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)
s = [weitht_dot_product(x, X[i, :]) for i in range(X.shape[0])]
return s
# predict ms of the isolate compounds
# run once, then save
pred_spec = np.zeros((len(test), 2000))
for a, i in enumerate(tqdm(test)):
smi = smiles[i]
writeSDF(smi, 'Temp/mol.sdf')
cwd = 'E:\\project\\deep-molecular-massspec'
cmd = 'python make_spectra_prediction.py --input_file=E:/project/DeepEI/Temp/mol.sdf --output_file=E:/project/DeepEI/Temp/mol_anno.sdf --weights_dir=model/massspec_weights'
subprocess.call(cmd, cwd=cwd)
try:
speci = parser_NEIMS('Temp/mol_anno.sdf')
pred_vec = ms2vec(speci['mz'], speci['intensity'])
os.unlink('Temp/mol_anno.sdf')
except:
pred_vec = np.zeros(
2000
) # # if error, use a zero vec as placeholder. but it won't count when comparsion.
pred_spec[a, :] = pred_vec
os.unlink('Temp/mol.sdf')
np.save('Discussion/NIST_test/neims_spec_nist.npy', pred_spec)
if __name__ == '__main__':
from scipy.sparse import load_npz
masses = np.load('DeepEI/data/molwt.npy')
spec = load_npz('DeepEI/data/peakvec.npz').todense()
split = json.load(js)
keep = np.array(split['keep'])
isolate = np.array(split['isolate'])
# NEIMS spectra of NIST
nist_smiles = np.array(json.load(open('DeepEI/data/all_smiles.json')))
writeSDF(nist_smiles, 'Temp/mol.sdf')
cwd = 'E:\\project\\deep-molecular-massspec'
cmd = 'python make_spectra_prediction.py --input_file=E:/project/DeepEI/Temp/mol.sdf --output_file=E:/project/DeepEI/Temp/mol_anno.sdf --weights_dir=model/massspec_weights'
subprocess.call(cmd, cwd=cwd)
spectra = parser_NEIMS('Temp/mol_anno.sdf')
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)
save_npz('DeepEI/data/neims_spec_nist.npz', spec_vecs1)
# NEIMS spectra of MassBank
exist_smiles = nist_smiles[keep]
data = msp.read('E:/data/GCMS DB_AllPublic-KovatsRI-VS2.msp')
msbk_smiles = []
msbk_spec = []
msbk_masses = []
for i, (param, ms) in enumerate(tqdm(data)):
smi = param['smiles']
try:
smi = Chem.MolToSmiles(Chem.MolFromSmiles(smi))
except:
from DeepEI.predict import predict_fingerprint
from DeepEI.utils import ms2vec, vec2ms, get_cdk_fingerprints
data = msp.read('E:/data/GCMS DB_AllPublic-KovatsRI-VS2.msp')
smiles = []
spec = []
molwt = []
for i, (param, ms) in enumerate(tqdm(data)):
smi = param['smiles']
try:
mass = CalcExactMolWt(Chem.MolFromSmiles(smi))
except:
continue
molwt.append(mass)
smiles.append(smi)
spec.append(ms2vec(ms[:, 0], ms[:, 1]))
mlp = pd.read_csv('Fingerprint/results/mlp_result.txt',
sep='\t',
header=None)
mlp.columns = ['id', 'accuracy', 'precision', 'recall', 'f1']
fpkeep = mlp['id'][np.where(mlp['f1'] > 0.5)[0]]
spec = np.array(spec)
pred_fps = predict_fingerprint(
spec, fpkeep) # predict fingerprint of the "unknown"
nist_smiles = np.array(json.load(open('DeepEI/data/all_smiles.json')))
nist_masses = np.load('DeepEI/data/molwt.npy')
nist_fps = load_npz('DeepEI/data/fingerprints.npz')
nist_fps = csr_matrix(
nist_masses = np.load('DeepEI/data/molwt.npy')
nist_spec = load_npz('DeepEI/data/peakvec.npz').todense()
data = msp.read('E:/data/GCMS DB_AllPublic-KovatsRI-VS2.msp')
smiles = []
spec = []
molwt = []
for i, (param, ms) in enumerate(tqdm(data)):
smi = param['smiles']
try:
mass = CalcExactMolWt(Chem.MolFromSmiles(smi))
except:
continue
molwt.append(mass)
smiles.append(smi)
spec.append(ms2vec(ms[:,0], ms[:,1]))
pred_spec = []
output = pd.DataFrame(columns=['smiles', 'mass', 'score', 'rank'])
for i in tqdm(range(len(smiles))):
smi = smiles[i] # smiles
try:
std_smi = Chem.MolToSmiles(Chem.MolFromSmiles(smi))
except:
std_smi = ''
specr = spec[i] # true spectrum
mass = molwt[i] # true mol weight
try:
writeSDF(smi, 'Temp/mol.sdf')
except:
continue
RI_data = []
Morgan_fp = []
CDK_fp = []
CDK_des = []
MolWt = []
mols = Chem.SDMolSupplier(f)
for m in tqdm(mols):
if m is None:
continue
smi = Chem.MolToSmiles(m)
morgan_fp = np.array(
AllChem.GetMorganFingerprintAsBitVect(m, 2, nBits=4096))
cdk_fp = get_cdk_fingerprints(smi)
cdk_des = np.array(get_cdk_descriptors(smi))
props = m.GetPropsAsDict()
molwt = props['EXACT MASS']
peaks = props['MASS SPECTRAL PEAKS']
peaks = peaks.split('\n')
peakindex = np.array([round(float(p.split(' ')[0])) for p in peaks])
peakintensity = np.array([float(p.split(' ')[1]) for p in peaks])
peak_vec = ms2vec(m['peakindex'], m['peakintensity'])
all_smiles.append(smi)
Peak_data.append(peak_vec)
Morgan_fp.append(morgan_fp)
CDK_fp.append(cdk_fp)
CDK_des.append(cdk_des)
MolWt.append(molwt)