READRetro: natural product biosynthesis predicting with retrieval‐augmented dual‐view retrosynthesis

• DOI: 10.1111/nph.20012
• Publication Date: 2024-07-31T06:09:45Z
• Authors: Taein Kim; Seul Lee; Yejin Kwak; Min‐Soo Choi; Jeongbin Park; Sung Ju Hwang; Sang‐Gyu Kim
• Keywords: Retrosynthetic analysis; Metabolic pathway; Natural product

Summary Plants, as a sessile organism, produce various secondary metabolites to interact with the environment. These chemicals have fascinated plant science community because of their ecological significance and notable biological activity. However, predicting complete biosynthetic pathways from target molecules metabolic building blocks remains challenge. Here, we propose retrieval‐augmented dual‐view retrosynthesis (READRetro) practical bio‐retrosynthesis tool predict natural products. Conventional models been limited in ability for READRetro was optimized prediction complex by incorporating cutting‐edge deep learning architectures, an ensemble approach, two retrievers. Evaluation single‐ multi‐step showed that each component significantly improved its pathways. also able known such monoterpene indole alkaloids unknown pathway menisdaurilide, demonstrating applicability real‐world For researchers interested biosynthesis production metabolites, user‐friendly website ( https://readretro.net ) open‐source code made available.