ResBiGAAT: Residual Bi-GRU with attention for protein-ligand binding affinity prediction
This study presents ResBiGAAT, a novel deep learning model that combines a deep Residual Bidirectional Gated Recurrent Unit with two-sided self-attention mechanisms. ResBiGAAT leverages protein and ligand sequence-level features and their physicochemical properties to efficiently predict protein-ligand binding affinity. Through rigorous evaluation using 5-fold cross-validation, we demonstrate the performance of our proposed approach. The model exhibits competitive performance on an external dataset, highlighting its generalizability. Our publicly available web interface, located at resbigaat.streamlit.app, allows users to conveniently input protein and ligand sequences to estimate binding affinity.PMID:37866117 | DOI:10.1016/j.compbiolchem.2023.107969
Source: Computational Biology and Chemistry - Category: Bioinformatics Authors: Gelany Aly Abdelkader Soualihou Ngnamsie Njimbouom Tae-Jin Oh Jeong-Dong Kim Source Type: research
More News: Bioinformatics | Biology | Chemistry | Learning | Study | Universities & Medical Training