Towards DNA-Encoded Library Generation with GFlowNets
This work addresses library design challenges in drug discovery for researchers, but it appears incremental as it applies existing GFlowNet methods to a new domain.
The paper tackled the problem of designing DNA-encoded libraries (DELs) for protein-protein interaction modulation by using GFlowNets as a generative approach, with results indicating it is a promising method for generating diverse combinatorial library candidates.
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.