E-ABIN: an explainable module for anomaly detection in biological networks
NAR Genomics and Bioinformatics · 2025
DOI: 10.1093/nargab/lqaf135 ↗Kurz gefasst
Fachartikel in der Zeitschrift NAR Genomics and Bioinformatics, 2025. Verfasst von Ugo Lomoio und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Surgical and Medical Sciences, Magna Graecia University, Viale Europa, 88100 Catanzaro, Italy. Hauptthemen laut MEDLINE: Software, Urinary Bladder Neoplasms, Gene Regulatory Networks, Celiac Disease. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: PNRR, Next Generation EU—Italian NRRP, Relatech S.p.A.
Abstract (Originalsprache)
The increasing availability of large-scale omics data calls for robust analytical frameworks capable of handling complex gene expression datasets while offering interpretable results. Recent advances in artificial intelligence have enabled the identification of aberrant molecular patterns distinguishing disease states from healthy controls. Coupled with improvements in model interpretability, these tools now support the identification of genes potentially driving disease phenotypes. However, current approaches to gene anomaly detection often remain limited to single datasets and lack accessible graphical interfaces. We introduce E-ABIN, a general-purpose, explainable framework for anomaly detection in biological networks. E-ABIN combines classical machine learning and graph-based deep learning techniques within a unified, user-friendly platform, enabling the detection and interpretation of anomalies from gene expression or methylation-derived networks. By integrating algorithms such as support vector machines, random forests, graph autoencoders, and graph adversarial attributed networks, E-ABIN ensures high predictive accuracy while maintaining interpretability. We demonstrate the utility of E-ABIN through case studies of bladder cancer and celiac disease, where it effectively uncovers biologically relevant anomalies and offers insights into disease mechanisms. E-ABIN is freely available on the Zenodo platform at https://doi.org/10.5281/zenodo.17062501.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Surgical and Medical Sciences, Magna Graecia University, Viale Europa, 88100 Catanzaro, Italy.
- Relatech, 87036 Rende, Italy.
- Computational Biology and Bioinformatics Unit, Fondazione Policlinico Universitario A. Gemelli IRCCS, 00168 Roma, Italy.
- DIMES, University of Calabria, 87036 Rende, Italy.
ORCID-Profile: Pietro Hiram Guzzi
Förderung
- PNRR
- Next Generation EU—Italian NRRP
- Relatech S.p.A
Zitieren
APA
Lomoio, U., Mazza, T., Veltri, P., & Guzzi, P. H. (2025). E-ABIN: an explainable module for anomaly detection in biological networks. NAR Genomics and Bioinformatics. https://doi.org/10.1093/nargab/lqaf135
Vancouver
Lomoio U, Mazza T, Veltri P, Guzzi PH. E-ABIN: an explainable module for anomaly detection in biological networks. NAR Genomics and Bioinformatics. 2025. doi:10.1093/nargab/lqaf135
BibTeX
@article{Lomoio2025,
author = {Lomoio, Ugo and Mazza, Tommaso and Veltri, Pierangelo and Guzzi, Pietro Hiram},
title = {E-ABIN: an explainable module for anomaly detection in biological networks},
journal = {NAR Genomics and Bioinformatics},
year = {2025},
doi = {10.1093/nargab/lqaf135}
}
EUVIMED