Enabling rapid COVID-19 small molecule drug design through scalable deep learning of generative models. (September 2021)

• Record Type: Journal Article
• Authors: Jacobs, Sam Ade; Moon, Tim; McLoughlin, Kevin; Jones, Derek; Hysom, David; Ahn, Dong H; Gyllenhaal, John; Watson, Pythagoras; Lightstone, Felice C; Allen, Jonathan E; Karlin, Ian; Van Essen, Brian
• Other Names: De Supinski Bronis guest-editor.
• Is Part Of: International journal of high performance computing applications. Volume 35:Number 5(2021)
• Page Start: 469
• Page End: 482
• Publication Date: 2021-09
• Subjects: COVID 19 -- machine learning -- scalable performance -- generative models -- drug design; High performance computing -- Periodicals; Supercomputers -- Periodicals; 004.1105
• DOI: 10.1177/10943420211010930
• Languages: English
• ISSNs: 1094-3420

Abstract

We improved the quality and reduced the time to produce machine learned models for use in small molecule antiviral design. Our globally asynchronous multi-level parallel training approach strong scales to all of Sierra with up to 97.7% efficiency. We trained a novel, character-based Wasserstein autoencoder that produces a higher quality model trained on 1.613 billion compounds in 23 minutes while the previous state of the art takes a day on 1 million compounds. Reducing training time from a day to minutes shifts the model creation bottleneck from computer job turnaround time to human innovation time. Our implementation achieves 318 PFLOPs for 17.1% of half-precision peak. We will incorporate this model into our molecular design loop enabling the generation of more diverse compounds; searching for novel, candidate antiviral drugs improves and reduces the time to synthesize compounds to be tested in the lab.