BERT4DTI : BERT-based Model for Predicting Drug-Protein Interactions
BERT4DTI is presented, which encodes SMILES strings with ChemBERTa and amino-acid sequences with ProtBERT, applies bidirectional mutual attention between token-level representations, and classifies the resulting interaction features using convolutional layers and a multilayer perceptron.
Thanina Hamitouch, Khadidja Henni, Abdelkrim Arie et al.
· 0 citations