adding raw featurizer (a85d57f1) · Commits · 钟慕尧 / deepchem

deepchem/feat/init.py

+1 −0

Original line number	Diff line number	Diff line
		@@ -21,3 +21,4 @@ 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
		from deepchem.feat.one_hot import OneHotFeaturizer
		from deepchem.feat.raw_featurizer import RawFeaturizer

deepchem/feat/raw_featurizer.py

0 → 100644

+19 −0

Original line number	Diff line number	Diff line
		#!/usr/bin/env python2
		# -- coding: utf-8 --
		from __future__ import print_function
		from __future__ import division
		from __future__ import unicode_literals

		from rdkit import Chem
		from deepchem.feat import Featurizer

		class RawFeaturizer(Featurizer):

		def __init__(self, smiles=False):
		self.smiles = smiles

		def _featurize(self, mol):
		if self.smiles:
		return Chem.MolToSmiles(mol)
		else:
		return mol
		No newline at end of file

deepchem/molnet/init.py

+15 −15

Original line number	Diff line number	Diff line

		from deepchem.molnet.chembl_datasets import load_chembl
		from deepchem.molnet.clintox_datasets import load_clintox
		from deepchem.molnet.delaney_datasets import load_delaney
		from deepchem.molnet.hiv_datasets import load_hiv
		from deepchem.molnet.kaggle_datasets import load_kaggle
		from deepchem.molnet.muv_datasets import load_muv
		from deepchem.molnet.nci_datasets import load_nci
		from deepchem.molnet.pcba_datasets import load_pcba
		from deepchem.molnet.pdbbind_datasets import load_pdbbind_grid
		from deepchem.molnet.qm7_datasets import load_qm7_from_mat, load_qm7b_from_mat
		from deepchem.molnet.qm9_datasets import load_qm9
		from deepchem.molnet.sampl_datasets import load_sampl
		from deepchem.molnet.sider_datasets import load_sider
		from deepchem.molnet.tox21_datasets import load_tox21
		from deepchem.molnet.toxcast_datasets import load_toxcast
		from deepchem.molnet.load_function.chembl_datasets import load_chembl
		from deepchem.molnet.load_function.clintox_datasets import load_clintox
		from deepchem.molnet.load_function.delaney_datasets import load_delaney
		from deepchem.molnet.load_function.hiv_datasets import load_hiv
		from deepchem.molnet.load_function.kaggle_datasets import load_kaggle
		from deepchem.molnet.load_function.muv_datasets import load_muv
		from deepchem.molnet.load_function.nci_datasets import load_nci
		from deepchem.molnet.load_function.pcba_datasets import load_pcba
		from deepchem.molnet.load_function.pdbbind_datasets import load_pdbbind_grid
		from deepchem.molnet.load_function.qm7_datasets import load_qm7_from_mat, load_qm7b_from_mat
		from deepchem.molnet.load_function.qm9_datasets import load_qm9
		from deepchem.molnet.load_function.sampl_datasets import load_sampl
		from deepchem.molnet.load_function.sider_datasets import load_sider
		from deepchem.molnet.load_function.tox21_datasets import load_tox21
		from deepchem.molnet.load_function.toxcast_datasets import load_toxcast

		from deepchem.molnet.run_benchmark import run_benchmark

deepchem/molnet/load_function/init.py

0 → 100644

+0 −0

Empty file added.

deepchem/molnet/chembl_datasets.py→deepchem/molnet/load_function/chembl_datasets.py

+7 −4

Original line number	Diff line number	Diff line
		@@ -8,7 +8,7 @@ from __future__ import unicode_literals
		import os
		import deepchem as dc

		from deepchem.molnet.chembl_tasks import chembl_tasks
		from deepchem.molnet.load_function.chembl_tasks import chembl_tasks

		def load_chembl(shard_size=2000, featurizer="ECFP", set="5thresh", split="random"):

		@@ -48,9 +48,12 @@ def load_chembl(shard_size=2000, featurizer="ECFP", set="5thresh", split="random

		# Featurize ChEMBL dataset
		print("About to featurize ChEMBL dataset.")
		featurizers = {'ECFP': dc.feat.CircularFingerprint(size=1024),
		'GraphConv': dc.feat.ConvMolFeaturizer()}
		featurizer = featurizers[featurizer]
		if featurizer == 'ECFP':
		featurizer = dc.feat.CircularFingerprint(size=1024)
		elif featurizer == 'GraphConv':
		featurizer = dc.feat.ConvMolFeaturizer()
		elif featurizer == 'Raw':
		featurizer = dc.feat.RawFeaturizer()

		loader = dc.data.CSVLoader(
		tasks=chembl_tasks, smiles_field="smiles", featurizer=featurizer)

Admin message