changes (c294a6e7) · Commits · 钟慕尧 / deepchem

contrib/visualization/utils.py

0 → 100644

+72 −0

Original line number	Diff line number	Diff line
		import nglview
		import tempfile
		import os
		import mdtraj as md
		import numpy as np
		import tempfile
		from rdkit import Chem
		from rdkit.Chem import Draw
		from itertools import islice
		from IPython.display import Image, HTML, display

		def combine_mdtraj(protein, ligand):
		chain = protein.topology.add_chain()
		residue = protein.topology.add_residue("LIG", chain, resSeq=1)
		for atom in ligand.topology.atoms:
		protein.topology.add_atom(atom.name, atom.element, residue)
		protein.xyz = np.hstack([protein.xyz, ligand.xyz])
		protein.topology.create_standard_bonds()
		return protein

		def visualize_complex(complex_mdtraj):
		ligand_atoms = [a.index for a in complex_mdtraj.topology.atoms if "LIG" in str(a.residue)]
		binding_pocket_atoms = md.compute_neighbors(complex_mdtraj, 0.5, ligand_atoms)[0]
		binding_pocket_residues = list(set([complex_mdtraj.topology.atom(a).residue.resSeq for a in binding_pocket_atoms]))
		binding_pocket_residues = [str(r) for r in binding_pocket_residues]
		binding_pocket_residues = " or ".join(binding_pocket_residues)

		traj = nglview.MDTrajTrajectory( complex_mdtraj ) # load file from RCSB PDB
		ngltraj = nglview.NGLWidget( traj )
		ngltraj.representations = [
		{ "type": "cartoon", "params": {
		"sele": "protein", "color": "residueindex"
		} },
		{ "type": "licorice", "params": {
		"sele": "(not hydrogen) and (%s)" % binding_pocket_residues
		} },
		{ "type": "ball+stick", "params": {
		"sele": "LIG"
		} }
		]
		return ngltraj

		def visualize_ligand(ligand_mdtraj):
		traj = nglview.MDTrajTrajectory( ligand_mdtraj ) # load file from RCSB PDB
		ngltraj = nglview.NGLWidget( traj )
		ngltraj.representations = [
		{ "type": "ball+stick", "params": {"sele": "all" } } ]
		return ngltraj

		def convert_lines_to_mdtraj(molecule_lines):
		tempdir = tempfile.mkdtemp()
		molecule_file = os.path.join(tempdir, "molecule.pdb")
		with open(molecule_file, "wb") as f:
		f.writelines(molecule_lines)
		molecule_mdtraj = md.load(molecule_file)
		return molecule_mdtraj

		def display_images(filenames):
		"""Helper to pretty-print images."""
		imagesList=''.join(
		["<img style='width: 140px; margin: 0px; float: left; border: 1px solid black;' src='%s' />"
		% str(s) for s in sorted(filenames)])
		display(HTML(imagesList))

		def mols_to_pngs(mols, basename="test"):
		"""Helper to write RDKit mols to png files."""
		filenames = []
		for i, mol in enumerate(mols):
		filename = "%s%d.png" % (basename, i)
		Draw.MolToFile(mol, filename)
		filenames.append(filename)
		return filenames

deepchem/feat/one_hot.py

+1 −1

Original line number	Diff line number	Diff line
		import numpy as np
		from deepchem.feat import Featurizer
		from rdkit import Chem

		zinc_charset = [
		' ', '#', ')', '(', '+', '-', '/', '1', '3', '2', '5', '4', '7', '6', '8',
		@@ -42,6 +41,7 @@ class OneHotFeaturizer(Featurizer):
		obj
		numpy array of features
		"""
		from rdkit import Chem
		smiles = [Chem.MolToSmiles(mol) for mol in mols]
		if self.charset is None:
		self.charset = self._create_charset(smiles)

deepchem/splits/tests/test_splitter.py

+0 −3

Original line number	Diff line number	Diff line
		@@ -4,8 +4,6 @@ Tests for splitter objects.
		from __future__ import division
		from __future__ import unicode_literals

		from rdkit.Chem.Fingerprints import FingerprintMols

		__author__ = "Bharath Ramsundar, Aneesh Pappu"
		__copyright__ = "Copyright 2016, Stanford University"
		__license__ = "MIT"
		@@ -16,7 +14,6 @@ import numpy as np
		import deepchem as dc
		from deepchem.data import NumpyDataset
		from deepchem.splits import IndexSplitter
		from rdkit import Chem, DataStructs


		class TestSplitters(unittest.TestCase):

deepchem/utils/init.py

+1 −2

Original line number	Diff line number	Diff line
		@@ -15,8 +15,6 @@ import tempfile
		import tarfile
		import zipfile

		from rdkit import Chem
		from rdkit.Chem.Scaffolds import MurckoScaffold

		try:
		from urllib.request import urlretrieve # Python 3
		@@ -152,5 +150,6 @@ class ScaffoldGenerator(object):
		mols : array_like
		Molecules.
		"""
		from rdkit.Chem.Scaffolds import MurckoScaffold
		return MurckoScaffold.MurckoScaffoldSmiles(
		mol=mol, includeChirality=self.include_chirality)

deepchem/utils/conformers.py

+5 −4

Original line number	Diff line number	Diff line
		@@ -8,10 +8,6 @@ __license__ = "3-clause BSD"

		import numpy as np

		from rdkit import Chem
		from rdkit.Chem import AllChem


		class ConformerGenerator(object):
		"""
		Generate molecule conformers.
		@@ -106,6 +102,8 @@ class ConformerGenerator(object):
		mol : RDKit Mol
		Molecule.
		"""
		from rdkit import Chem
		from rdkit.Chem import AllChem
		mol = Chem.AddHs(mol) # add hydrogens
		n_confs = self.max_conformers * self.pool_multiplier
		AllChem.EmbedMultipleConfs(mol, numConfs=n_confs, pruneRmsThresh=-1.)
		@@ -124,6 +122,7 @@ class ConformerGenerator(object):
		kwargs : dict, optional
		Keyword arguments for force field constructor.
		"""
		from rdkit.Chem import AllChem
		if self.force_field == 'uff':
		ff = AllChem.UFFGetMoleculeForceField(
		mol, confId=conf_id, **kwargs)
		@@ -218,6 +217,7 @@ class ConformerGenerator(object):

		# create a new molecule to hold the chosen conformers
		# this ensures proper conformer IDs and energy-based ordering
		from rdkit import Chem
		new = Chem.Mol(mol)
		new.RemoveAllConformers()
		conf_ids = [conf.GetId() for conf in mol.GetConformers()]
		@@ -236,6 +236,7 @@ class ConformerGenerator(object):
		mol : RDKit Mol
		Molecule.
		"""
		from rdkit.Chem import AllChem
		rmsd = np.zeros((mol.GetNumConformers(), mol.GetNumConformers()),
		dtype=float)
		for i, ref_conf in enumerate(mol.GetConformers()):

Admin message