Active Learning on Synthons for Molecular Design

Tom George Grigg, Mason Burlage, Oliver Brook Scott, Dominique Sydow, Liam Wilbraham

Track: Machine learning: computational method and/or computational results

Nature Biotechnology: Yes

Keywords: Active Learning, Drug Discovery, Chemical Synthesis

TL;DR: Factored active learning approach for molecular design in combinatorial chemical space.

Abstract:

Exhaustive virtual screening is highly informative but often intractable against the expensive objective functions involved in modern drug discovery. This problem is exacerbated in combinatorial contexts such as multi-vector expansion, where molecular spaces can quickly become ultra-large. Here, we introduce Scalable Active Learning via Synthon Acquisition (SALSA): a simple algorithm applicable to multi-vector expansion which extends pool-based active learning to non-enumerable spaces by factoring modeling and acquisition over synthon or fragment choices. Through experiments on ligand- and structure-based objectives we highlight SALSA's sample efficiency, and its ability to scale to spaces of trillions of compounds. Further, we demonstrate application toward multi-parameter objective design tasks on three protein targets – finding SALSA-generated molecules have comparable chemical property profiles to known bioactives, and
exhibit greater diversity and higher scores over an industry-leading generative approach.

Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.

Presenter: ~Tom_George_Grigg1

Format: Yes, the presenting author will attend in person if this work is accepted to the workshop.

Funding: No, the presenting author of this submission does *not* fall under ICLR’s funding aims, or has sufficient alternate funding.

Submission Number: 65