def from_feat_back_to_mols(dset, smi):
"""
Retrieves the list of molecules that contain the given feature in the given dataset. THIS IS EXTREMELY SLOW!!!!!!!
"""
mols = []
molids = []
indices = []
classes = []
mfm = MalariaFingerprintsManager(dset=dset)
print('I am here')
with open(mfm.original_file, 'r') as reader:
for i, line in enumerate(reader):
info = line.split('\t')
molid = info[0]
ecfps = [feat.split()[0] for feat in info[1:]]
if smi in ecfps:
print(molid)
molids.append(molid)
indices.append(i)
mc = MalariaCatalog()
classes.append(mc.label(molid, as01=True))
mols.append(None)
print('Got the first lists')
molids = np.array(molids)
indices = np.array(indices)
classes = np.array(classes)
mols = np.array(mols)
# Now we need to retrieve the real rdkit mols for each molid.
if dset == 'lab':
for molid, _, _, _, _, smiles in read_labelled_smiles():
if molid in molids:
mols[molids == molid] = smiles
return zip(mols, molids, indices, classes)
def from_feat_back_to_mols_faster(dset, smi):
"""
Retrieves the list of molecules that contain the given feature in the given dataset.
"""
# The non-folded version is easy
mfm = MalariaFingerprintsManager(dset=dset)
X = mfm.X()
col = mfm.s2i(smi) # the column where we have to look for in the X matrix
cooX = X.tocoo()
indices_mols = cooX.row[cooX.col == col]
molids = [mfm.i2m(i) for i in indices_mols]
mc = MalariaCatalog()
activities = [mc.label(molid, as01=True) for molid in molids]
mols = mc.molids2mols(molids)
return zip(mols, molids, indices_mols, activities)
def mispredicted_compounds(folding_size=None):
"""
At each fold, collect the list of mispredicted compounds and assemble it into one list of molids
"""
FOLDS = range(10)
mfm = MalariaFingerprintsManager(dset='lab')
mispredicted = []
if folding_size is None:
path = op.join(MALARIA_EXPS_ROOT, 'folding_rdkit', 'no_folding')
else:
path = op.join(MALARIA_EXPS_ROOT, 'folding_rdkit', 'fs=%i' % folding_size)
for fold in FOLDS:
with open(op.join(path, 'fold=%i' % fold, 'results.pkl'), 'r') as reader:
_, scores, fold, _, _, _ = pickle.load(reader)
scores = scores >= 0.5 # dummy threshold
molids_test = [mfm.i2m(i) for i in fold]
mc = MalariaCatalog()
classes_test = [mc.label(molid, as01=True) for molid in molids_test]
for i, mol in enumerate(molids_test):
if scores[i] != classes_test[i] and not np.isnan(classes_test[i]):
mispredicted.append(mol)
return mispredicted