Multi-Omics Feature Selection to Identify Biomarkers for Hepatocellular Carcinoma
Metabolites · 28.08.2025 · 15 (9) · 575
DOI: 10.3390/metabo15090575 ↗Kurz gefasst
Fachartikel in der Zeitschrift Metabolites, online erschienen am 28.08.2025. Verfasst von Rency S Varghese und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Oncology, Lombardi Comprehensive Cancer Center, Georgetown University Medical Center, Washington, DC 20057, USA. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIGMS NIH HHS, NIH HHS, the National Institutes of Health (NIH).
Abstract (Originalsprache)
Introduction
Hepatocellular carcinoma (HCC), the most prevalent form of liver cancer, ranks as the third leading cause of mortality globally. Patients diagnosed with HCC exhibit a dismal prognosis mostly due to the emergence of symptoms in the advanced stages of the disease. Moreover, conventional biomarkers demonstrate insufficient efficacy in the early detection of HCC, hence highlighting the need for the identification of novel and more effective biomarkers.
Methods
In this paper, we investigate methods for integration of multi-omics data we generated by both untargeted and targeted mass spectrometric analysis of serum samples from HCC cases and patients with liver cirrhosis. Specifically, the performances of several feature selection methods are evaluated on their abilities to identify a panel of multi-omics features that distinguish HCC cases from cirrhotic controls.
Results
The integrative analysis identified key molecules associated with liver including such as leucine and isoleucine as well as SERPINA1, which is involved in LXR/RXR Activation and Acute Response signaling. A new method that uses recursive feature selection in conjunction with a transformer-based deep learning model as an estimator led to more promising results compared to other deep learning methods that perform disease classification and feature selection sequentially.
Conclusions
The findings in this study reinforce the importance of adapting or extending deep learning models to support robust feature selection, especially for integration of multi-omics data with limited sample size to avoid the risk of overfitting and the need for evaluation of the multi-omics features discovered in this study via blood samples from a larger and independent cohort to identify robust biomarkers for HCC.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Oncology, Lombardi Comprehensive Cancer Center, Georgetown University Medical Center, Washington, DC 20057, USA.
- MedStar Georgetown Transplant Institute, MedStar Georgetown University Hospital and the Center for Translational Transplant Medicine, Georgetown University Medical Center, Washington, DC 20057, USA.
ORCID-Profile: Rency S Varghese, Sarada Giridharan, Habtom W Ressom
Förderung
- NIGMS NIH HHS
- NIH HHS
- the National Institutes of Health (NIH)
Zitieren
APA
Varghese, R. S., Zhang, X., Giridharan, S., Sajid, M. S., Rashid, M. M., Kroemer, A., & Ressom, H. W. (2025). Multi-Omics Feature Selection to Identify Biomarkers for Hepatocellular Carcinoma. Metabolites, 15(9), 575. https://doi.org/10.3390/metabo15090575
Vancouver
Varghese RS, Zhang X, Giridharan S, Sajid MS, Rashid MM, Kroemer A, et al. Multi-Omics Feature Selection to Identify Biomarkers for Hepatocellular Carcinoma. Metabolites. 2025;15(9):575. doi:10.3390/metabo15090575
BibTeX
@article{Varghese2025,
author = {Varghese, Rency S and Zhang, Xinran and Giridharan, Sarada and Sajid, Muhammad Salman and Rashid, Md Mamunur and Kroemer, Alexander and Ressom, Habtom W},
title = {Multi-Omics Feature Selection to Identify Biomarkers for Hepatocellular Carcinoma},
journal = {Metabolites},
year = {2025},
volume = {15},
number = {9},
pages = {575},
doi = {10.3390/metabo15090575}
}
EUVIMED