AlphaGEM enables precise genome-scale metabolic modelling by integrating protein structure alignment with deep-learning-based dark metabolism mining
Journal article, 2026
Constructing high-quality genome-scale metabolic models (GEMs) for non-model organisms remains challenging. To address this, we developed AlphaGEM, a versatile toolbox leveraging proteome-scale structural alignment, protein language models (PLMSearch), and deep-learning-based predictions for efficient genomic mining to generate GEMs ready for applications. AlphaGEM enhances homologous relationship identification compared to traditional sequence-based methods. Crucially, it employs an ensemble procedure empowered by multiple deep learning toolboxes to effectively mine dark metabolic functions encoded by nonhomologous proteins, thereby expanding species-specific networks. We validated AlphaGEM across prokaryotes (Klebsiella pneumoniae, Bacillus subtilis), eukaryotes (Rhodosporidium toruloides, Pichia pastoris), and complex mammals (Mus musculus, Cricetulus griseus), achieving predictions comparable to manually curated models while outperforming existing tools. Furthermore, we demonstrated its scalability by automatically reconstructing high-fidelity GEMs for 332 distinct yeast species. In summary, AlphaGEM enables precise, rapid GEM construction across diverse domains, providing a solid foundation for universal functional analysis of organisms having genome sequences available.
Author
Weishang Han
State Key Laboratory of Microbial Metabolism
Luchi Xiao
State Key Laboratory of Microbial Metabolism
Haocheng Sun
State Key Laboratory of Microbial Metabolism
Guangming Xiang
State Key Laboratory of Microbial Metabolism
Qianxi Jia
State Key Laboratory of Microbial Metabolism
Chinese Academy of Sciences
Haoyu Wang
State Key Laboratory of Microbial Metabolism
Chinese Academy of Sciences
Boyang Ji
BII Holdings A/S
C. Zhang
Royal Institute of Technology (KTH)
Zhengzhou University
Eduard Kerkhoven
Novo Nordisk Foundation
Chalmers, Life Sciences, Systems and Synthetic Biology
Jens B Nielsen
BII Holdings A/S
Chalmers, Life Sciences, Systems and Synthetic Biology
Hongzhong Lu
State Key Laboratory of Microbial Metabolism
Nature Communications
2041-1723 (ISSN) 20411723 (eISSN)
Vol. 17 1 8720Subject Categories (SSIF 2025)
Bioinformatics (Computational Biology)
Bioinformatics and Computational Biology
Genetics and Genomics
DOI
10.1038/s41467-026-75549-w
PubMed
42463708