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 501–600 of 1,019
Ignácz, G., Alqadhi, N., & Székely, G. (2023) · Advanced Membranes · doi:10.1016/j.advmem.2023.100061 · Cited by 70
“This con-fi dence interval is considered good in molecular prediction datasets, as they are prone to relatively high noise [50].”
Convolutional Neural Networks for the Design and Analysis of Non-Fullerene Acceptors
Peng, S.-P., & Zhao, Y. (2019) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.9b00732 · Cited by 59
Bennett, W. F. D., He, S., Bilodeau, C. L., Jones, D., Sun, D., Kim, H., Allen, J. E., Lightstone, F. C., & Ingólfsson, H. I. (2020) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.0c00318 · Cited by 56
A Perspective on Deep Learning for Molecular Modeling and Simulations
Zhang, J., Lei, Y.-K., Zhang, Z., Chang, J., Li, M., Han, X., Yang, L., Yang, Y., & Gao, Y. Q. (2020) · The Journal of Physical Chemistry A · doi:10.1021/acs.jpca.0c04473 · Cited by 61
Liu, C., Sun, Y., Davis, R. L., Cardona, S. T., & Hu, P. (2023) · Journal of Cheminformatics · doi:10.1186/s13321-023-00698-9 · Cited by 61
“In addition, we conducted prediction of molecular properties using 4 classification and 4 regression molecular benchmarks from MoleculeNet [26] (Table 2).”
BackgroundMethodInfluentialPei, Q., Zhang, W., Zhu, J., Wu, K., Gao, K., Wu, L., Xia, Y., & Yan, R. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.70 · Cited by 187
Lu, X., Xie, L., Xu, L., Mao, R., Xu, X., & Chang, S. (2024) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2024.04.030 · Cited by 64
“(g) The refined set of PDBbind v2020 dataset after data cleaning and molecular representation conversion has a total of 5089 binding constants for biological molecular complexes [61].”
BackgroundMethodpdCSM-cancer: Using Graph-Based Signatures to Identify Small Molecules with Anticancer Properties
Al‐Jarf, R., de Sá, A. G. C., Pires, D. E. V., & Ascher, D. B. (2021) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.1c00168 · Cited by 65
Using chemical and biological data to predict drug toxicity
Liu, A., Seal, S., Yang, H., & Bender, A. (2023) · SLAS Discovery · doi:10.1016/j.slasd.2022.12.003 · Cited by 54
Improving the quality of chemical language model outcomes with atom-in-SMILES tokenization
Ucak, U. V., Ashyrmamatov, I., & Lee, J. (2023) · Journal of Cheminformatics · doi:10.1186/s13321-023-00725-9 · Cited by 76
“To evaluate the performance of these schemes, we used the MoleculeNet benchmark datasets [58], which includes three regression tasks: ESOL for estimating solubility, FreeSolv for hydration free energies, and Lipophilicity for octanol/water distribution coefficient, logD at pH 7.”
MethodCan large language models understand molecules?
Sadeghi, S., Bui, A., Forooghi, A., Lu, J., & Ngom, A. (2024) · BMC Bioinformatics · doi:10.1186/s12859-024-05847-x · Cited by 81
“It should be noted that we conduct data removal because of some improper drug SMILES strings in Drugbank, which can not be converted into molecular graphs, as determined by the RDKit library.”
MethodCross-disciplinary perspectives on the potential for artificial intelligence across chemistry
Mroz, A. M., Basford, A. R., Hastedt, F., Jayasekera, I. S., Mosquera‐Lois, I., Sedgwick, R., Ballester, P. J., Bocarsly, J. D., del Rio‐Chanona, E. A., Evans, M. L., et al. (2025) · Chemical Society Reviews · doi:10.1039/d5cs00146c · Cited by 71
Artificial intelligence (AI) in drug design and discovery: A comprehensive review
Bhat, A. R., & Ahmed, S. (2025) · In Silico Research in Biomedicine · doi:10.1016/j.insi.2025.100049 · Cited by 76
Prediction of Intramolecular Reorganization Energy Using Machine Learning
Atahan-Evrenk, Ş., & Atalay, F. B. (2019) · The Journal of Physical Chemistry A · doi:10.1021/acs.jpca.9b02733 · Cited by 59
An Ecosystem for Digital Reticular Chemistry
Jablonka, K. M., Rosen, A., Krishnapriyan, A. S., & Smit, B. (2023) · ACS Central Science · doi:10.1021/acscentsci.2c01177 · Cited by 65
Baptista, D., Correia, J. V. M., Pereira, B., & Rocha, M. (2022) · Berichte aus der medizinischen Informatik und Bioinformatik/Journal of integrative bioinformatics · doi:10.1515/jib-2022-0006 · Cited by 67
Li, L., Yu, N., Wang, X., Shi, W. F., Liu, H., Zhang, X., Yang, L., Pan, B., Yu, H., & Wei, S. (2022) · Environmental Science & Technology · doi:10.1021/acs.est.2c03345 · Cited by 59
Few-Shot Learning for Low-Data Drug Discovery
Vella, D., & Ebejer, J.-P. (2022) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.2c00779 · Cited by 67
A survey of graph neural networks and their industrial applications
Lu, H., Wang, L., Ma, X., Cheng, J., & Zhou, M. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128761 · Cited by 73
A machine learning workflow for molecular analysis: application to melting points
Sivaraman, G., Jackson, N. E., Sánchez-Lengeling, B., Vázquez‐Mayagoitia, Á., Aspuru‐Guzik, A., Vishwanath, V., & Pablo, J. (2020) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ab8aa3 · Cited by 67
Learning Atomic Interactions through Solvation Free Energy Prediction Using Graph Neural Networks
Pathak, Y., Mehta, S., & Priyakumar, U. D. (2021) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.0c01413 · Cited by 60
Mol2Context-vec: learning molecular representation from context awareness for drug discovery
Lv, Q., Chen, G., Zhao, L., Zhong, W., & Chen, C. Y. (2021) · Briefings in Bioinformatics · doi:10.1093/bib/bbab317 · Cited by 54
Stecuła, A., Hussain, M. S., & Viola, R. E. (2020) · Journal of Medicinal Chemistry · doi:10.1021/acs.jmedchem.0c00473 · Cited by 55
Lim, K. S., Reidenbach, A. G., Hua, B. K., Mason, J. W., Gerry, C. J., Clemons, P. A., & Coley, C. W. (2022) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.2c00041 · Cited by 55
Yes SIR! On the structure–inactivity relationships in drug discovery
López‐López, E., Gortari, E. F., & Medina‐Franco, J. L. (2022) · Drug Discovery Today · doi:10.1016/j.drudis.2022.05.005 · Cited by 60
Pinheiro, G. A., Silva, J. L. F. D., & Quiles, M. G. (2022) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.2c00521 · Cited by 66
Liu, Y., Zhang, R., Li, T., Jiang, J., Ma, J., & Wang, P. (2022) · Journal of Molecular Graphics and Modelling · doi:10.1016/j.jmgm.2022.108344 · Cited by 62
Physical pooling functions in graph neural networks for molecular property prediction
Schweidtmann, A. M., Rittig, J. G., Weber, J. M., Grohe, M., Dahmen, M., Leonhard, K. O., & Mitsos, A. (2023) · Computers & Chemical Engineering · doi:10.1016/j.compchemeng.2023.108202 · Cited by 61
Shilpa, S., Kashyap, G., & Sunoj, R. B. (2023) · The Journal of Physical Chemistry A · doi:10.1021/acs.jpca.3c04779 · Cited by 61
Towards understanding structure–property relations in materials with interpretable deep learning
Vu, T.-S., Ha, M.-Q., Nguyen, D., Nguyen, V.-C., Abe, Y., Tran, T., Huan, T. D., Kino, H., Miyake, T., Tsuda, K., et al. (2023) · npj Computational Materials · doi:10.1038/s41524-023-01163-9 · Cited by 74
FP2VEC: a new molecular featurizer for learning molecular properties
Jeon, W., & Kim, D. (2019) · Bioinformatics · doi:10.1093/bioinformatics/btz307 · Cited by 58
Ward, L. T., Blaiszik, B. J., Foster, I. T., Assary, R. S., Narayanan, B., & Curtiss, L. A. (2019) · MRS Communications · doi:10.1557/mrc.2019.107 · Cited by 57
Coverage-Guided Testing for Recurrent Neural Networks
Huang, W., Sun, Y., Zhao, X., Sharp, J., Ruan, W., Meng, J., & Huang, X. (2021) · IEEE Transactions on Reliability · doi:10.1109/tr.2021.3080664 · Cited by 55
“6278 in test dataset, which are better than the traditional and convolutional methods used in [50].”
MethodGhanakota, P., Bos, P. H., Konze, K. D., Staker, J., Marques, G. F. F., Marshall, K., Leswing, K., Abel, R., & Bhat, S. (2020) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.0c00120 · Cited by 56
Self-citationAlchemy: A Quantum Chemistry Dataset for Benchmarking AI ModelsPreprint
Chen, G., Chen, P., Hsieh, C., Lee, C., Liao, B., Liao, R., Liu, W., Qiu, J., Sun, Q., Tang, J., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.09427 · Cited by 129
“Recognizing the importance of high-quality data for ML model developments, the chemistry community has recently compiled a comprehensive collection of benchmarking datasets, the MoleculeNet (Wu et al., 2018), including a variety of supervised learning tasks.”
BackgroundInfluentialMemory-Based Graph NetworksPreprint
Khasahmadi, A. H., Hassani, K., Moradi, P., Lee, L., & Morris, Q. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.09518 · Cited by 98
“…contain initial edge features (refer to Appendix A.2 for further details), we train the MemGNN model and compare the results to the baseline mod-2 (Wu et al., 2018) including graph based methods such as GCN, MPNN, directed acyclic graph (DAG) model, and Weave as well as other conventional methods…”
BackgroundMethodResultInfluentialZhang, C., Tao, M., Chen, W., & Fan, J. (2023) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.13098 · Cited by 58
“…in modeling unstructured data (Ektefaie et al., 2023), and deep learning on graphs using graph neural networks (GNNs) has contributed to significant advancements in various fields such as biology (Greener et al., 2022), chemistry (Wu et al., 2018), and physics (Sanchez-Gonzalez et al., 2018).”
BackgroundSimulations meet machine learning in structural biology
Pérez, A., Martínez-Rosell, G., & De Fabritiis, G. (2018) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2018.02.004 · Cited by 51
“Also, the DeepChem software [54] and the MoleculeNet challenge [55] provide multiple featurization algorithms and access to relevant QSAR prediction datasets.”
MethodHusch, T., Sun, J., Cheng, L., Lee, S. J. R., & Miller, T. F. (2021) · The Journal of Chemical Physics · doi:10.1063/5.0032362 · Cited by 53
Transfer learning with graph neural networks for optoelectronic properties of conjugated oligomers
Lee, C., Lu, C., Yu, Y., Sun, Q., Hsieh, C., Zhang, S., Liu, Q., & Shi, L. (2021) · The Journal of Chemical Physics · doi:10.1063/5.0037863 · Cited by 53
Advancing Targeted Protein Degradation via Multiomics Profiling and Artificial Intelligence
Duran-Frigola, M., Cigler, M., & Winter, G. E. (2023) · Journal of the American Chemical Society · doi:10.1021/jacs.2c11098 · Cited by 50
Artificial Intelligence Effecting a Paradigm Shift in Drug Development
Rashid, M. B. M. A. (2020) · SLAS TECHNOLOGY · doi:10.1177/2472630320956931 · Cited by 62
“87,88 Built on multiple public databases, it covers approximately 700,000 compounds that have been tested across different properties.”
BackgroundValidating ADME QSAR Models Using Marketed Drugs
Siramshetty, V. B., Williams, J., Nguyễn, Ð.-T., Neyra, J., Southall, N. T., Mathé, E. A., Xu, X., & Shah, P. (2021) · SLAS DISCOVERY · doi:10.1177/24725552211017520 · Cited by 67
Artificial Intelligence for Autonomous Molecular Design: A Perspective
Joshi, R. P., & Kumar, N. (2021) · Molecules · doi:10.3390/molecules26226761 · Cited by 64
MoleGuLAR: Molecule Generation Using Reinforcement Learning with Alternating Rewards
Goel, M., Raghunathan, S., Laghuvarapu, S., & Priyakumar, U. D. (2021) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.1c01341 · Cited by 64
Chemical representation learning for toxicity prediction
Born, J., Markert, G., Janakarajan, N., Kimber, T. B., Volkamer, A., Martínez, M. R., & Manica, M. (2023) · Digital Discovery · doi:10.1039/d2dd00099g · Cited by 63
Seal, S., Spjuth, O., Hosseini-Gerami, L., García-Ortegón, M., Singh, S., Bender, A., & Carpenter, A. E. (2024) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.3c01834 · Cited by 56
Scaffold Splits Overestimate Virtual Screening Performance
Guo, Q., Hernández-Hernández, S., & Ballester, P. J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72359-9_5 · Cited by 68
Role of artificial intelligence in cancer drug discovery and development
Sarvepalli, S., & Vadarevu, S. (2025) · Cancer Letters · doi:10.1016/j.canlet.2025.217821 · Cited by 68
Fooladi, H., Vu, T. N. L., Mathea, M., & Kirchmair, J. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c00475 · Cited by 75
Eguchi, R., Ono, N., Morita, A. H., Katsuragi, T., Nakamura, S., Huang, M., Altaf‐Ul‐Amin, M., & Kanaya, S. (2019) · BMC Bioinformatics · doi:10.1186/s12859-019-2963-6 · Cited by 55
Playe, B., & Stoven, V. (2020) · Journal of Cheminformatics · doi:10.1186/s13321-020-0413-0 · Cited by 53
Scheen, J., Wu, W., Mey, A. S. J. S., Tosco, P., Mackey, M. D., & Michel, J. (2020) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.0c00600 · Cited by 47
Rahman, A. S. M. Z., Liu, C., Sturm, H., Hogan, A. M., Davis, R. L., Hu, P., & Cardona, S. T. (2022) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1010613 · Cited by 62
Duong‐Trung, N., Born, S., Kim, J. W., Schermeyer, M., Paulick, K., Borisyak, M., Bournazou, M. N. C., Werner, T., Scholz, R., Schmidt-Thieme, L., et al. (2022) · Biochemical Engineering Journal · doi:10.1016/j.bej.2022.108764 · Cited by 67
Ji, Y., Zhang, L., Wu, J., Wu, B., Li, L., Huang, L.-K., Xu, T., Rong, Y., Ren, J., Ding, X., et al. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i7.25970 · Cited by 169
“MoleculeNet (Wu et al. 2018) provides a collection of molecular property prediction tasks on which various featurization and models are benchmarked.”
BackgroundHarnessing the power of artificial intelligence to advance cell therapy
Capponi, S., & Daniels, K. G. (2023) · Immunological Reviews · doi:10.1111/imr.13236 · Cited by 54
Prado-Romero, M. A., Prenkaj, B., Stilo, G., & Giannotti, F. (2023) · ACM Computing Surveys · doi:10.1145/3618105 · Cited by 92
“jsp [93] ESOL [147] molecular https://github.”
BackgroundMethodInfluentialGraph neural network based coarse-grained mapping prediction
Li, Z., Wellawatte, G. P., Chakraborty, M., Gandhi, H. A., Xu, C., & White, A. D. (2020) · Chemical Science · doi:10.1039/d0sc02458a · Cited by 57
Large-Scale Ligand-Based Virtual Screening for SARS-CoV-2 Inhibitors Using Deep Neural Networks
Hofmarcher, M., Mayr, A., Rumetshofer, E., Ruch, P., Renz, P., Schimunek, J., Seidl, P., Vall, A., Widrich, M., Hochreiter, S., et al. (2020) · SSRN Electronic Journal · doi:10.2139/ssrn.3561442 · Cited by 49
Using molecular embeddings in QSAR modeling: does it make a difference?
Sabando, M. V., Ponzoni, I., Milios, E., & Soto, A. J. (2021) · Briefings in Bioinformatics · doi:10.1093/bib/bbab365 · Cited by 57
“In addition to our comparative analysis, we present the results obtained by the top-performing molecular representations on each dataset side by side to the results reported in the reference papers 14,17 and other state-of-the-art results for the datasets under study 15,16,47 in Tables 4 and 5.”
MethodResultIn Silico Prediction and Insights Into the Structural Basis of Drug Induced Nephrotoxicity
Shi, Y., Hua, Y., Wang, B., Zhang, R., & Li, X. (2022) · Frontiers in Pharmacology · doi:10.3389/fphar.2021.793332 · Cited by 54
Machine Learning in Chemoinformatics and Medicinal Chemistry
Rodríguez-Pérez, R., Miljković, F. N., & Bajorath, J. (2022) · Annual Review of Biomedical Data Science · doi:10.1146/annurev-biodatasci-122120-124216 · Cited by 56
Federated learning of molecular properties with graph neural networks in a heterogeneous setting
Zhu, W., Luo, J., & White, A. D. (2022) · Patterns · doi:10.1016/j.patter.2022.100521 · Cited by 73
Blood–brain barrier penetration prediction enhanced by uncertainty estimation
Tong, X., Wang, D., Ding, X., Tan, X., Ren, Q., Chen, G., Rong, Y., Xu, T., Huang, J., Jiang, H., et al. (2022) · Journal of Cheminformatics · doi:10.1186/s13321-022-00619-2 · Cited by 54
“collection MoleculeNet [23] is a benchmark for molecular machine learning that curates multiple public datasets focus on different levels of properties of molecules, including a BBBp dataset [39].”
BackgroundMethodInfluentialRoughness of Molecular Property Landscapes and Its Impact on Modellability
Aldeghi, M., Graff, D., Frey, N. C., Morrone, J. A., Pyzer‐Knapp, E. O., Jordan, K. E., & Coley, C. W. (2022) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.2c00903 · Cited by 55
DEEPCYPs: A deep learning platform for enhanced cytochrome P450 activity prediction
Ai, D., Cai, H., Wei, J., Zhao, D., Chen, Y., & Wang, L. (2023) · Frontiers in Pharmacology · doi:10.3389/fphar.2023.1099093 · Cited by 50
“A basic overview of these CML and DL techniques can be obtained elsewhere (Wu et al., 2017; He et al., 2021).”
BackgroundDeveloping ChemDFM as a large language foundation model for chemistry
Zhao, Z., Ma, D., Chen, L., Sun, L., Li, Z., Xia, Y., Chen, B., Xu, H., Zhu, Z., Su, Z., et al. (2025) · Cell Reports Physical Science · doi:10.1016/j.xcrp.2025.102523 · Cited by 194
“The molecular property prediction tasks in ChemLLMBench consist of five tasks from MoleculeNet benchmark [Wu et al., 2018], including BACE, BBBP, HIV, ClinTox, and Tox21.”
Zhang, D., Xia, S., & Zhang, Y. (2022) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.2c00260 · Cited by 57
He, S., Zhao, D., Ling, Y., Cai, H., Cai, Y., Zhang, J., & Wang, L. (2021) · Frontiers in Pharmacology · doi:10.3389/fphar.2021.796534 · Cited by 58
MLSolvA: solvation free energy prediction from pairwise atomistic interactions by machine learning
Lim, H., & Jung, Y. (2021) · Journal of Cheminformatics · doi:10.1186/s13321-021-00533-z · Cited by 61
Developing ChemDFM as a large language foundation model for chemistry
Zhao, Z., Ma, D., Chen, L., Sun, L., Li, Z., Xia, Y., Chen, B., Xu, H., Zhu, Z., Zhu, S., et al. (2024) · arXiv · doi:10.48550/arxiv.2401.14818 · Cited by 48
Grebner, C., Matter, H., Plowright, A. T., & Hessler, G. (2020) · Journal of Medicinal Chemistry · doi:10.1021/acs.jmedchem.9b02044 · Cited by 46
Li, C., Feng, J., Liu, S., & Yao, J. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/8464452 · Cited by 61
“We use five molecular property datasets recommended by MoleculeNet [8] for the experiments.”
InfluentialHigh-Energy and Long-Lasting Organic Electrode for a Rechargeable Aqueous Battery
Lee, M. H., Kwon, G., Lim, H., Kim, J., Kim, S. J., Lee, S., Kim, H., Eum, D., Song, J., Park, H., et al. (2022) · ACS Energy Letters · doi:10.1021/acsenergylett.2c01535 · Cited by 49
Retention Time Prediction with Message-Passing Neural Networks
Osipenko, S. V., Николаев, Е. Н., & Kostyukevich, Y. (2022) · Separations · doi:10.3390/separations9100291 · Cited by 53
Machine learning for small molecule drug discovery in academia and industry
Volkamer, A., Riniker, S., Nittinger, E., Lanini, J., Grisoni, F., Evertsson, E., Rodríguez-Pérez, R., & Schneider, N. (2023) · Artificial Intelligence in the Life Sciences · doi:10.1016/j.ailsci.2022.100056 · Cited by 66
Federated learning for molecular discovery
Hanser, T. (2023) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2023.102545 · Cited by 53
Liu, W., Wang, Z., Chen, J., Tang, W., & Wang, H. (2023) · Chemical Research in Toxicology · doi:10.1021/acs.chemrestox.3c00074 · Cited by 48
Jung, W. J., Goo, S., Hwang, T., Lee, H., Kim, Y., Chae, J., Yun, H., & Jung, S. (2024) · Pharmaceuticals · doi:10.3390/ph17030382 · Cited by 54
“Each file contained drug information such as the name, description, attribute values, related molecules, and applications.”
BackgroundAmbreen, S., Umar, M., Noor, A., Jain, H., & Ali, R. (2024) · European Journal of Medicinal Chemistry · doi:10.1016/j.ejmech.2024.117164 · Cited by 53
Prototype-Based Compound Discovery Using Deep Generative Models
Harel, S., & Radinsky, K. (2018) · Molecular Pharmaceutics · doi:10.1021/acs.molpharmaceut.8b00474 · Cited by 47
Making machine learning a useful tool in the accelerated discovery of transition metal complexes
Kulik, H. J. (2019) · Wiley Interdisciplinary Reviews Computational Molecular Science · doi:10.1002/wcms.1439 · Cited by 52
Tuplewise Material Representation Based Machine Learning for Accurate Band Gap Prediction
Na, G. S., Jang, S., Lee, Y., & Chang, H. (2020) · The Journal of Physical Chemistry A · doi:10.1021/acs.jpca.0c07802 · Cited by 54
Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentations
You, Y., Chen, T., Wang, Z., & Shen, Y. (2022) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3488560.3498416 · Cited by 83
“Onepre-trainingdatasetformolecules and eight fine-tuning/evaluation datasets are taken from ZINC15 [89] and MoleculeNet [3, 90], respectively.”
MethodSelf-supervised Auxiliary Learning with Meta-paths for Heterogeneous GraphsPreprint
Hwang, D., Park, J., Kwon, S., Kim, K.-M., Ha, J.-W., & Kim, H. J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.08294 · Cited by 89
“The powerful representation yields state-of-the-art performance in a variety of applications including social network analysis [5], citation network analysis [2], visual understanding [6, 7], recommender systems [8], physics [9], and drug discovery [10].”
Application of Deep Neural Network Models in Drug Discovery Programs
Grebner, C., Matter, H., Kofink, D., Wenzel, J., Schmidt, F., & Heßler, G. (2021) · ChemMedChem · doi:10.1002/cmdc.202100418 · Cited by 53
Molecular Dynamics and Machine Learning in Catalysts
Liu, W., Zhu, Y., Wu, Y., Chen, C., Hong, Y., Yue, Y., Zhang, J., & Hou, B. (2021) · Catalysts · doi:10.3390/catal11091129 · Cited by 50
“Different types of molecular dynamics are outlined, including AIMD and ReaxFF molecular dynamics.”
MethodHASEBE, T. (2021) · ACS Omega · doi:10.1021/acsomega.1c03839 · Cited by 53
DeLA-Drug: A Deep Learning Algorithm for Automated Design of Druglike Analogues
Creanza, T. M., Lamanna, G., Delre, P., Contino, M., Corriero, N., Saviano, M., Mangiatordi, G. F., & Ancona, N. (2022) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.2c00205 · Cited by 50
A pre-trained multi-representation fusion network for molecular property prediction
Zhang, H., Wu, J., Liu, S., & Shen, H. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.102092 · Cited by 52
A molecular video-derived foundation model for scientific drug discovery
Xiang, H., Zeng, L., Hou, L., Li, K., Fu, Z., Qiu, Y., Nussinov, R., Hu, J., Rosen‐Zvi, M., Zeng, X., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-53742-z · Cited by 61
“Speci fi cally, mean and standard deviations of MoleculeNet are reported with 10 different random seeds and mean and standard deviation of other datasets are reported with 3 different random seeds.”
A Multi‐Task Self‐Supervised Strategy for Predicting Molecular Properties and FGFR1 Inhibitors
Yang, X., Wang, Y., Lin, Y., Zhang, M., Liu, O., Shuai, J., & Zhao, Q. (2025) · Advanced Science · doi:10.1002/advs.202412987 · Cited by 54
Xu, Y., Cui, H., Pang, K., Li, G., Gong, F., Dong, S., Wang, B., & Li, B. (2026) · Cell · doi:10.1016/j.cell.2026.01.012 · Cited by 83
How to approach machine learning-based prediction of drug/compound–target interactions
Ataş, H., & Doğan, T. (2023) · Journal of Cheminformatics · doi:10.1186/s13321-023-00689-w · Cited by 62
“Recently, there have been efforts in terms of applying different dataset splitting strategies including temporal splitting [37], non-overlapped sampling [9, 38], cluster-cross-validation [39], and scaffold-based splitting [40] to build robust models.”
BackgroundNeural Architecture Search for GNN-Based Graph Classification
Wei, L., Zhao, H., He, Z., & Yao, Q. (2023) · ACM Transactions on Information Systems · doi:10.1145/3584945 · Cited by 59
“The ogbg-molhiv dataset (denoted as ogbg in this paper) is a molecular property prediction dataset derived from MoleculeNet [64].”
MethodCalibration and generalizability of probabilistic models on low-data chemical datasets with DIONYSUS
Tom, G., Hickman, R. J., Zinzuwadia, A. N., Mohajeri, A., Sánchez-Lengeling, B., & Aspuru‐Guzik, A. (2023) · Digital Discovery · doi:10.1039/d2dd00146b · Cited by 57
Proietti, M., Ragno, A., Rosa, B. L., Ragno, R., & Capobianco, R. (2023) · Machine Learning · doi:10.1007/s10994-023-06369-y · Cited by 59
“We have chosen the concepts to be used for Tox21 by following the same procedure we described in Appendix A for ClinTox dataset.”
InfluentialLi, B., Lin, M., Chen, T., & Wang, L. (2023) · Briefings in Bioinformatics · doi:10.1093/bib/bbad398 · Cited by 47
Artificial intelligence as a tool in drug discovery and development
Kokudeva, M., Vichev, M., Naseva, E., Miteva, D., & Velikova, T. V. (2024) · World Journal of Experimental Medicine · doi:10.5493/wjem.v14.i3.96042 · Cited by 78
“Another platform, MoleculeNet, can be used to translate molecular structures and predict toxicity[10].”
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.