def main(ligand, clusters_file, conf_folder, topology=None):
trajFolder = "allTrajs_nonRepeat"
cluster_centers = np.loadtxt(clusters_file)
if not os.path.exists("discretized"):
os.makedirs("discretized")
if not os.path.exists(trajFolder):
os.makedirs(trajFolder)
stride = 1
clusterCountsThreshold = 0
trajBasename = "coord*"
if topology is not None:
topology_contents = utilities.getTopologyFile(topology)
else:
topology_contents = None
epoch_folders = utilities.get_epoch_folders(conf_folder)
numClusters = cluster_centers.shape[0]
coordinates = [[] for cl in range(numClusters)]
for it in epoch_folders:
files = glob.glob(conf_folder + "%s/extractedCoordinates/coord*" % it)
for f in files:
traj = os.path.splitext(f)[0].split("_")[-1]
shutil.copy(f, trajFolder + "/coord_%s_%s.dat" % (it, traj))
clusteringObject = cluster.Cluster(numClusters,
trajFolder,
trajBasename,
alwaysCluster=False,
stride=stride)
clusteringObject.clusterTrajectories()
clusteringObject.eliminateLowPopulatedClusters(clusterCountsThreshold)
for i in range(numClusters):
if not os.path.exists("cluster_%d" % i):
os.makedirs("cluster_%d/allStructures" % i)
dtrajs_files = glob.glob("discretized/*.disctraj")
for dtraj in dtrajs_files:
print(dtraj)
traj = np.loadtxt(dtraj)
epoch, traj_num = map(int,
os.path.splitext(dtraj)[0].split("_", 3)[1:])
trajPositions = np.loadtxt(trajFolder + "/coord_%d_%d.dat" %
(epoch, traj_num))
trajFile = glob.glob(
os.path.join(conf_folder + "%d/trajectory_%d*" %
(epoch, traj_num)))[0]
snapshots = utilities.getSnapshots(trajFile, topology=topology)
for nSnap, cluster_num in enumerate(traj):
coordinates[int(cluster_num)].append(trajPositions[nSnap])
filename = "cluster_%d/allStructures/conf_%d_%d_%d.pdb" % (
cluster_num, epoch, traj_num, nSnap)
if isinstance(snapshots[nSnap], basestring):
with open(filename, "w") as fw:
fw.write(snapshots[nSnap])
else:
utilities.write_mdtraj_object_PDB(snapshots[nSnap], filename,
topology_contents)
for cl in range(numClusters):
np.savetxt("cluster_%d/positions.dat" % cl, coordinates[cl])
def main(representatives_files, path_structures, output="", clusters=None, trajNames="trajectory", topology=None):
if clusters is None:
clusters = ['a']
# Load the representative structures file
try:
clusters_info = np.loadtxt(representatives_files, skiprows=1, dtype=int)
except IOError:
raise IOError("Couldn't find a representative file in %s, please check that the path is correct" % representatives_files)
# Organize to minimise pdb loading
if clusters != ['a']:
clusters_info = clusters_info[list(map(int, clusters))]
extract_info = getExtractInfo(clusters_info)
# Write appropiate pdbs
destFolder = output
if not output:
destFolder, _ = os.path.split(representatives_files)
destFolder = os.path.join(destFolder, "representative_structures_pdbs")
if not os.path.exists(destFolder):
os.makedirs(destFolder)
else:
destFolder += "_%d"
it = 1
while os.path.exists(destFolder % it):
it += 1
destFolder %= it
os.makedirs(destFolder)
structureFolder = os.path.join(path_structures, "%d", trajNames+"_%d.*")
if topology is not None:
topology_contents = utilities.getTopologyFile(topology)
else:
topology_contents = None
for trajFile, extraInfo in extract_info.items():
try:
pdbFile = glob.glob(structureFolder % trajFile)[0]
except IndexError:
raise ValueError("Structure %s not found" % (structureFolder % trajFile))
try:
snapshots = utilities.getSnapshots(pdbFile, topology=topology)
except IOError:
raise IOError("Unable to open %s, please check that the path to structures provided is correct" % pdbFile)
for pair in extraInfo:
if topology_contents is None:
with open(os.path.join(destFolder, "cluster_%d.pdb" % pair[0]), "w") as fw:
fw.write(snapshots[pair[1]])
fw.write("\n")
else:
utilities.write_mdtraj_object_PDB(snapshots[pair[1]], os.path.join(destFolder, "cluster_%d.pdb" % pair[0]), topology=topology_contents)
def writeInitialStructures(centers_info, filename_template, topology=None):
if topology is not None:
topology_contents = utilities.getTopologyFile(topology)
for cluster_num in centers_info:
epoch_num, traj_num, snap_num = map(
int, centers_info[cluster_num]['structure'])
trajectory = glob.glob("%d/trajectory_%d*" % (epoch_num, traj_num))[0]
snapshots = utilities.getSnapshots(trajectory, topology=topology)
if isinstance(snapshots[0], basestring):
with open(filename_template % cluster_num, "w") as fw:
fw.write(snapshots[snap_num])
else:
utilities.write_mdtraj_object_PDB(snapshots[snap_num],
filename_template % cluster_num,
topology_contents)
def main(n_clusters,
output_folder,
SASAColumn,
norm_energy,
num_bins,
percentile,
plots,
atom_Ids,
folder_name,
traj_basename,
cluster_energy,
topology=None):
energyColumn = 3
if output_folder is not None:
outputFolder = os.path.join(output_folder, "")
if not os.path.exists(outputFolder):
os.makedirs(outputFolder)
else:
outputFolder = ""
extractCoords.main(folder_name,
lig_resname=ligand_resname,
non_Repeat=True,
atom_Ids=atom_Ids)
epochFolders = utilities.get_epoch_folders(folder_name)
points = []
for epoch in epochFolders:
report_files = glob.glob(os.path.join(epoch, "*report*"))
report_files.sort(key=lambda x: int(x[x.rfind("_") + 1:]))
for report_name in report_files:
traj_num = int(report_name[report_name.rfind("_") + 1:])
coordinates = np.loadtxt(
os.path.join(
folder_name, "%s/extractedCoordinates/coord_%d.dat" %
(epoch, traj_num)))
report = np.loadtxt(report_name)
if len(report.shape) < 2:
points.append([
report[energyColumn], report[SASAColumn],
int(epoch), traj_num, 0
] + coordinates[1:].tolist())
else:
epoch_line = np.array([int(epoch)] * report.shape[0])
traj_line = np.array([traj_num] * report.shape[0])
snapshot_line = np.array(range(report.shape[0]))
points.extend(
np.hstack(
(report[:, (energyColumn, SASAColumn)],
epoch_line[:, np.newaxis], traj_line[:, np.newaxis],
snapshot_line[:, np.newaxis], coordinates[:, 1:])))
points = np.array(points)
points = points[points[:, 1].argsort()]
minSASA = points[0, 1]
maxSASA = points[-1, 1]
left_bins = np.linspace(minSASA, maxSASA, num=num_bins, endpoint=False)
indices = np.searchsorted(points[:, 1], left_bins)
thresholds = np.array([
np.percentile(points[i:j, 0], percentile)
for i, j in zip(indices[:-1], indices[1:])
])
new_points = []
occupation = []
for ij, (i, j) in enumerate(zip(indices[:-1], indices[1:])):
found = np.where(points[i:j, 0] < thresholds[ij])[0]
occupation.append(len(found))
if len(found) == 1:
new_points.append(points[found + i])
elif len(found) > 1:
new_points.extend(points[found + i])
points = np.array(new_points)
if norm_energy:
energyMin = points.min(axis=0)[0]
points[:, 0] -= energyMin
energyMax = points.max(axis=0)[0]
points[:, 0] /= energyMax
if cluster_energy:
print("Clustering using energy and SASA")
kmeans = KMeans(n_clusters=n_clusters).fit(points[:, :2])
title = "clusters_%d_energy_SASA.pdb"
else:
print("Clustering using ligand coordinates")
kmeans = KMeans(n_clusters=n_clusters).fit(points[:, 5:8])
title = "clusters_%d_energy_SASA_coords.pdb"
centers_energy = []
centers_coords = []
if topology is not None:
topology_contents = utilities.getTopologyFile(topology)
else:
topology = None
for i, center in enumerate(kmeans.cluster_centers_):
if cluster_energy:
dist = np.linalg.norm((points[:, :2] - center), axis=1)
else:
dist = np.linalg.norm((points[:, 5:8] - center), axis=1)
epoch, traj, snapshot = points[dist.argmin(), 2:5]
centers_energy.append(points[dist.argmin(), :2])
centers_coords.append(points[dist.argmin(), 5:8])
traj_file = glob.glob("%d/%s_%d*" % (epoch, traj_basename, traj))[0]
conf = utilities.getSnapshots(traj_file,
topology=topology)[int(snapshot)]
if isinstance(conf, basestring):
with open(os.path.join(outputFolder, "initial_%d.pdb" % i),
"w") as fw:
fw.write(conf)
else:
utilities.write_mdtraj_object_PDB(
conf, os.path.join(outputFolder, "initial_%d.pdb" % i),
topology_contents)
centers_energy = np.array(centers_energy)
centers_coords = np.array(centers_coords)
writePDB(centers_coords, os.path.join(outputFolder, title % n_clusters))
if plots:
plt.scatter(points[:, 1], points[:, 0], c=kmeans.labels_, alpha=0.5)
plt.scatter(centers_energy[:, 1],
centers_energy[:, 0],
c=list(range(n_clusters)),
marker='x',
s=56,
zorder=1)
plt.xlabel("SASA")
if norm_energy:
plt.ylabel("Energy (normalized)")
plt.savefig(
os.path.join(outputFolder, "clusters_energy_normalized.png"))
else:
plt.ylabel("Energy (kcal/mol)")
plt.savefig(
os.path.join(outputFolder, "clusters_no_normalized.png"))
plt.show()
topology = None
filename = "conformation_data.dat"
if not os.path.exists(filename):
raise IOError(
"File conformation_data.dat not found, please be sure to run extract_COM_metric.py before this script"
)
print("Selected names: ", ' '.join(names))
with open(filename) as f:
f.readline()
for line in f:
line = line.strip().split()
if line[0] not in names:
continue
epoch, iTraj, nSnap = line[1:4]
report = np.loadtxt("%s/report_%s" % (epoch, iTraj))
print(line[0], "=>",
"epoch %s, trajectory %s, snapshot %s" % tuple(line[1:4]),
"metric", report[int(nSnap), metricCol])
traj_file = glob.glob("%s/%s_%s*" % (epoch, traj_name, iTraj))
snapshots = utilities.getSnapshots(traj_file, topology=topology)
if isinstance(snapshots[int(nSnap)], basestring):
with open(
output_folder + "conf_%s_%s_%s.pdb" %
(epoch, iTraj, nSnap), "w") as fw:
fw.write(snapshots[int(nSnap)])
else:
utilities.write_mdtraj_object_PDB(
snapshots[int(nSnap)],
output_folder + "conf_%s_%s_%s.pdb" % (epoch, iTraj, nSnap),
topology_contents)