def collect():
all_smiles = []
Peak_data = []
RI_data = []
Morgan_fp = []
CDK_fp = []
CDK_des = []
MolWt = []
# for i in tqdm(range(20)):
for i in tqdm(range(len(all_mol))):
try:
m = read_mol(i)
except:
continue
'''
if 'TMS derivative' in m['name']:
derive = 1
else:
derive = 0
'''
try:
mol = Chem.MolFromSmiles(m['smiles'])
molwt = CalcExactMolWt(mol)
if molwt > 2000:
continue
smiles = Chem.MolToSmiles(mol)
# check element
elements = parser_formula(MolToFormula(MolFromSmiles(smiles)))
for e in elements:
if e not in [
'C', 'H', 'O', 'N', 'S', 'P', 'Si', 'F', 'Cl', 'Br',
'I'
]:
raise ValueError('contain uncommon element')
morgan_fp = np.array(
AllChem.GetMorganFingerprintAsBitVect(mol, 2, nBits=4096))
cdk_fp = get_cdk_fingerprints(smiles)
# cdk_fp = fp2vec(cdk_fp)
cdk_des = np.array(get_cdk_descriptors(smiles))
# cdk_des = getMolecularDescriptor(MolFromSmiles(smiles)).values()
# cdk_des = np.array(list(itertools.chain(*cdk_des)))
ri = list(m['RI'].values())
peak_vec = ms2vec(m['peakindex'], m['peakintensity'])
except:
continue
all_smiles.append(smiles)
Peak_data.append(peak_vec)
RI_data.append(ri)
Morgan_fp.append(morgan_fp)
CDK_fp.append(cdk_fp)
CDK_des.append(cdk_des)
MolWt.append(molwt)
# save
np.save('DeepEI/data/retention.npy', np.array(RI_data))
np.save('DeepEI/data/descriptor.npy', np.array(CDK_des))
np.save('DeepEI/data/molwt.npy', np.array(MolWt))
Peak_data = csr_matrix(np.array(Peak_data))
Morgan_fp = csr_matrix(np.array(Morgan_fp))
CDK_fp = csr_matrix(np.array(CDK_fp))
save_npz('DeepEI/data/peakvec.npz', Peak_data)
save_npz('DeepEI/data/morgan.npz', Morgan_fp)
save_npz('DeepEI/data/fingerprints.npz', CDK_fp)
with open('DeepEI/data/all_smiles.json', 'w') as t:
json.dump(all_smiles, t)
nist_fps)[:, fpkeep].todense() # fingerprints of nist compounds
nist_spec = load_npz('DeepEI/data/peakvec.npz').todense()
pred_spec = np.load(
'DeepEI/data/neims_spec_massbank.npy') # spectra predicted by NEIMS
output = pd.DataFrame(columns=['smiles', 'mass', 'score', 'rank'])
for i in tqdm(range(len(smiles))):
smi = smiles[i]
std_smi = Chem.MolToSmiles(Chem.MolFromSmiles(smi))
mass = molwt[i]
speci = spec[i]
pred_fp = pred_fps[i]
pred_sp = pred_spec[i]
try:
true_fp = np.array(get_cdk_fingerprints(
std_smi)) # true fingerprint of the "unknown"
except:
continue
true_fp = true_fp[fpkeep]
true_score_fp = jaccard_score(pred_fp,
true_fp) # fp score of the true compound
true_score_sp = weitht_dot_product(
speci, pred_sp) # sp score of the true compound
true_score = true_score_fp * 0.7 + true_score_sp * 0.3
candidate = np.where(
np.abs(nist_masses - mass) < 5)[0] # candidate of nist
cand_smi = nist_smiles[candidate]
rep_ind = np.where(
cand_smi == std_smi)[0] # if the compound in nist, remove it.
candidate = np.delete(candidate, rep_ind)
pred_smiles.append(Chem.MolToSmiles(m))
pred_masses.append(CalcExactMolWt(m))
spec_vecs = []
for spec in tqdm(spectra):
spec_vecs.append(ms2vec(spec['mz'], spec['intensity']))
spec_vecs = np.array(spec_vecs)
spec_vecs1 = csr_matrix(spec_vecs)
msbk_spec = np.array(msbk_spec)
msbk_spec = csr_matrix(msbk_spec)
save_npz('DeepEI/data/neims_spec_msbk.npz', spec_vecs1)
save_npz('DeepEI/data/msbk_spec.npz', msbk_spec)
with open('DeepEI/data/msbk_smiles.json', 'w') as t:
json.dump(msbk_smiles, t)
with open('DeepEI/data/neims_msbk_smiles.json', 'w') as t:
json.dump(pred_smiles, t)
np.save('DeepEI/data/msbk_masses.npy', msbk_masses)
np.save('DeepEI/data/neims_msbk_masses.npy', pred_masses)
neims_msbk_cdkfps = []
for smi in tqdm(pred_smiles):
try:
fp = get_cdk_fingerprints(smi)
except:
fp = np.zeros(8034)
neims_msbk_cdkfps.append(fp)
neims_msbk_cdkfps = np.array(neims_msbk_cdkfps)
neims_msbk_cdkfps = csr_matrix(np.array(neims_msbk_cdkfps))
save_npz('DeepEI/data/neims_msbk_cdkfps', neims_msbk_cdkfps)
pred_fps = predict_fingerprint(
test_spec, fpkeep) # predict fingerprint of the "unknown"
cdk_fp = load_npz('DeepEI/data/fingerprints.npz')
cdk_fp = csr_matrix(cdk_fp)[:, fpkeep].todense()
output = pd.DataFrame(columns=['smiles', 'mass', 'score', 'rank'])
for i in tqdm(range(len(test))):
smi = test_smiles[i]
std_smi = Chem.MolToSmiles(Chem.MolFromSmiles(smi))
mass = test_mass[i]
speci = test_spec[i]
pred_fp = pred_fps[i]
pred_sp = pred_spec[i]
try:
true_fp = np.array(
get_cdk_fingerprints(smi)) # true fingerprint of the "unknown"
except:
continue
true_fp = true_fp[fpkeep]
true_score_fp = jaccard_score(pred_fp,
true_fp) # fp score of the true compound
true_score_sp = weitht_dot_product(
speci, pred_sp) # sp score of the true compound
true_score = 0.7 * true_score_fp + 0.3 * true_score_sp
candidate = np.where(np.abs(masses - mass) < 5)[0] # candidate of nist
cand_smi = smiles[candidate]
rep_ind = np.where(
cand_smi == std_smi)[0] # if the compound in nist, remove it.
candidate = np.delete(candidate, rep_ind)