SynTwins: A Retrosynthesis-Guided Framework for Synthesizable Molecular Analog Generation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911279387508736 |
|---|---|
| author | Chen, Shuan Nam, Gunwook Aspuru-Guzik, Alan Jung, Yousung |
| author_facet | Chen, Shuan Nam, Gunwook Aspuru-Guzik, Alan Jung, Yousung |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_02752 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SynTwins: A Retrosynthesis-Guided Framework for Synthesizable Molecular Analog Generation Chen, Shuan Nam, Gunwook Aspuru-Guzik, Alan Jung, Yousung Chemical Physics Artificial Intelligence 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. |
| title | SynTwins: A Retrosynthesis-Guided Framework for Synthesizable Molecular Analog Generation |
| topic | Chemical Physics Artificial Intelligence |
| url | https://arxiv.org/abs/2507.02752 |