get_ensemble_medoid_stats.py

# UMAP_TSNE_STATS.py

from util import *
import sys
import pymol
from pymol import cmd
from paths import *

from paths import *
if __name__ == "__main__":
    def get_data(bound):
        data_source_file = CSP_Rank_Scores + './CSP_'+bound+'_CSpred.csv'
        parsed_data = parse_csv(data_source_file)
        holo_model_files = [data['holo_model_path'][data['holo_model_path'].rfind('/')+1:] for data in parsed_data]
        holo_model_files_raw = [data['holo_model_path'] for data in parsed_data]
        consensus_scores = []#[float(data['consensus']) for data in parsed_data]
        Confidence_scores = []
        dp_scores = []
        recall_scores = []
        precision_scores = []
        plddt_scores = []
        for data in parsed_data:
            try:
                conf = float(data['Confidence'])
                cons = float(data['consensus'])
                plddt = float(data['plddt'])
                consensus_scores.append(cons)
                #consensus_scores.append(cons)# * df / (cons + df))
                Confidence_scores.append(conf)
                plddt_scores.append(plddt)
            except:
                consensus_scores.append(0)
                Confidence_scores.append(0)
                plddt_scores.append(0)
            try:
                dp = float(data['DP'])
                precision = float(data['RPF_PRECISION'])
                recall = float(data['RPF_RECALL'])
                recall_scores.append(recall)
                precision_scores.append(precision)
                dp_scores.append(dp)
            except Exception as e:
                recall_scores.append(0)
                precision_scores.append(0)
                dp_scores.append(0)
        return holo_model_files, consensus_scores

    output_dirs = ['./PDB_FILES/' + f for f in listdir('./PDB_FILES/') if isdir('./PDB_FILES/' + f) and f.find('NLDR') != -1]
    print(output_dirs)
    for outdir in output_dirs:

        pdb = outdir[outdir.rfind('/')+1:outdir.rfind('/')+5]
        holo_model_files, consensus_scores = get_data(pdb)
        medoid_file = ""
        try:
            medoid_file = find_medoid_structure([outdir + '/'+ f for f in listdir(outdir)])
        except:
            continue
        medoid_file_basename = medoid_file[medoid_file.rfind('/')+1:]
        index = 0
        try:
            index = holo_model_files.index(medoid_file_basename)
        except:
            print("Could not find medoid file in data_source_file for " + medoid_file_basename)
            continue
        print(outdir)
        #print(holo_model_files[index])
        print(consensus_scores[index])