Uncovering subtype-specific metabolic signatures in breast cancer through multimodal integration, attention-based deep learning, and self-organizing maps

Abstract This study integrates multimodal metabolomic data from three platforms—LC–MS, GC–MS, and NMR—to systematically identify biomarkers distinguishing breast cancer subtypes. A feedforward attention-based deep learning model effectively selected 99 significant metabolites, outperforming traditio...

Full description

Bibliographic Details

Published in:	Scientific Reports
Main Authors:	Parisa Shahnazari, Kaveh Kavousi, Hamid Reza Khorram Khorshid, Zarrin Minuchehr, Bahram Goliaei, Reza M. Salek
Format:	Article
Language:	English
Published:	Nature Portfolio 2025-07-01
Subjects:	Multimodal Metabolomics Breast Cancer Subtypes Attention-Based Deep Learning Self-Organizing Map Metabolic Signatures Feature Selection
Online Access:	https://doi.org/10.1038/s41598-025-06459-y