Effects of similarity networks in graph-based multi-omics classification
PLOS One · 19.03.2026 · 21 (3) · e0344754
DOI: 10.1371/journal.pone.0344754 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 19.03.2026. Verfasst von Masrafe Bin Hannan Siam und 4 weiteren Autor:innen. Beteiligte Einrichtung: Data Science Lab, Department of Software Engineering, Daffodil International University, Daffodil Smart City, Birulia, Dhaka, Bangladesh. Hauptthemen laut MEDLINE: Multiomics, Computational Biology. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Accurate classification of disease subtypes is a fundamental requirement of precision medicine especially for complex and heterogeneous conditions such as breast cancer and Alzheimer’s disease. Recent advances in graph-based deep learning have shown strong potential in multi-omics integration by modeling inter-sample relationships through similarity networks. Yet, the question of how best to construct these networks remains an open and underexplored challenge. In this work, we present a systematic evaluation of six distinct similarity network construction strategies including Cosine Similarity, Cosine Distance, RBF-based measures, and two hybrid combinations leveraging a graph convolutional network (GCN) integrated with a view correlation discovery network (VCDN) framework for multi-omics disease classification. Using two benchmark datasets (BRCA and ROSMAP), we assessed the impact of each method on classification performance, variance across runs, and statistical robustness. Surprisingly, our results demonstrate that Cosine Similarity outperforms all other metrics, consistently achieving the highest accuracy, F1-score, and AUC, while also showing the lowest standard deviation across cross-validation splits. Despite the growing popularity of kernel-based and hybrid similarity designs, our findings highlight the unique effectiveness of simple angular similarity in capturing biologically meaningful structure in high-dimensional omics data. In our study, we showed that simple yet biologically meaningful similarity measures like Cosine Similarity can outperform more complex techniques in accuracy, consistency, and clarity. This insight sets the stage for building more effective and interpretable graph-based models to support precision medicine.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Data Science Lab, Department of Software Engineering, Daffodil International University, Daffodil Smart City, Birulia, Dhaka, Bangladesh.
ORCID-Profile: Masrafe Bin Hannan Siam, Md Fazla Elahe
Zitieren
APA
Siam, M. B. H., Khan, M. R., Elahe, M. F., Arman, M. S., & Akter, S. (2026). Effects of similarity networks in graph-based multi-omics classification. PLOS One, 21(3), e0344754. https://doi.org/10.1371/journal.pone.0344754
Vancouver
Siam MBH, Khan MR, Elahe MF, Arman MS, Akter S. Effects of similarity networks in graph-based multi-omics classification. PLOS One. 2026;21(3):e0344754. doi:10.1371/journal.pone.0344754
BibTeX
@article{Siam2026,
author = {Siam, Masrafe Bin Hannan and Khan, Md Rayhan and Elahe, Md Fazla and Arman, Md Shohel and Akter, Swarna},
title = {Effects of similarity networks in graph-based multi-omics classification},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {3},
pages = {e0344754},
doi = {10.1371/journal.pone.0344754}
}
EUVIMED