def select_and_evaluate_decoys(f, target, file_loc='./', output_loc='./',
dataset='ALL', num_cand_dec_per_act=100,
num_dec_per_act=50, max_idx_cmpd=10000):
print("Processing: ", f)
dec_results = [f]
dec_results.append(dataset)
# Read data
data = decoy_utils.read_paired_file(file_loc+f)
# Filter dupes and actives that are too small
dec_results.append(len(set([d[0] for d in data])))
tmp = [Chem.MolFromSmiles(d[0]) for d in data]
data = [d for idx, d in enumerate(data) if tmp[idx] is not None \
and tmp[idx].GetNumHeavyAtoms()>min_active_size]
data = pd.DataFrame(data, columns=['act', 'dec'])
pss = get_pss_from_smiles(
data['act'].values, data['dec'].values)
data['pss'] = pss.mean(0)
data['score'] = data['pss']
result = []
for key, tmp_df in data.groupby('act'):
tmp_df = tmp_df.sort_values('score', ascending=False)
tmp_df = tmp_df.reset_index(drop=True)
for i in range(min([5, tmp_df.shape[0]])):
result.append([key, tmp_df['dec'].values[i]])
result = pd.DataFrame(result, columns=['act', 'dec'])
result.to_csv('tmp.smi', index=False, header=None, sep=' ')
# =============================================================================
#
# =============================================================================
decoy_smis_gen = list(set(result['dec']))
decoy_mols_gen = [Chem.MolFromSmiles(smi) for smi in decoy_smis_gen]
active_smis_gen = list(set(result['act']))
active_mols_gen = [Chem.MolFromSmiles(smi) for smi in active_smis_gen]
dataset = 'dude'
print('Calc props for chosen decoys')
actives_feat = decoy_utils.calc_dataset_props_dude(active_mols_gen)
decoys_feat = decoy_utils.calc_dataset_props_dude(decoy_mols_gen)
print('ML model performance')
print(actives_feat.shape)
print(decoys_feat.shape)
dec_results.extend(list(decoy_utils.calc_xval_performance(
actives_feat, decoys_feat, n_jobs=1)))
print('DEKOIS paper metrics (LADS, DOE, Doppelganger score)')
dec_results.append(decoy_utils.doe_score(actives_feat, decoys_feat))
lads_scores = decoy_utils.lads_score_v2(active_mols_gen, decoy_mols_gen)
dec_results.append(np.mean(lads_scores))
dg_scores, dg_ids = decoy_utils.dg_score(active_mols_gen, decoy_mols_gen)
dec_results.extend([np.mean(dg_scores), max(dg_scores)])
print('Save decoy mols')
print(dec_results)
return dec_results
def select_and_evaluate_decoys(f, target, file_loc='./', output_loc='./'):
print("Processing: ", f)
dec_results = [f]
# Read data
data = decoy_utils.read_paired_file(file_loc + f)
# Filter dupes and actives that are too small
dec_results.append(len(set([d[0] for d in data])))
tmp = [Chem.MolFromSmiles(d[0]) for d in data]
data = [d for idx, d in enumerate(data) if tmp[idx] is not None \
and tmp[idx].GetNumHeavyAtoms()>10]
data = pd.DataFrame(data, columns=['act', 'dec'])
if target == 'SA':
data['style'] = data['dec'].apply(lambda x: get_sa(x))
data['style'] = (5 - data['style']) / 3
else:
style = pd.read_csv('./eval/results/predict_TOX.csv')
style = style.rename(columns={
'smiles': 'dec',
'pred_0': 'style'
})[['dec', 'style']]
data = data.merge(style, on='dec', how='inner')
data['style'] = 1 - data['style']
pss = get_pss_from_smiles(data['act'].values, data['dec'].values)
data['pss'] = pss.mean(0)
data['score'] = data['pss'] + data['style']
result = []
for key, tmp_df in data.groupby('act'):
tmp_df = tmp_df.sort_values('score', ascending=False)
tmp_df = tmp_df.reset_index(drop=True)
for i in range(min([1, tmp_df.shape[0]])):
result.append([key, tmp_df['dec'].values[i]])
result = pd.DataFrame(result, columns=['act', 'dec'])
output_name = output_loc + \
f'/{target}_results.smi'
result = result.drop_duplicates().reset_index(drop=True)
result.to_csv(output_name, index=False, header=None, sep=' ')
def select_and_evaluate_decoys(f,
target,
file_loc='./',
output_loc='./',
T_simi=0.15,
N=5):
print("Processing: ", f)
# Read data
data = decoy_utils.read_paired_file(file_loc + f)
data = pd.DataFrame(data,
columns=['act', 'dec'
]) #.sample(frac=0.01).reset_index(drop=True)
mol_acts = [Chem.MolFromSmiles(smi) for smi in data['act'].values]
mol_decs = [Chem.MolFromSmiles(smi) for smi in data['dec'].values]
fp_acts = [get_fp(mol) for mol in mol_acts]
fp_decs = [get_fp(mol) for mol in mol_decs]
simi = [
get_scaffold_simi(fp_acts[i], fp_decs[i]) for i in range(len(fp_acts))
]
idxs = np.where(np.array(simi) < T_simi)
mol_acts = np.array(mol_acts)[idxs]
mol_decs = np.array(mol_decs)[idxs]
pss = get_pss_from_smiles(mol_acts, mol_decs)
data = pd.DataFrame(data.values[idxs], columns=['act', 'dec'])
data['pss'] = pss.mean(0)
data['score'] = data['pss']
result = []
for key, tmp_df in data.groupby('act'):
tmp_df = tmp_df.sort_values('score', ascending=False)
tmp_df = tmp_df.reset_index(drop=True)
for i in range(min([N, tmp_df.shape[0]])):
result.append([key, tmp_df['dec'].values[i]])
result = pd.DataFrame(result, columns=['act', 'dec'])
result = result.drop_duplicates().reset_index(drop=True)
result.to_csv(f'{target}_decoys.smi', index=False, header=None, sep=' ')
pred = pd.read_csv('./eval/zinc_all_alerts_pred.csv',
usecols=['smiles', 'pred']).rename(columns={
'smiles': 'content',
'pred': 'content_TOX'
})[['content', 'content_TOX']]
df = df.merge(pred, on='content', how='left')
df = df.drop_duplicates(['content', 'gene'])
df['tmp'] = df[['content', 'gene']].values.tolist()
print(df.shape)
pss = get_pss_from_smiles(df['content'].values, df['gene'].values)
df['PSS'] = pss.mean(0)
df['content_fp'] = df['content'].apply(lambda x: get_mol_features(x))
df['gene_fp'] = df['gene'].apply(lambda x: get_mol_features(x))
df['similarity'] = df[['content_fp', 'gene_fp']].values.tolist()
df['similarity'] = df['similarity'].apply(
lambda x: np.sum(np.array(x[0]) * np.array(x[1])))
# higher is better