A Structure-Based Deep Learning Framework for Correcting Marine Natural Products’ Misannotations Attributed to Host–Microbe Symbiosis
Marine Drugs · 01.01.2026 · 24 (1) · 20
DOI: 10.3390/md24010020 ↗Kurz gefasst
Fachartikel in der Zeitschrift Marine Drugs, online erschienen am 01.01.2026. Verfasst von Xiaohe Tian und 5 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Natural and Biomimetic Drugs, School of Pharmaceutical Sciences, Peking University, Beijing 100191, China. Hauptthemen laut MEDLINE: Biological Products, Symbiosis, Aquatic Organisms, Deep Learning. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Key R&D Program of China, the Beijing Natural Science Foundation, National Key R&D Program of China.
Abstract (Originalsprache)
Marine natural products (MNPs) are a diverse group of bioactive compounds with varied chemical structures, but their biological origins are often misannotated due to complex host–microbe symbiosis. Propagated through public databases, such errors hinder biosynthetic studies and AI-driven drug discovery. Here, we develop a structure-based workflow of origin classification and misannotation correction for marine datasets. Using CMNPD and NPAtlas compounds, we integrate a two-step cleaning strategy that detects label inconsistencies and filters structural outliers with a microbial-pretrained graph neural network. The optimized model achieves a balanced accuracy of 85.56% and identifies 3996 compounds whose predicted microbial origins contradict their Animalia labels. These putative symbiotic metabolites cluster within known high-risk taxa, and interpretability analysis reveal biologically coherent structural patterns. This framework provides a scalable quality-control approach for natural product databases and supports more accurate biosynthetic gene cluster (BGC) tracing, host selection, and AI-driven marine natural product discovery.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- State Key Laboratory of Natural and Biomimetic Drugs, School of Pharmaceutical Sciences, Peking University, Beijing 100191, China.
ORCID-Profile: Chuanyu Lyu, Aili Fan, Zhenming Liu
Förderung
- the National Key R&D Program of China
- the Beijing Natural Science Foundation
- National Key R&D Program of China
- Beijing Natural Science Foundation
Zitieren
APA
Tian, X., Lyu, C., Zhou, Y., Zhang, L., Fan, A., & Liu, Z. (2026). A Structure-Based Deep Learning Framework for Correcting Marine Natural Products’ Misannotations Attributed to Host–Microbe Symbiosis. Marine Drugs, 24(1), 20. https://doi.org/10.3390/md24010020
Vancouver
Tian X, Lyu C, Zhou Y, Zhang L, Fan A, Liu Z. A Structure-Based Deep Learning Framework for Correcting Marine Natural Products’ Misannotations Attributed to Host–Microbe Symbiosis. Marine Drugs. 2026;24(1):20. doi:10.3390/md24010020
BibTeX
@article{Tian2026,
author = {Tian, Xiaohe and Lyu, Chuanyu and Zhou, Yiran and Zhang, Liangren and Fan, Aili and Liu, Zhenming},
title = {A Structure-Based Deep Learning Framework for Correcting Marine Natural Products’ Misannotations Attributed to Host–Microbe Symbiosis},
journal = {Marine Drugs},
year = {2026},
volume = {24},
number = {1},
pages = {20},
doi = {10.3390/md24010020}
}
EUVIMED