Research indexDataset
DTBAffinity_data
Saud
Figshare1 Jan 2025Open access
NobleIDark:/48914/w1/20261005/82F6A2D2DOI10.6084/m9.figshare.29997982
DTBAffinity_data
Saud · Figshare · 2025
NobleIDark:/48914/w1/20261005/82F6A2D2DOI10.6084/m9.figshare.29997982
Free to read at the publisher
You can read the abstract here, or the full text at the publisher.
Abstract
A feature-rich regression pipeline that concatenates chemically meaningful ligand descriptors (RDKit/Mordred physicochemical and topological indices, MACCS keys, Open Babel fingerprints, circular ECFP/Morgan) and SMILES-derived fingerprints/descriptors generated via iFeatureOmega with protein-side features that combine iFeatureOmega sequence descriptors and ESM-1b/ESM-2 embeddings. After sanitization and univariate selection, an XGBoost regressor models continuous affinity on Davis (pKd) and KIBA (KIBA score).