VisionDES is a vision-oriented Dynamic Ensemble Selection (DES) framework that adapts classical DES techniques to modern deep learning pipelines.
-
Updated
Jun 1, 2026 - HTML
VisionDES is a vision-oriented Dynamic Ensemble Selection (DES) framework that adapts classical DES techniques to modern deep learning pipelines.
Evidence-aware somatic variant pathogenicity classifier using topology (TDA), fractal (FCGR) features, and dynamic ensemble selection (KNORA). MCC=0.8702, AUROC=0.9666 on 207K variants from dbNSFP v5.3a.
Add a description, image, and links to the dynamic-ensemble-selection topic page so that developers can more easily learn about it.
To associate your repository with the dynamic-ensemble-selection topic, visit your repo's landing page and select "manage topics."