AI-based language models powering drug discovery and development

Zhichao Liu; Ruth A Roberts; Madhu Lal-Nag; Xi Chen; Ruili Huang; Weida Tong

doi:10.1016/j.drudis.2021.06.009

AI-based language models powering drug discovery and development

Drug Discov Today. 2021 Nov;26(11):2593-2607. doi: 10.1016/j.drudis.2021.06.009. Epub 2021 Jun 30.

Authors

Zhichao Liu¹, Ruth A Roberts², Madhu Lal-Nag³, Xi Chen⁴, Ruili Huang⁵, Weida Tong⁶

Affiliations

¹ National Center for Toxicological Research, US Food and Drug Administration, Jefferson, AR 72079, USA. Electronic address: zhichao.liu@fda.hhs.gov.
² National Center for Toxicological Research, US Food and Drug Administration, Jefferson, AR 72079, USA; ApconiX, BioHub at Alderley Park, Alderley Edge SK10 4TG, UK; University of Birmingham, Edgbaston, Birmingham B15 2TT, UK.
³ Office of Translational Sciences, Center for Drug Evaluation and Research, US FDA, Silver Spring, MD 20993, USA.
⁴ National Center for Toxicological Research, US Food and Drug Administration, Jefferson, AR 72079, USA.
⁵ National Center for Advancing Translational Sciences, National Institutes of Health, Rockville, MD 20850, USA.
⁶ National Center for Toxicological Research, US Food and Drug Administration, Jefferson, AR 72079, USA. Electronic address: weida.tong@fda.hhs.gov.

Abstract

The discovery and development of new medicines is expensive, time-consuming, and often inefficient, with many failures along the way. Powered by artificial intelligence (AI), language models (LMs) have changed the landscape of natural language processing (NLP), offering possibilities to transform treatment development more effectively. Here, we summarize advances in AI-powered LMs and their potential to aid drug discovery and development. We highlight opportunities for AI-powered LMs in target identification, clinical design, regulatory decision-making, and pharmacovigilance. We specifically emphasize the potential role of AI-powered LMs for developing new treatments for Coronavirus 2019 (COVID-19) strategies, including drug repurposing, which can be extrapolated to other infectious diseases that have the potential to cause pandemics. Finally, we set out the remaining challenges and propose possible solutions for improvement.

Keywords: Artificial intelligence; COVID-19; Drug development; Drug discovery; Language models; Natural language processing.

Publication types

Research Support, U.S. Gov't, P.H.S.
Review

MeSH terms

Artificial Intelligence
COVID-19 Drug Treatment*
Drug Development*
Drug Discovery*
Humans
Natural Language Processing*
Pharmacovigilance*
SARS-CoV-2