Open access
Sep 2026
Knowledge-Driven Feature Selection with the Grouping–Scoring–Modeling Framework for Biomarker Discovery in High-Dimensional Transcriptomic Data
The Grouping–Scoring–Modeling (G-S-M) framework is proposed, a knowledge-driven pipeline that anchors feature selection in established disease–gene associations that provides a reproducible computational framework for candidate biomarker discovery.
Malik Yousef, Jens Allmer, Yasin Inal et al.
· Applied Sciences · 0 citations