READRetro : natural product biosynthesis predicting with retrieval‐augmented dual‐view retrosynthesis
New Phytologist · 2024-09 · 243 (6) · 2512-2527
DOI: 10.1111/nph.20012 ↗Kurz gefasst
Fachartikel in der Zeitschrift New Phytologist, online erschienen am 30.07.2024. Verfasst von Taein Kim und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biological Sciences, KAIST, Daejeon, 34141, Korea. Hauptthemen laut MEDLINE: Biological Products, Biosynthetic Pathways. Die Arbeit wurde bisher 32-mal zitiert (Crossref) und nennt 70 Literaturangaben. Gefördert von: National Research Foundation of Korea, Rural Development Administration, Ministry of Science and ICT, South Korea.
Abstract (Originalsprache)
Plants, as a sessile organism, produce various secondary metabolites to interact with the environment. These chemicals have fascinated the plant science community because of their ecological significance and notable biological activity. However, predicting the complete biosynthetic pathways from target molecules to metabolic building blocks remains a challenge. Here, we propose retrieval‐augmented dual‐view retrosynthesis (READRetro) as a practical bio‐retrosynthesis tool to predict the biosynthetic pathways of plant natural products. Conventional bio‐retrosynthesis models have been limited in their ability to predict biosynthetic pathways for natural products. READRetro was optimized for the prediction of complex metabolic pathways by incorporating cutting‐edge deep learning architectures, an ensemble approach, and two retrievers. Evaluation of single‐ and multi‐step retrosynthesis showed that each component of READRetro significantly improved its ability to predict biosynthetic pathways. READRetro was also able to propose the known pathways of secondary metabolites such as monoterpene indole alkaloids and the unknown pathway of menisdaurilide, demonstrating its applicability to real‐world bio‐retrosynthesis of plant natural products. For researchers interested in the biosynthesis and production of secondary metabolites, a user‐friendly website ( https://readretro.net ) and the open‐source code of READRetro have been made available.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Biological Sciences, KAIST, Daejeon, 34141, Korea.
- Kim Jaechul Graduate School of AI, KAIST, Daejeon, 34141, Korea.
- Department of BioMedical Convergence Engineering, Pusan National University, Yangsan, 50612, Korea.
- School of Computing, KAIST, Daejeon, 34141, Korea.
ORCID-Profile: Jeongbin Park, Sang-Gyu Kim
Förderung
- National Research Foundation of Korea
- Rural Development Administration
- Ministry of Science and ICT, South Korea
Zitieren
APA
Kim, T., Lee, S., Kwak, Y., Choi, M. S., Park, J., Hwang, S. J., & Kim, S. G. (2024). READRetro : natural product biosynthesis predicting with retrieval‐augmented dual‐view retrosynthesis. New Phytologist, 243(6), 2512-2527. https://doi.org/10.1111/nph.20012
Vancouver
Kim T, Lee S, Kwak Y, Choi MS, Park J, Hwang SJ, et al. READRetro : natural product biosynthesis predicting with retrieval‐augmented dual‐view retrosynthesis. New Phytologist. 2024;243(6):2512-2527. doi:10.1111/nph.20012
BibTeX
@article{Kim2024,
author = {Kim, Taein and Lee, Seul and Kwak, Yejin and Choi, Min-Soo and Park, Jeongbin and Hwang, Sung Ju and Kim, Sang-Gyu},
title = {READRetro : natural product biosynthesis predicting with retrieval‐augmented dual‐view retrosynthesis},
journal = {New Phytologist},
year = {2024},
volume = {243},
number = {6},
pages = {2512--2527},
doi = {10.1111/nph.20012}
}
EUVIMED