Abstract
High throughput screening (HTS) is routinely used to identify bioactive small molecules. This requires physical compounds, which limits coverage of accessible chemical space. Computational approaches combined with vast on-demand chemical libraries can access far greater chemical space, provided that the predictive accuracy is sufficient to identify useful molecules. Through the largest and most diverse virtual HTS campaign reported to date, comprising 318 individual projects, we demonstrate that our AtomNet® convolutional neural network successfully finds novel hits across every major therapeutic area and protein class. We address historical limitations of computational screening by demonstrating success for target proteins without known binders, high-quality X-ray crystal structures, or manual cherry-picking of compounds. We show that the molecules selected by the AtomNet® model are novel drug-like scaffolds rather than minor modifications to known bioactive compounds. Our empirical results suggest that computational methods can substantially replace HTS as the first step of small-molecule drug discovery.
Recommended Citation
I. Wallach and D. Bernard and K. Nguyen and G. Ho and A. Morrison and A. Stecula and A. Rosnik and A. M. O'Sullivan and A. Davtyan and B. Samudio and B. Thomas and B. Worley and B. Butler and C. Laggner, "AI is a Viable Alternative to High throughput Screening: A 318-target Study," Scientific Reports, vol. 14, no. 1, article no. 7526, Nature Research, Dec 2024.
The definitive version is available at https://doi.org/10.1038/s41598-024-54655-z
Department(s)
Chemistry
Publication Status
Open Access
International Standard Serial Number (ISSN)
2045-2322
Document Type
Article - Journal
Document Version
Final Version
File Type
text
Language(s)
English
Rights
© 2024 The Authors, All rights reserved.
Creative Commons Licensing
This work is licensed under a Creative Commons Attribution 4.0 License.
Publication Date
01 Dec 2024
