Can We Learn To Distinguish between “Drug-like” and “Nondrug-like” Molecules?
Abstract
We have used a Bayesian neural network to distinguish between drugs and nondrugs. For this purpose, the CMC acts as a surrogate for drug-like molecules while the ACD is a surrogate for nondrug-like molecules. This task is performed by using two different set of 1D and 2D parameters. The 1D parameters contain information about the entire molecule like the molecular weight and the the 2D parameters contain information about specific functional groups within the molecule. Our best results predict correctly on over 90% of the compounds in the CMC while classifying about 10% of the molecules in the ACD as drug-like. Excellent generalization ability is shown by the models in that roughly 80% of the molecules in the MDDR are classified as drug-like. We propose to use the models to design combinatorial libraries. In a computer experiment on generating a drug-like library of size 100 from a set of 10 000 molecules we obtain at least a 3 or 4 order of magnitude improvement over random methods. The neighborhoods defined by our models are not similar to the ones generated by standard Tanimoto similarity calculations. Therefore, new and different information is being generated by our models, and so it can supplement standard diversity approaches to library design.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
Machine learning models that discriminate 'drugs' from 'non-drugs' emerged in 1998, when scientists from Vertex and BASF independently proposed models to estimate 'drug-likeness,' showing that it is possible to train ML models based on chemical features to discriminate 'drugs' from 'non-drugs'.
“Machine learning (ML) models that discriminate 'drugs' from 'non-drugs' emerged in 1998, when scientists from Vertex (27) and BASF (28) independently proposed models to estimate 'drug-likeness,' showing that it is possible to train ML models based on chemical features to discriminate 'drugs' (specifically, compounds that medicinal chemists have proposed for biological testing)”
From Artificial Intelligence for Drug Discovery: Are We There Yet? (2024) · cites this paper as [28]
Cites
Equation of State Calculations by Fast Computing Machines
Metropolis, N., Rosenbluth, A. W., Rosenbluth, M. N., Teller, A. H., & Teller, E. (1953) · The Journal of Chemical Physics · doi:10.1063/1.1699114 · Cited by 37,192 · see citing works
(1992) · Cited by 23,431 · see citing works
Lipinski, C. A., Lombardo, F., Dominy, B. W., & Feeney, P. J. (1997) · Advanced Drug Delivery Reviews · doi:10.1016/s0169-409x(96)00423-1 · Cited by 11,484 · see citing works
Duane, S., Kennedy, A. D., Pendleton, B. J., & Roweth, D. (1987) · Physics Letters B · doi:10.1016/0370-2693(87)91197-x · Cited by 3,920 · see citing works
The Properties of Known Drugs. 1. Molecular Frameworks
Bemis, G. W., & Murcko, M. A. (1996) · Journal of Medicinal Chemistry · doi:10.1021/jm9602928 · Cited by 2,501 · see citing works
Self-citationIntroduction to the Theory of Neural Computation
Hertz, J., Krogh, A., & Palmer, R. G. (2018) · CRC Press eBooks · doi:10.1201/9780429499661 · Cited by 1,788 · see citing works
Applied Multivariate Statistical Analysis.
Johnson, R. A., & Wichern, D. W. (1998) · Biometrics · doi:10.2307/2533879 · Cited by 1,122 · see citing works
Brown, R. D., & Martin, Y. C. (1996) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci9501047 · Cited by 631 · see citing works
Nilakantan, R., Bauman, N., Dixon, J. S., & Venkataraghavan, R. (1987) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci00054a008 · Cited by 367 · see citing works
Matter, H. (1997) · Journal of Medicinal Chemistry · doi:10.1021/jm960352+ · Cited by 251 · see citing works
An Improved Acceptance Procedure for the Hybrid Monte Carlo Algorithm
Neal, R. M. (1994) · Journal of Computational Physics · doi:10.1006/jcph.1994.1054 · Cited by 179 · see citing works
Reviews in Computational Chemistry
(1990) · Reviews in computational chemistry · doi:10.1002/9780470125786 · Cited by 152 · see citing works
Cummins, D. J., Andrews, C. W., Bentley, J. A., et al. (1996) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci950168h · Cited by 110 · see citing works
Lewis, R. A., Mason, J. S., & McLay, I. M. (1997) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci960471y · Cited by 81 · see citing works
The NIEHS Predictive-Toxicology Evaluation Project.
Bristol, D. W., Wachsman, J. T., & Greenwell, A. (1996) · Environmental Health Perspectives · doi:10.1289/ehp.96104s51001 · Cited by 79 · see citing works
Discovery of enzyme inhibitors through combinatorial chemistry
Dolle, R. E. (1997) · Molecular Diversity · doi:10.1007/bf01715638 · Cited by 51 · see citing works
Future pathways for combinatorial chemistry
Brown, D. (1997) · Molecular Diversity · doi:10.1007/bf01715637 · Cited by 37 · see citing works
Libraries of non-polymeric organic molecules
Gordon, E. M. (1995) · Current Opinion in Biotechnology · doi:10.1016/0958-1669(95)80103-0 · Cited by 32 · see citing works
Formation and decay of hot nuclei
Volant, C., Conjeaud, M., Harar, S., et al. (1987) · Physics Letters B · doi:10.1016/0370-2693(87)90879-3 · Cited by 19 · see citing works
Phasing out leaded gasoline will not end lead poisoning in developing countries.
Finkelman, J. (1996) · Environmental Health Perspectives · doi:10.1289/ehp.9610410 · Cited by 18 · see citing works
(1995) · Environmental Science & Technology · doi:10.1021/es00001a734 · Cited by 8 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Molecular properties that influence the oral bioavailability of drug candidates
Veber, D. F., Johnson, S. R., Cheng, H.-Y., Smith, B. R., Ward, K. W., & Kopple, K. D. (2002) · Journal of Medicinal Chemistry · doi:10.1021/jm020017n · Cited by 8,420 · see citing works
QSAR Modeling: Where have you been? Where are you going to?
Cherkasov, A., Muratov, E. N., Fourches, D., Varnek, A., Baskin, I. I., Cronin, M., Dearden, J., Gramatica, P., Martin, Y. C., Todeschini, R., et al. (2014) · Journal of Medicinal Chemistry · doi:10.1021/jm4004285 · Cited by 2,164 · see citing works
Schneider, G. (2018) · Nature Reviews Drug Discovery · doi:10.1038/nrd.2017.232 · Cited by 910 · see citing works
Deep learning for computational chemistry
Goh, G. B., Hodas, N. O., & Vishnu, A. (2017) · Journal of Computational Chemistry · doi:10.1002/jcc.24764 · Cited by 809 · see citing works
Drug research: myths, hype and reality
Kubinyi, H. (2003) · Nature Reviews Drug Discovery · doi:10.1038/nrd1156 · Cited by 348 · see citing works
Ursu, O., Rayan, A., Goldblum, A., & Oprea, T. I. (2011) · WIREs Computational Molecular Science · doi:10.1002/wcms.52 · Cited by 276 · see citing works
Artificial Intelligence for Drug Discovery: Are We There Yet?
Hasselgren, C., & Oprea, T. I. (2024) · Annual Review of Pharmacology and Toxicology · doi:10.1146/annurev-pharmtox-040323-040828 · Cited by 236 · see citing works
Smith, A. J. T., Zhang, X., Leach, A. G., & Houk, K. N. (2009) · Journal of Medicinal Chemistry · doi:10.1021/jm800498e · Cited by 193 · see citing works
Badapple: promiscuity patterns from noisy evidence
Yang, J. J., Ursu, O., Lipinski, C. A., Sklar, L. A., Oprea, T. I., & Bologa, C. G. (2016) · Journal of Cheminformatics · doi:10.1186/s13321-016-0137-3 · Cited by 103 · see citing works
Pharmacokinetically Based Mapping Device for Chemical Space Navigation
Oprea, T. I., Zamora, I., & Ungell, A.-L. (2002) · Journal of Combinatorial Chemistry · doi:10.1021/cc010093w · Cited by 77 · see citing works
How do metabolites differ from their parent molecules and how are they excreted?
Kirchmair, J., Howlett, A., Peironcely, J. E., Murrell, D. S., Williamson, M. J., Adams, S. E., Hankemeier, T., van Buren, L., Duchateau, G., Klaffke, W., et al. (2013) · Journal of Chemical Information and Modeling · doi:10.1021/ci300487z · Cited by 43 · see citing works
Cherkasov, A. (2005) · International Journal of Molecular Sciences · doi:10.3390/i6010063 · Cited by 39 · see citing works
- Authors
- Ajay, Walters, W. P., & Murcko, M. A.
- Affiliations
- Vertex Pharmaceuticals (United States) (US)
- Corresponding author
- Ajay
- Venue
- Journal of Medicinal Chemistry
- Publisher
- American Chemical Society (ACS)
- Published
- 1998-07-23
- Volume
- 41
- Issue
- 18
- Pages
- 3314-3324
- ISSN
- 0022-2623 (ISSN-L)
- 1520-4804
- OpenAlex
- W2046564413
- Cited by
- 484
- References
- 21
- Citations by year
- 2026: 6 · 2025: 9 · 2024: 9 · 2023: 11 · 2022: 8 · 2021: 8 · 2020: 14 · 2019: 6 · 2018: 10 · 2017: 9 · 2016: 6 · 2015: 13 · 2014: 13 · 2013: 10 · 2012: 13
- FWCI
- 48.31
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Journal of Medicinal Chemistry (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computational Theory and Mathematics › Computational Drug Discovery Methods
- Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
- Physical Sciences › Chemistry › Organic Chemistry › Synthesis and Characterization of Heterocyclic Compounds
- Keywords
- drug-likeness prediction, Bayesian neural networks, molecular descriptors, 2D molecular descriptors, combinatorial library design, molecular diversity, Tanimoto similarity
- MeSH terms
- Bayes Theorem, Pharmaceutical Preparations, Drug Design, Databases, Factual, Neural Networks, Computer
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
