizes)]
elif mindist_mode == "same":
sets = [(P,P),(N,N)]
sets_idxs = [(Pidxs,Pidxs),(Nidxs,Nidxs)]
sets_sizes = [(Psizes,Psizes),(Nsizes,Nsizes)]
elif mindist_mode == "both":
sets = [(chosenselections, chosenselections)]
sets_idxs = [(idxs, idxs)]
sizes = [len(s) for s in chosenselections]
sets_sizes = [(sizes,sizes)]
else: raise
percmats = []
coords = []
for s in sets:
coords.append([[],[]])
for ts in uni.trajectory:
sys.stdout.write( "Caching coordinates: frame %d / %d (%3.1f%%)\r" % (a,numframes,float(a)/float(numframes)*100.0) )
sys.stdout.flush()
a+=1
for si,s in enumerate(sets):
if s[0] == s[1]: # triangular case
log.info("Caching coordinates...")
for group in s[0]:
coords[si][0].append(group.coordinates())
coords[si][1].append(group.coordinates())
else: # square case
log.info("Caching coordinates...")
for group in s[0]:
coords[si][0].append(group.coordinates())
for group in s[1]:
coords[si][1].append(group.coordinates())
for si,s in enumerate(sets): # recover the final matrix
if s[0] == s[1]:
this_coords = np.array(np.concatenate(coords[si][0]),dtype=np.float64)
inner_loop = LoopDistances(this_coords, this_coords, co)
percmats.append(inner_loop.run_triangular_mindist(sets_sizes[si][0]))
else:
this_coords1 = np.array(np.concatenate(coords[si][0]),dtype=np.float64)
this_coords2 = np.array(np.concatenate(coords[si][1]),dtype=np.float64)
inner_loop = LoopDistances(this_coords1, this_coords2, co)
percmats.append( inner_loop.run_square_mindist(sets_sizes[si][0], sets_sizes[si][1]))
for si,s in enumerate(sets): # recover the final matrix
Pidxs = sets_idxs[si][0]
Nidxs = sets_idxs[si][1]
if s[0] == s[1]: # triangular case
for j in range(len(s[0])):
for k in range(0,j):
final_percmat[idxs.index(Pidxs[j]), idxs.index(Pidxs[k])] = percmats[si][j,k]
final_percmat[idxs.index(Pidxs[k]), idxs.index(Pidxs[j])] = percmats[si][j,k]
else: # square case
for j in range(len(s[0])):
for k in range(len(s[1])):
final_percmat[idxs.index(Pidxs[j]), idxs.index(Nidxs[k])] = percmats[si][j,k]
final_percmat[idxs.index(Nidxs[k]), idxs.index(Pidxs[j])] = percmats[si][j,k]
final_percmat = np.array(final_percmat, dtype=np.float)/numframes*100.0
else:
all_coms = []
for ts in uni.trajectory:
sys.stdout.write( "now analyzing: frame %d / %d (%3.1f%%)\r" % (a,numframes,float(a)/float(numframes)*100.0) )
sys.stdout.flush()
a+=1
distmat = np.zeros((len(chosenselections),len(chosenselections)))
coms = np.zeros([len(chosenselections),3])
for j in range(len(chosenselections)):
coms[j,:] = chosenselections[j].centerOfMass()
all_coms.append(coms)
all_coms = np.concatenate(all_coms)
inner_loop = LoopDistances(all_coms, all_coms, co)
percmat = inner_loop.run_triangular_distmatrix(coms.shape[0])
distmats = []
final_percmat = np.array(percmat, dtype=np.float)/numframes*100.0
return (final_percmat,distmats)
def dopotential(kbp_atomlist, residues_list, potential_file, seq_dist_co = 0, grof = None, xtcf = None, pdbf = None, uni = None, pdb = None, dofullmatrix = True, kbT=1.0):
residues_list = ["ALA","ARG","ASN","ASP","CYS","GLN","GLU","HIS", "ILE","LEU","LYS","MET","PHE","PRO","SER","THR","TRP","TYR","VAL"] # Residues for which the potential is defined: all except G
log.info("Loading potential definition . . .")
sparses = parse_sparse(potential_file)
log.info("Loading input files...")
if not pdb or not uni:
if not pdbf or not grof or not xtcf:
raise ValueError
pdb,uni = loadsys(pdbf,grof,xtcf)
ok_residues = []
discarded_residues = set()
residue_pairs = []
atom_selections = []
ordered_sparses = []
numframes = len(uni.trajectory)
for i in range(len(uni.residues)):
if uni.residues[i].name in residues_list:
ok_residues.append(i)
else:
discarded_residues.add(uni.residues[i])
continue
for j in ok_residues[:-1]:
ii = i
if not (abs(i-j) < seq_dist_co or uni.residues[ii].segment.name != uni.residues[j].segment.name):
if uni.residues[j].name < uni.residues[ii].name:
ii,j = j,ii
this_sparse = sparses[uni.residues[ii].name][uni.residues[j].name]
this_atoms = (kbp_atomlist[uni.residues[ii].name][this_sparse.p1_1],
kbp_atomlist[uni.residues[ii].name][this_sparse.p1_2],
kbp_atomlist[uni.residues[j].name][this_sparse.p2_1],
kbp_atomlist[uni.residues[j].name][this_sparse.p2_2])
try:
selected_atoms = mda.core.AtomGroup.AtomGroup((uni.residues[ii].atoms[uni.residues[ii].atoms.names().index(this_atoms[0])],
uni.residues[ii].atoms[uni.residues[ii].atoms.names().index(this_atoms[1])],
uni.residues[j].atoms[uni.residues[j].atoms.names().index(this_atoms[2])],
uni.residues[j].atoms[uni.residues[j].atoms.names().index(this_atoms[3])]))
except:
log.warning("could not identify essential atoms for the analysis (%s%s, %s%s)" % ( uni.residues[ii].name, uni.residues[ii].id, uni.residues[j].name, uni.residues[j].id ))
continue
residue_pairs.append((ii,j))
atom_selections.append(selected_atoms)
ordered_sparses.append(this_sparse)
scores = np.zeros((len(residue_pairs)), dtype=float)
a=0
#log.info("the following residues will not be considered: %s" % (", ".join(["%s %s"%(res.name,res.id) for res in discarded_residues] )))
coords = None
#coords = atom_selections[0].coordinates()
#for sel in atom_selections[1:]:
#coords = np.concatenate((coords, sel.coordinates()))
for ts in uni.trajectory:
tmp_coords = []
sys.stdout.write( "now analyzing: frame %d / %d (%3.1f%%)\r" % (a,numframes,float(a)/float(numframes)*100.0) )
sys.stdout.flush()
a+=1
for sel in atom_selections:
#coords = np.concatenate((coords, sel.coordinates()))
tmp_coords.append(sel.coordinates())
coords = np.array(np.concatenate(tmp_coords),dtype=np.float64)
#if coords == None:
#coords = tmp_coords
#else:
#coords = np.concatenate([coords] + [tmp_coords])
#coords = np.array(coords, dtype=np.float64)
#coords = np.array(np.concatenate(coords),dtype=np.float64)
inner_loop = LoopDistances(coords, coords, None)
distances = inner_loop.run_potential_distances(len(atom_selections), 4, 1)
scores += calc_potential(distances, ordered_sparses, pdb, uni, seq_dist_co, kbT=kbT)
scores /= float(len(uni.trajectory))
outstr = ""
for i,s in enumerate(scores):
if abs(s) > 0.000001:
outstr += "%s-%s%s:%s-%s%s\t%.3f\n" % (pdb.residues[residue_pairs[i][0]].segment.name, pdb.residues[residue_pairs[i][0]].name, pdb.residues[residue_pairs[i][0]].id, pdb.residues[residue_pairs[i][1]].segment.name, pdb.residues[residue_pairs[i][1]].name, pdb.residues[residue_pairs[i][1]].id, s)
dm = None
if dofullmatrix:
dm = np.zeros((len(pdb.residues), len(pdb.residues)))
for i,k in enumerate(residue_pairs):
dm[k[0],k[1]] = scores[i]
dm[k[1],k[0]] = scores[i]
return (outstr, dm)
