Merge pull request #1454 from rbharath/rdkit_soft (f6e80071) · 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/data/data_loader.py

+6 −3

Original line number	Diff line number	Diff line
		@@ -10,9 +10,6 @@ import numpy as np
		import csv
		import numbers
		import tempfile
		from rdkit.Chem import rdmolfiles
		from rdkit.Chem import rdmolops
		from rdkit import Chem
		import time
		import sys
		from deepchem.utils.save import log
		@@ -66,6 +63,9 @@ def featurize_smiles_df(df, featurizer, field, log_every_N=1000, verbose=True):
		sample_elems = df[field].tolist()

		features = []
		from rdkit import Chem
		from rdkit.Chem import rdmolfiles
		from rdkit.Chem import rdmolops
		for ind, elem in enumerate(sample_elems):
		mol = Chem.MolFromSmiles(elem)
		# TODO (ytz) this is a bandage solution to reorder the atoms so
		@@ -91,6 +91,9 @@ def featurize_smiles_np(arr, featurizer, log_every_N=1000, verbose=True):
		features array
		"""
		features = []
		from rdkit import Chem
		from rdkit.Chem import rdmolfiles
		from rdkit.Chem import rdmolops
		for ind, elem in enumerate(arr.tolist()):
		mol = Chem.MolFromSmiles(elem)
		if mol:

deepchem/feat/adjacency_fingerprints.py

+1 −2

Original line number	Diff line number	Diff line
		from collections import deque

		from rdkit import Chem

		import sys
		import tensorflow as tf
		import pickle
		@@ -160,6 +158,7 @@ class AdjacencyFingerprint(Featurizer):
		def featurize(self, rdkit_mols):
		featurized_mols = np.empty((len(rdkit_mols)), dtype=object)

		from rdkit import Chem
		for idx, mol in enumerate(rdkit_mols):
		if self.add_hydrogens:
		mol = Chem.AddHs(mol)

deepchem/feat/base_classes.py

+0 −2

Original line number	Diff line number	Diff line
		@@ -4,8 +4,6 @@ Feature calculations.
		import logging
		import types
		import numpy as np
		from rdkit import Chem
		from rdkit.Chem import rdGeometry, rdMolTransforms
		import multiprocessing

		__author__ = "Steven Kearnes"

deepchem/feat/basic.py

+2 −1

Original line number	Diff line number	Diff line
		@@ -8,7 +8,6 @@ __author__ = "Steven Kearnes"
		__copyright__ = "Copyright 2014, Stanford University"
		__license__ = "MIT"

		from rdkit.Chem import Descriptors
		from deepchem.feat import Featurizer


		@@ -27,6 +26,7 @@ class MolecularWeight(Featurizer):
		mol : RDKit Mol
		Molecule.
		"""
		from rdkit.Chem import Descriptors
		wt = Descriptors.ExactMolWt(mol)
		wt = [wt]
		return wt
		@@ -74,6 +74,7 @@ class RDKitDescriptors(Featurizer):
		def __init__(self):
		self.descriptors = []
		self.descList = []
		from rdkit.Chem import Descriptors
		for descriptor, function in Descriptors.descList:
		if descriptor in self.allowedDescriptors:
		self.descriptors.append(descriptor)

Admin message