Research talk: AI for drug discovery

Опубликовано 8 февраля 2022, 17:47

Speakers:
Tong Wang, Researcher, Microsoft Research Asia
Yingce Xia, Senior Researcher, Microsoft Research Asia

Drug discovery is an important task with large social and business impacts. It usually takes tens of years and billions of dollars to discover a new drug. A promising and exciting direction in research involves using artificial intelligence (AI) to speed up drug discovery. In this talk, we will present two AI technologies designed for drug discovery: pretraining on compounds and AI-powered molecular docking. Inspired by the success of pretraining in natural language processing (NLP) and computer vision, we propose a new pretraining technique for molecules that involves dual-view molecule pretraining. Drug-target interaction prediction that identifies active binding drugs for target proteins plays an essential role in drug discovery. It is also the key challenge for virtual screening. In this talk, we present the Intermolecular Graph Transformer (IGT), which pays special attention to intermolecular information with a dedicated three-way transformer-based architecture.

Learn more about the 2021 Microsoft Research Summit: Aka.ms/researchsummit