Login / Signup

ELECTRA-DTA: a new compound-protein binding affinity prediction model based on the contextualized sequence encoding.

Junjie WangNaiFeng WenChunyu WangLingling ZhaoLiang Cheng
Published in: Journal of cheminformatics (2022)
We present an end-to-end deep learning framework, ELECTRA-DTA, to predict the binding affinity of drug-target pairs. This framework incorporates an unsupervised learning mechanism to train two ELECTRA-based contextual embedding models, one for protein amino acids and the other for compound SMILES string encoding. In addition, ELECTRA-DTA leverages a squeeze-and-excitation (SE) convolutional neural network block stacked over three fully connected layers to further capture the sequential and spatial features of the protein sequence and SMILES for the DTA regression task. Experimental evaluations show that ELECTRA-DTA outperforms various state-of-the-art DTA prediction models, especially with the challenging, interaction-sparse BindingDB dataset. In target selection and drug repurposing for COVID-19, ELECTRA-DTA also offers competitive performance, suggesting its potential in speeding drug discovery and generalizability for other compound- or protein-related computational tasks.
Keyphrases
  • amino acid
  • deep learning
  • convolutional neural network
  • drug discovery
  • protein protein
  • coronavirus disease
  • sars cov
  • working memory
  • small molecule
  • artificial intelligence
  • adverse drug
  • solar cells