AI is a viable alternative to high throughput screening: a 318-target study

By The Atomwise AIMS Program, including Perry B, Kratz JM. Nature Scientific Reports 2024, 14:7526. doi: 10.1038/s41598-024-54655-z

Summary: High throughput screening is the most widely-used tool to identify bioactive small molecules. All physical screening methods are limited because they require molecules that have been synthesized. Computational methods enable a fundamental shift to a test-then-make paradigm. The authors of this manuscript report on 318 projects for which the AtomNet® platform was used as the primary screening tool, coupled with low-throughput physical screens to validate the results. AtomNet® technology can identify bioactive scaffolds across a wide range of proteins, even without known binders, X-ray structures, or manual cherry-picking of compounds. The results of this study suggest that machine learning approaches have reached a computational accuracy that can replace high throughput screening as the first step of small-molecule drug discovery.

The post AI is a viable alternative to high throughput screening: a 318-target study first appeared on DNDi.