A systematic study of key elements underlying molecular property prediction
Open accessThe DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Abstract
Artificial intelligence (AI) has been widely applied in drug discovery with a major task as molecular property prediction. Despite booming techniques in molecular representation learning, key elements underlying molecular property prediction remain largely unexplored, which impedes further advancements in this field. Herein, we conduct an extensive evaluation of representative models using various representations on the MoleculeNet datasets, a suite of opioids-related datasets and two additional activity datasets from the literature. To investigate the predictive power in low-data and high-data space, a series of descriptors datasets of varying sizes are also assembled to evaluate the models. In total, we have trained 62,820 models, including 50,220 models on fixed representations, 4200 models on SMILES sequences and 8400 models on molecular graphs. Based on extensive experimentation and rigorous comparison, we show that representation learning models exhibit limited performance in molecular property prediction in most datasets. Besides, multiple key elements underlying molecular property prediction can affect the evaluation results. Furthermore, we show that activity cliffs can significantly impact model prediction. Finally, we explore into potential causes why representation learning models can fail and show that dataset size is essential for representation learning models to excel.
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
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.
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
XGBoost: A Scalable Tree Boosting System
Chen, T., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939785 · Cited by 54,569
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1412.3555 · Cited by 11,008
Weininger, D. (1988) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci00057a005 · Cited by 7,436
The Kolmogorov-Smirnov Test for Goodness of Fit
Massey, F. J. (1951) · Journal of the American Statistical Association · doi:10.1080/01621459.1951.10500769 · Cited by 7,210
Saito, T., & Rehmsmeier, M. (2015) · PLOS ONE · doi:10.1371/journal.pone.0118432 · Cited by 5,309
Applications of machine learning in drug discovery and development
Vamathevan, J., Clark, D., Czodrowski, P., Dunham, I., Ferran, E., Lee, G., Li, B., Madabhushi, A., Shah, P., Spitzer, M., et al. (2019) · Nature Reviews Drug Discovery · doi:10.1038/s41573-019-0024-5 · Cited by 3,228
ZINC 15 – Ligand Discovery for Everyone
Sterling, T., & Irwin, J. J. (2015) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5b00559 · Cited by 3,224
MoleculeNet: a benchmark for molecular machine learning
Wu, Z., Ramsundar, B., Feinberg, E. N., Gomes, J., Geniesse, C., Pappu, A. S., Leswing, K., & Pande, V. (2018) · Chemical Science · doi:10.1039/c7sc02664a · Cited by 3,107 · cited 18×
“Usually, when a new technique is developed for molecularpropertyprediction,improvedmetricsbyexperimentingon the MoleculeNet benchmark datasets 16 are used to substantiate the claimthatthemodelachieveschemicalspacegeneralization.”
InfluentialSelf-Attention with Relative Position Representations
Shaw, P., Uszkoreit, J., & Vaswani, A. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) · doi:10.18653/v1/n18-2074 · Cited by 2,505 · cited 1×
“To support arbi-trarylengthofSMILESstringsatinference,relativepositionalencoding is used 47 .”
Cited by
Deep learning for low-data drug discovery: Hurdles and opportunities
van Tilborg, D., Brinkmann, H., Criscuolo, E., Rossen, L., Özçelik, R., & Grisoni, F. (2024) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2024.102818 · Cited by 61
Voronov, G., Lightheart, R., Frandsen, A., Bargh, B., Haynes, S. E., Spencer, E., Schoenhardt, K. E., Davidson, C., Schaum, A., Macherla, V. R., et al. (2022) · doi:10.1101/2022.10.09.511482 · Cited by 18
Wozniak, S., Janson, G., & Feig, M. (2025) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.4c01682 · Cited by 14
Elder, L. H., & Onufriev, A. V. (2025) · The Journal of Physical Chemistry B · doi:10.1021/acs.jpcb.5c02263 · Cited by 2
Metadata
- Authors
- Deng, J., Yang, Z., Wang, H., Ojima, I., Samaras, D., & Wang, F.
- Venue
- Nature Communications
- Published
- 2023-10-13
- Volume
- 14
- Issue
- 1
- Pages
- 6395-6395
- ISSN
- 2041-1723 (ISSN-L)
- OpenAlex
- W4387617009
- Cited by
- 213
- References
- 23
- FWCI
- 27.90
- Type
- journal article
- Language
- en
- Open access
- gold
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: A systematic study of key elements underlying molecular property prediction. https://app.cochat.ai/papers/10.1038/s41467-023-41948-6
- The paper
- Deng, J., Yang, Z., Wang, H., Ojima, I., Samaras, D., & Wang, F. (2023). A systematic study of key elements underlying molecular property prediction. Nature Communications. https://doi.org/10.1038/s41467-023-41948-6
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.