Saving binding pocket feat (24ac9c6d) · Commits · 钟慕尧 / deepchem

deepchem/dock/binding_pocket.py

+10 −3

Original line number	Diff line number	Diff line
		@@ -164,7 +164,7 @@ def merge_overlapping_boxes(mapping, boxes, threshold=.8):
		class BindingPocketFinder(object):
		"""Abstract superclass for binding pocket detectors"""

		def find_pockets(self, protein_file):
		def find_pockets(self, protein_file, ligand_file):
		"""Finds potential binding pockets in proteins."""
		raise NotImplementedError

		@@ -188,5 +188,12 @@ class ConvexHullPocketFinder(BindingPocketFinder):
		ligand_coords = load_molecule(ligand_file)[0]
		boxes = get_all_boxes(protein_coords, self.pad)
		mapping = boxes_to_atoms(protein_coords, boxes)
		merged_boxes, mapping = merge_overlapping_boxes(mapping, boxes)
		return merged_boxes, mapping
		pockets, pocket_atoms = merge_overlapping_boxes(mapping, boxes)
		pocket_coords = []
		for pocket in pockets:
		atoms = pocket_atoms[pocket]
		coords = np.zeros((len(atoms), 3))
		for ind, atom in enumerate(atoms):
		coords[ind] = protein_coords[atom]
		pocket_coords.append(coords)
		return pockets, pocket_atoms, pocket_coords

deepchem/dock/tests/test_binding_pocket.py

+2 −2

Original line number	Diff line number	Diff line
		@@ -124,7 +124,7 @@ class TestPoseGeneration(unittest.TestCase):
		finder = dc.dock.ConvexHullPocketFinder()

		all_pockets = finder.find_all_pockets(protein_file)
		pockets = finder.find_pockets(protein_file, ligand_file)
		pockets, _, _ = finder.find_pockets(protein_file, ligand_file)

		assert len(pockets) < len(all_pockets)

		@@ -138,7 +138,7 @@ class TestPoseGeneration(unittest.TestCase):
		dc.dock.binding_pocket.extract_active_site(
		protein_file, ligand_file))
		finder = dc.dock.ConvexHullPocketFinder()
		pockets, pocket_atoms = finder.find_pockets(protein_file, ligand_file)
		pockets, pocket_atoms, _ = finder.find_pockets(protein_file, ligand_file)

		# Add active site to dict
		print("active_site_box")

deepchem/feat/init.py

+1 −0

Original line number	Diff line number	Diff line
		@@ -18,3 +18,4 @@ from deepchem.feat.basic import RDKitDescriptors
		from deepchem.feat.coulomb_matrices import CoulombMatrixEig
		from deepchem.feat.grid_featurizer import GridFeaturizer
		from deepchem.feat.nnscore_utils import hydrogenate_and_compute_partial_charges
		from deepchem.feat.binding_pocket_features import BindingPocketFeaturizer

deepchem/feat/binding_pocket_features.py

0 → 100644

+50 −0

Original line number	Diff line number	Diff line
		"""
		Featurizes proposed binding pockets.
		"""
		from __future__ import print_function
		from __future__ import division
		from __future__ import unicode_literals

		__author__ = "Bharath Ramsundar"
		__copyright__ = "Copyright 2017, Stanford University"
		__license__ = "GPL"

		import numpy as np
		import os
		import pybel
		import tempfile
		import mdtraj as md
		from scipy.spatial import ConvexHull
		from deepchem.feat import hydrogenate_and_compute_partial_charges
		from deepchem.feat.atomic_coordinates import AtomicCoordinates
		from deepchem.feat.grid_featurizer import load_molecule
		from deepchem.feat import Featurizer

		class BindingPocketFeaturizer(Featurizer):
		"""
		Featurizes binding pockets with information about chemical environments.
		"""

		residues = ["ALA", "ARG", "ASN", "ASP", "CYS", "GLN", "GLU", "GLY", "HIS",
		"ILE", "LEU", "LYS", "MET", "PHE", "PRO", "PYL", "SER", "SEC",
		"THR", "TRP", "TYR", "VAL", "ASX", "GLX"]

		def featurize(self, protein_file, pockets, pocket_atoms, pocket_coords):
		"""
		Calculate atomic coodinates.
		"""
		protein = md.load(protein_file)
		n_pockets = len(pockets)
		n_residues = len(BindingPocketFeaturizer.residues)
		res_map = dict(zip(BindingPocketFeaturizer.residues, range(n_residues)))
		all_features = np.zeros((n_pockets, n_residues))
		for pocket_num, (pocket, coords) in enumerate(zip(pockets, pocket_coords)):
		atoms = pocket_atoms[pocket]
		for atom in atoms:
		atom_name = str(protein.top.atom(atom))
		# atom_name is of format RESX-ATOMTYPE
		# where X is a 1 to 4 digit number
		residue = atom_name[:3]
		atomtype = atom_name.split("-")[1]
		all_features[pocket_nu, res_map[residue]] += 1
		return all_features

deepchem/feat/tests/test_binding_pocket_features.py

0 → 100644

+32 −0

Original line number	Diff line number	Diff line
		"""
		Test atomic coordinates and neighbor lists.
		"""
		import os
		import numpy as np
		import unittest
		from rdkit import Chem
		import deepchem as dc

		class TestAtomicCoordinates(unittest.TestCase):
		"""
		Test AtomicCoordinates.
		"""

		def test_atomic_coordinates(self):
		"""
		Simple test that atomic coordinates returns ndarray of right shape.
		"""
		current_dir = os.path.dirname(os.path.realpath(__file__))
		protein_file = os.path.join(current_dir, "../../dock/tests/1jld_protein.pdb")
		ligand_file = os.path.join(current_dir, "../../dock/tests/1jld_ligand.sdf")

		finder = dc.dock.ConvexHullPocketFinder()
		pocket_featurizer = dc.feat.BindingPocketFeaturizer()
		pockets, pocket_atoms, pocket_coords = finder.find_pockets(protein_file, ligand_file)
		n_pockets = len(pockets)

		pocket_features = pocket_featurizer.featurize(
		protein_file, pockets, pocket_atoms, pocket_coords)

		assert isinstance(pocket_features, np.ndarray)
		assert pocket_features.shape[0] == n_pockets

Admin message