![]() ![]() Notably, we also uncovered novel scaffolds significantly dissimilar to Inferred by our GM workflow was significantly greater than that in the trainingĭata. Particularly, the proportion of high-affinity molecules Our model generated chemically viable molecules with a high predicted affinity We tested our GM workflow on two model systems, CDK2 and KRAS. ![]() In addition, we also included a hierarchical set of criteriaīased on advanced molecular modeling simulations during a final selection step. Molecular metrics, including drug likeliness, synthesizability, similarity, andĭocking scores. The designed GM workflow iteratively learns from Have developed a workflow based on a variational autoencoder coupled withĪctive learning steps. To improve the applicability domain of GM methods, we However, current GM methods have limitations, suchĪs low affinity towards the target, unknown ADME/PK properties, or the lack of Among these, Generative AI methods (GM) have gainedĪttention due to their ability to design new molecules and enhance specific Download a PDF of the paper titled Optimizing Drug Design by Merging Generative AI With Active Learning Frameworks, by Isaac Filella-Merce and 9 other authors Download PDF Abstract: Traditional drug discovery programs are being transformed by the advent of ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |