Genes That Reliably Differentiate Liver‐Fibrosis Stages Identified Using a Novel Integrated Statistical and Machine‐Learning Algorithm
Genetic Epidemiology · 2026-12 · 50 (8)
DOI: 10.1002/gepi.70064 ↗Kurz gefasst
Fachartikel in der Zeitschrift Genetic Epidemiology, online erschienen am 16.11.2026. Verfasst von Vivekananda Mallik und 5 weiteren Autor:innen. Beteiligte Einrichtung: John C. Martin Center for Liver Research and Innovations, Kolkata, India. Hauptthemen laut MEDLINE: Liver Cirrhosis, Machine Learning. Die Arbeit nennt 40 Literaturangaben. Gefördert von: Indian Council of Medical Research.
Abstract (Originalsprache)
Accurate prediction of stage of liver fibrosis is essential for risk stratification and management of metabolic dysfunction–associated steatotic liver disease (MASLD). However, previously reported genomic and transcriptomic predictors of fibrosis‐stage have shown limited reproducibility. We aimed to identify robust biomarkers predictive of the stage (mild [F1] or advanced [F3 or F4]) of fibrosis. Transcriptomic data were curated from public repositories using stringent quality‐control procedures to generate high‐quality whole‐transcriptome profiles from 278 patients (F1: n = 139; F3: n = 109; F4: n = 30). Samples were randomly divided into equal‐sized discovery and validation cohorts. To distinguish mild from advanced fibrosis, we initially applied linear discriminant analysis (LDA) and support vector machine (SVM) classification with recursive backward feature elimination (RFE). These approaches yielded suboptimal results; both LDA and SVM‐RFE required large gene sets—74 and 88 genes, respectively—but with limited percentages of correct classification of patients with mild and advanced fibrosis—69.78% and 79.86%, respectively. We, therefore, developed a novel integrative algorithm combining LDA pre‐screening and SVM‐Elastic Net with cross validation. This algorithm identified 20 genes whose expression‐levels—that were not significantly correlated—achieved an accuracy of 85.61% (AUC = 0.8892) in classifying patients with mild and advanced stages of liver fibrosis in an independent dataset. We also assessed classification performance using a Multilayer Perceptron and an SVM with an RBF kernel—both non‐linear classifiers—that achieved accuracies of 82.3% (average) and 81.29%, respectively; both accuracies are less than that achieved by SVM‐EN. Of the 20 genes identified by us, previous studies have strongly implicated 10 genes in liver fibrosis, while the remaining 10 genes are novel in the context of involvement in liver fibrosis and require confirmation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- John C. Martin Center for Liver Research and Innovations, Kolkata, India.
- Indian Statistical Institute, Kolkata, India.
ORCID-Profile: Vivekananda Mallik, Ankita Chatterjee, Nikhil Ranjan Pal, Partha P Majumder
Förderung
- Indian Council of Medical Research
Zitieren
APA
Mallik, V., Naskar, P., Chowdhury, A., Chatterjee, A., Pal, N. R., & Majumder, P. P. (2026). Genes That Reliably Differentiate Liver‐Fibrosis Stages Identified Using a Novel Integrated Statistical and Machine‐Learning Algorithm. Genetic Epidemiology, 50(8). https://doi.org/10.1002/gepi.70064
Vancouver
Mallik V, Naskar P, Chowdhury A, Chatterjee A, Pal NR, Majumder PP. Genes That Reliably Differentiate Liver‐Fibrosis Stages Identified Using a Novel Integrated Statistical and Machine‐Learning Algorithm. Genetic Epidemiology. 2026;50(8). doi:10.1002/gepi.70064
BibTeX
@article{Mallik2026,
author = {Mallik, Vivekananda and Naskar, Pranoy and Chowdhury, Abhijit and Chatterjee, Ankita and Pal, Nikhil Ranjan and Majumder, Partha P},
title = {Genes That Reliably Differentiate Liver‐Fibrosis Stages Identified Using a Novel Integrated Statistical and Machine‐Learning Algorithm},
journal = {Genetic Epidemiology},
year = {2026},
volume = {50},
number = {8},
doi = {10.1002/gepi.70064}
}
EUVIMED