def get_centroid(points, metric_name, num_confs, labs, traj_file, inputfile):
"""
Takes the output from DBSCAN and produces the trajectory and centroid from each cluster.
Parameters:
points (numpy.array): The points fed to the clstering algorithm.
metric_name (str): The type of data the points represent.
labs (numpy.array): The cluster each point belongs to.
traj_file (str): The analyzed trajectory file.
inputfile (str): The input file used to run the analyzed simulation.
"""
print("INFO: splitting clusters...", file=stderr)
print("INFO: Will write cluster trajectories to traj_<cluster_number>.dat", file=stderr)
print ("cluster\tn\tavg_E\tE_dev\tavg_H\tH_dev\tcentroid_t")
for cluster in (set(labs)):
if metric_name == "precomputed":
masked = points[labs == cluster]
in_cluster_id = np.sum(masked, axis = 1).argmin()
in_cluster = list(labs).count(cluster)
centroid_id = find_element(in_cluster_id, cluster, labs)
top_file = get_input_parameter(inputfile, "topology")
r = LorenzoReader2(traj_file, top_file)
output = r._get_system(N_skip=centroid_id)
filename = "centroid"+str(cluster)
output.print_lorenzo_output(filename+".dat", filename+".top")
make_heatmap(inputfile, output, filename)
def main():
#doesn't actually do anything...
import argparse
from UTILS.readers import LorenzoReader2, get_input_parameter
parser = argparse.ArgumentParser(
description=
"A python wrapper for getting all vectors between nucleotides from a simulation"
)
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 file containing the configurations of which the contact map is needed"
)
args = parser.parse_args()
from oxDNA_analysis_tools.config import check_dependencies
check_dependencies(["python", "numpy"])
inputfile = args.inputfile[0]
traj_file = args.trajectory[0]
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
r = LorenzoReader2(traj_file, top_file)
system = r._get_system()
while system:
m = all_vectors(inputfile, system, True)
system = r._get_system()
print("well, it finished...")
nargs=1,
type=int,
dest='parallel',
help="(optional) How many cores to use")
args = parser.parse_args()
from config import check_dependencies
check_dependencies(["python", "numpy", "matplotlib"])
traj_file = args.trajectory[0]
inputfile = args.inputfile[0]
parallel = args.parallel
if parallel:
n_cpus = args.parallel[0]
top_file = get_input_parameter(inputfile, "topology")
if "RNA" in get_input_parameter(inputfile, "interaction_type"):
environ["OXRNA"] = "1"
else:
environ["OXRNA"] = "0"
num_confs = cal_confs(traj_file)
import UTILS.base #this needs to be imported after the model type is set
r2 = LorenzoReader2(traj_file, top_file)
#how do you want to get your eRMSDs? Do you need to do the time-consuming calculation or is it done and you have a pickle?
if not parallel:
r1 = LorenzoReader2(traj_file, top_file)
eRMSDs = get_eRMSDs(r1, r2, inputfile, traj_file, top_file, num_confs)
if parallel:
#-o names the output file
if args.output:
outfile = args.output[0]
else:
outfile = "forces.txt"
print(
"INFO: No outfile name provided, defaulting to \"{}\"".format(outfile),
file=stderr)
if args.pairs:
pairsfile = args.pairs[0]
else:
pairsfile = False
#Get relevant parameters from the input file
top_file = get_input_parameter(inputfile, "topology")
#get base pairs
r = LorenzoReader2(conf_file, top_file)
mysystem = r._get_system()
out = output_bonds(inputfile, mysystem)
out = out.split('\n')
#Find out the forming bonds series
print("INFO: Analyze the output...", file=stderr)
Bonded = {}
for i in out:
if i[0] == '#':
continue
splitline = i.split(' ')
try:
n_dists = sum([len(l) for l in p1s])
#Make sure that the input is correctly formatted
if (len(input_files) != len(trajectories)):
print(
"ERROR: bad input arguments\nPlease supply an equal number of input and, trajectory files",
file=stderr)
exit(1)
if len(p1s) != len(p2s):
print(
"ERROR: bad input arguments\nPlease supply an even number of particles",
file=stderr)
exit(1)
#get the topology from the input
topology_files = [get_input_parameter(i, "topology") for i in input_files]
#-o names the output file
if args.output:
outfile = args.output[0]
else:
print("INFO: No outfile name provided, defaulting to \"distance.png\"",
file=stderr)
outfile = "distance.png"
#-f defines which type of graph to produce
hist = False
lineplt = False
if args.format:
if "histogram" in args.format:
hist = True
def split_trajectory(traj_file, inputfile, labs, n_clusters):
"""
Splits the trajectory into the clustered trajectories
Parameters:
traj_file (str): The analyzed trajectory file.
inputfile (str): The input file used to run the analyzed simulation.
labs (numpy.array): The cluster each point belongs to.
"""
top_file = get_input_parameter(inputfile, "topology")
print ("cluster\tmembers")
#energies = []
#H_counts = []
for cluster in (set(labs)):
in_cluster = list(labs).count(cluster)
print ("{}\t{}".format(cluster, in_cluster))
#energies.append([])
#H_counts.append([])
#for making trajectories of each cluster
try:
remove("cluster_"+str(cluster)+".dat")
except: pass
confid = 0
r1 = LorenzoReader2(traj_file, top_file)
system = r1._get_system()
print ("INFO: splitting trajectory...", file=stderr)
print ("INFO: Will write cluster trajectories to cluster_<cluster number>.dat", file=stderr)
while system != False:
system.print_traj_output("cluster_"+str(labs[confid])+".dat", "/dev/null")
###########
#If you want to get additional information about a cluster, add that code here
#for example, if you want average energy and hydrogen bonds:
'''
energies[labs[confid]].append(0)
H_counts[labs[confid]].append(0)
system.map_nucleotides_to_strands()
out = output_bonds(inputfile, system)
for line in out.split('\n'):
if line[0] != '#' and line[0] != '\n':
line = line.split(" ")
for m in line[2:9]:
energies[labs[confid]][-1] += float(m)
if float(line[6]) != 0:
H_counts[labs[confid]][-1] += 1
energies[labs[confid]][-1] /= len(system._nucleotides)
'''
############
confid += 1
system = r1._get_system()
#This is where you print the information about each cluster
'''
