Luoshu Geometric Framework for Protein Druggability Prediction: Polynomial Interaction Terms, Higher-Order Curvature Features, and Rigorous Statistical Validation on 123 Structurally Diverse Proteins
Abstract
We present the Luoshu Geometric Framework for protein druggability prediction. Key results (n=123, Drug=87, Undrug=36): ROC-AUC=0.861 (95% CI [0.778,0.930]), PR-AUC=0.928 (95% CI [0.868,0.974]), F1=0.874, perm-p
Fields of Study & Subjects
Computational Drug Discovery Methods
Protein Structure and Dynamics
Machine Learning in Bioinformatics
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 8 May 2026
- Document type
- Preprint