Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

MoleculeNet: a benchmark for molecular machine learning (2017-03-02T00:00:00.000000Z)

MoleculeNet: a benchmark for molecular machine learning

Published in

Chemical Science(2017)

External Links:

Generate Graph DownloadPDF

On This Page

TL;DR
Abstract
Authors
References

Abstract

A large scale benchmark for molecular machine learning consisting of multiple public datasets, metrics, featurizations and learning algorithms.

Authors

Bharath Ramsundar

5 papers

Zhenqin Wu

1 papers

Evan N. Feinberg

2 papers

Joseph Gomes

3 papers

Caleb Geniesse

1 papers

Aneesh S. Pappu

1 papers

K. Leswing

1 papers

V. Pande

4 papers

References124 items

1

Improving the accuracy of Møller-Plesset perturbation theory with neural networks.

2

Is Multitask Deep Learning Practical for Pharma?

3

Neural Message Passing for Quantum Chemistry

4

Low Data Drug Discovery with One-Shot Learning

5

ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost

Research Impact

2218

Citations

124

References

8

Authors

3

6

A Data-Driven Approach to Predicting Successes and Failures of Clinical Trials.

7

Computational Modeling of β-Secretase 1 (BACE-1) Inhibitors Using Ligand Based Approaches

8

Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules

9

Quantum-chemical insights from deep tensor neural networks

10

ToxCast Chemical Landscape: Paving the Road to 21st Century Toxicology.

11

Modeling Industrial ADMET Data with Multitask Networks

12

The Cambridge Structural Database

13

TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems

14

XGBoost: A Scalable Tree Boosting System

15

Molecular graph convolutions: moving beyond fingerprints

16

Deep Residual Learning for Image Recognition

17

Order Matters: Sequence to sequence for sets

18

The SIDER database of drugs and side effects

19

AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery

20

Convolutional Networks on Graphs for Learning Molecular Fingerprints

21

Nucleic Acids Research

22

Electronic spectra from TDDFT and machine learning in chemical space.

23

Deep Neural Nets as a Method for Quantitative Structure-Activity Relationships

24

Massively Multitask Networks for Drug Discovery

25

PDB-wide collection of binding data: current status of the PDBbind database

26

Going deeper with convolutions

27

ImageNet Large Scale Visual Recognition Challenge

28

Structural Protein–Ligand Interaction Fingerprints (SPLIF) for Structure-Based Virtual Screening: Method and Benchmark Study

29

Quantum chemistry structures and properties of 134 kilo molecules

30

FreeSolv: a database of experimental and calculated hydration free energies, with input files

31

Deep learning in neural networks: An overview

32

Blind prediction of solvation free energies from the SAMPL4 challenge

33

Machine learning methods in chemoinformatics

34

SWEETLEAD: an In Silico Database of Approved Drugs, Regulated Chemicals, and Herbal Isolates for Computer-Aided Drug Discovery

35

Deep Architectures and Deep Learning in Chemoinformatics: The Prediction of Aqueous Solubility for Drug-Like Molecules

36

Machine learning of molecular electronic properties in chemical compound space

37

Time-Split Cross-Validation as a Method for Estimating the Goodness of Prospective Prediction

38

ImageNet classification with deep convolutional neural networks

39

Enumeration of 166 Billion Organic Small Molecules in the Chemical Universe Database GDB-17

40

A Bayesian Approach to in Silico Blood-Brain Barrier Penetration Modeling

41

Machine Learning Methods for Property Prediction in Chemoinformatics: Quo Vadis?

42

PubChem's BioAssay Database

43

NNScore 2.0: A Neural-Network Receptor–Ligand Scoring Function

44

Fast and accurate modeling of molecular atomization energies with machine learning.

45

Scikit-learn: Machine Learning in Python

46

Extended-Connectivity Fingerprints

47

ImageNet: A large-scale hierarchical image database

48

970 million druglike small molecules for virtual screening in the chemical universe database GDB-13.

49

Crystallography Open Database – an open-access collection of crystal structures

50

The Journal of the American Chemical Society

51

Influence Relevance Voting: An Accurate And Interpretable Virtual High Throughput Screening Method

52

Maximum Unbiased Validation (MUV) Data Sets for Virtual Screening Based on PubChem Bioactivity Data

53

Recommendations for evaluation of computational methods

54

Generalized neural-network representation of high-dimensional potential-energy surfaces.

55

Anharmonic magnetic deformation of self-assembled molecular nanocapsules.

56

Annals of Statistics

57

The relationship between Precision-Recall and ROC curves

58

Acta Crystallographica Section B: Structural Science

59

The PDBbind database: methodologies and updates.

60

The Elements of Statistical Learning: Data Mining, Inference, and Prediction

61

The PDBbind database: collection of binding affinities for protein-ligand complexes with known three-dimensional structures.

62

ESOL: Estimating Aqueous Solubility Directly from Molecular Structure

63

Announcing the worldwide Protein Data Bank

64

Greedy function approximation: A gradient boosting machine.

65

Special Invited Paper-Additive logistic regression: A statistical view of boosting

66

Artificial neural networks for computer-based molecular design.

67

A Neural Device for Searching Direct Correlations between Structures and Properties of Chemical Compounds

68

Neural Networks in QSAR and Drug Design. Edited by J. Devillers. Volume 2 in the Series: Principles of QSAR and Drug Design. Academic Press: San Diego, 1996, 284 pp. ISBN 0-12-213815-5

69

Neural Networks in QSAR and Drug Design

70

The properties of known drugs. 1. Molecular frameworks.

71

WordNet: A Lexical Database for English

72

Support-Vector Networks

73

Neural networks in chemistry

74

SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules

75

Progress in Biophysics and Molecular Biology

76

Blum and J.-L. Reymond

77

Aggregate Analysis of ClincalTrials.gov (AACT) Database

78

Deep Learning

79

N. S.; Elemento, O. Cell Chemical Biology

80

Deep Learning as an Opportunity in Virtual Screening

81

Nature

82

ChEMBL Deposited Data Set - AZ dataset

83

Bioinformatics

84

Learning and Representation Learning Workshop (NIPS

85

DeepChem: Deep-learning models for Drug Discovery and Quantum Chemistry

86

21) others, et al. arXiv preprint arXiv:1603

87

A. v. New Journal of Physics

88

A. v. Physical Review Letters

89

20) others, et al

90

/github.com/deepchem/deepchem, Accessed: 2017-09-27

91

50) Durrant

92

Journal of Medicinal Chemistry

93

Le Bail, A. Journal of Applied Crystallography

94

PubChem: Integrated Platform of Small Molecules and Biological Activities

95

Annual reports in computational chemistry

96

Journal of Chemical Information and Modeling

97

Journal of Computer-Aided Molecular Design incorporating Perspectives in Drug Discovery and Design

98

Random Forests

99

55) Breiman, L. Machine learning

100

Neural networks in chemistry and drug design

101

Interdisciplinary Reviews: Computational Molecular Science 2014, 4, 468–481

102

Journal of chemical information and computer sciences.

103

ChemNet: A Novel Neural Network Based Method for Graph/Property Mapping

104

13) Miller, G. A. Communications of the ACM

105

Chemical research in toxicology.

106

Manuscript in preparation (58) Wallach

107

RDKit: Open-Source Cheminformatics So  ware

108

Experimental in vitro DMPK and physicochemical data on a set of publicly disclosed compounds

109

Note that performances of our models might be different from values in the benchmark tables due to no limitation imposed on running time(more epochs), different random splitting patterns

110

• Original result: 0.846 ∼ 0.867 for different model structure settings

111

All model validation scripts and trained models can be found in DeepChem

112

Directed Acyclic Graph models

113

International Journal of Computer Vision (IJCV)

114

Graph Convolutional models

115

MAE in kcal/mol: • Original result: 0.93 ± 0.02 with 2 DTNN layers and 100,000 training samples

116

36) AIDS Antiviral Screen Data. https://wiki.nci.nih.gov/display

117

RMSE in logS(log solubility in mol per litre): • Original

118

AIDS Antiviral Screen Data

119

Medical Dictionary for Regulatory Activities

120

Quantum Machine

121

• Reimplementation: 0.68 for valid subset, 0.58 for test subset Weave models

122

28) Quantum Machine. http://quantum-machine.org/datasets

123

Tox21 Challenge

124

We evaluate the model on ESOL dataset, note that we provide performances based on a 80/10/10 random train, valid, test splitting, while the original paper reported performance under cross validation

Views

Field of Study

MedicineComputer SciencePhysicsMathematics

Journal Information

Name

Chemical Science

Page

513 - 530

Volume

9

Venue Information

Name

Chemical Science

Type

journal

URL

http://www.rsc.org/chemicalscience

Alternate Names

Chem Sci
Chem sci
Chemical science