Ensembling methods for protein-ligand binding affinity prediction

Abstract Protein-ligand binding affinity prediction is a key element of computer-aided drug discovery. Most of the existing deep learning methods for protein-ligand binding affinity prediction utilize single models and suffer from low accuracy and generalization capability. In this paper, we train 1...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiffriya Mohamed Abdul Cader, M. A. Hakim Newton, Julia Rahman, Akmal Jahan Mohamed Abdul Cader, Abdul Sattar
Format: Article
Language:English
Published: Nature Portfolio 2024-10-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-024-72784-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850181536745259008
author Jiffriya Mohamed Abdul Cader
M. A. Hakim Newton
Julia Rahman
Akmal Jahan Mohamed Abdul Cader
Abdul Sattar
author_facet Jiffriya Mohamed Abdul Cader
M. A. Hakim Newton
Julia Rahman
Akmal Jahan Mohamed Abdul Cader
Abdul Sattar
author_sort Jiffriya Mohamed Abdul Cader
collection DOAJ
description Abstract Protein-ligand binding affinity prediction is a key element of computer-aided drug discovery. Most of the existing deep learning methods for protein-ligand binding affinity prediction utilize single models and suffer from low accuracy and generalization capability. In this paper, we train 13 deep learning models from combinations of 5 input features. Then, we explore all possible ensembles of the trained models to find the best ensembles. Our deep learning models use cross-attention and self-attention layers to extract short and long-range interactions. Our method is named Ensemble Binding Affinity (EBA). EBA extracts information from various models using different combinations of input features, such as simple 1D sequential and structural features of the protein-ligand complexes rather than 3D complex features. EBA is implemented to accurately predict the binding affinity of a protein-ligand complex. One of our ensembles achieves the highest Pearson correlation coefficient (R) value of 0.914 and the lowest root mean square error (RMSE) value of 0.957 on the well-known benchmark test set CASF2016. Our ensembles show significant improvements of more than 15% in R-value and 19% in RMSE on both well-known benchmark CSAR-HiQ test sets over the second-best predictor named CAPLA. Furthermore, the superior performance of the ensembles across all metrics compared to existing state-of-the-art protein-ligand binding affinity prediction methods on all five benchmark test datasets demonstrates the effectiveness and robustness of our approach. Therefore, our approach to improving binding affinity prediction between proteins and ligands can contribute to improving the success rate of potential drugs and accelerate the drug development process.
format Article
id doaj-art-0b903dadb99e4327be50e498b6f6ddae
institution OA Journals
issn 2045-2322
language English
publishDate 2024-10-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-0b903dadb99e4327be50e498b6f6ddae2025-08-20T02:17:53ZengNature PortfolioScientific Reports2045-23222024-10-0114111910.1038/s41598-024-72784-3Ensembling methods for protein-ligand binding affinity predictionJiffriya Mohamed Abdul Cader0M. A. Hakim Newton1Julia Rahman2Akmal Jahan Mohamed Abdul Cader3Abdul Sattar4School of Information and Communication Technology, Griffith UniversityInstitute for Integrated and Intelligent Systems (IIIS), Griffith UniversitySchool of Information and Communication Technology, Griffith UniversityDepartment of Computer Science, Faculty of Applied Sciences, South Eastern University of Sri LankaSchool of Information and Communication Technology, Griffith UniversityAbstract Protein-ligand binding affinity prediction is a key element of computer-aided drug discovery. Most of the existing deep learning methods for protein-ligand binding affinity prediction utilize single models and suffer from low accuracy and generalization capability. In this paper, we train 13 deep learning models from combinations of 5 input features. Then, we explore all possible ensembles of the trained models to find the best ensembles. Our deep learning models use cross-attention and self-attention layers to extract short and long-range interactions. Our method is named Ensemble Binding Affinity (EBA). EBA extracts information from various models using different combinations of input features, such as simple 1D sequential and structural features of the protein-ligand complexes rather than 3D complex features. EBA is implemented to accurately predict the binding affinity of a protein-ligand complex. One of our ensembles achieves the highest Pearson correlation coefficient (R) value of 0.914 and the lowest root mean square error (RMSE) value of 0.957 on the well-known benchmark test set CASF2016. Our ensembles show significant improvements of more than 15% in R-value and 19% in RMSE on both well-known benchmark CSAR-HiQ test sets over the second-best predictor named CAPLA. Furthermore, the superior performance of the ensembles across all metrics compared to existing state-of-the-art protein-ligand binding affinity prediction methods on all five benchmark test datasets demonstrates the effectiveness and robustness of our approach. Therefore, our approach to improving binding affinity prediction between proteins and ligands can contribute to improving the success rate of potential drugs and accelerate the drug development process.https://doi.org/10.1038/s41598-024-72784-3
spellingShingle Jiffriya Mohamed Abdul Cader
M. A. Hakim Newton
Julia Rahman
Akmal Jahan Mohamed Abdul Cader
Abdul Sattar
Ensembling methods for protein-ligand binding affinity prediction
Scientific Reports
title Ensembling methods for protein-ligand binding affinity prediction
title_full Ensembling methods for protein-ligand binding affinity prediction
title_fullStr Ensembling methods for protein-ligand binding affinity prediction
title_full_unstemmed Ensembling methods for protein-ligand binding affinity prediction
title_short Ensembling methods for protein-ligand binding affinity prediction
title_sort ensembling methods for protein ligand binding affinity prediction
url https://doi.org/10.1038/s41598-024-72784-3
work_keys_str_mv AT jiffriyamohamedabdulcader ensemblingmethodsforproteinligandbindingaffinityprediction
AT mahakimnewton ensemblingmethodsforproteinligandbindingaffinityprediction
AT juliarahman ensemblingmethodsforproteinligandbindingaffinityprediction
AT akmaljahanmohamedabdulcader ensemblingmethodsforproteinligandbindingaffinityprediction
AT abdulsattar ensemblingmethodsforproteinligandbindingaffinityprediction