Explainable Serum Microbiome Signatures for Fatty Liver Screening and Early Risk Stratification
Main Article Content
Abstract
Nonalcoholic fatty liver disease represents one of the most prevalent chronic liver conditions worldwide, characterized by the progressive accumulation of hepatic steatosis without significant alcohol consumption. Despite its growing epidemiological burden, early and non-invasive screening remains a significant clinical challenge. Traditional diagnostic modalities, such as liver biopsy, are inherently invasive, whereas conventional imaging and standard serological markers frequently lack the requisite sensitivity to detect early-stage metabolic alterations. Recent advancements in multi-omics technologies have illuminated the complex bidirectional communication within the gut-liver axis, suggesting that host systemic metabolism and gut microbiota composition are inextricably linked during the pathogenesis of hepatic steatosis. This paper presents a comprehensive framework for identifying explainable serum-microbiome signatures to facilitate the early screening of nonalcoholic fatty liver disease. By integrating high-throughput microbiome sequencing data with serum metabolomic profiles, we aim to capture the multidimensional biological perturbations that precede structural hepatic changes. Furthermore, the application of explainable artificial intelligence techniques ensures that the predictive models transcend traditional black-box paradigms, providing clinicians with transparent, biologically interpretable feature importances. Through the systematic evaluation of interacting microbial taxa and circulating metabolites, this approach not only achieves superior predictive performance but also elucidates the underlying pathophysiological mechanisms, thereby paving the way for targeted therapeutic interventions and personalized clinical management strategies.
Downloads
Article Details
Section
This work is licensed under a Creative Commons Attribution 4.0 International License.
-
All published articles are open access, with copyright shared between the authors and the journal. The journal retains the exclusive right to first publication and identifies itself as original publisher.
-
Articles are made available under a Creative Commons CC BY‑NC‑ND 4.0 license, permitting users to copy and distribute the content for non‑commercial purposes only, without modification, provided proper credit is given to authors and JCPHS.
-
Redistribution or reuse must preserve the full citation details and include a link to the license. No derivatives, adaptations, or commercial uses are permitted without prior written permission.
References
1. Chu, Y. B., Li, J., Jia, P., Cui, J., Zhang, R., Kang, X., Lv, M., & Zhang, S. (2021). Irf1- and Egr1-activated transcription plays a key role in macrophage polarization: A multiomics sequencing study with partial validation. International immunopharmacology, 99, 108072. https://doi.org/10.1016/j.intimp.2021.108072
2. Luo, Y., Ma, H., Sun, J., Li, X., Wang, H., Qin, M., ... & Li, J. (2026). Inhibition of USAG-1 improved delayed graft function in renal transplantation. Transplant Immunology, 102348.
3. Senior, A. W., Evans, R., Jumper, J., Kirkpatrick, J., Sifre, L., Green, T., et al. (2020). Improved protein structure prediction using potentials from deep learning. Nature, 577(7792), 706–710.
4. Chai, L., Zhang, J., Fernando, W. G. D., Li, H., Huang, X., Cui, C., ... & Jiang, L. (2021). Detection of blackleg resistance gene rlm1 in double-low rapeseed accessions from Sichuan Province, by kompetitive allele-specific PCR. The Plant Pathology Journal, 37(2), 194.
5. Shi, M., & Chow, S. C. (2024). Statistical Analysis for Rating Scale in Clinical Trials. Therapeutic Innovation & Regulatory Science, 58(5), 930-945.
6. Chen, Y., Sun, Y., Zhang, X., Chen, Y., Zhao, S., Shi, M., ... & Peng, M. (2025). A nomogram based on coagulation markers for predicting meige syndrome risk. Frontiers in Aging Neuroscience, 17, 1665276.
7. Zhang, W., Zhu, J., Zhang, Y., Sun, L., Wang, K., Dong, Y., ... & Shang, A. (2025). Personalized prediction of lymph node metastasis in papillary thyroid microcarcinoma: a nomogram and web calculator. Scientific Reports.
8. Xu, X., Bowtell, J., Young, W. R., Fong, D. T., & Williams, G. K. (2025). Distinct patterns in neuromuscular adaptation to repeated perturbations in chronic ankle instability. Journal of NeuroEngineering and Rehabilitation.
9. Xu, X., Bowtell, J., Young, W. R., Fong, D. T., & Williams, G. K. (2026). Increased common corticospinal input during eyes-closed unilateral stance in people with chronic ankle instability. Scientific Reports.
10. Wei, D., Lin, X., & Bresalier, R. S. (2025). Reframing cancer cachexia: the vagal brain–liver axis as a novel neuro-metabolic target. Signal Transduction and Targeted Therapy, 10(1), 370.
11. Chai, L., Li, H., Zhao, X., Cui, C., Zheng, B., Zhang, K., ... & Jiang, L. (2023). Analysis of altered flowering related genes in a multi-silique rapeseed (Brassica napus L.) line zws-ms based on combination of genome, transcriptome and proteome Data. Plants, 12(13), 2429.
12. Li, Yongwei, et al. "Potential Therapeutic Targets for Androgenetic Alopecia (AGA) in Obese Individuals as Revealed by a Gut Microbiome Analysis: A Mendelian Randomization Study." Nutrients 17.11 (2025): 1892.
13. Tao, Xiaoyu, et al. "A structural roadmap to gut health: A comprehensive review of edible insect chitin–protein complexes as alternative protein-derived, structure-specific prebiotics." International Journal of Biological Macromolecules (2026): 151312.
14. Rajpurkar, P., Irvin, J., Zhu, K., Yang, B., Mehta, H., Duan, T., et al. (2017). CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning. arXiv preprint arXiv:1711.05225.
15. Lin, Q., & Cheung, A. (2026). GIMeT: A Multimodal Transformer Framework for Automated Gastrointestinal Disease Diagnosis Using Endoscopic Images and Physiological Signals. Journal of Computer Science and Frontier Technologies, 3(3), 11-27.
16. Ma, H., Sun, J., Li, X., Luo, Y., Liu, J., & Li, J. (2024). Regulatory immune cells in organ transplantation. Frontiers in Immunology, 15, 1383563.
17. Chai, L., Zhang, J., Li, H., Zheng, B., Jiang, J., Cui, C., & Jiang, L. (2020). Investigation for a multi-silique trait in Brassica napus by alternative splicing analysis. PeerJ, 8, e10135.
18. Yu, X., Li, J., Wang, J., Wang, Y., Li, S., Ma, X., ... & Wang, H. (2026). Prediction of risk of hearing loss by industry noise from cross-sectional and longitudinal data. Communications Medicine.
19. Ding, S., Yu, X., Wang, Q., Luo, P., Li, H., Li, Z., ... & Zhang, C. (2025). Multifunctional hydrogel sensors with dynamic covalent networks for machine learning-assisted Parkinson's disease diagnosis and encrypted human-computer interaction. Materials Today Bio, 102524.
20. Thompson, J. D., Higgins, D. G., & Gibson, T. J. (1994). CLUSTAL W: Improving the sensitivity of progressive multiple sequence alignment through sequence weighting, position-specific gap penalties and weight matrix choice. Nucleic Acids Research, 22(22), 4673–4680.
21. Lin, Xinwen, et al. "Homeostatic regulation of T follicular helper and antibody response to particle antigens by IL-1Ra of medullary sinus macrophage origin." Proceedings of the National Academy of Sciences 118.17 (2021): e2019798118.
22. Xu, X., Bowtell, J., Fong, D. T., Young, W. R., & Williams, G. K. (2025). Kinematics of balance controls in people with chronic ankle instability during unilateral stance on a moving platform. Scientific Reports, 15(1), 1126.
23. Yang, Y., Li, G., Zhong, Y., Xu, Q., Chen, B. J., Lin, Y. T., ... & Cai, J. J. (2023). Gene knockout inference with variational graph autoencoder learning single-cell gene regulatory networks. Nucleic acids research, 51(13), 6578-6592.
24. Zhang, W., Xu, Y., Zhao, F., Tarbe, M., Zhou, S., Wang, W., ... & Tang, H. (2020). The pre-existing cellular immunity to Japanese encephalitis virus heterotypically protects mice from Zika virus infection. Science Bulletin, 65(5), 402-409.
25. Eraslan, G., Avsec, Ž., Gagneur, J., & Theis, F. J. (2019). Single-cell transcriptomics meets deep learning. Nature Methods, 16(11), 1083–1091.
26. Wang, J., Faghihpirayesh, R., Golland, P., & Gholipour, A. (2024, October). Spaer: Learning spatio-temporal equivariant representations for fetal brain motion tracking. In International Workshop on Preterm, Perinatal and Paediatric Image Analysis (pp. 3-13). Cham: Springer Nature Switzerland.
27. Lin, X., Twelkmeyer, T., Wang, S. Y., Xu, R. N., Wang, F. S., Zhang, C., & Tang, H. (2020). An immunopathogenic perspective of interleukin-1 signaling. Cellular & Molecular Immunology, 17(8), 892-893.