There is a growing evidence that Artificial Intelligence and Machine Learning can improve small molecule drug discovery processes and, in particular, the compound design process. Augmentation with an AI component can lead to a reduced number of compounds tested in vitro (hence reduced cost and time), as well as to a diversification of the explored chemical space (hence higher likelihood of success). Thereby, we can optimize key stages of the compound design process: hit identification, hit to lead, and lead optimization. Here, we discuss the capabilities of our AI Platform for Compound Design with components for property/affinity prediction (with in silico validation) and molecule optimization. We provide examples of applications of our algorithms to a drug discovery project of our client (with in vitro validation): virtual screening, prioritization of molecules in the drug discovery pipeline, and molecule optimization.
To read full article, complete the form below.
