Towards DNA-Encoded Library Generation with GFlowNets

Michał Koziarski, Mohammed Abukalam, Vedant Shah, Louis Vaillancourt, Doris Alexandra Schuetz, Moksh Jain, Almer M. van der Sloot, Mathieu Bourgey, Anne Marinier, Yoshua Bengio

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

Keywords: GFlowNets, DNA-encoded libraries, combinatorial libraries

TL;DR: Diverse DNA-encoded library candidate generation using GFlowNets

Abstract: DNA-encoded libraries (DELs) are a powerful approach for rapidly screening large numbers of diverse compounds. One of the key challenges in using DELs is library design, which involves choosing the building blocks that will be combinatorially combined to produce the final library. In this paper we consider the task of protein-protein interaction (PPI) biased DEL design. To this end, we evaluate several machine learning algorithms on the PPI modulation task and use them as a reward for the proposed GFlowNet-based generative approach. We additionally investigate the possibility of using structural information about building blocks to design a hierarchical action space for the GFlowNet. The observed results indicate that GFlowNets are a promising approach for generating diverse combinatorial library candidates.

Submission Number: 84