Generative Model for Synthesizing Ionizable Lipids: A Monte Carlo Tree Search Approach

TL;DR

This paper presents a Monte Carlo tree search-based generative model for designing synthesizable ionizable lipids, accelerating lipid nanoparticle development for mRNA delivery while ensuring practical synthesis feasibility.

Contribution

It introduces a novel MCTS-guided generative approach using a synthetically accessible dataset and specialized predictors for practical ionizable lipid design.

Findings

Generated lipids are synthesizable with known pathways

The model accelerates lipid discovery process

Guided search improves chemical feasibility

Abstract

Ionizable lipids are essential in developing lipid nanoparticles (LNPs) for effective messenger RNA (mRNA) delivery. While traditional methods for designing new ionizable lipids are typically time-consuming, deep generative models have emerged as a powerful solution, significantly accelerating the molecular discovery process. However, a practical challenge arises as the molecular structures generated can often be difficult or infeasible to synthesize. This project explores Monte Carlo tree search (MCTS)-based generative models for synthesizable ionizable lipids. Leveraging a synthetically accessible lipid building block dataset and two specialized predictors to guide the search through chemical space, we introduce a policy network guided MCTS generative model capable of producing new ionizable lipids with available synthesis pathways.