Open access
Aug 2026
A hybrid high activity aware framework integrating graph attention network and transformer for half maximal inhibitory concentration prediction
Experimental results demonstrate that HGATT outperforms not only individual graph neural network (GNN)- and machine learning-based models but also other related drug-target prediction methods and baseline regression approaches, exhibiting superior predictive accuracy.
D. Ban, Lu Pan, Xue-Li Zhang et al.
· Frontiers in Immunology · 0 citations