Example updates

# Dataset Description

This example is based on the DUD-E group; it contained 102

datasets that were designed for the evaluation of methods to

predict interactions between proteins and small molecules

Mysinger, Michael M., et al. "Directory of useful decoys, enhanced (DUD-E): better ligands and decoys for better benchmarking." Journal of medicinal chemistry 55.14 (2012): 6582-6594.

This example featurizes binding pockets extracted from the

PDBBind dataset and trains a random forest model to predict the

binding score of a ligand to this binding pocket.

def compute_binding_pocket_features(pocket_featurizer, ligand_featurizer,

                                    pdb_subdir, pdb_code, threshold=.3):

  """Compute features for a given complex"""

  """Compute binding pocket features for a given complex

  Params

  ------

  pocket_featurizer: dc.feat.BindingPocketFeaturizer

    Pocket featurizer to use

  ligand_featurizer: dc.feat.Featurizer

    Ligand Featurizer to use

  pdb_subdir: str

    Directory holding PDB files

  pdb_code: str

    The 4 character PDB code for the protein

  threshold: float, optional

    TODO: Is this needed?

  """

  protein_file = os.path.join(pdb_subdir, "%s_protein.pdb" % pdb_code)

  ligand_file = os.path.join(pdb_subdir, "%s_ligand.sdf" % pdb_code)

  ligand_mol2 = os.path.join(pdb_subdir, "%s_ligand.mol2" % pdb_code)

"""

Script that trains Sklearn RF models on PDBbind Pockets dataset.

"""

from __future__ import print_function

from __future__ import division

from __future__ import unicode_literals

import os

import deepchem as dc

import numpy as np

np.random.seed(123)

split = "random"

subset = "full"

subset = "core"

pdbbind_tasks, pdbbind_datasets, transformers = load_pdbbind_pockets(

    split=split, subset=subset)

train_dataset, valid_dataset, test_dataset = pdbbind_datasets

    mode='regression')

# Fit trained model

model.fit(train_dataset, nb_epoch=50, checkpoint_interval=100)

model.fit(train_dataset, nb_epoch=10, checkpoint_interval=100)

print("Evaluating model")

train_scores = model.evaluate(train_dataset, [metric], transformers)

valid_scores = model.evaluate(valid_dataset, [metric], transformers)