SynTwins: A Retrosynthesis-Guided Framework for Synthesizable Molecular Analog Generation

TL;DR

SynTwins is a retrosynthesis-guided framework that generates synthetically accessible molecular analogs, bridging the gap between AI-designed molecules and practical chemical synthesis, thus accelerating drug and material discovery.

Contribution

It introduces a search-based approach emulating chemist strategies for synthesizable molecule generation, outperforming existing ML models in accessibility and maintaining property integrity.

Findings

Outperforms state-of-the-art models in synthesizability.

Maintains high structural similarity to target molecules.

Effectively integrates with property-optimization frameworks.

Abstract

The disconnect between AI-generated molecules with desirable properties and their synthetic feasibility remains a critical bottleneck in computational discovery of drugs and materials. While generative AI has accelerated the proposal of candidate molecules, many of these structures prove challenging or impossible to synthesize using established chemical reactions. Here, we introduce SynTwins, a novel retrosynthesis-guided molecule design framework that finds synthetically accessible molecular analogs by emulating expert chemists' strategies in three steps: retrosynthesis, searching similar building blocks, and virtual synthesis. Using a search algorithm instead of a stochastic data-driven generator, SynTwins outperforms state-of-the-art machine learning models at exploring synthetically accessible analogs while maintaining high structural similarity to original target molecules. Furthermore, when integrated into existing molecular property-optimization frameworks, our hybrid approach produces synthetically feasible analogs with minimal loss in property scores. Our comprehensive benchmarking across diverse molecular datasets demonstrates that SynTwins effectively bridges the gap between computational design and experimental synthesis, providing a practical solution for accelerating the discovery of synthesizable molecules with desired properties for a wide range of applications.