rdkit_desc_update (#228)

* rdkit_desc_update 1. include desc_list to allow selection of descriptor feature in rdkit 2. change test as length of rdkit DescriptorFeature becomes 208 (originally 200) * Update fingerprint.py * Update linux_win_env.yml * Update macos_env.yml Co-authored-by: Chang.Liu <TsumiNa@users.noreply.github.com>
yoshida-lab · Feb 18, 2021 · fb97cd7 · fb97cd7
1 parent c2d07bc
commit fb97cd7
Show file tree

Hide file tree

Showing 4 changed files with 49 additions and 10 deletions.
diff --git a/.github/config/linux_win_env.yml b/.github/config/linux_win_env.yml
@@ -9,7 +9,7 @@ dependencies:
   - numpy
   - scipy
   - requests
-  - rdkit=2020.03.3.0
+  - rdkit=2020.09
   - scikit-learn
   - scipy
   - pytorch >=1.7.0,<2.0.0

diff --git a/.github/config/macos_env.yml b/.github/config/macos_env.yml
@@ -9,7 +9,7 @@ dependencies:
   - numpy
   - scipy
   - requests
-  - rdkit=2020.03.3.0
+  - rdkit=2020.09
   - scikit-learn
   - scipy
   - pytorch >=1.7.0,<2.0.0

diff --git a/tests/descriptor/test_fingerprint.py b/tests/descriptor/test_fingerprint.py
@@ -228,7 +228,7 @@ def test_fps_4(data):
     fps = Fingerprints(n_jobs=1, input_type='any', on_errors='nan')
     ret = fps.transform(data['err_smis'])
     assert isinstance(ret, pd.DataFrame)
-    assert ret.shape == (4, 16751)
+    assert ret.shape == (4, 16759)
     assert np.isnan(ret.values[1][10])
     assert np.isnan(ret.values[2][20])
 
@@ -246,7 +246,7 @@ def test_fps_6(data):
     fps = Fingerprints(n_jobs=1, input_type='any', on_errors='nan', counting=True)
     ret = fps.transform(data['smis'])
     assert isinstance(ret, pd.DataFrame)
-    assert ret.shape == (4, 16751)
+    assert ret.shape == (4, 16759)
 
 
 if __name__ == "__main__":

diff --git a/xenonpy/descriptor/fingerprint.py b/xenonpy/descriptor/fingerprint.py
@@ -4,7 +4,7 @@
 
 import numpy as np
 from rdkit import Chem
-from rdkit.Chem import Descriptors
+from rdkit.Chem import Descriptors as ChemDesc
 from rdkit.Chem import MACCSkeys as MAC
 from rdkit.Chem import rdMolDescriptors as rdMol
 from rdkit.Chem import rdmolops as rdm
@@ -643,8 +643,39 @@ def feature_labels(self):
 
 class DescriptorFeature(BaseFeaturizer):
 
+    classic = ['MaxEStateIndex', 'MinEStateIndex', 'MaxAbsEStateIndex', 'MinAbsEStateIndex', 'qed', 'MolWt',
+               'HeavyAtomMolWt', 'ExactMolWt', 'NumValenceElectrons', 'NumRadicalElectrons', 'MaxPartialCharge',
+               'MinPartialCharge', 'MaxAbsPartialCharge', 'MinAbsPartialCharge', 'FpDensityMorgan1', 'FpDensityMorgan2',
+               'FpDensityMorgan3', 'BalabanJ', 'BertzCT', 'Chi0', 'Chi0n', 'Chi0v', 'Chi1', 'Chi1n', 'Chi1v', 'Chi2n',
+               'Chi2v', 'Chi3n', 'Chi3v', 'Chi4n', 'Chi4v', 'HallKierAlpha', 'Ipc', 'Kappa1', 'Kappa2', 'Kappa3',
+               'LabuteASA', 'PEOE_VSA1', 'PEOE_VSA10', 'PEOE_VSA11', 'PEOE_VSA12', 'PEOE_VSA13', 'PEOE_VSA14',
+               'PEOE_VSA2', 'PEOE_VSA3', 'PEOE_VSA4', 'PEOE_VSA5', 'PEOE_VSA6', 'PEOE_VSA7', 'PEOE_VSA8', 'PEOE_VSA9',
+               'SMR_VSA1', 'SMR_VSA10', 'SMR_VSA2', 'SMR_VSA3', 'SMR_VSA4', 'SMR_VSA5', 'SMR_VSA6', 'SMR_VSA7',
+               'SMR_VSA8', 'SMR_VSA9', 'SlogP_VSA1', 'SlogP_VSA10', 'SlogP_VSA11', 'SlogP_VSA12', 'SlogP_VSA2',
+               'SlogP_VSA3', 'SlogP_VSA4', 'SlogP_VSA5', 'SlogP_VSA6', 'SlogP_VSA7', 'SlogP_VSA8', 'SlogP_VSA9', 'TPSA',
+               'EState_VSA1', 'EState_VSA10', 'EState_VSA11', 'EState_VSA2', 'EState_VSA3', 'EState_VSA4',
+               'EState_VSA5', 'EState_VSA6', 'EState_VSA7', 'EState_VSA8', 'EState_VSA9', 'VSA_EState1', 'VSA_EState10',
+               'VSA_EState2', 'VSA_EState3', 'VSA_EState4', 'VSA_EState5', 'VSA_EState6', 'VSA_EState7', 'VSA_EState8',
+               'VSA_EState9', 'FractionCSP3', 'HeavyAtomCount', 'NHOHCount', 'NOCount', 'NumAliphaticCarbocycles',
+               'NumAliphaticHeterocycles', 'NumAliphaticRings', 'NumAromaticCarbocycles', 'NumAromaticHeterocycles',
+               'NumAromaticRings', 'NumHAcceptors', 'NumHDonors', 'NumHeteroatoms', 'NumRotatableBonds',
+               'NumSaturatedCarbocycles', 'NumSaturatedHeterocycles', 'NumSaturatedRings', 'RingCount', 'MolLogP',
+               'MolMR', 'fr_Al_COO', 'fr_Al_OH', 'fr_Al_OH_noTert', 'fr_ArN', 'fr_Ar_COO', 'fr_Ar_N', 'fr_Ar_NH',
+               'fr_Ar_OH', 'fr_COO', 'fr_COO2', 'fr_C_O', 'fr_C_O_noCOO', 'fr_C_S', 'fr_HOCCN', 'fr_Imine', 'fr_NH0',
+               'fr_NH1', 'fr_NH2', 'fr_N_O', 'fr_Ndealkylation1', 'fr_Ndealkylation2', 'fr_Nhpyrrole', 'fr_SH',
+               'fr_aldehyde', 'fr_alkyl_carbamate', 'fr_alkyl_halide', 'fr_allylic_oxid', 'fr_amide', 'fr_amidine',
+               'fr_aniline', 'fr_aryl_methyl', 'fr_azide', 'fr_azo', 'fr_barbitur', 'fr_benzene', 'fr_benzodiazepine',
+               'fr_bicyclic', 'fr_diazo', 'fr_dihydropyridine', 'fr_epoxide', 'fr_ester', 'fr_ether', 'fr_furan',
+               'fr_guanido', 'fr_halogen', 'fr_hdrzine', 'fr_hdrzone', 'fr_imidazole', 'fr_imide', 'fr_isocyan',
+               'fr_isothiocyan', 'fr_ketone', 'fr_ketone_Topliss', 'fr_lactam', 'fr_lactone', 'fr_methoxy',
+               'fr_morpholine', 'fr_nitrile', 'fr_nitro', 'fr_nitro_arom', 'fr_nitro_arom_nonortho', 'fr_nitroso',
+               'fr_oxazole', 'fr_oxime', 'fr_para_hydroxylation', 'fr_phenol', 'fr_phenol_noOrthoHbond', 'fr_phos_acid',
+               'fr_phos_ester', 'fr_piperdine', 'fr_piperzine', 'fr_priamide', 'fr_prisulfonamd', 'fr_pyridine',
+               'fr_quatN', 'fr_sulfide', 'fr_sulfonamd', 'fr_sulfone', 'fr_term_acetylene', 'fr_tetrazole',
+               'fr_thiazole', 'fr_thiocyan', 'fr_thiophene', 'fr_unbrch_alkane', 'fr_urea']
+
     def __init__(self, n_jobs=-1,
-                 *, input_type='mol', on_errors='raise', return_type='any', target_col=None):
+                 *, input_type='mol', on_errors='raise', return_type='any', target_col=None, desc_list='all'):
         """
         All descriptors in RDKit (length = 200) [may include NaN]
             see https://www.rdkit.org/docs/GettingStartedInPython.html#list-of-available-descriptors for the full list
@@ -672,12 +703,21 @@ def __init__(self, n_jobs=-1,
             Specify a single column to be used for transformation.
             If ``None``, all columns of the pd.DataFrame is used.
             Default is None.
+        desc_list: string or list
+            List of descriptor names to be called in rdkit to calculate molecule descriptors.
+            If ``classic``, the full list of rdkit v.2020.03.xx is used. (length = 200)
+            Default is to use the latest list available in the rdkit. (length = 208 in rdkit v.2020.09.xx)
         """
         # self.arg = arg # arg[0] = radius, arg[1] = bit length
         super().__init__(n_jobs=n_jobs, on_errors=on_errors, return_type=return_type, target_col=target_col)
         self.input_type = input_type
-        nms = [x[0] for x in Descriptors._descList]
-        self.calc = MoleculeDescriptors.MolecularDescriptorCalculator(nms)
+        if desc_list == 'all':
+            self.nms = [x[0] for x in ChemDesc._descList]
+        elif desc_list == 'classic':
+            self.nms = self.classic
+        else:
+            self.nms = desc_list
+        self.calc = MoleculeDescriptors.MolecularDescriptorCalculator(self.nms)
         self.__authors__ = ['Stephen Wu', 'TsumiNa']
 
     def featurize(self, x):
@@ -696,8 +736,7 @@ def featurize(self, x):
 
     @property
     def feature_labels(self):
-        return [x[0] for x in Descriptors._descList]
-        # return ['desc200:' + str(i) for i in range(200)]
+        return self.nms
 
 
 class Fingerprints(BaseDescriptor):