def do_convergence_test(trajectory, traj_type):
path, file_name = os.path.split(trajectory["path"])
traj_id = file_name.split(".")[0]
base_path = os.path.join("convergence",traj_type,"%s"%traj_id)
for n in range(1000,10000,1000):
print "- Working with %s with %d frames"%(trajectory["path"],n)
this_path = os.path.join(base_path, "%d"%n)
create_dir(this_path)
pdb_path = os.path.join(this_path,"%d.pdb"%n)
extract_first_n_frames(n, trajectory["path"], pdb_path)
script = copy.deepcopy(script_template)
script["global"]["workspace"]["base"] = this_path
script["data"]["files"] = [pdb_path]
# script["clustering"]["evaluation"]["maximum_noise"] = trajectory["noise"]
# script["clustering"]["evaluation"]["minimum_cluster_size"] = int(n/trajectory["max"])
# script["clustering"]["evaluation"]["minimum_clusters"] = trajectory["min"]
# script["clustering"]["evaluation"]["maximum_clusters"] = trajectory["max"]
script_path = os.path.join(this_path,"script.json")
save_dic_in_json(script, script_path)
os.system("python %s %s "%(PYPROCT, script_path))
os.system("rm %s"%pdb_path)
# working_dir = os.path.join("comparisons","profasi","%svs%s"%(A_traj_id,B_traj_id))
# create_dir(working_dir)
# script["global"]["workspace"]["base"] = working_dir
# script["data"]["files"] = [A_traj, B_traj]
# script_path = os.path.join(working_dir,"script.json")
# save_dic_in_json(script, script_path)
# os.system("python %s %s "%(PYPROCT, script_path))
# initial_j_offset = 0
# initial_i_offset = 0
# Campari vs Profasi
for i in [15]: #range(0,len(profasi_trajs)):
A_traj = campari_trajs[i]
path, file = os.path.split(A_traj)
A_traj_id = file.split(".")[0]
B_traj = profasi_trajs[i]
path, file = os.path.split(B_traj)
B_traj_id = file.split(".")[0]
script = copy.deepcopy(script_template)
working_dir = os.path.join("comparisons","campari_vs_profasi","%svs%s"%(A_traj_id,B_traj_id))
create_dir(working_dir)
script["global"]["workspace"]["base"] = working_dir
script["data"]["files"] = [{"file":A_traj,"base_selection":"resnum 3to53"},{"file": B_traj,"base_selection":"resnum 3to53"}]
script_path = os.path.join(working_dir,"script.json")
save_dic_in_json(script, script_path)
os.system("python %s %s "%(PYPROCT, script_path))
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] = {}
results[cluster.id]["max_energy"] = numpy.max(energies)
results[cluster.id]["min_energy"] = numpy.min(energies)
results[cluster.id]["mean_energy"] = numpy.mean(energies)
results[cluster.id]["mean_distance"] = numpy.mean(distances)
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
#####################################################################
#####################################################################
best_clustering = get_best_clustering(working_directory)
best_clustering = Clustering.from_dic(best_clustering["clustering"])
scores = []
for a_cluster in best_clustering.clusters: