Abstract
BackgroundAccurate prediction of protein–ligand binding affinity is important for lowering the overall cost of drug discovery in structure-based drug design. For accurate predictions, many classical scoring functions and machine learning-based methods have been developed. However, these techniques tend to have limitations, mainly resulting from a lack of sufficient energy terms to describe the complex interactions between proteins and ligands. Recent deep-learning techniques can potentially solve this problem. However, the search for more efficient and appropriate deep-learning architectures and methods to represent protein–ligand complex is ongoing.ResultsIn this study, we proposed a deep-neural network model to improve the prediction accuracy of protein–ligand complex binding affinity. The proposed model has two important features, descriptor embeddings with information on the local structures of a protein–ligand complex and an attention mechanism to highlight important descriptors for binding affinity prediction. The proposed model performed better than existing binding affinity prediction models on most benchmark datasets.ConclusionsWe confirmed that an attention mechanism can capture the binding sites in a protein–ligand complex to improve prediction performance. Our code is available at https://github.com/Blue1993/BAPA.
Highlights
Accurate prediction of protein–ligand binding affinity is important for lowering the overall cost of drug discovery in structure-based drug design
Seo et al BMC Bioinformatics (2021) 22:542 virtual screening or lead optimization, accurate prediction of binding affinity can reduce the cost of a de novo drug design [3]
This study proposes a deep learning-based model: binding affinity prediction with attention (BAPA), to improve the accuracy of protein–ligand binding affinity prediction
Summary
Accurate prediction of protein–ligand binding affinity is important for lowering the overall cost of drug discovery in structure-based drug design. Many classical scoring functions and machine learning-based methods have been developed These techniques tend to have limitations, mainly resulting from a lack of sufficient energy terms to describe the complex interactions between proteins and ligands. Empirical scoring functions are known to have the best prediction performance among these three categories [10] and exploit the descriptors of various protein–ligand interactions to calculate a binding affinity score. These descriptors generally include hydrogen bonds with desolvation, van der Waals (vdw), and hydrophobic effects. This is primarily because the empirical methods only use few terms related to protein–ligand complexes for easy interpretation of the results, resulting in a failure to describe the actual complexity of protein–ligand complexes [11]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
