The DOI matches its Crossref record; 65 of the 65 references it cites were found in a registry or an index.
Bayer’s in silico ADMET platform: a journey of machine learning over the past two decades
Open accessAbstract
Over the past two decades, an in silico absorption, distribution, metabolism, and excretion (ADMET) platform has been created at Bayer Pharma with the goal to generate models for a variety of pharmacokinetic and physicochemical endpoints in early drug discovery. These tools are accessible to all scientists within the company and can be a useful in assisting with the selection and design of novel leads, as well as the process of lead optimization. Here. we discuss the development of machine-learning (ML) approaches with special emphasis on data, descriptors, and algorithms. We show that high company internal data quality and tailored descriptors, as well as a thorough understanding of the experimental endpoints, are essential to the utility of our models. We discuss the recent impact of deep neural networks and show selected application examples.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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 cited source says what the claim attributes to it.
In the citing paper
“Recent lessons shared by scientists at AstraZeneca (83), Bayer (84), Merck (85) and GSK (86) highlight the complexities of ADMET property prediction (87).”
From Artificial Intelligence for Drug Discovery: Are We There Yet? (2024) · cites this paper as [85]
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
Cortes, C., & Vapnik, V. (1995) · Machine Learning · doi:10.1007/bf00994018 · Cited by 59,421
Cortes, C., & Vapnik, V. N. (1995) · Machine Learning · doi:10.1023/a:1022627411411 · Cited by 34,565
Semi-supervised classification with graph convolutional networks
Kipf, T. N., & Welling, M. (2016) · arXiv · doi:10.48550/arxiv.1609.02907 · Cited by 24,853
Lipinski, C. A., Lombardo, F., Dominy, B. W., & Feeney, P. J. (2001) · Advanced Drug Delivery Reviews · doi:10.1016/s0169-409x(00)00129-0 · Cited by 18,139
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
Extended-Connectivity Fingerprints
Rogers, D. O. W., & Hahn, M. (2010) · Journal of Chemical Information and Modeling · doi:10.1021/ci100050t · Cited by 7,925
On the Properties of Neural Machine Translation: Encoder–Decoder Approaches
Cho, K., van Merriënboer, B., Bahdanau, D., & Bengio, Y. (2014) · SSST@EMNLP · doi:10.3115/v1/w14-4012 · Cited by 7,251
On the generalized distance in statistics
Mahalanobis, P. C. (1936) · DOAJ (DOAJ: Directory of Open Access Journals) · Cited by 6,068
Handbook of Molecular Descriptors
Todeschini, R., & Consonni, V. (2000) · Methods and Principles in Medicinal Chemistry · doi:10.1002/9783527613106 · Cited by 4,107
Cited by
Sorted by citations
Items 201–215 of 215
OPLE: Drug Discovery Platform Combining 2D Similarity with AI to Predict Off-Target Liabilities
Biehn, S. E., Lehmann, J., Mueller, C., Tillier, F., & Sage, C. R. (2026) · Pharmaceuticals · doi:10.3390/ph19020228
Enhancing ADMET property predictions using cross-aligned multimodal attention mechanisms
Li, X., Ye, Y., Xu, R., Jiao, F., Hu, Z., Tong, H. H. Y., Zheng, L., & Guo, J. (2026) · Molecular Diversity · doi:10.1007/s11030-026-11485-7
Weber, C., Xu, X., & Shah, P. (2026) · Results in Chemistry · doi:10.1016/j.rechem.2026.103305
Decoding drug classification: A machine learning journey with decision trees and random forests
Kumar, S. S., Ibrahim, S. P. S., Gokulnath, B. V., Bharadwaja, C. S. S., Royal, K. V. H., Rajesh, V. C., & Pavithra, G. (2026) · AIP conference proceedings · doi:10.1063/5.0329126
Guha, R., Wang, W., Price, E., Bhhatarai, B., Hassan, M., DiFranzo, A., Keefer, C. E., Woody, N. A., Broccatelli, F., Winiwarter, S., et al. (2026) · Journal of Medicinal Chemistry · doi:10.1021/acs.jmedchem.5c03681
In Silico ADMET: From Current Practices to Novel Profilers
Llompart, P., Minoletti, C., Marcou, G., & Varnek, A. A. (2026) · Journal of Medicinal Chemistry · doi:10.1021/acs.jmedchem.6c00049 · Cited by 1
Song, X., Chen, Z., An, Y. F., & Zhang, J. (2026) · British Journal of Pharmacology · doi:10.1111/bph.70592 · Cited by 1
Goswami, P., Antal, S., & Patel, A. K. (2026) · Journal of Pharmaceutical Innovation · doi:10.1007/s12247-026-11008-9
A Self-Attention Algorithm for Monitoring of Enterprise Impression Management under ESG Reports
Lv, Z., & Zhou, Z. (2026) · International Conference on Machine Intelligence and Digital Applications (MIDA) · doi:10.1145/3801438.3801483
Artificial intelligence in medical image processing and translational science
Kashyap, K., & Zujam, D. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-40338-5.00004-4
ADMET all-inclusive: Accountability for the full end-to-end model life cycle is key to success
Kuhnke, L., & Göller, A. H. (2026) · Drug Discovery Today · doi:10.1016/j.drudis.2026.104827
Self-citationAbbasi, A., González-Franquesa, A., McCoy, M. G., Göller, A. H., Guo, Y., Clifton, J., Orsi, M., Pillai, N., Mitra, K., Argikar, U. A., et al. (2026) · Drug Discovery Today · doi:10.1016/j.drudis.2026.104828
Self-citationRevolutionizing Pharmaceuticals With AI-Driven Drug Delivery, Design, and Development
Kesavardhini, K., Saranraj, P., Lokeshwari, B., Gayathri, K. V., & Arthi, K. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-8562-4.ch008
BindingDB Entry 50020776: Discovery of IRAK4 Inhibitors
BindingDB (2024) · UC San Diego · doi:10.7270/q25q51jw
Metadata
- Authors
- Göller, A. H., Kuhnke, L., Montanari, F., Bonin, A., Schneckener, S., ter Laak, A., Wichard, J., Lobell, M., & Hillisch, A.
- Affiliations
- Bayer (Germany) (DE)
- Corresponding author
- Hillisch, Alexander
- ORCID
- Venue
- Drug Discovery Today
- Publisher
- Elsevier BV
- Published
- 2020-09
- Volume
- 25
- Issue
- 9
- Pages
- 1702-1709
- ISSN
- 1359-6446 (ISSN-L)
- OpenAlex
- W3041286284
- Cited by
- 215
- References
- 62
- Citations by year
- 2026: 22 · 2025: 38 · 2024: 56 · 2023: 38 · 2022: 30 · 2021: 27 · 2020: 3
- FWCI
- 2.18
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Drug Discovery Today (publishedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- Topics
- Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
- Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
- Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Pharmacology › Pharmacogenetics and Drug Metabolism
- Keywords
- machine learning, pharmacokinetic prediction, physicochemical properties, early drug discovery, deep neural network, molecular descriptors, lead optimization
- MeSH terms
- Machine Learning, Animals, Computer Simulation, Pharmaceutical Preparations, Humans, Intestinal Absorption, Models, Theoretical, Pharmacokinetics
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
