Drug-Target Interaction Prediction via Hierarchical Sequential Cross-Attention over Chemical and Protein Language Models
This paper proposes a sequence-only DTI prediction architecture that combines two pre-trained language models, ChemBERTa for drug SMILES strings and ESM-2 for protein amino acid sequences, with a hierarchical interaction module, and implements a sequential bidirectional cross-attention mechanism inspired by the induced...
Khadidja Henni, Hamza Abdelali, Abdelkrim Aries et al.
· 0 citations