BiMSGP: A Bidirectional Mamba-Based Model for Scalable and Accurate Genomic Prediction in Plants
Genes · 2026
DOI: 10.3390/genes17091156 ↗Kurz gefasst
Fachartikel in der Zeitschrift Genes, 2026. Verfasst von Qingjie Liu und 7 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China. Hauptthemen laut MEDLINE: Genomics, Triticum, Genome, Plant, Plant Breeding. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Department of Science and Technology of Zhejiang Province, Central-Local Collaborative Project “High-Performance Brain-inspired Computer and Applications”.
Abstract (Originalsprache)
Background/Objectives: Accurate prediction of complex traits from high-dimensional genomic markers remains difficult in plant breeding. Linear models have limited capacity for non-linear interactions, and many deep learning models scale poorly on long marker sequences. This study introduces BiMSGP, a bidirectional Mamba-based model for scalable genomic prediction.
Methods
BiMSGP extends a selective state space model with forward and backward processing so that each marker can integrate sequence context from both directions while retaining linear computational complexity; this is a modeling device for long-range marker dependencies, not a demonstration of biological epistasis. Regression was evaluated on Wheat599, Wheat2000, and SoyBase, and classification on SoyBase, using 10-fold cross-validation with shared fold assignments and no inner validation split; the held-out fold was used for checkpoint selection, learning-rate adjustment, and reporting. Ablation studies compared bidirectional and unidirectional stacks and different depths. Exploratory paired tests of fold-wise PCC differences were used to distinguish numerical rank from a paired difference under this protocol.
Results
Under the reported evaluation protocol, BiMSGP attained the numerically highest mean Pearson correlation coefficient (PCC) in all four Wheat599 environments, six of eight Wheat2000 traits, and five of seven quantitative SoyBase traits. Several of these numerical ranks did not have exploratory pt
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China.
- China Nanhu Academy of Electronics and Information Technology, Jiaxing 314001, China.
- Academy for Advanced Interdisciplinary Science and Technology, Zhejiang University of Technology, Hangzhou 310014, China.
- Applied Mathematics, College of Informatics, Huazhong Agricultural University, Wuhan 430070, China.
ORCID-Profile: Xinwei Yao, Xu Liu
Förderung
- Department of Science and Technology of Zhejiang Province
- Central-Local Collaborative Project “High-Performance Brain-inspired Computer and Applications”
Zitieren
APA
Liu, Q., Yao, X., Ma, J., Cheng, H., Zhou, H., Ding, L., Huai, S., & Liu, X. (2026). BiMSGP: A Bidirectional Mamba-Based Model for Scalable and Accurate Genomic Prediction in Plants. Genes. https://doi.org/10.3390/genes17091156
Vancouver
Liu Q, Yao X, Ma J, Cheng H, Zhou H, Ding L, et al. BiMSGP: A Bidirectional Mamba-Based Model for Scalable and Accurate Genomic Prediction in Plants. Genes. 2026. doi:10.3390/genes17091156
BibTeX
@article{Liu2026,
author = {Liu, Qingjie and Yao, Xinwei and Ma, Jinyan and Cheng, Huilin and Zhou, Huahao and Ding, Licong and Huai, Songyang and Liu, Xu},
title = {BiMSGP: A Bidirectional Mamba-Based Model for Scalable and Accurate Genomic Prediction in Plants},
journal = {Genes},
year = {2026},
doi = {10.3390/genes17091156}
}
EUVIMED