BriGHT: transcriptome-regularized multimodal neuroimaging for brain disorder prediction
Bioinformatics · 31.08.2026 · 42 (9)
DOI: 10.1093/bioinformatics/btag681 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 11.09.2026. Verfasst von Zhoujie Fan und 9 weiteren Autor:innen. Beteiligte Einrichtung: College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin, 150001, China. Hauptthemen laut MEDLINE: Neuroimaging, Transcriptome, Brain Diseases. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science and Technology Major Project, Shandong Provincial Natural Science Foundation, Fundamental Research Funds for Central Universities at Harbin Engineering Univ.
Abstract (Originalsprache)
Motivation Hypergraph-based models for brain disorder prediction mainly adopt imaging-derived hypergraphs as propagation backbones. However, the entanglement of topology construction and feature propagation leaves regional representations weakly constrained by underlying biological organization, making them vulnerable to subject-specific variation and noise, particularly in heterogeneous multimodal settings. Results We present BriGHT, a Brain transcriptome-reGularized Hypergraph framework for mulTimodal disorder prediction. BriGHT employs a transcriptome-derived structural reference as a soft anchoring prior to regularize neuroimaging ROI embeddings, stabilizing representation geometry while preserving disease-relevant subject-specific variation. BriGHT further incorporates a reliability-aware fusion module to estimate subject-specific modality reliability from prediction confidence, cross-modal consistency, and decision certainty, enabling adaptive integration under heterogeneous modality quality. Experiments on three neuroimaging cohorts (ADNI, ADHD-200, REST-meta-MDD) and four modalities (VBM, fMRI, FDG, AV45) demonstrate that BriGHT consistently outperforms competing graph/hypergraph learning methods across six brain disorder prediction tasks. Perturbation analyses show that BriGHT benefits from the spatial correspondence between transcriptomic modules and imaging ROIs, rather than from arbitrary hypergraph regularization alone. Ablation and meta-analytic interpretability analyses support the contribution of transcriptomic anchoring and adaptive fusion to robust and biologically meaningful brain disorder prediction. Availability The software is publicly available at: https://github.com/Yaolab-fantastic/BriGHT.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin, 150001, China.
- Qingdao Innovation and Development Center, Harbin Engineering University, Qingdao, 266000, China.
- Sanya Nanhai Innovation and Development Base, Harbin Engineering University, Sanya, 572024, China.
- School of Hotel and Tourism Management, Hong Kong Polytechnic University, Hong Kong, 999077, China.
- School of Psychological and Cognitive Sciences, Peking University, Beijing, 100871, China.
- School of Biomedical Engineering, Hainan University, Sanya, 572025, China.
ORCID-Profile: Huazhu Fu, Xiaohui Yao
Förderung
- National Science and Technology Major Project
- Shandong Provincial Natural Science Foundation
- Fundamental Research Funds for Central Universities at Harbin Engineering Univ
- Hainan Provincial Natural Science Foundation
- National Natural Science Foundation of China
Zitieren
APA
Fan, Z., Luo, H., Zhou, H., Meng, H., Liang, H., Wang, Z., Fu, H., Cheng, C. Y., Cong, S., & Yao, X. (2026). BriGHT: transcriptome-regularized multimodal neuroimaging for brain disorder prediction. Bioinformatics, 42(9). https://doi.org/10.1093/bioinformatics/btag681
Vancouver
Fan Z, Luo H, Zhou H, Meng H, Liang H, Wang Z, et al. BriGHT: transcriptome-regularized multimodal neuroimaging for brain disorder prediction. Bioinformatics. 2026;42(9). doi:10.1093/bioinformatics/btag681
BibTeX
@article{Fan2026,
author = {Fan, Zhoujie and Luo, Haoran and Zhou, Huilong and Meng, Hao and Liang, Hong and Wang, Zheng and Fu, Huazhu and Cheng, Ching-Yu and Cong, Shan and Yao, Xiaohui},
title = {BriGHT: transcriptome-regularized multimodal neuroimaging for brain disorder prediction},
journal = {Bioinformatics},
year = {2026},
volume = {42},
number = {9},
doi = {10.1093/bioinformatics/btag681}
}
EUVIMED