def process_results(this_folders):
results_matrix = {}
#fig = plt.figure(figsize=(18, 18))
# Plot by temperature
for folder in this_folders:
subfolder_results = []
for subfolder in subfolders:
results_file = os.path.join(folder, subfolder, "results", "results.json")
if os.path.exists(results_file):
results = load_dic_in_json(results_file)
print results_file, results["selected"][results["best_clustering"]]["clustering"]["number_of_clusters"],\
results["selected"][results["best_clustering"]]["evaluation"]["Noise level"]
subfolder_results.append(results["selected"][results["best_clustering"]]["clustering"]["number_of_clusters"])
else:
subfolder_results.append(0.)
results_matrix[folder] = subfolder_results
plt.plot(range(len(subfolders)), subfolder_results, linewidth=2, label = folder.split("/")[2])
plt.legend(loc=2,prop={'size':6})
plt.show()
## Now plot by trajectory length
for i in range(len(subfolders)):
plot_by_size = []
for folder in this_folders:
plot_by_size.append(results_matrix[folder][i])
plt.plot(range(len(this_folders)), plot_by_size, linewidth=2,label = subfolders[i])
plt.legend(prop={'size':6})
plt.show()
def process_campari_vs_profasi(campari, profasi):
data = []
for i in range(len(campari)):
A_folder = campari[i]
B_folder = profasi[i]
results_file =os.path.join("comparisons","campari_vs_profasi", "%svs%s"%(A_folder, B_folder), "results", "conf_space_comp.json")
if os.path.exists(results_file):
data.append(load_dic_in_json(results_file)["overlap"])
else:
data.append(0.)
print results_file, "not found"
plt.plot(range(len(data)), data, linewidth=2)
plt.show()
def process_matrix(folders, image_path, sim_type):
data = []
for i in range(0,len(folders)-1):
A_folder = folders[i]
for j in range(i+1,len(campari_folders)):
B_folder = folders[j]
results_file = os.path.join("comparisons",sim_type, "%svs%s"%(A_folder, B_folder), "results", "conf_space_comp.json")
print results_file
if os.path.exists(results_file):
data.append(load_dic_in_json(results_file)["overlap"])
else:
data.append(0.)
print data
matrixToImage(CondensedMatrix(data), image_path, diagonal_value=1.)
def process_matrix_stats(this_folders):
mean = []
stddev = []
for folder in this_folders:
subfolder = "9000"
matrix_stats_file = os.path.join(folder, subfolder, "matrix", "statistics.json")
if os.path.exists(matrix_stats_file):
stats = load_dic_in_json(matrix_stats_file)
mean.append(stats["Mean"])
stddev.append(stats["Std. Dev."])
else:
mean.append(0)
stddev.append(0)
plt.errorbar(range(len(mean)), mean, yerr = stddev, linewidth=2)
plt.show()
"""
Created on 27/03/2014
@author: victor
"""
import copy
import os
from tools import load_dic_in_json, create_dir, save_dic_in_json
script_template = load_dic_in_json("template.json")
campari_trajs = [
"trajectories/campari/N_000_.pdb",
"trajectories/campari/N_001_.pdb",
"trajectories/campari/N_002_.pdb",
"trajectories/campari/N_003_.pdb",
"trajectories/campari/N_004_.pdb",
"trajectories/campari/N_005_.pdb",
"trajectories/campari/N_006_.pdb",
"trajectories/campari/N_007_.pdb",
"trajectories/campari/N_008_.pdb",
"trajectories/campari/N_009_.pdb",
"trajectories/campari/N_010_.pdb",
"trajectories/campari/N_011_.pdb",
"trajectories/campari/N_012_.pdb",
"trajectories/campari/N_013_.pdb",
"trajectories/campari/N_014_.pdb",
"trajectories/campari/N_015_.pdb"
]
selection = filterRecords("'L1 Binding Ene' < -226 and 'L1 Binding Ene' > -424 and 'L1(24.954.352.7)' < 14.1 and 'L1(24.954.352.7)' > 5.9", records)
genSingleTrajFast(FILTERED_PDB_FILE, records, selection)
genMetricsFile(METRICS_FILE, ["L1(24.954.352.7)","L1 Binding Ene"], selection)
metrics = genMetrics(["L1(24.954.352.7)","L1 Binding Ene"], selection).T
metrics = numpy.loadtxt(METRICS_FILE).T
#--------------------------------
# Prepare the clustering for this guy
#--------------------------------
## Load template and modify its contents for this case
CLUSTERING_PATH = os.path.join(RESULTS_PATH,"%s_%s_clustering"%(options.drug, options.protein))
MAX_CLUSTERS = 10
SCRIPT_PATH = os.path.join(RESULTS_PATH,"clustering.json")
OUT_FILE = os.path.join(RESULTS_PATH, "clustering.out")
script = load_dic_in_json(options.template)
script["global"]["workspace"]["base"] = CLUSTERING_PATH
script["data"]["files"].append(FILTERED_PDB_FILE)
script["clustering"]["evaluation"]["maximum_clusters"] = MAX_CLUSTERS
save_dic_in_json(script, SCRIPT_PATH)
os.system("python -m pyproct.main %s > %s"%(SCRIPT_PATH, OUT_FILE))
best_clustering = Clustering.from_dic(get_best_clustering(CLUSTERING_PATH)["clustering"])
#--------------------------------
# Now calculate the values
#--------------------------------
results = {}
for cluster in best_clustering.clusters:
energies = metrics[1][cluster.all_elements]
distances = metrics[0][cluster.all_elements]
results[cluster.id] = {}
# RMSD_script["data"]["files"].append(os.path.join("RDCvsRMSD", "campari.pdb"))
#
# RCD_script = copy.deepcopy(template_script)
# RCD_script["global"]["workspace"]["base"] = os.path.join("RDCvsRMSD", "campari", "RDC", "clustering")
# RCD_script["data"]["matrix"]["method"] = "load"
# RCD_script["data"]["matrix"]["parameters"]["path"] = os.path.join("RDCvsRMSD", "campari", "RDC", "matrix")
# RCD_script["data"]["files"].append(os.path.join("RDCvsRMSD", "campari.pdb"))
#
# tools.save_dic_in_json(RCD_script, os.path.join("RDCvsRMSD", "campari", "RDC", "script.json"))
# tools.save_dic_in_json(RMSD_script, os.path.join("RDCvsRMSD", "campari", "RMSD", "script.json"))
#
# os.system("python %s %s "%(PYPROCT, os.path.join("RDCvsRMSD", "campari", "RDC", "script.json")))
# os.system("python %s %s "%(PYPROCT, os.path.join("RDCvsRMSD", "campari", "RMSD", "script.json")))
results = tools.load_dic_in_json(os.path.join("RDCvsRMSD", "campari", "RDC_refined", "clustering","results","results.json"))
RDC_clustering = Clustering.from_dic(results["selected"][results["best_clustering"]]["clustering"]).gen_class_list(number_of_elements = 5926)
results = tools.load_dic_in_json(os.path.join("RDCvsRMSD", "campari", "RMSD_refined", "clustering","results","results.json"))
RMSD_clustering = Clustering.from_dic(results["selected"][results["best_clustering"]]["clustering"]).gen_class_list(number_of_elements = 5926)
results = tools.load_dic_in_json(os.path.join("RDCvsRMSD", "campari", "Dihedral", "clustering","results","results.json"))
Dihedral_clustering = Clustering.from_dic(results["selected"][results["best_clustering"]]["clustering"]).gen_class_list(number_of_elements = 5926)
results = tools.load_dic_in_json(os.path.join("RDCvsRMSD", "campari", "Dihedral", "clustering","results","results.json"))
Dihedral_bad_score = Clustering.from_dic(results["selected"]["clustering_0098"]["clustering"]).gen_class_list(number_of_elements = 5926)
results = tools.load_dic_in_json(os.path.join("RDCvsRMSD", "campari", "Dihedral", "clustering","results","results.json"))
Dihedral_medium_score = Clustering.from_dic(results["selected"]["clustering_0056"]["clustering"]).gen_class_list(number_of_elements = 5926)
results = tools.load_dic_in_json(os.path.join("RDCvsRMSD", "campari", "Dihedral", "clustering","results","results.json"))
records = []
processFile(traj_pdb, records, True)
all_metrics = genMetrics(plots["totale_spawning"], records)
matrix_data = scipy.spatial.distance.pdist(normalize_metrics(all_metrics), 'euclidean')
m_handler = MatrixHandler()
m_handler.distance_matrix = CondensedMatrix(matrix_data)
matrix_file = os.path.join(base_dir, TENERGY_SPAWN_MATRIX)
m_handler.saveMatrix(matrix_file)
#######################################################################################################################
# Cluster by metrics
#######################################################################################################################
print "* Spawning - totalE clustering"
be_rmsd_clustering_script_path = os.path.join(base_dir, 'scripts', CLUSTERING_SPAWN_TOTE_SCRIPT)
working_directory = os.path.join(base_dir, TOTALE_SPAWN_WORKSPACE)
params = load_dic_in_json(be_rmsd_clustering_script_path)
params['global']['workspace']['base'] = working_directory
params['data']['files'] = [os.path.join(os.getcwd(), traj_pdb)]
params['data']['matrix']['parameters']['path'] = matrix_file
save_dic_in_json(params, be_rmsd_clustering_script_path)
use_pyproct(working_directory, be_rmsd_clustering_script_path)
#######################################################################################################################
# Get 5 representatives. 2 strategies.
#######################################################################################################################
#####################################################################
#####################################################################
# Work only with best clustering/ find best cluster
#####################################################################
#####################################################################
