MoleculeNet: a benchmark for molecular machine learning
Open accessThe DOI matches its Crossref record; 82 of the 82 references it cites were found in a registry or an index.
Abstract
A large scale benchmark for molecular machine learning consisting of multiple public datasets, metrics, featurizations and learning algorithms.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures















Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“the availability of larger data sets (9) and easy-to-use tools (10,11) has particularly transformed this landscape.”
From Machine Learning for the Discovery, Design, and Engineering of Materials. (2022) · cites this paper as [10]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Another platform called MoleculeNet is also used to translate two-dimensional molecular structures into novel features/descriptors, which can then be used in predicting toxicity of the given molecule. The MoleculeNet platform is built on data from various public databases and more than 700,000 compounds have already been tested for toxicity or other properties [20].”
From The rise of artificial intelligence in healthcare applications (2020) · cites this paper as [20]
The cited source says what the claim attributes to it.
In the citing paper
“Initiatives like the DREAM Challenges,284 MoleculeNet,110 and Therapeutic Data Commons285 offer benchmark data sets across a wide spectrum of prediction tasks for pharmacology.”
From Advancing Targeted Protein Degradation via Multiomics Profiling and Artificial Intelligence (2023) · cites this paper as [110]
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“However, ChemBERTa was found to perform better than Chemprop on a number of other MoleculeNet benchmark tasks51”
From OnSIDES database: Extracting adverse drug events from drug labels using natural language processing models (2025) · cites this paper as [51]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Cortes, C., & Vapnik, V. (1995) · Machine Learning · doi:10.1007/bf00994018 · Cited by 59,421
Cortes, C., & Vapnik, V. (1995) · Machine-mediated learning · doi:10.1023/a:1022627411411 · Cited by 48,445
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
Greedy function approximation: A gradient boosting machine
Friedman, J. H. (2001) · The Annals of Statistics · doi:10.1214/aos/1013203451 · Cited by 30,731
The Elements of Statistical Learning
Hastie, T., Tibshirani, R., & Friedman, J. (2009) · Springer Series in Statistics · doi:10.1007/978-0-387-84858-7 · Cited by 25,970
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570
Research works printed but not linked: 11
- Mitchell, 2014, Wiley Interdiscip. Rev.: Comput. Mol. Sci., 4, 468
- T. Unterthiner , A.Mayr , G.Klambauer , M.Steijaert , J.Wenger , H.Ceulemans and S.Hochreiter , Deep Learning and Representation Learning Workshop (NIPS 2014) , 2014
- Delaney, 2004, J. Chem. Inf. Model., 44, 1000
- J. Deng , W.Dong , R.Socher , L.-J.Li , K.Li and L.Fei-Fei , CVPR09 , 2009
- A. Krizhevsky , I.Sutskever and G. E.Hinton , NIPS Proceedings , 2012
- Pedregosa, 2011, J. Mach. Learn. Res., 12, 2825
- Quantum Machine , http://quantum-machine.org/datasets/ , accessed 2017-09-27
- Medical Dictionary for Regulatory Activities , http://www.meddra.org/ , accessed 2017-09-27
- Artemov, 2016, bioRxiv, Biochem., 095653
- Aggregate Analysis of ClincalTrials.gov (AACT) Database , http://www.ctti-clinicaltrials.org/aact-database , accessed 2017-09-27
- Cortes, 1995, Mach. Learn., 20, 273
Cited by
Items 301–400 of 1,019
Coloring Molecules with Explainable Artificial Intelligence for Preclinical Relevance Assessment
Jiménez-Luna, J., Skalic, M., Weskamp, N., & Schneider, G. (2021) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.0c01344 · Cited by 96
The role of computational results databases in accelerating the discovery of catalysts
Bó, C., Maseras, F., & López, N. (2018) · Nature Catalysis · doi:10.1038/s41929-018-0176-4 · Cited by 110
Generative Models for Automatic Chemical Design
Schwalbe‐Koda, D., & Gómez‐Bombarelli, R. (2020) · Lecture notes in physics · doi:10.1007/978-3-030-40245-7_21 · Cited by 124
Deng, D., Chen, X., Zhang, R., Lei, Z., Wang, X., & Zhou, F. (2021) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.0c01489 · Cited by 111
Chen, J., Si, Y., Un, C.-W., & Siu, S. W. I. (2021) · Journal of Cheminformatics · doi:10.1186/s13321-021-00570-8 · Cited by 117
“For unlabeled data, other chemical compound datasets were sought from the MoleculeNet website, including ClinTox, SIDER, ToxCast, and HIV datasets [37].”
BackgroundMethodInfluentialMolecular representations for machine learning applications in chemistry
Raghunathan, S., & Priyakumar, U. D. (2021) · International Journal of Quantum Chemistry · doi:10.1002/qua.26870 · Cited by 121
Bioactivity descriptors for uncharacterized chemical compounds
Bertoni, M., Duran-Frigola, M., Badia-i-Mompel, P., Pauls, E., Orozco-Ruiz, M., Guitart-Pla, O., Alcalde, V., Diaz, V. M., Berenguer-Llergo, A., Brun-Heath, I., et al. (2021) · Nature Communications · doi:10.1038/s41467-021-24150-4 · Cited by 92
Graph Neural Networks for Molecules
Wang, Y., Li, Z., & Farimani, A. B. (2023) · Challenges and advances in computational chemistry and physics · doi:10.1007/978-3-031-37196-7_2 · Cited by 173
“Mechanics QM7 7,165 1 Regression Yes [93, 119]”
BackgroundMethodInfluentialMeyer, J. G., Liu, S., Miller, I. J., Coon, J. J., & Gitter, A. (2019) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.9b00236 · Cited by 96
Multilabel Classification Models for the Prediction of Cross-Coupling Reaction Conditions
Maser, M., Cui, A. Y., Ryou, S., DeLano, T. J., Yue, Y., & Reisman, S. E. (2021) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.0c01234 · Cited by 106
Predicting Infrared Spectra with Message Passing Neural Networks
McGill, C. J., Forsuelo, M. A., Guan, Y., & Green, W. H. (2021) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.1c00055 · Cited by 120
GIT-Mol: A multi-modal large language model for molecular science with graph, image, and text
Liu, P., Ren, Y., Tao, J., & Ren, Z. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108073 · Cited by 89
“Furthermore, molecular structured graphs offer a topological view of molecules in two-dimensional space, where atoms are nodes and bonds are edges.”
BackgroundMethodInfluentialJinich, A., Sanchez-Lengeling, B., Ren, H., Harman, R., & Aspuru-Guzik, A. (2019) · ACS Central Science · doi:10.1021/acscentsci.9b00297 · Cited by 90
Jiang, D., Lei, T., Wang, Z., Shen, C., Cao, D., & Hou, T. (2020) · Journal of Cheminformatics · doi:10.1186/s13321-020-00421-y · Cited by 102
Machine Learning Approaches in Polymer Science: Progress and Fundamental for a New Paradigm
Xie, C., Qiu, H., Liu, L., You, Y., Li, H., Li, Y., Sun, Z., Lin, J., & An, L. (2025) · SmartMat · doi:10.1002/smm2.1320 · Cited by 111
“Poly-Name2Structure (PN2S) made efforts to convert polymer names to structures with nomination entries based on unique names [40], and dataset moleculeNet annotated by experts was developed to support benchmark test for new ML approaches [41].”
Sánchez-Lengeling, B., Wei, J. N., Lee, B. K., Gerkin, R. C., Aspuru‐Guzik, A., & Wiltschko, A. B. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.10685 · Cited by 90
Thafar, M. A., Alshahrani, M., Albaradei, S., Gojobori, T., Essack, M., & Gao, X. (2022) · Scientific Reports · doi:10.1038/s41598-022-08787-9 · Cited by 85
Zhu, W., Zhang, Y., Zhao, D., Xu, J., & Wang, L. (2022) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.2c01099 · Cited by 106
Can Graph Neural Networks Count Substructures?Preprint
Chen, Z., Chen, L., Villar, S., & Bruna, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.04025 · Cited by 216
“We evaluate LRP on the molecular prediction datasets ogbg-molhiv [63], QM9 [54] and ZINC [14].”
MethodDuan, C., Janet, J. P., Liu, F., Nandy, A., & Kulik, H. J. (2019) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.9b00057 · Cited by 87
Applying Deep Learning to Fast Radio Burst Classification
Connor, L., & van Leeuwen, J. (2018) · The Astronomical Journal · doi:10.3847/1538-3881/aae649 · Cited by 115
Advances and challenges in deep generative models for de novo molecule generation
Xue, D., Gong, Y., Yang, Z., Chuai, G., Qu, S., Shen, A., Yu, J., & Liu, Q. (2019) · WIREs Computational Molecular Science · doi:10.1002/wcms.1395 · Cited by 86
The immuneML ecosystem for machine learning analysis of adaptive immune receptor repertoires
Pavlović, M., Scheffer, L., Motwani, K., Kanduri, C., Kompova, R., Vazov, N., Waagan, K., Bernal, F. L. M., da Costa, A. A., Corrie, B., et al. (2021) · Nature Machine Intelligence · doi:10.1038/s42256-021-00413-z · Cited by 101
“Tailored ML frameworks and platforms that account for the idiosyncrasies of the underlying data have been published for applications in genomics 41,42 , proteomics 43,44 , biomedicine 45 and chemistry 46 .”
BackgroundReinforcement Learning on Graphs: A Survey
Nie, M., Chen, D., & Wang, D. (2023) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2022.3222545 · Cited by 113
“95 [114] SubgraphX [40] GRAPH-SST2 70042 10.”
Song, Z., Chen, J., Cheng, J., Chen, G., & Qi, Z. (2023) · Chemical Reviews · doi:10.1021/acs.chemrev.3c00223 · Cited by 97
Explainable Machine Learning for Property Predictions in Compound Optimization
Rodríguez-Pérez, R., & Bajorath, J. (2021) · Journal of Medicinal Chemistry · doi:10.1021/acs.jmedchem.1c01789 · Cited by 95
Mirza, A., Alampara, N., Kunchapu, S., Ríos-García, M., Emoekabu, B., Krishnan, A., Gupta, T., Schilling-Wilhelmi, M., Okereke, M., Aneesh, A., et al. (2025) · Nature Chemistry · doi:10.1038/s41557-025-01815-x · Cited by 369
“Owing to the lack of widely accepted standard benchmarks, the developers of chemical language models 16,44–47 frequently utilize language-interfaced 48 tabular datasets such as the ones reported in MoleculeNet 49,50 , Therapeutic Data Commons 51 , safety databases 52 or MatBench 53 .”
CensNet: Convolution with Edge-Node Switching in Graph Neural Networks
Jiang, X., Ji, P., & Li, S. (2019) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/369 · Cited by 112
“The extensive experiments on citation networks (Cora, Citeseer [Sen et al., 2008], and PubMed [Namata et al., 2012]) and Quantum Chemistry data sets (Tox21 and Lipophilicity [Wu et al., 2018]) show that our method has achieved or matched state-of-the-art performance.”
BackgroundMethodInfluentialEffective drug–target interaction prediction with mutual interaction neural network
Li, F., Zhang, Z., Guan, J., & Zhou, S. (2022) · Bioinformatics · doi:10.1093/bioinformatics/btac377 · Cited by 89
Probing out-of-distribution generalization in machine learning for materials
Li, K., Rubungo, A. N., Lei, X., Persaud, D., Choudhary, K. K., DeCost, B., Dieng, A. B., & Hattrick-Simpers, J. R. (2025) · Communications Materials · doi:10.1038/s43246-024-00731-w · Cited by 154
Naser, M. Z., Kodur, V. K. R., Thai, H., Hawileh, R. A., Abdalla, J. A., & Degtyarev, V. V. (2021) · Journal of Building Engineering · doi:10.1016/j.jobe.2021.102977 · Cited by 98
Graph Rationalization with Environment-based Augmentations
Liu, G., Zhao, T., Xu, J., Luo, T., & Jiang, M. (2022) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3534678.3539347 · Cited by 102
“It attempts to separate structurally different molecules into different subsets, which provides a more realistic estimate of model performance in experiments [36].”
BackgroundExplainable uncertainty quantifications for deep learning-based molecular property prediction
Yang, C.-I., & Li, Y. (2023) · Journal of Cheminformatics · doi:10.1186/s13321-023-00682-3 · Cited by 105
“Computational details The datasets used for benchmarks in this work include QM9 [60], Zinc15 [61], Delaney [62], and Lipophilicity [63] (Table 1), which were accessed from MoleculeNet [64].”
MethodAdvancing material property prediction: using physics-informed machine learning models for viscosity
Chew, A. K., Sender, M., Kaplan, Z., Chandrasekaran, A. R., Elk, J. C., Browning, A. R., Kwak, H. S., Halls, M. D., & Afzal, M. A. F. (2024) · Journal of Cheminformatics · doi:10.1186/s13321-024-00820-5 · Cited by 107
“GNNs are a promising approach to autonomously create structure–property relationships without having to pre-define descriptors based on expert domain knowledge [14].”
BackgroundRelational Pooling for Graph RepresentationsPreprint
Murphy, R. L., Srinivasan, B., Rao, V., & Ribeiro, B. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.02541 · Cited by 273
Zhai, C., Li, T., Shi, H., & Yeo, J. (2020) · Journal of Materials Chemistry B · doi:10.1039/d0tb00896f · Cited by 89
Olympus: a benchmarking framework for noisy optimization and experiment planning
Häse, F., Aldeghi, M., Hickman, R. J., Roch, L. M., Christensen, M., Liles, E., Hein, J. E., & Aspuru‐Guzik, A. (2021) · Machine Learning Science and Technology · doi:10.1088/2632-2153/abedc8 · Cited by 153
Improvement of Prediction Performance With Conjoint Molecular Fingerprint in Deep Learning
Xie, L., Xu, L., Kong, R., Chang, S., & Xu, X. (2020) · Frontiers in Pharmacology · doi:10.3389/fphar.2020.606668 · Cited by 91
Predicting chemical shifts with graph neural networks
Yang, Z., Chakraborty, M., & White, A. D. (2021) · Chemical Science · doi:10.1039/d1sc01895g · Cited by 108
Text2Mol: Cross-Modal Molecule Retrieval with Natural Language Queries
Edwards, C., Zhai, C., & Ji, H. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.47 · Cited by 83
“…begun to rely increasingly on computational techniques for cataloging molecules and predicting chemical reactions, products, and properties, such as yield, toxicity, and water solubility (Wu et al., 2018; Glavatskikh et al., 2019; Coley et al., 2017; Ah-neman et al., 2018; Fooshee et al., 2018).”
BackgroundLarge language models for scientific discovery in molecular property prediction
Zheng, Y., Koh, H. Y., Ju, J., Nguyen, A. T. N., May, L. T., Webb, G. I., & Pan, S. (2025) · Nature Machine Intelligence · doi:10.1038/s42256-025-00994-z · Cited by 253
“By training an interpretable machine learning model using these vectors, we show that this pipeline achieves the current state of the art on molecular property prediction across 58 benchmark tasks from the MoleculeNet dataset curated by the Stanford PANDE group 9 .”
Hierarchical visualization of materials space with graph convolutional neural networks
Xie, T., & Grossman, J. C. (2018) · The Journal of Chemical Physics · doi:10.1063/1.5047803 · Cited by 69
Cross-dependent graph neural networks for molecular property prediction
Ma, H., Bian, Y., Rong, Y., Huang, W., Xu, T., Xie, W., Ye, G., & Huang, J. (2022) · Bioinformatics · doi:10.1093/bioinformatics/btac039 · Cited by 155
He, Y., Zhou, Y., Wen, T., Zhang, S., Huang, F., Zou, X., Ma, X., & Zhu, Y. (2022) · Applied Geochemistry · doi:10.1016/j.apgeochem.2022.105273 · Cited by 95
Xie, T., France‐Lanord, A., Wang, Y., Lopez, J., Stolberg, M. A., Hill, M. R., Leverick, G., Gómez‐Bombarelli, R., Johnson, J. A., Shao‐Horn, Y., et al. (2022) · Nature Communications · doi:10.1038/s41467-022-30994-1 · Cited by 101
SELFormer: molecular representation learning via SELFIES language models
Yüksel, A., Ulusoy, E., Ünlü, A., & Doğan, T. (2023) · Machine Learning: Science and Technology · doi:10.1088/2632-2153/acdb30 · Cited by 81
“We fine-tuned our models (Figure 1B) on several molecular property prediction tasks using the MoleculeNet (Wu et al., 2018) benchmarking datasets of varying sizes including the blood–brain barrier penetration (BBBP), the Side Effect Resource (SIDER), The “Toxicology in the 21st Century” (Tox21), the ability to inhibit…”
BackgroundMethodInfluentialFraGAT: a fragment-oriented multi-scale graph attention model for molecular property prediction
Zhang, Z., Guan, J., & Zhou, S. (2021) · Bioinformatics · doi:10.1093/bioinformatics/btab195 · Cited by 92
Delfos: deep learning model for prediction of solvation free energies in generic organic solvents
Lim, H., & Jung, Y. (2019) · Chemical Science · doi:10.1039/c9sc02452b · Cited by 96
Uni-Mol: A Universal 3D Molecular Representation Learning Framework
Zhou, G., Gao, Z., Ding, Q., Zheng, H., Xu, H., Wei, Z., Zhang, L., & Ke, G. (2022) · doi:10.26434/chemrxiv-2022-jjm0j · Cited by 81
Ishida, S., Terayama, K., Kojima, R., Takasu, K., & Okuno, Y. (2019) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.9b00538 · Cited by 84
Attention-Diffusion-Bilinear Neural Network for Brain Network Analysis
Huang, J., Zhou, L., Wang, L., & Zhang, D. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.2973650 · Cited by 85
“For some general graph-structured data with clear node interaction information (e.g., Molecular networks [53], Protein-Protein Interaction networks [54], and chemical compound data [55]), the Diffusion-Bilinear module proposed by our method could be very useful in learning a discriminant…”
MethodIn Silico Chemical Experiments in the Age of AI: From Quantum Chemistry to Machine Learning and Back
Aldossary, A., Campos-Gonzalez-Angulo, J. A., Pablo‐García, S., Leong, S. X., Rajaonson, E. M., Thiede, L., Tom, G., Wang, A., Avagliano, D., & Aspuru‐Guzik, A. (2024) · Advanced Materials · doi:10.1002/adma.202402369 · Cited by 106
Ash, J. R., Wognum, C., Rodríguez-Pérez, R., Aldeghi, M., Cheng, A. C., Clevert, D.-A., Engkvist, O., Fang, C., Price, D. J., Hughes‐Oliver, J. M., et al. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c01609 · Cited by 130
Chemical diversity in molecular orbital energy predictions with kernel ridge regression
Stuke, A., Todorović, M., Rupp, M., Künkel, C., Ghosh, K., Himanen, L., & Rinke, P. (2019) · The Journal of Chemical Physics · doi:10.1063/1.5086105 · Cited by 95
Nakata, M., Shimazaki, T., Hashimoto, M., & Maeda, T. (2020) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.0c00740 · Cited by 87
DeepMalaria: Artificial Intelligence Driven Discovery of Potent Antiplasmodials
Keshavarzi Arshadi, A., Salem, M., Collins, J., Yuan, J. S., & Chakrabarti, D. (2020) · Frontiers in Pharmacology · doi:10.3389/fphar.2019.01526 · Cited by 77
“With the availability of large datasets, such as whole genome sequencing, transcript profiling or HTS, artificial intelligence is expected to have major impacts on various aspects of biomedical research (Jiang et al., 2017; Wainberg et al., 2018; Reddy et al., 2019; Zhavoronkov et al., 2019).”
BackgroundMaterials discovery through machine learning formation energy
Peterson, G. G. C., & Brgoch, J. (2021) · Journal of Physics Energy · doi:10.1088/2515-7655/abe425 · Cited by 109
Rankine, C. D., & Penfold, T. J. (2021) · The Journal of Physical Chemistry A · doi:10.1021/acs.jpca.0c11267 · Cited by 87
When Do Quantum Mechanical Descriptors Help Graph Neural Networks to Predict Chemical Properties?
Li, S., Wu, H., Menon, A., Spiekermann, K., Li, Y., & Green, W. H. (2024) · Journal of the American Chemical Society · doi:10.1021/jacs.4c04670 · Cited by 93
Deep learning of pharmacogenomics resources: moving towards precision oncology
Chiu, Y.-C., Chen, H.-I. H., Gorthi, A., Mostavi, M., Zheng, S., Huang, Y., & Chen, Y. (2020) · Briefings in Bioinformatics · doi:10.1093/bib/bbz144 · Cited by 78
Machine learning assisted optimization of electrochemical properties for Ni-rich cathode materials
Min, K., Choi, B., Park, K., & Cho, E. (2018) · Scientific Reports · doi:10.1038/s41598-018-34201-4 · Cited by 82
Fast Haar Transforms for Graph Neural Networks
Li, M., Ma, Z., Wang, Y. G., & Zhuang, X. (2020) · Neural Networks · doi:10.1016/j.neunet.2020.04.028 · Cited by 88
Machine Learning for Absorption Cross Sections
Xue, B.-X., Barbatti, M., & Dral, P. O. (2020) · The Journal of Physical Chemistry A · doi:10.1021/acs.jpca.0c05310 · Cited by 76
Big data and artificial intelligence (AI) methodologies for computer-aided drug design (CADD)
Lee, J. W., Maria‐Solano, M. A., Vu, T. N. L., Yoon, S.-H., & Choi, S. (2022) · Biochemical Society Transactions · doi:10.1042/bst20211240 · Cited by 82
KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction
Li, H., Zhao, D. Y., & Zeng, J. (2022) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3534678.3539426 · Cited by 138
“Following the previous research [44, 55], for each dataset, we performed three repeated tests with three randomly seeded splittings and then reported the means and standard deviations.”
BackgroundMethodInfluentialApplication of message passing neural networks for molecular property prediction
Tang, M., Li, B., & Chen, H. (2023) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2023.102616 · Cited by 102
Zakharov, A. V., Zhao, T., Nguyen, D.-T., Peryea, T., Sheils, T., Yasgar, A., Huang, R., Southall, N., & Simeonov, A. (2019) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.9b00526 · Cited by 76
Janet, J. P., & Kulik, H. J. (2020) · ACS in focus · doi:10.1021/acs.infocus.7e4001 · Cited by 84
Predicting Energetics Materials’ Crystalline Density from Chemical Structure by Machine Learning
Nguyen, P., Loveland, D., Kim, J. T., Karande, P., Hiszpanski, A. M., & Han, T. Y.-J. (2021) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.0c01318 · Cited by 80
PyRMD: A New Fully Automated AI-Powered Ligand-Based Virtual Screening Tool
Amendola, G., & Cosconati, S. (2021) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.1c00653 · Cited by 85
AI in drug development: a multidisciplinary perspective
Gallego, V., Naveiro, R., Roca, C., Ríos Insua, D., & Campillo, N. E. (2021) · Molecular Diversity · doi:10.1007/s11030-021-10266-8 · Cited by 73
“Regarding molecular representations, ChemBERTa has been recently introduced leading to encouraging results on MoleculeNet tasks [50, 51].”
ResultNa, G. S., Jang, S., & Chang, H. (2021) · npj Computational Materials · doi:10.1038/s41524-021-00564-y · Cited by 83
Wang, D. D., Zhu, M., & Yan, H. (2021) · Briefings in Bioinformatics · doi:10.1093/bib/bbaa107 · Cited by 72
Toward an Integrated Machine Learning Model of a Proteomics Experiment
Neely, B. A., Dorfer, V., Martens, L., Bludau, I., Bouwmeester, R., Degroeve, S., Deutsch, E. W., Gessulat, S., Käll, L., Palczynski, P., et al. (2023) · Journal of Proteome Research · doi:10.1021/acs.jproteome.2c00711 · Cited by 83
Tandem mass spectrum prediction for small molecules using graph transformers
Young, A., Röst, H. L., & Wang, B. (2024) · Nature Machine Intelligence · doi:10.1038/s42256-024-00816-8 · Cited by 143
“Scaffold splitting introduces a distributional shift between training and test data and is commonly used to evaluate deep learning models in small molecule applications 86 .”
Qiao, J., Jin, J., Wang, D., Teng, S., Zhang, J., Yang, X., Liu, Y., Wang, Y., Cui, L., Zou, Q., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-59634-0 · Cited by 99
“…analyze molecular properties. a Using one atom as a benchmark, we select 30% and 60% of its 2D distance to calculate the receptive fi eld. b Results for eight of the datasets (BACE, BBBP, ClinTox, Tox21, CHEMBL1862_Ki, CHEMBL204_Ki, CHEMBL231_Ki and CHEMBL233_Ki) 36,42 using a single threshold.”
InfluentialRobinson, M. C., Glen, R. C., & Lee, A. A. (2020) · Journal of Computer-Aided Molecular Design · doi:10.1007/s10822-019-00274-0 · Cited by 74
Ryu, S., Lim, J., Hong, S. H., & Kim, W. Y. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.10988 · Cited by 73
“In chemistry, both the CNN and RNN have been used by representing molecules with SMILES 18-23 and molecular fingerprints 11-13 , because those models are readily available.”
MethodHeo, S., Safder, U., & Yoo, C. (2019) · Environmental Pollution · doi:10.1016/j.envpol.2019.06.081 · Cited by 77
GGL-Tox: Geometric Graph Learning for Toxicity Prediction
Jiang, J., Wang, R., & Wei, G. (2021) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.0c01294 · Cited by 83
Ulrich, N., Goss, K., & Ebert, A. (2021) · Communications Chemistry · doi:10.1038/s42004-021-00528-9 · Cited by 82
A fingerprints based molecular property prediction method using the BERT model
Wen, N., Liu, G., Zhang, J., Zhang, R., Fu, Y., & Han, X. (2022) · Journal of Cheminformatics · doi:10.1186/s13321-022-00650-3 · Cited by 95
“And our proposed models perform generally better than other molecular fingerprint-based methods, those are the FP2VEC, FCNN nad ECFP, in regression tasks.”
BackgroundMethodInfluentialChakraborty, C., Bhattacharya, M., Lee, S., Wen, Z., & Lo, Y.-H. (2024) · Molecular Therapy — Nucleic Acids · doi:10.1016/j.omtn.2024.102295 · Cited by 99
“MoleculeNet ML https://moleculenet.org/ Used for accurate predictions about molecular properties of drug – and its comparison Wu et al. 79 13.”
MethodArtificial intelligence for science in quantum, atomistic, and continuum systems
Zhang, X., Wang, L., Helwig, J., Luo, Y., Fu, C., Xie, Y., Liu, M., Lin, Y., Zhao, X., Yan, K., et al. (2025) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000115 · Cited by 255
How Much Chemistry Does a Deep Neural Network Need to Know to Make Accurate Predictions?
Goh, G. B., Siegel, C., Vishnu, A., Hodas, N., & Baker, N. (2018) · 2018 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv.2018.00151 · Cited by 71
Sakai, M., Nagayasu, K., Shibui, N., Andoh, C., Takayama, K., Shirakawa, H., & Kaneko, S. (2021) · Scientific Reports · doi:10.1038/s41598-020-80113-7 · Cited by 84
De Novo Peptide and Protein Design Using Generative Adversarial Networks: An Update
Lin, E., Lin, C., & Lane, H. (2022) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.1c01361 · Cited by 83
Compound–protein interaction prediction by deep learning: Databases, descriptors and models
Du, B.-X., Qin, Y., Jiang, Y.-F., Xu, Y., Yiu, S.-M., Yu, H., & Shi, J.-Y. (2022) · Drug Discovery Today · doi:10.1016/j.drudis.2022.02.023 · Cited by 73
Wang, Y., Magar, R., Chen, L., & Farimani, A. B. (2022) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.2c00495 · Cited by 93
“28 Moreover, it is challenging for DL models trained on such limited data to generalize among the gigantic chemical space, 29 which significantly restricts real-world applications like drug discovery and material design.”
BackgroundMethodPharmacophoric-constrained heterogeneous graph transformer model for molecular property prediction
Jiang, Y., Jin, S., Jin, X., Xiao, X., Wu, W., Liu, X., Zhang, Q., Zeng, X., Yang, G., & Niu, Z. (2023) · Communications Chemistry · doi:10.1038/s42004-023-00857-x · Cited by 97
“We also presented the results of PharmHGT for molecular property prediction on ten datasets, these experiments datasets are from Wu et al. 22 , including four classi fi cation and three regression tasks.”
MethodWang, X., Cheng, Y., Yang, Y., Yu, Y., Li, F., & Peng, S. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00640-6 · Cited by 84
“To demonstrate superiority of MSSL2drug, PairDistance-EdgeMask-SimCon are compared with six state-of-the-art methods, including deepDTnet [37], MoleculeNet [38], KGE_NFM [5], DTINet [6], DDIMDL [39], and DeepR2cov [31].”
Integrated Molecular Modeling and Machine Learning for Drug Design
Xia, S., Chen, E., & Zhang, Y. (2023) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.3c00814 · Cited by 81
Machine Learning‐Enabled Drug‐Induced Toxicity Prediction
Bai, C., Wu, L., Li, R., Cao, Y., He, S., & Bo, X. (2025) · Advanced Science · doi:10.1002/advs.202413405 · Cited by 148
CogMol: Target-Specific and Selective Drug Design for COVID-19 Using Deep Generative Models
Chenthamarakshan, V., Das, P., Hoffman, S. C., Strobelt, H., Padhi, I., Lim, K. W., Hoover, B., Manica, M., Born, J., Laino, T., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.01215 · Cited by 73
“The MT-DNN was used to predict the toxicity on 12 in vitro endpoints as in the Tox21 challenge.1 We also predicted whether the generated molecules would fail the clinical trials, using the ClinTox data [Wu et al., 2018].”
MethodDeepChemStable: Chemical Stability Prediction with an Attention-Based Graph Convolution Network
Li, X., Yan, X., Gu, Q., Zhou, H., Wu, D., & Xu, J. (2019) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.8b00672 · Cited by 72
Siramshetty, V. B., Nguyễn, Ð.-T., Martinez, N. J., Southall, N. T., Simeonov, A. M., & Zakharov, A. V. (2020) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.0c00884 · Cited by 80
Practical Model Selection for Prospective Virtual Screening
Liu, S., Alnammi, M., Ericksen, S. S., Voter, A. F., Ananiev, G. E., Keck, J. L., Hoffmann, F. M., Wildman, S. A., & Gitter, A. (2018) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.8b00363 · Cited by 82
“38 Consensus docking 50 failed to recover any actives in the PriA-SSB prospective data set, even though some of the individual docking programs did.”
InfluentialStructure‐Based Drug Discovery with Deep Learning**
Özçelik, R., van Tilborg, D., Jiménez-Luna, J., & Grisoni, F. (2023) · ChemBioChem · doi:10.1002/cbic.202200776 · Cited by 86
“For these applications, numerous systematic studies [20,21] and experimental proofs-of-concept [16,17,22] have been published.”
BackgroundFrom intuition to AI: evolution of small molecule representations in drug discovery
McGibbon, M., Shave, S., Dong, J. N., Gao, Y., Houston, D. R., Xie, J., Yang, Y., Schwaller, P., & Blay, V. (2023) · Briefings in Bioinformatics · doi:10.1093/bib/bbad422 · Cited by 87
Application of Transformers in Cheminformatics
Luong, K.-D., & Singh, A. K. (2024) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.3c02070 · Cited by 85
Metadata
- Authors
- Wu, Z., Ramsundar, B., Feinberg, E. N., Gomes, J., Geniesse, C., Pappu, A. S., Leswing, K., & Pande, V.
- Affiliations
- Stanford University (US)
- Stanford Medicine (US)
- Schrodinger (United States) (US)
- Corresponding author
- Pande, Vijay
- Venue
- Chemical Science
- Publisher
- Royal Society of Chemistry (RSC)
- Published
- 2018
- Volume
- 9
- Issue
- 2
- Pages
- 513-530
- ISSN
- 2041-6520 (ISSN-L)
- 2041-6539
- PMC
- PMC5868307
- OpenAlex
- W2594183968
- Cited by
- 3,107
- References
- 62
- Citations by year
- 2026: 553 · 2025: 561 · 2024: 485 · 2023: 387 · 2022: 328 · 2021: 309 · 2020: 251 · 2019: 144 · 2018: 73
- FWCI
- 98.85
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- Locations
- Chemical Science (publishedVersion, cc-by-nc)
- Europe PMC (PubMed Central) (publishedVersion, cc-by-nc)
- PubMed Central (publishedVersion, cc-by-nc)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- The HKU Scholars Hub (University of Hong Kong) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Hertz Foundation
- NIH (R01 GM062868, U19 AI109662)
- Topics
- Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
- Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
- Physical Sciences › Physics and Astronomy › Atomic and Molecular Physics, and Optics › Advanced Chemical Physics Studies
- Keywords
- molecular machine learning, benchmark, MoleculeNet, molecular property prediction, DeepChem, open source software, data scarcity, imbalanced classification, quantum mechanical properties, biophysical properties
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.