Generative Molecular Design with Steerable and Granular Synthesizability Control

TL;DR

This paper introduces a flexible generative framework for small molecules that allows precise control over synthesizability, enabling multi-parameter optimization, reaction constraint enforcement, and efficient virtual screening with high success rates.

Contribution

It presents a novel reinforcement learning-based method for steerable, granular control of synthesizability in molecular generation, outperforming existing models in efficiency and constraint handling.

Findings

Generated molecules have >90% exact match rate with reaction constraints.

Able to generate and dock 15k molecules using a single GPU.

Achieved highest sample efficiency among synthesizability-constrained models.

Abstract

Synthesizability in small molecule generative design remains a bottleneck. Existing works that do consider synthesizability can output predicted synthesis routes for generated molecules. However, there has been minimal attention in addressing the ease of synthesis and enabling flexibility to incorporate desired reaction constraints. In this work, we propose a small molecule generative design framework that enables steerable and granular synthesizability control. Generated molecules satisfy arbitrary multi-parameter optimization objectives with predicted synthesis routes containing pre-defined allowed reactions, while optionally avoiding others. One can also enforce that all reactions belong to a pre-defined set. We show the capability to mix-and-match these reaction constraints across the most common medicinal chemistry transformations. Next, we show how our framework can be used to valorize industrial byproducts towards de novo optimized molecules. Going further, we demonstrate how granular control over synthesizability constraints can loosely mimic virtual screening of ultra-large make-on-demand libraries. Using only a single GPU, we generate and dock 15k molecules to identify promising candidates in Freedom 4.0 constituting 142B make-on-demand molecules (assessing only 0.00001% of the library). Generated molecules satisfying the reaction constraints have > 90% exact match rate. Lastly, we benchmark our framework against recent synthesizability-constrained generative models and demonstrate the highest sample efficiency even when imposing the additional constraint that all molecules must be synthesizable from a single reaction type. The main theme is demonstrating that a pre-trained generalist molecular generative model can be incentivized to generate property-optimized small molecules under challenging synthesizability constraints through reinforcement learning.