Example #1
0
 
 #--------------------------------  
 # 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)
     results[cluster.id]["population"] = len(cluster.all_elements)
      
    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:
        scores.append((score_cluster(a_cluster, m_handler.distance_matrix, all_metrics), a_cluster))

    # Remember: first metric is spawning point,  second metric must be energy
    most_negative = find_most_negative_cluster(scores)
    most_negative_cluster = most_negative[1]

    #######################################################################################################################
    # Plot clusters
    #######################################################################################################################
    plot_clusters(os.path.join(base_dir, "clusters.svg"), all_metrics, scores, scores.index(most_negative))

    #######################################################################################################################