def test_internal_vina():
"""Compare internal vs orignal Vina partial scores"""
mols = list(
oddt.toolkit.readfile(
'sdf',
os.path.join(test_data_dir, 'data/dude/xiap/actives_docked.sdf')))
list(map(lambda x: x.addh(), mols))
rec = next(
oddt.toolkit.readfile(
'pdb',
os.path.join(test_data_dir, 'data/dude/xiap/receptor_rdkit.pdb')))
rec.protein = True
rec.addh()
# Delete molecule which has differences in Acceptor-Donor def in RDK and OB
del mols[65]
vina_scores = [
'vina_gauss1', 'vina_gauss2', 'vina_repulsion', 'vina_hydrophobic',
'vina_hydrogen'
]
autodock_vina_results = np.loadtxt(os.path.join(
test_data_dir, 'data/results/xiap/autodock_vina_scores.csv'),
delimiter=',',
dtype=np.float64)
oddt_vina_results = oddt_vina_descriptor(
protein=rec, vina_scores=vina_scores).build(mols)
assert_array_almost_equal(oddt_vina_results,
autodock_vina_results,
decimal=4)
def __init__(self, protein = None):
""" Descriptor build from binana script (as used in NNScore 2.0
Parameters
----------
protein: oddt.toolkit.Molecule object (default=None)
Protein object to be used while generating descriptors.
"""
self.protein = protein
self.vina = oddt_vina_descriptor(protein, vina_scores = ['vina_affinity', 'vina_gauss1', 'vina_gauss2', 'vina_repulsion', 'vina_hydrophobic', 'vina_hydrogen'])
# Close contacts descriptor generators
cc_4_types = (('A', 'A'), ('A', 'C'), ('A', 'CL'), ('A', 'F'), ('A', 'FE'), ('A', 'HD'), ('A', 'MG'), ('A', 'MN'), ('A', 'N'), ('A', 'NA'), ('A', 'OA'), ('A', 'SA'), ('A', 'ZN'), ('BR', 'C'), ('BR', 'HD'), ('BR', 'OA'), ('C', 'C'), ('C', 'CL'), ('C', 'F'), ('C', 'HD'), ('C', 'MG'), ('C', 'MN'), ('C', 'N'), ('C', 'NA'), ('C', 'OA'), ('C', 'SA'), ('C', 'ZN'), ('CL', 'FE'), ('CL', 'HD'), ('CL', 'MG'), ('CL', 'N'), ('CL', 'OA'), ('CL', 'ZN'), ('F', 'HD'), ('F', 'N'), ('F', 'OA'), ('F', 'SA'), ('FE', 'HD'), ('FE', 'N'), ('FE', 'OA'), ('HD', 'HD'), ('HD', 'I'), ('HD', 'MG'), ('HD', 'MN'), ('HD', 'N'), ('HD', 'NA'), ('HD', 'OA'), ('HD', 'P'), ('HD', 'S'), ('HD', 'SA'), ('HD', 'ZN'), ('MG', 'NA'), ('MG', 'OA'), ('MN', 'N'), ('MN', 'OA'), ('N', 'N'), ('N', 'NA'), ('N', 'OA'), ('N', 'SA'), ('N', 'ZN'), ('NA', 'OA'), ('NA', 'SA'), ('NA', 'ZN'), ('OA', 'OA'), ('OA', 'SA'), ('OA', 'ZN'), ('S', 'ZN'), ('SA', 'ZN'), ('A', 'BR'), ('A', 'I'), ('A', 'P'), ('A', 'S'), ('BR', 'N'), ('BR', 'SA'), ('C', 'FE'), ('C', 'I'), ('C', 'P'), ('C', 'S'), ('CL', 'MN'), ('CL', 'NA'), ('CL', 'P'), ('CL', 'S'), ('CL', 'SA'), ('CU', 'HD'), ('CU', 'N'), ('FE', 'NA'), ('FE', 'SA'), ('I', 'N'), ('I', 'OA'), ('MG', 'N'), ('MG', 'P'), ('MG', 'S'), ('MG', 'SA'), ('MN', 'NA'), ('MN', 'P'), ('MN', 'S'), ('MN', 'SA'), ('N', 'P'), ('N', 'S'), ('NA', 'P'), ('NA', 'S'), ('OA', 'P'), ('OA', 'S'), ('P', 'S'), ('P', 'SA'), ('P', 'ZN'), ('S', 'SA'), ('SA', 'SA'), ('A', 'CU'), ('C', 'CD') )
cc_4_rec_types, cc_4_lig_types = zip(*cc_4_types)
self.cc_4 = cc_4_nn = close_contacts(protein, cutoff=4, protein_types=cc_4_rec_types, ligand_types=cc_4_lig_types, mode='atom_types_ad4', aligned_pairs=True)
cc_25_types = [('A', 'A'), ('A', 'C'), ('A', 'CL'), ('A', 'F'), ('A', 'FE'), ('A', 'HD'), ('A', 'MG'), ('A', 'MN'), ('A', 'N'), ('A', 'NA'), ('A', 'OA'), ('A', 'SA'), ('A', 'ZN'), ('BR', 'C'), ('BR', 'HD'), ('BR', 'OA'), ('C', 'C'), ('C', 'CL'), ('C', 'F'), ('C', 'HD'), ('C', 'MG'), ('C', 'MN'), ('C', 'N'), ('C', 'NA'), ('C', 'OA'), ('C', 'SA'), ('C', 'ZN'), ('CD', 'OA'), ('CL', 'FE'), ('CL', 'HD'), ('CL', 'MG'), ('CL', 'N'), ('CL', 'OA'), ('CL', 'ZN'), ('F', 'HD'), ('F', 'N'), ('F', 'OA'), ('F', 'SA'), ('F', 'ZN'), ('FE', 'HD'), ('FE', 'N'), ('FE', 'OA'), ('HD', 'HD'), ('HD', 'I'), ('HD', 'MG'), ('HD', 'MN'), ('HD', 'N'), ('HD', 'NA'), ('HD', 'OA'), ('HD', 'P'), ('HD', 'S'), ('HD', 'SA'), ('HD', 'ZN'), ('MG', 'NA'), ('MG', 'OA'), ('MN', 'N'), ('MN', 'OA'), ('N', 'N'), ('N', 'NA'), ('N', 'OA'), ('N', 'SA'), ('N', 'ZN'), ('NA', 'OA'), ('NA', 'SA'), ('NA', 'ZN'), ('OA', 'OA'), ('OA', 'SA'), ('OA', 'ZN'), ('S', 'ZN'), ('SA', 'ZN')]
cc_25_rec_types, cc_25_lig_types = zip(*cc_25_types)
self.cc_25 = close_contacts(protein, cutoff=2.5, protein_types=cc_25_rec_types, ligand_types=cc_25_lig_types, mode='atom_types_ad4', aligned_pairs=True)
def __init__(self, protein=None, n_jobs=-1, version=1, spr=0, **kwargs):
self.protein = protein
self.n_jobs = n_jobs
self.version = version
self.spr = spr
if version == 1:
cutoff = 12
mtry = 6
descriptors = close_contacts_descriptor(
protein,
cutoff=cutoff,
protein_types=protein_atomic_nums,
ligand_types=ligand_atomic_nums)
elif version == 2:
cutoff = np.array([0, 2, 4, 6, 8, 10, 12])
mtry = 14
descriptors = close_contacts_descriptor(
protein,
cutoff=cutoff,
protein_types=protein_atomic_nums,
ligand_types=ligand_atomic_nums)
elif version == 3:
cutoff = 12
mtry = 6
cc = close_contacts_descriptor(protein,
cutoff=cutoff,
protein_types=protein_atomic_nums,
ligand_types=ligand_atomic_nums)
vina_scores = [
'vina_gauss1', 'vina_gauss2', 'vina_repulsion',
'vina_hydrophobic', 'vina_hydrogen', 'vina_num_rotors'
]
vina = oddt_vina_descriptor(protein, vina_scores=vina_scores)
descriptors = ensemble_descriptor((vina, cc))
model = randomforest(n_estimators=500,
oob_score=True,
n_jobs=n_jobs,
max_features=mtry,
bootstrap=True,
min_samples_split=6,
**kwargs)
super(rfscore, self).__init__(model,
descriptors,
score_title='rfscore_v%i' % self.version)
def test_ensemble_descriptor():
mols = list(oddt.toolkit.readfile('sdf', actives_sdf))[:10]
list(map(lambda x: x.addh(), mols))
rec = next(oddt.toolkit.readfile('pdb', receptor_pdb))
rec.protein = True
rec.addh()
desc1 = rfscore(version=1).descriptor_generator
desc2 = oddt_vina_descriptor()
ensemble = ensemble_descriptor((desc1, desc2))
ensemble.set_protein(rec)
assert len(ensemble) == len(desc1) + len(desc2)
# set protein
assert desc1.protein == rec
assert desc2.protein == rec
ensemble_scores = ensemble.build(mols)
scores1 = desc1.build(mols)
scores2 = desc2.build(mols)
assert_array_almost_equal(ensemble_scores, np.hstack((scores1, scores2)))
def __init__(self, protein=None):
""" Descriptor build from binana script (as used in NNScore 2.0
Parameters
----------
protein: oddt.toolkit.Molecule object (default=None)
Protein object to be used while generating descriptors.
"""
self.protein = protein
self.titles = []
self.vina = oddt_vina_descriptor(protein,
vina_scores=[
'vina_gauss1', 'vina_gauss2',
'vina_repulsion',
'vina_hydrophobic',
'vina_hydrogen'
])
self.titles += self.vina.titles
# Close contacts descriptor generators
cc_4_types = (('A', 'A'), ('A', 'C'), ('A', 'CL'), ('A', 'F'),
('A', 'FE'), ('A', 'HD'), ('A', 'MG'), ('A', 'MN'),
('A', 'N'), ('A', 'NA'), ('A', 'OA'), ('A', 'SA'),
('A', 'ZN'), ('BR', 'C'), ('BR', 'HD'), ('BR', 'OA'),
('C', 'C'), ('C', 'CL'), ('C', 'F'), ('C', 'HD'), ('C',
'MG'),
('C', 'MN'), ('C', 'N'), ('C', 'NA'), ('C', 'OA'),
('C', 'SA'), ('C', 'ZN'), ('CL', 'FE'), ('CL', 'HD'),
('CL', 'MG'), ('CL', 'N'), ('CL', 'OA'), ('CL', 'ZN'),
('F', 'HD'), ('F', 'N'), ('F', 'OA'), ('F', 'SA'),
('FE', 'HD'), ('FE', 'N'), ('FE', 'OA'), ('HD', 'HD'),
('HD', 'I'), ('HD', 'MG'), ('HD', 'MN'), ('HD', 'N'),
('HD', 'NA'), ('HD', 'OA'), ('HD', 'P'), ('HD', 'S'),
('HD', 'SA'), ('HD', 'ZN'), ('MG', 'NA'), ('MG', 'OA'),
('MN', 'N'), ('MN', 'OA'), ('N', 'N'), ('N', 'NA'),
('N', 'OA'), ('N', 'SA'), ('N', 'ZN'), ('NA', 'OA'),
('NA', 'SA'), ('NA', 'ZN'), ('OA', 'OA'), ('OA', 'SA'),
('OA', 'ZN'), ('S', 'ZN'), ('SA', 'ZN'), ('A', 'BR'),
('A', 'I'), ('A', 'P'), ('A', 'S'), ('BR', 'N'), ('BR',
'SA'),
('C', 'FE'), ('C', 'I'), ('C', 'P'), ('C', 'S'), ('CL',
'MN'),
('CL', 'NA'), ('CL', 'P'), ('CL', 'S'), ('CL', 'SA'),
('CU', 'HD'), ('CU', 'N'), ('FE', 'NA'), ('FE', 'SA'),
('I', 'N'), ('I', 'OA'), ('MG', 'N'), ('MG', 'P'), ('MG',
'S'),
('MG', 'SA'), ('MN', 'NA'), ('MN', 'P'), ('MN', 'S'),
('MN', 'SA'), ('N', 'P'), ('N', 'S'), ('NA', 'P'), ('NA',
'S'),
('OA', 'P'), ('OA',
'S'), ('P', 'S'), ('P', 'SA'), ('P', 'ZN'),
('S', 'SA'), ('SA', 'SA'), ('A', 'CU'), ('C', 'CD'))
cc_4_rec_types, cc_4_lig_types = zip(*cc_4_types)
self.titles += ['cc_%s.%s_4' % (t1, t2) for t1, t2 in cc_4_types]
self.cc_4 = close_contacts_descriptor(protein,
cutoff=4,
protein_types=cc_4_rec_types,
ligand_types=cc_4_lig_types,
mode='atom_types_ad4',
aligned_pairs=True)
self.ele_types = (
('A', 'A'), ('A', 'C'), ('A', 'CL'), ('A', 'F'), ('A', 'FE'),
('A', 'HD'), ('A', 'MG'), ('A', 'MN'), ('A', 'N'), ('A', 'NA'),
('A', 'OA'), ('A', 'SA'), ('A', 'ZN'),
('BR', 'C'), ('BR', 'HD'), ('BR', 'OA'), ('C', 'C'),
('C', 'CL'), ('C', 'F'), ('C', 'HD'), ('C', 'MG'),
('C', 'MN'), ('C', 'N'), ('C', 'NA'), ('C', 'OA'), ('C', 'SA'),
('C', 'ZN'), ('CL', 'FE'), ('CL', 'HD'), ('CL', 'MG'),
('CL', 'N'), ('CL', 'OA'), ('CL', 'ZN'), ('F', 'HD'),
('F', 'N'), ('F', 'OA'), ('F', 'SA'), ('F', 'ZN'), ('FE', 'HD'),
('FE', 'N'), ('FE', 'OA'), ('HD', 'HD'), ('HD',
'I'), ('HD',
'MG'), ('HD',
'MN'),
('HD', 'N'), ('HD', 'NA'), ('HD', 'OA'), ('HD', 'P'),
('HD', 'S'), ('HD', 'SA'), ('HD', 'ZN'), ('MG', 'NA'), ('MG',
'OA'),
('MN', 'N'), ('MN',
'OA'), ('N', 'N'), ('N', 'NA'), ('N', 'OA'), ('N',
'SA'),
('N', 'ZN'), ('NA', 'OA'), ('NA', 'SA'), ('NA', 'ZN'), ('OA',
'OA'),
('OA',
'SA'), ('OA',
'ZN'), ('S', 'ZN'), ('SA',
'ZN'), ('A', 'BR'), ('A', 'I'),
('A', 'P'), ('A', 'S'), ('BR', 'N'), ('BR', 'SA'), ('C',
'FE'),
('C', 'I'), ('C', 'P'), ('C', 'S'), ('CL', 'MN'), ('CL',
'NA'), ('CL',
'P'),
('CL', 'S'), ('CL', 'SA'), ('CU', 'HD'), ('CU', 'N'), ('FE', 'NA'),
('FE',
'SA'), ('I', 'N'), ('I', 'OA'),
('MG', 'N'), ('MG', 'P'), ('MG', 'S'), ('MG', 'SA'), ('MN', 'NA'),
('MN', 'P'), ('MN', 'S'), ('MN', 'SA'), ('N', 'P'), ('N', 'S'),
('NA', 'P'), ('NA', 'S'), ('OA', 'P'), ('OA', 'S'), ('P', 'S'),
('P', 'SA'), ('P', 'ZN'), ('S', 'SA'), ('SA', 'SA'))
self.titles += ['ele_%s.%s_4' % (t1, t2) for t1, t2 in self.ele_types]
self.ligand_atom_types = [
'A', 'BR', 'C', 'CL', 'F', 'HD', 'I', 'N', 'NA', 'OA', 'P', 'S',
'SA'
]
self.titles += ['lig_%s' % t1 for t1 in self.ligand_atom_types]
cc_25_types = [('A', 'A'), ('A', 'C'), ('A', 'CL'), ('A', 'F'),
('A', 'FE'), ('A', 'HD'), ('A', 'MG'), ('A', 'MN'),
('A', 'N'), ('A', 'NA'), ('A', 'OA'), ('A', 'SA'),
('A', 'ZN'), ('BR', 'C'), ('BR', 'HD'), ('BR', 'OA'),
('C', 'C'), ('C', 'CL'), ('C', 'F'), ('C', 'HD'),
('C', 'MG'), ('C', 'MN'), ('C', 'N'), ('C', 'NA'),
('C', 'OA'), ('C', 'SA'), ('C', 'ZN'), ('CD', 'OA'),
('CL', 'FE'), ('CL', 'HD'), ('CL', 'MG'), ('CL', 'N'),
('CL', 'OA'), ('CL', 'ZN'), ('F', 'HD'), ('F', 'N'),
('F', 'OA'), ('F', 'SA'), ('F', 'ZN'), ('FE', 'HD'),
('FE', 'N'), ('FE', 'OA'), ('HD', 'HD'), ('HD', 'I'),
('HD', 'MG'), ('HD', 'MN'), ('HD', 'N'), ('HD', 'NA'),
('HD', 'OA'), ('HD', 'P'), ('HD', 'S'), ('HD', 'SA'),
('HD', 'ZN'), ('MG', 'NA'), ('MG', 'OA'), ('MN', 'N'),
('MN', 'OA'), ('N', 'N'), ('N', 'NA'), ('N', 'OA'),
('N', 'SA'), ('N', 'ZN'), ('NA', 'OA'), ('NA', 'SA'),
('NA', 'ZN'), ('OA', 'OA'), ('OA', 'SA'), ('OA', 'ZN'),
('S', 'ZN'), ('SA', 'ZN')]
cc_25_rec_types, cc_25_lig_types = zip(*cc_25_types)
self.cc_25 = close_contacts_descriptor(protein,
cutoff=2.5,
protein_types=cc_25_rec_types,
ligand_types=cc_25_lig_types,
mode='atom_types_ad4',
aligned_pairs=True)
self.titles += ['cc_%s.%s_2.5' % (t1, t2) for t1, t2 in cc_25_types]
# H-Bonds (<4A)
self.titles += [
'hb_4_mol_backbone_alpha', 'hb_4_mol_backbone_beta',
'hb_4_mol_backbone_other', 'hb_4_mol_sidechain_alpha',
'hb_4_mol_sidechain_beta', 'hb_4_mol_sidechain_other',
'hb_4_rec_backbone_alpha', 'hb_4_rec_backbone_beta',
'hb_4_rec_backbone_other', 'hb_4_rec_sidechain_alpha',
'hb_4_rec_sidechain_beta', 'hb_4_rec_sidechain_other'
]
# Hydrophobic Contact <4A
self.titles += [
'hyd_4_backbone_alpha', 'hyd_4_backbone_beta',
'hyd_4_backbone_other', 'hyd_4_sidechain_alpha',
'hyd_4_sidechain_beta', 'hyd_4_sidechain_other', 'hyd_4_all'
]
# Pi-stacking (<7.5A)
self.titles += [
'pi_stack_7.5_alpha', 'pi_stack_7.5_beta', 'pi_stack_7.5_other'
]
# T-shaped Pi-Pi interaction
self.titles += ['pi_t_7.5_alpha', 'pi_t_7.5_beta', 'pi_t_7.5_other']
# Pi-cation (<6A)
self.titles += [
'pi_cat_mol_6_alpha', 'pi_cat_mol_6_beta', 'pi_cat_mol_6_other',
'pi_cat_rec_6_alpha', 'pi_cat_rec_6_beta', 'pi_cat_rec_6_other'
]
# Active site flexibility (<4A)
self.titles += [
'as_flex_backbone_alpha', 'as_flex_backbone_beta',
'as_flex_backbone_other', 'as_flex_sidechain_alpha',
'as_flex_sidechain_beta', 'as_flex_sidechain_other', 'as_flex_all'
]
# Salt bridges (<5.5)
self.titles += [
'salt_bridge_5.5_alpha', 'salt_bridge_5.5_beta',
'salt_bridge_5.5_other', 'salt_bridge_5.5_all'
]
# Rotatable bonds
self.titles += ['num_rotors']
assert len(self.titles) == len(self)
def __init__(self, protein=None, n_jobs=-1, version=1, spr=0, **kwargs):
"""Scoring function implementing RF-Score variants. It predicts the
binding affinity (pKi/d) of ligand in a complex utilizng simple
descriptors (close contacts of atoms <12A) with sophisticated
machine-learning model (random forest). The third variand supplements
those contacts with Vina partial scores. For futher details see RF-Score
publications v1[1]_, v2[2]_, v3[3]_.
Parameters
----------
protein : oddt.toolkit.Molecule object
Receptor for the scored ligands
n_jobs: int (default=-1)
Number of cores to use for scoring and training. By default (-1)
all cores are allocated.
version: int (default=1)
Scoring function variant. The deault is the simplest one (v1).
spr: int (default=0)
The minimum number of contacts in each pair of atom types in
the training set for the column to be included in training.
This is a way of removal of not frequent and empty contacts.
References
----------
.. [1] Ballester PJ, Mitchell JBO. A machine learning approach to
predicting protein-ligand binding affinity with applications to
molecular docking. Bioinformatics. 2010;26: 1169-1175.
doi:10.1093/bioinformatics/btq112
.. [2] Ballester PJ, Schreyer A, Blundell TL. Does a more precise
chemical description of protein-ligand complexes lead to more
accurate prediction of binding affinity? J Chem Inf Model. 2014;54:
944-955. doi:10.1021/ci500091r
.. [3] Li H, Leung K-S, Wong M-H, Ballester PJ. Improving AutoDock Vina
Using Random Forest: The Growing Accuracy of Binding Affinity
Prediction by the Effective Exploitation of Larger Data Sets.
Mol Inform. WILEY-VCH Verlag; 2015;34: 115-126.
doi:10.1002/minf.201400132
"""
self.protein = protein
self.n_jobs = n_jobs
self.version = version
self.spr = spr
if version == 1:
cutoff = 12
mtry = 6
descriptors = close_contacts_descriptor(
protein,
cutoff=cutoff,
protein_types=protein_atomic_nums,
ligand_types=ligand_atomic_nums)
elif version == 2:
cutoff = np.array([0, 2, 4, 6, 8, 10, 12])
mtry = 14
descriptors = close_contacts_descriptor(
protein,
cutoff=cutoff,
protein_types=protein_atomic_nums,
ligand_types=ligand_atomic_nums)
elif version == 3:
cutoff = 12
mtry = 6
cc = close_contacts_descriptor(
protein,
cutoff=cutoff,
protein_types=protein_atomic_nums,
ligand_types=ligand_atomic_nums)
vina_scores = ['vina_gauss1',
'vina_gauss2',
'vina_repulsion',
'vina_hydrophobic',
'vina_hydrogen',
'vina_num_rotors']
vina = oddt_vina_descriptor(protein, vina_scores=vina_scores)
descriptors = ensemble_descriptor((vina, cc))
model = randomforest(n_estimators=500,
oob_score=True,
n_jobs=n_jobs,
max_features=mtry,
bootstrap=True,
min_samples_split=6,
**kwargs)
super(rfscore, self).__init__(model, descriptors,
score_title='rfscore_v%i' % self.version)
def __init__(self, protein=None, n_jobs=-1, version=1, spr=0, **kwargs):
"""Scoring function implementing RF-Score variants. It predicts the
binding affinity (pKi/d) of ligand in a complex utilizng simple
descriptors (close contacts of atoms <12A) with sophisticated
machine-learning model (random forest). The third variand supplements
those contacts with Vina partial scores. For futher details see RF-Score
publications v1[1]_, v2[2]_, v3[3]_.
Parameters
----------
protein : oddt.toolkit.Molecule object
Receptor for the scored ligands
n_jobs: int (default=-1)
Number of cores to use for scoring and training. By default (-1)
all cores are allocated.
version: int (default=1)
Scoring function variant. The deault is the simplest one (v1).
spr: int (default=0)
The minimum number of contacts in each pair of atom types in
the training set for the column to be included in training.
This is a way of removal of not frequent and empty contacts.
References
----------
.. [1] Ballester PJ, Mitchell JBO. A machine learning approach to
predicting protein-ligand binding affinity with applications to
molecular docking. Bioinformatics. 2010;26: 1169-1175.
doi:10.1093/bioinformatics/btq112
.. [2] Ballester PJ, Schreyer A, Blundell TL. Does a more precise
chemical description of protein-ligand complexes lead to more
accurate prediction of binding affinity? J Chem Inf Model. 2014;54:
944-955. doi:10.1021/ci500091r
.. [3] Li H, Leung K-S, Wong M-H, Ballester PJ. Improving AutoDock Vina
Using Random Forest: The Growing Accuracy of Binding Affinity
Prediction by the Effective Exploitation of Larger Data Sets.
Mol Inform. WILEY-VCH Verlag; 2015;34: 115-126.
doi:10.1002/minf.201400132
"""
self.protein = protein
self.n_jobs = n_jobs
self.version = version
self.spr = spr
if version == 1:
cutoff = 12
mtry = 6
descriptors = close_contacts_descriptor(
protein,
cutoff=cutoff,
protein_types=protein_atomic_nums,
ligand_types=ligand_atomic_nums)
elif version == 2:
cutoff = np.array([0, 2, 4, 6, 8, 10, 12])
mtry = 14
descriptors = close_contacts_descriptor(
protein,
cutoff=cutoff,
protein_types=protein_atomic_nums,
ligand_types=ligand_atomic_nums)
elif version == 3:
cutoff = 12
mtry = 6
cc = close_contacts_descriptor(protein,
cutoff=cutoff,
protein_types=protein_atomic_nums,
ligand_types=ligand_atomic_nums)
vina_scores = [
'vina_gauss1', 'vina_gauss2', 'vina_repulsion',
'vina_hydrophobic', 'vina_hydrogen', 'vina_num_rotors'
]
vina = oddt_vina_descriptor(protein, vina_scores=vina_scores)
descriptors = ensemble_descriptor((vina, cc))
# elif version == 5:
# cutoff = np.array([0, 2, 4, 6, 8, 10, 12])
# mtry = 14
# descriptors = close_contacts_descriptor(
# protein,
# cutoff=cutoff,
# protein_types=protein_atomic_nums,
# ligand_types=ligand_atomic_nums)
model = randomforest(n_estimators=500,
oob_score=True,
n_jobs=n_jobs,
max_features=mtry,
bootstrap=True,
min_samples_split=6,
**kwargs)
super(rfscore, self).__init__(model,
descriptors,
score_title='rfscore_v%i' % self.version)
def __init__(self, protein=None):
""" Descriptor build from binana script (as used in NNScore 2.0
Parameters
----------
protein: oddt.toolkit.Molecule object (default=None)
Protein object to be used while generating descriptors.
"""
self.protein = protein
self.titles = []
self.vina = oddt_vina_descriptor(protein, vina_scores=['vina_gauss1',
'vina_gauss2',
'vina_repulsion',
'vina_hydrophobic',
'vina_hydrogen'])
self.titles += self.vina.titles
# Close contacts descriptor generators
cc_4_types = (('A', 'A'), ('A', 'C'), ('A', 'CL'), ('A', 'F'),
('A', 'FE'), ('A', 'HD'), ('A', 'MG'), ('A', 'MN'),
('A', 'N'), ('A', 'NA'), ('A', 'OA'), ('A', 'SA'),
('A', 'ZN'), ('BR', 'C'), ('BR', 'HD'), ('BR', 'OA'),
('C', 'C'), ('C', 'CL'), ('C', 'F'), ('C', 'HD'),
('C', 'MG'), ('C', 'MN'), ('C', 'N'), ('C', 'NA'),
('C', 'OA'), ('C', 'SA'), ('C', 'ZN'), ('CL', 'FE'),
('CL', 'HD'), ('CL', 'MG'), ('CL', 'N'), ('CL', 'OA'),
('CL', 'ZN'), ('F', 'HD'), ('F', 'N'), ('F', 'OA'),
('F', 'SA'), ('FE', 'HD'), ('FE', 'N'), ('FE', 'OA'),
('HD', 'HD'), ('HD', 'I'), ('HD', 'MG'), ('HD', 'MN'),
('HD', 'N'), ('HD', 'NA'), ('HD', 'OA'), ('HD', 'P'),
('HD', 'S'), ('HD', 'SA'), ('HD', 'ZN'), ('MG', 'NA'),
('MG', 'OA'), ('MN', 'N'), ('MN', 'OA'), ('N', 'N'),
('N', 'NA'), ('N', 'OA'), ('N', 'SA'), ('N', 'ZN'),
('NA', 'OA'), ('NA', 'SA'), ('NA', 'ZN'), ('OA', 'OA'),
('OA', 'SA'), ('OA', 'ZN'), ('S', 'ZN'), ('SA', 'ZN'),
('A', 'BR'), ('A', 'I'), ('A', 'P'), ('A', 'S'),
('BR', 'N'), ('BR', 'SA'), ('C', 'FE'), ('C', 'I'),
('C', 'P'), ('C', 'S'), ('CL', 'MN'), ('CL', 'NA'),
('CL', 'P'), ('CL', 'S'), ('CL', 'SA'), ('CU', 'HD'),
('CU', 'N'), ('FE', 'NA'), ('FE', 'SA'), ('I', 'N'),
('I', 'OA'), ('MG', 'N'), ('MG', 'P'), ('MG', 'S'),
('MG', 'SA'), ('MN', 'NA'), ('MN', 'P'), ('MN', 'S'),
('MN', 'SA'), ('N', 'P'), ('N', 'S'), ('NA', 'P'),
('NA', 'S'), ('OA', 'P'), ('OA', 'S'), ('P', 'S'),
('P', 'SA'), ('P', 'ZN'), ('S', 'SA'), ('SA', 'SA'),
('A', 'CU'), ('C', 'CD'))
cc_4_rec_types, cc_4_lig_types = zip(*cc_4_types)
self.titles += ['cc_%s.%s_4' % (t1, t2) for t1, t2 in cc_4_types]
self.cc_4 = close_contacts_descriptor(protein,
cutoff=4,
protein_types=cc_4_rec_types,
ligand_types=cc_4_lig_types,
mode='atom_types_ad4',
aligned_pairs=True)
self.ele_types = (('A', 'A'), ('A', 'C'), ('A', 'CL'), ('A', 'F'),
('A', 'FE'), ('A', 'HD'), ('A', 'MG'), ('A', 'MN'),
('A', 'N'), ('A', 'NA'), ('A', 'OA'), ('A', 'SA'),
('A', 'ZN'), ('BR', 'C'), ('BR', 'HD'), ('BR', 'OA'),
('C', 'C'), ('C', 'CL'), ('C', 'F'), ('C', 'HD'),
('C', 'MG'), ('C', 'MN'), ('C', 'N'), ('C', 'NA'),
('C', 'OA'), ('C', 'SA'), ('C', 'ZN'), ('CL', 'FE'),
('CL', 'HD'), ('CL', 'MG'), ('CL', 'N'), ('CL', 'OA'),
('CL', 'ZN'), ('F', 'HD'), ('F', 'N'), ('F', 'OA'),
('F', 'SA'), ('F', 'ZN'), ('FE', 'HD'), ('FE', 'N'),
('FE', 'OA'), ('HD', 'HD'), ('HD', 'I'), ('HD', 'MG'),
('HD', 'MN'), ('HD', 'N'), ('HD', 'NA'), ('HD', 'OA'),
('HD', 'P'), ('HD', 'S'), ('HD', 'SA'), ('HD', 'ZN'),
('MG', 'NA'), ('MG', 'OA'), ('MN', 'N'), ('MN', 'OA'),
('N', 'N'), ('N', 'NA'), ('N', 'OA'), ('N', 'SA'),
('N', 'ZN'), ('NA', 'OA'), ('NA', 'SA'), ('NA', 'ZN'),
('OA', 'OA'), ('OA', 'SA'), ('OA', 'ZN'), ('S', 'ZN'),
('SA', 'ZN'), ('A', 'BR'), ('A', 'I'), ('A', 'P'),
('A', 'S'), ('BR', 'N'), ('BR', 'SA'), ('C', 'FE'),
('C', 'I'), ('C', 'P'), ('C', 'S'), ('CL', 'MN'),
('CL', 'NA'), ('CL', 'P'), ('CL', 'S'), ('CL', 'SA'),
('CU', 'HD'), ('CU', 'N'), ('FE', 'NA'), ('FE', 'SA'),
('I', 'N'), ('I', 'OA'), ('MG', 'N'), ('MG', 'P'),
('MG', 'S'), ('MG', 'SA'), ('MN', 'NA'), ('MN', 'P'),
('MN', 'S'), ('MN', 'SA'), ('N', 'P'), ('N', 'S'),
('NA', 'P'), ('NA', 'S'), ('OA', 'P'), ('OA', 'S'),
('P', 'S'), ('P', 'SA'), ('P', 'ZN'), ('S', 'SA'),
('SA', 'SA'))
self.titles += ['ele_%s.%s_4' % (t1, t2) for t1, t2 in self.ele_types]
self.ligand_atom_types = ['A', 'BR', 'C', 'CL', 'F', 'HD', 'I', 'N', 'NA', 'OA', 'P', 'S', 'SA']
self.titles += ['lig_%s' % t1 for t1 in self.ligand_atom_types]
cc_25_types = [('A', 'A'), ('A', 'C'), ('A', 'CL'), ('A', 'F'),
('A', 'FE'), ('A', 'HD'), ('A', 'MG'), ('A', 'MN'),
('A', 'N'), ('A', 'NA'), ('A', 'OA'), ('A', 'SA'),
('A', 'ZN'), ('BR', 'C'), ('BR', 'HD'), ('BR', 'OA'),
('C', 'C'), ('C', 'CL'), ('C', 'F'), ('C', 'HD'),
('C', 'MG'), ('C', 'MN'), ('C', 'N'), ('C', 'NA'),
('C', 'OA'), ('C', 'SA'), ('C', 'ZN'), ('CD', 'OA'),
('CL', 'FE'), ('CL', 'HD'), ('CL', 'MG'), ('CL', 'N'),
('CL', 'OA'), ('CL', 'ZN'), ('F', 'HD'), ('F', 'N'),
('F', 'OA'), ('F', 'SA'), ('F', 'ZN'), ('FE', 'HD'),
('FE', 'N'), ('FE', 'OA'), ('HD', 'HD'), ('HD', 'I'),
('HD', 'MG'), ('HD', 'MN'), ('HD', 'N'), ('HD', 'NA'),
('HD', 'OA'), ('HD', 'P'), ('HD', 'S'), ('HD', 'SA'),
('HD', 'ZN'), ('MG', 'NA'), ('MG', 'OA'), ('MN', 'N'),
('MN', 'OA'), ('N', 'N'), ('N', 'NA'), ('N', 'OA'),
('N', 'SA'), ('N', 'ZN'), ('NA', 'OA'), ('NA', 'SA'),
('NA', 'ZN'), ('OA', 'OA'), ('OA', 'SA'), ('OA', 'ZN'),
('S', 'ZN'), ('SA', 'ZN')]
cc_25_rec_types, cc_25_lig_types = zip(*cc_25_types)
self.cc_25 = close_contacts_descriptor(protein,
cutoff=2.5,
protein_types=cc_25_rec_types,
ligand_types=cc_25_lig_types,
mode='atom_types_ad4',
aligned_pairs=True)
self.titles += ['cc_%s.%s_2.5' % (t1, t2) for t1, t2 in cc_25_types]
# H-Bonds (<4A)
self.titles += ['hb_4_mol_backbone_alpha',
'hb_4_mol_backbone_beta',
'hb_4_mol_backbone_other',
'hb_4_mol_sidechain_alpha',
'hb_4_mol_sidechain_beta',
'hb_4_mol_sidechain_other',
'hb_4_rec_backbone_alpha',
'hb_4_rec_backbone_beta',
'hb_4_rec_backbone_other',
'hb_4_rec_sidechain_alpha',
'hb_4_rec_sidechain_beta',
'hb_4_rec_sidechain_other']
# Hydrophobic Contact <4A
self.titles += ['hyd_4_backbone_alpha',
'hyd_4_backbone_beta',
'hyd_4_backbone_other',
'hyd_4_sidechain_alpha',
'hyd_4_sidechain_beta',
'hyd_4_sidechain_other',
'hyd_4_all']
# Pi-stacking (<7.5A)
self.titles += ['pi_stack_7.5_alpha',
'pi_stack_7.5_beta',
'pi_stack_7.5_other']
# T-shaped Pi-Pi interaction
self.titles += ['pi_t_7.5_alpha',
'pi_t_7.5_beta',
'pi_t_7.5_other']
# Pi-cation (<6A)
self.titles += ['pi_cat_mol_6_alpha',
'pi_cat_mol_6_beta',
'pi_cat_mol_6_other',
'pi_cat_rec_6_alpha',
'pi_cat_rec_6_beta',
'pi_cat_rec_6_other']
# Active site flexibility (<4A)
self.titles += ['as_flex_backbone_alpha',
'as_flex_backbone_beta',
'as_flex_backbone_other',
'as_flex_sidechain_alpha',
'as_flex_sidechain_beta',
'as_flex_sidechain_other',
'as_flex_all']
# Salt bridges (<5.5)
self.titles += ['salt_bridge_5.5_alpha',
'salt_bridge_5.5_beta',
'salt_bridge_5.5_other',
'salt_bridge_5.5_all']
# Rotatable bonds
self.titles += ['num_rotors']
assert len(self.titles) == len(self)
