Deep Batch Active Learning for Drug Discovery

• DOI: 10.7554/elife.89679.1
• Publication Date: 2023-09-13T13:46:29Z
• Authors: Michael Bailey; Saeed Moayedpour; Ruijiang Li; Alejandro Corroch...; Alexander Kötter; Lorenzo Kogler-Anele; Saleh Riahi; Christoph Grebner; Gerhard Hessler; Hans Matter; Marc Bianciotto; Pablo Mas; Ziv Bar-Joseph; Sven Jager

A key challenge in drug discovery is to optimize, silico, various absorption and affinity properties of small molecules. One strategy that was proposed for such optimization process active learning. In learning molecules are selected testing based on their likelihood improving model performance. To enable the use with advanced neural network models we developed two novel batch selection methods. These methods were tested several public datasets different goals sizes. We have also curated new provide chronological information state-of-the-art experimental strategy. As show, all greatly improved existing current leading significant potential saving number experiments needed reach same Our general can be used any package including popular DeepChem library.