eRMSDs = get_eRMSDs(r1, r2, inputfile, traj_file, top_file, num_confs)
if parallel:
out = parallelize.fire_multiprocess(traj_file,
top_file,
get_eRMSDs,
num_confs,
n_cpus,
r2,
inputfile,
traj_file,
top_file,
matrix=True)
eRMSDs = np.sum((i for i in out), axis=0)
#eRMSDs = pickle.load(open('tmp_eRMSDs', 'rb'))
#the eRMSD matrix is actually only half a matrix
for ni, i in enumerate(eRMSDs):
for nj, j in enumerate(i):
eRMSDs[nj][ni] = j
if ni == nj:
eRMSDs[ni][nj] = 0
#since calculating the eRMSDs are so time-consuming to calculate we're gonna pickle it to iterate the DBSCAN later.
with open("tmp_eRMSDs", "wb") as file:
pickle.dump(eRMSDs, file)
###############################################################################################################
#Next, we're going to perform a DBSCAN on that matrix of eRMSDs to find clusters of similar structures
perform_DBSCAN(eRMSDs, num_confs, traj_file, inputfile)
##############################################################################################################
eRMSDs = get_eRMSDs(r1, r2, inputfile, traj_file, top_file, num_confs)
if parallel:
out = parallelize_lorenzo_onefile.fire_multiprocess(traj_file,
top_file,
get_eRMSDs,
num_confs,
n_cpus,
r2,
inputfile,
traj_file,
top_file,
matrix=True)
eRMSDs = np.sum((i for i in out), axis=0)
#eRMSDs = pickle.load(open('tmp_eRMSDs', 'rb'))
#the eRMSD matrix is actually only half a matrix
for ni, i in enumerate(eRMSDs):
for nj, j in enumerate(i):
eRMSDs[nj][ni] = j
if ni == nj:
eRMSDs[ni][nj] = 0
#since calculating the eRMSDs are so time-consuming to calculate we're gonna pickle it to iterate the DBSCAN later.
with open("tmp_eRMSDs", "wb") as file:
pickle.dump(eRMSDs, file)
###############################################################################################################
#Next, we're going to perform a DBSCAN on that matrix of eRMSDs to find clusters of similar structures
perform_DBSCAN(eRMSDs, num_confs, traj_file, inputfile, "precomputed")
##############################################################################################################
#Create an oxView overlay showing the first SUM components
SUM = 1
print("INFO: Change the number of eigenvalues to sum and display by modifying the SUM variable in the script. Current value: {}".format(SUM), file=stderr)
weighted_sum = np.zeros_like(evectors[0])
for i in range(0, SUM): #how many eigenvalues do you want?
weighted_sum += evalues[i]*evectors[i]
prep_pos_for_json = lambda conf: list(
list(p) for p in conf
)
with catch_warnings(): #this produces an annoying warning about casting complex values to real values that is not relevant
simplefilter("ignore")
output_vectors = weighted_sum.reshape(int(weighted_sum.shape[0]/3), 3).astype(float)
with open(outfile, "w+") as file:
file.write(dumps({
"pca" : prep_pos_for_json(output_vectors)
}))
#If we're running clustering, feed the linear terms into the clusterer
if cluster:
print("INFO: Mapping configurations to component space...", file=stderr)
#If you want to cluster on only some of the components, uncomment this
#out = out[:,0:3]
from clustering import perform_DBSCAN
labs = perform_DBSCAN(out, num_confs, traj_file, inputfile, "euclidean")
if outfile.split(".")[1] != "json":
raise Exception
f = outfile.split(".")[0] + str(i) + "." + outfile.split(".")[1]
except:
print(
"ERROR: oxView overlays must have a '.json' extension. No overlays will be produced",
file=stderr)
break
out = np.sqrt(evalues[i]) * evectors[i]
with catch_warnings(
): #this produces an annoying warning about casting complex values to real values that is not relevant
simplefilter("ignore")
output_vectors = out.reshape(int(out.shape[0] / 3),
3).astype(float)
with open(f, "w+") as file:
file.write(dumps({"pca": prep_pos_for_json(output_vectors)}))
#If we're running clustering, feed the linear terms into the clusterer
if cluster:
print("INFO: Mapping configurations to component space...",
file=stderr)
#If you want to cluster on only some of the components, uncomment this
#out = out[:,0:3]
from clustering import perform_DBSCAN
labs = perform_DBSCAN(coordinates, num_confs, traj_file, inputfile,
"euclidean")
if lineplt == True:
if hist == True:
#clear the histogram plot
plt.clf()
#if making two plots, automatically append the plot type to the output file name
out = outfile[:outfile.find(".")] + "_traj" + outfile[outfile.
find("."):]
else:
out = outfile
graph_count = 0
for traj_set in distances:
for dist_list in traj_set:
a = plt.plot(dist_list, alpha=0.5, label=names[graph_count])
graph_count += 1
plt.xlabel("Simulation Steps")
plt.ylabel("Distance (nm)")
plt.legend()
#plt.show()
print("INFO: Writing trajectory plot to file {}".format(out),
file=stderr)
plt.savefig("{}".format(out))
if cluster == True:
if not all([x == trajectories[0] for x in trajectories]):
print("ERROR: Clustering can only be run on a single trajectory",
file=stderr)
exit(1)
from clustering import perform_DBSCAN
labs = perform_DBSCAN(distances[0].T, len(distances[0][0]),
trajectories[0], input_files[0], "euclidean")
def main():
parser = argparse.ArgumentParser(
prog=path.basename(__file__),
description=
"Calculates a principal component analysis of nucleotide deviations over a trajectory"
)
parser.add_argument('inputfile',
type=str,
nargs=1,
help="The inputfile used to run the simulation")
parser.add_argument('trajectory',
type=str,
nargs=1,
help='the trajectory file you wish to analyze')
parser.add_argument(
'meanfile',
type=str,
nargs=1,
help='The mean structure .json file from compute_mean.py')
parser.add_argument(
'outfile',
type=str,
nargs=1,
help='the name of the .json file where the PCA will be written')
parser.add_argument('-p',
metavar='num_cpus',
nargs=1,
type=int,
dest='parallel',
help="(optional) How many cores to use")
parser.add_argument(
'-c',
metavar='cluster',
dest='cluster',
action='store_const',
const=True,
default=False,
help="Run the clusterer on each configuration's position in PCA space?"
)
args = parser.parse_args()
check_dependencies(["python", "numpy", "Bio"])
traj_file = args.trajectory[0]
inputfile = args.inputfile[0]
mean_file = args.meanfile[0]
outfile = args.outfile[0]
parallel = args.parallel
if parallel:
n_cpus = args.parallel[0]
#-c makes it run the clusterer on the output
cluster = args.cluster
top_file = get_input_parameter(inputfile, "topology")
if "RNA" in get_input_parameter(inputfile, "interaction_type"):
environ["OXRNA"] = "1"
else:
environ["OXRNA"] = "0"
import UTILS.base #this needs to be imported after the model type is set
num_confs = cal_confs(traj_file)
if mean_file.split(".")[-1] == "json":
with open(mean_file) as file:
align_conf = load(file)['g_mean']
elif mean_file.split(".")[-1] == "dat":
fetch_np = lambda conf: np.array([n.cm_pos for n in conf._nucleotides])
with LorenzoReader2(mean_file, top_file) as reader:
s = reader._get_system()
align_conf = fetch_np(s)
cms = np.mean(align_conf,
axis=0) #all structures must have the same center of mass
align_conf -= cms
#Compute the deviations
if not parallel:
r = LorenzoReader2(traj_file, top_file)
deviations_matrix = get_pca(r, align_conf, num_confs)
if parallel:
out = parallelize_lorenzo_onefile.fire_multiprocess(
traj_file, top_file, get_pca, num_confs, n_cpus, align_conf)
deviations_matrix = np.concatenate([i for i in out])
#now that we have the deviations matrix we're gonna get the covariance and PCA it
#note that in the future we might want a switch for covariance vs correlation matrix because correlation (cov/stdev so all diagonals are 1) is better for really floppy structures
pca = PCA(n_components=3)
pca.fit(deviations_matrix)
transformed = pca.transform(deviations_matrix)
#THIS IS AS FAR AS I GOT
import matplotlib.pyplot as plt
print("INFO: Saving scree plot to scree.png", file=stderr)
plt.scatter(range(0, len(evalues)), evalues, s=25)
plt.xlabel("component")
plt.ylabel("eigenvalue")
plt.savefig("scree.png")
print(
"INFO: Creating coordinate plot from first three eigenvectors. Saving to coordinates.png",
file=stderr)
#if you want to weight the components by their eigenvectors
#mul = np.einsum('ij,i->ij',evectors[0:3], evalues[0:3])
mul = evectors
#reconstruct configurations in component space
out = np.dot(deviations_matrix, mul).astype(float)
#make a quick plot from the first three components
from mpl_toolkits.mplot3d import Axes3D
fig = plt.figure()
ax = fig.gca(projection='3d')
ax.scatter(out[:, 0], out[:, 1], out[:, 2], c='g', s=25)
plt.savefig("coordinates.png")
#Create an oxView overlay showing the first SUM components
SUM = 1
print(
"INFO: Change the number of eigenvalues to sum and display by modifying the SUM variable in the script. Current value: {}"
.format(SUM),
file=stderr)
weighted_sum = np.zeros_like(evectors[0])
for i in range(0, SUM): #how many eigenvalues do you want?
weighted_sum += evalues[i] * evectors[i]
prep_pos_for_json = lambda conf: list(list(p) for p in conf)
with catch_warnings(
): #this produces an annoying warning about casting complex values to real values that is not relevant
simplefilter("ignore")
output_vectors = weighted_sum.reshape(int(weighted_sum.shape[0] / 3),
3).astype(float)
with open(outfile, "w+") as file:
file.write(dumps({"pca": prep_pos_for_json(output_vectors)}))
#If we're running clustering, feed the linear terms into the clusterer
if cluster:
print("INFO: Mapping configurations to component space...",
file=stderr)
#If you want to cluster on only some of the components, uncomment this
#out = out[:,0:3]
from clustering import perform_DBSCAN
labs = perform_DBSCAN(out, num_confs, traj_file, inputfile,
"euclidean", 12, 8)
