Changes

#!/usr/bin/env python2

# -*- coding: utf-8 -*-

"""

Created on Tue Mar  7 00:07:10 2017

@author: zqwu

This file holds the current best set of hyperparameters for the Molnet benchmark.

"""

import deepchem

# -*- coding: utf-8 -*-

"""

Created on Mon Mar 06 14:25:40 2017

@author: Zhenqin Wu

This file provides utilities to run the MoleculeNet benchmark suite.

"""

import os

import time

import csv

import logging

import numpy as np

import tensorflow as tf

import deepchem

from deepchem.molnet.check_availability import CheckFeaturizer, CheckSplit

from deepchem.molnet.preset_hyper_parameters import hps

logger = logging.getLogger(__name__)

# Loading functions available

loading_functions = {

    'bace_c': deepchem.molnet.load_bace_classification,

    'bace_r': deepchem.molnet.load_bace_regression,

    'bbbp': deepchem.molnet.load_bbbp,

    'chembl': deepchem.molnet.load_chembl,

    'clearance': deepchem.molnet.load_clearance,

    'clintox': deepchem.molnet.load_clintox,

    'delaney': deepchem.molnet.load_delaney,

    'factors': deepchem.molnet.load_factors,

    'hiv': deepchem.molnet.load_hiv,

    'hopv': deepchem.molnet.load_hopv,

    'hppb': deepchem.molnet.load_hppb,

    'kaggle': deepchem.molnet.load_kaggle,

    'kinase': deepchem.molnet.load_kinase,

    'lipo': deepchem.molnet.load_lipo,

    'muv': deepchem.molnet.load_muv,

    'nci': deepchem.molnet.load_nci,

    'pcba': deepchem.molnet.load_pcba,

    'pcba_146': deepchem.molnet.load_pcba_146,

    'pcba_2475': deepchem.molnet.load_pcba_2475,

    'pdbbind': deepchem.molnet.load_pdbbind_grid,

    'ppb': deepchem.molnet.load_ppb,

    'qm7': deepchem.molnet.load_qm7_from_mat,

    'qm7b': deepchem.molnet.load_qm7b_from_mat,

    'qm8': deepchem.molnet.load_qm8,

    'qm9': deepchem.molnet.load_qm9,

    'sampl': deepchem.molnet.load_sampl,

    'sider': deepchem.molnet.load_sider,

    'thermosol': deepchem.molnet.load_thermosol,

    'tox21': deepchem.molnet.load_tox21,

    'toxcast': deepchem.molnet.load_toxcast,

    'uv': deepchem.molnet.load_uv,

}

def run_benchmark(datasets,

                  model,

                  test=False,

                  reload=True,

                  seed=123):

  """

  Run benchmark test on designated datasets with deepchem(or user-defined) model

  """Run MoleculeNet benchmark suite.

  This is a utility function to help run the MoleculeNet benchmark

  suite on a specified model and a specified dataset.

  Run benchmark test on designated datasets with deepchem(or

  user-defined) model.

  Parameters

  ----------

  datasets: list of string

      choice of which datasets to use, should be: bace_c, bace_r, bbbp, chembl,

      clearance, clintox, delaney, hiv, hopv, kaggle, lipo, muv, nci, pcba,

      pdbbind, ppb, qm7, qm7b, qm8, qm9, sampl, sider, tox21, toxcast, uv, factors,

      kinase

      choice of which datasets to use, should be one of: bace_c,

      bace_r, bbbp, chembl, clearance, clintox, delaney, hiv, hopv,

      kaggle, lipo, muv, nci, pcba, pdbbind, ppb, qm7, qm7b, qm8, qm9,

      sampl, sider, tox21, toxcast, uv, factors, kinase

  model: string or user-defined model stucture

      choice of which model to use, deepchem provides implementation of

      logistic regression, random forest, multitask network,

  split: string,  optional (default=None)

      choice of splitter function, None = using the default splitter

  metric: string, optional (default=None)

      choice of evaluation metrics, None = using the default metrics(AUC & R2)

  direction: bool, optional(default=True)

      Optimization direction when doing hyperparameter search

      Maximization(True) or minimization(False)

      Choice of evaluation metrics, None = using the default metrics(AUC & R2)

  use_max: bool, (default True)

    Specifies whether to maximize or minimize `metric`.

    maximization(True) or minimization(False)

  featurizer: string or dc.feat.Featurizer,  optional (default=None)

      choice of featurization, None = using the default corresponding to model

      (string only applicable to deepchem models)

    if not split in [None] + CheckSplit[dataset]:

      continue

    loading_functions = {

        'bace_c': deepchem.molnet.load_bace_classification,

        'bace_r': deepchem.molnet.load_bace_regression,

        'bbbp': deepchem.molnet.load_bbbp,

        'chembl': deepchem.molnet.load_chembl,

        'clearance': deepchem.molnet.load_clearance,

        'clintox': deepchem.molnet.load_clintox,

        'delaney': deepchem.molnet.load_delaney,

        'factors': deepchem.molnet.load_factors,

        'hiv': deepchem.molnet.load_hiv,

        'hopv': deepchem.molnet.load_hopv,

        'hppb': deepchem.molnet.load_hppb,

        'kaggle': deepchem.molnet.load_kaggle,

        'kinase': deepchem.molnet.load_kinase,

        'lipo': deepchem.molnet.load_lipo,

        'muv': deepchem.molnet.load_muv,

        'nci': deepchem.molnet.load_nci,

        'pcba': deepchem.molnet.load_pcba,

        'pcba_146': deepchem.molnet.load_pcba_146,

        'pcba_2475': deepchem.molnet.load_pcba_2475,

        'pdbbind': deepchem.molnet.load_pdbbind_grid,

        'ppb': deepchem.molnet.load_ppb,

        'qm7': deepchem.molnet.load_qm7_from_mat,

        'qm7b': deepchem.molnet.load_qm7b_from_mat,

        'qm8': deepchem.molnet.load_qm8,

        'qm9': deepchem.molnet.load_qm9,

        'sampl': deepchem.molnet.load_sampl,

        'sider': deepchem.molnet.load_sider,

        'thermosol': deepchem.molnet.load_thermosol,

        'tox21': deepchem.molnet.load_tox21,

        'toxcast': deepchem.molnet.load_toxcast,

        'uv': deepchem.molnet.load_uv,

    }

    print('-------------------------------------')

    print('Benchmark on dataset: %s' % dataset)

    print('-------------------------------------')

    logger.info('-------------------------------------')

    logger.info('Benchmark on dataset: %s' % dataset)

    logger.info('-------------------------------------')

    # loading datasets

    if split is not None:

      print('Splitting function: %s' % split)

      logger.info('Splitting function: %s' % split)

      tasks, all_dataset, transformers = loading_functions[dataset](

          featurizer=featurizer, split=split, reload=reload)

    else:

          valid_dataset,

          transformers,

          metric,

          direction=direction,

          n_features=n_features,

          use_max=use_max,

          n_tasks=len(tasks),

          max_iter=max_iter,

          search_range=search_range)

            test_dataset,

            tasks,

            transformers,

            n_features,

            metric,

            model,

            test=test,

    if hyper_param_search:

      with open(os.path.join(out_path, dataset + model + '.pkl'), 'w') as f:

        pickle.dump(hyper_parameters, f)

#

# Note by @XericZephyr. Reason why I spun off this function:

#   1. Some model needs dataset information.

#   2. It offers us possibility to **cache** the dataset

#      if the featurizer runs very slow, e.g., GraphConv.

#   2+. The cache can even happen at Travis CI to accelerate

#       CI testing.

#

def load_dataset(dataset, featurizer, split='random'):

  """

  Load specific dataset for benchmark.

  Parameters

  ----------

  dataset: string

      choice of which datasets to use, should be: tox21, muv, sider,

      toxcast, pcba, delaney, factors, hiv, hopv, kaggle, kinase, nci,

      clintox, hiv, pcba_128, pcba_146, pdbbind, chembl, qm7, qm7b, qm9,

      sampl, uv

  featurizer: string or dc.feat.Featurizer.

      choice of featurization.

  split: string,  optional (default=None)

      choice of splitter function, None = using the default splitter

  """

  dataset_loading_functions = {

      'bace_c': deepchem.molnet.load_bace_classification,

      'bace_r': deepchem.molnet.load_bace_regression,

      'bbbp': deepchem.molnet.load_bbbp,

      'chembl': deepchem.molnet.load_chembl,

      'clearance': deepchem.molnet.load_clearance,

      'clintox': deepchem.molnet.load_clintox,

      'delaney': deepchem.molnet.load_delaney,

      'factors': deepchem.molnet.load_factors,

      'hiv': deepchem.molnet.load_hiv,

      'hopv': deepchem.molnet.load_hopv,

      'hppb': deepchem.molnet.load_hppb,

      'kaggle': deepchem.molnet.load_kaggle,

      'kinase': deepchem.molnet.load_kinase,

      'lipo': deepchem.molnet.load_lipo,

      'muv': deepchem.molnet.load_muv,

      'nci': deepchem.molnet.load_nci,

      'pcba': deepchem.molnet.load_pcba,

      'pcba_128': deepchem.molnet.load_pcba_128,

      'pcba_146': deepchem.molnet.load_pcba_146,

      'pcba_2475': deepchem.molnet.load_pcba_2475,

      'pdbbind': deepchem.molnet.load_pdbbind_grid,

      'ppb': deepchem.molnet.load_ppb,

      'qm7': deepchem.molnet.load_qm7_from_mat,

      'qm7b': deepchem.molnet.load_qm7b_from_mat,

      'qm8': deepchem.molnet.load_qm8,

      'qm9': deepchem.molnet.load_qm9,

      'sampl': deepchem.molnet.load_sampl,

      'sider': deepchem.molnet.load_sider,

      'thermosol': deepchem.molnet.load_thermosol,

      'tox21': deepchem.molnet.load_tox21,

      'toxcast': deepchem.molnet.load_toxcast,

      'uv': deepchem.molnet.load_uv

  }

  print('-------------------------------------')

  print('Loading dataset: %s' % dataset)

  print('-------------------------------------')

  # loading datasets

  if split is not None:

    print('Splitting function: %s' % split)

  tasks, all_dataset, transformers = dataset_loading_functions[dataset](

      featurizer=featurizer, split=split)

  return tasks, all_dataset, transformers

def benchmark_model(model, all_dataset, transformers, metric, test=False):

  """

  Benchmark custom model.

  model: user-defined model stucture

    For user define model, it should include function: fit, evaluate.

  all_dataset: (train, test, val) data tuple.

    Returned by `load_dataset` function.

  transformers

  metric: string

    choice of evaluation metrics.

  """

  time_start_fitting = time.time()

  train_score = .0

  valid_score = .0

  test_score = .0

  train_dataset, valid_dataset, test_dataset = all_dataset

  model.fit(train_dataset)

  train_score = model.evaluate(train_dataset, metric, transformers)

  valid_score = model.evaluate(valid_dataset, metric, transformers)

  if test:

    test_score = model.evaluate(test_dataset, metric, transformers)

  time_finish_fitting = time.time()

  time_for_running = time_finish_fitting - time_start_fitting

  return train_score, valid_score, test_score, time_for_running

#!/usr/bin/env python2

# -*- coding: utf-8 -*-

"""

Created on Mon Mar  6 23:41:26 2017

For this reason, :code:`deepchem` provides an extensive collection of

featurization methods which we will review on this page.

Featurizer-Model Matchups

-------------------------

If you're using DeepChem in practical applications, you probably want

to use a given model on some dataset. Your first question when you try

to do this will probably be which featurizer should I use?

+------------+--------------------------+-----------+

| Model      | Acceptable Featurizers   | Header 3  |

+============+==========================+===========+

| body row 1 | column 2   | column 3  |

+------------+------------+-----------+

| body row 2 | Cells may span columns.|

+------------+------------+-----------+

| body row 3 | Cells may  | - Cells   |

+------------+ span rows. | - contain |

| body row 4 |            | - blocks. |

+------------+------------+-----------+

Featurizer

----------

===========

The DeepChem library is packaged alongside the MoleculeNet suite of datasets. One of the most important parts of machine learning applications is finding a suitable dataset. The MoleculeNet suite has curated a whole range of datasets and loaded them into DeepChem :code:`dc.data.Dataset` objects for convenience.

Running Benchmark

-----------------

At present, there is only support for running benchmark models

.. autofunction:: deepchem.molnet.run_benchmark

Best Known Hyperparameters

--------------------------

MoleculeNet maintains a list of the currently best known

hyperparameters for various models on MoleculeNet benchmarks.

MoleculeNet Datasets

--------------------

MoleculeNet is actively maintained and contains a growing set of

different datasets. Here are the set of currently available

MoleculeNet datasets.

BACE Dataset

------------

^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_bace_classification

.. autofunction:: deepchem.molnet.load_bace_regression

BBBC Datasets

-------------

^^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_bbbc001

.. autofunction:: deepchem.molnet.load_bbbc002

BBBP Datasets

-------------

^^^^^^^^^^^^^

BBBP stands for Blood-Brain-Barrier Penetration

.. autofunction:: deepchem.molnet.load_bbbp

Cell Counting Datasets

----------------------

^^^^^^^^^^^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_cell_counting

Chembl Datasets

---------------

^^^^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_chembl

Chembl25 Datasets

---------------

^^^^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_chembl25

Clearance Datasets

------------------

^^^^^^^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_clearance

Clintox Datasets

----------------

^^^^^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_clintox

Delaney Datasets

----------------

^^^^^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_delaney

Factors Datasets

----------------

^^^^^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_factors

HIV Datasets

------------

^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_hiv

HOPV Datasets

-------------

^^^^^^^^^^^^^

HOPV stands for the Harvard Organic Photovoltaic Dataset.

.. autofunction:: deepchem.molnet.load_hopv

HPPB Datasets

-------------

^^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_hppb

KAGGLE Datasets

---------------

^^^^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_kaggle

Kinase Datasets

---------------

^^^^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_kinase

Lipo Datasets

-------------

^^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_lipo

MUV Datasets

------------

^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_muv

NCI Datasets

------------

^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_nci

PCBA Datasets

-------------

^^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_pcba

PDBBIND Datasets

----------------

^^^^^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_pdbbind

PPB Datasets

------------

^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_ppb

QM7 Datasets

------------

^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_qm7

.. autofunction:: deepchem.molnet.load_qm7b_from_mat

QM8 Datasets

------------

^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_qm8

QM9 Datasets

------------

^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_qm9

SAMPL Datasets

--------------

^^^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_sampl

SIDER Datasets

--------------

^^^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_sider

SWEETLEAD Datasets

------------------

^^^^^^^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_sweetlead

Thermosol Datasets

------------------

^^^^^^^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_thermosol

Tox21 Datasets

--------------

^^^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_tox21

Toxcast Datasets

----------------

^^^^^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_toxcast

USPTO Datasets

--------------

^^^^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_uspto

UV Datasets

-----------

^^^^^^^^^^^

.. autofunction:: deepchem.molnet.load_uv