final_eval.py

import sys
import rdkit
from argparse import ArgumentParser
from rdkit import Chem, DataStructs
from rdkit.Chem import AllChem

import pandas as pd

pred_mols = pd.read_csv('',
                        header=None).values.reshape(-1)

ref_path = 'actives.txt'

with open(ref_path) as f:
    next(f)
    true_mols = [line.split(',')[0] for line in f]
print('number of active reference', len(true_mols))

true_mols = [Chem.MolFromSmiles(s) for s in true_mols]
true_mols = [x for x in true_mols if x is not None]
true_fps = [AllChem.GetMorganFingerprintAsBitVect(x, 3, 2048) for x in true_mols]

pred_mols = [Chem.MolFromSmiles(s) for s in pred_mols]
pred_mols = [x for x in pred_mols if x is not None]
pred_fps = [AllChem.GetMorganFingerprintAsBitVect(x, 3, 2048) for x in pred_mols]

fraction_similar = 0

sim_distribution = []
for i in range(len(pred_fps)):
    sims = DataStructs.BulkTanimotoSimilarity(pred_fps[i], true_fps)

    if max(sims) >= 0.4:
        fraction_similar += 1
    sim_distribution.append(max(sims))

print('novelty:', 1 - fraction_similar / len(pred_mols))

similarity = 0
for i in range(len(pred_fps)):
    sims = DataStructs.BulkTanimotoSimilarity(pred_fps[i], pred_fps[:i])
    similarity += sum(sims)

n = len(pred_fps)
n_pairs = n * (n - 1) / 2
diversity = 1 - similarity / n_pairs
print('diversity:', diversity)