The Algebraic Extended Atom-type Graph-based Model for Precise Ligand-receptor Binding Affinity Prediction

Overview

Journal J Cheminform

Publisher Biomed Central

Date 2025 Jan 23

PMID 39844277

Authors

Farjana Tasnim Mukta

Md Masud Rana

Avery Meyer

Sally Ellingson

Duc D Nguyen

Affiliations

Soon will be listed here.

Abstract

Accurate prediction of ligand-receptor binding affinity is crucial in structure-based drug design, significantly impacting the development of effective drugs. Recent advances in machine learning (ML)-based scoring functions have improved these predictions, yet challenges remain in modeling complex molecular interactions. This study introduces the AGL-EAT-Score, a scoring function that integrates extended atom-type multiscale weighted colored subgraphs with algebraic graph theory. This approach leverages the eigenvalues and eigenvectors of graph Laplacian and adjacency matrices to capture high-level details of specific atom pairwise interactions. Evaluated against benchmark datasets such as CASF-2016, CASF-2013, and the Cathepsin S dataset, the AGL-EAT-Score demonstrates notable accuracy, outperforming existing traditional and ML-based methods. The model's strength lies in its comprehensive similarity analysis, examining protein sequence, ligand structure, and binding site similarities, thus ensuring minimal bias and over-representation in the training sets. The use of extended atom types in graph coloring enhances the model's capability to capture the intricacies of protein-ligand interactions. The AGL-EAT-Score marks a significant advancement in drug design, offering a tool that could potentially refine and accelerate the drug discovery process.Scientific Contribution The AGL-EAT-Score presents an algebraic graph-based framework that predicts ligand-receptor binding affinity by constructing multiscale weighted colored subgraphs from the 3D structure of protein-ligand complexes. It improves prediction accuracy by modeling interactions between extended atom types, addressing challenges like dataset bias and over-representation. Benchmark evaluations demonstrate that AGL-EAT-Score outperforms existing methods, offering a robust and systematic tool for structure-based drug design.

References

Mason O, Verwoerd M . Graph theory and networks in Biology. IET Syst Biol. 2007; 1(2):89-119. DOI: 10.1049/iet-syb:20060038. View

Su M, Feng G, Liu Z, Li Y, Wang R . Tapping on the Black Box: How Is the Scoring Power of a Machine-Learning Scoring Function Dependent on the Training Set?. J Chem Inf Model. 2020; 60(3):1122-1136. DOI: 10.1021/acs.jcim.9b00714. View

Parks C, Gaieb Z, Chiu M, Yang H, Shao C, Walters W . D3R grand challenge 4: blind prediction of protein-ligand poses, affinity rankings, and relative binding free energies. J Comput Aided Mol Des. 2020; 34(2):99-119. PMC: 7261493. DOI: 10.1007/s10822-020-00289-y. View

Beard H, Cholleti A, Pearlman D, Sherman W, Loving K . Applying physics-based scoring to calculate free energies of binding for single amino acid mutations in protein-protein complexes. PLoS One. 2013; 8(12):e82849. PMC: 3858304. DOI: 10.1371/journal.pone.0082849. View

Eldridge M, MURRAY C, Auton T, Paolini G, Mee R . Empirical scoring functions: I. The development of a fast empirical scoring function to estimate the binding affinity of ligands in receptor complexes. J Comput Aided Mol Des. 1997; 11(5):425-45. DOI: 10.1023/a:1007996124545. View

Huang C, Chang P, Hsu C, Huang C, Ng K . Drug repositioning for non-small cell lung cancer by using machine learning algorithms and topological graph theory. BMC Bioinformatics. 2016; 17 Suppl 1:2. PMC: 4895785. DOI: 10.1186/s12859-015-0845-0. View

Cang Z, Wei G . TopologyNet: Topology based deep convolutional and multi-task neural networks for biomolecular property predictions. PLoS Comput Biol. 2017; 13(7):e1005690. PMC: 5549771. DOI: 10.1371/journal.pcbi.1005690. View

Durant G, Boyles F, Birchall K, Marsden B, Deane C . Robustly interrogating machine learning-based scoring functions: what are they learning?. Bioinformatics. 2025; 41(2). PMC: 11821266. DOI: 10.1093/bioinformatics/btaf040. View

Wang R, Nguyen D, Wei G . Persistent spectral graph. Int J Numer Method Biomed Eng. 2020; 36(9):e3376. PMC: 7719081. DOI: 10.1002/cnm.3376. View

10.

Moore G, Howell S, Brady M, Xu X, McNeil K . Anomalous collapses of Nares Strait ice arches leads to enhanced export of Arctic sea ice. Nat Commun. 2021; 12(1):1. PMC: 7782487. DOI: 10.1038/s41467-020-20314-w. View

10.

Verkhivker G, Appelt K, FREER S, Villafranca J . Empirical free energy calculations of ligand-protein crystallographic complexes. I. Knowledge-based ligand-protein interaction potentials applied to the prediction of human immunodeficiency virus 1 protease binding affinity. Protein Eng. 1995; 8(7):677-91. DOI: 10.1093/protein/8.7.677. View

11.

Nguyen D, Wei G . DG-GL: Differential geometry-based geometric learning of molecular datasets. Int J Numer Method Biomed Eng. 2019; 35(3):e3179. PMC: 6598676. DOI: 10.1002/cnm.3179. View

12.

Moon S, Zhung W, Yang S, Lim J, Kim W . PIGNet: a physics-informed deep learning model toward generalized drug-target interaction predictions. Chem Sci. 2022; 13(13):3661-3673. PMC: 8966633. DOI: 10.1039/d1sc06946b. View

13.

Gramatica R, Matteo T, Giorgetti S, Barbiani M, Bevec D, Aste T . Graph theory enables drug repurposing--how a mathematical model can drive the discovery of hidden mechanisms of action. PLoS One. 2014; 9(1):e84912. PMC: 3886994. DOI: 10.1371/journal.pone.0084912. View

14.

Stepniewska-Dziubinska M, Zielenkiewicz P, Siedlecki P . Development and evaluation of a deep learning model for protein-ligand binding affinity prediction. Bioinformatics. 2018; 34(21):3666-3674. PMC: 6198856. DOI: 10.1093/bioinformatics/bty374. View

15.

Li H, Lu G, Sze K, Su X, Chan W, Leung K . Machine-learning scoring functions trained on complexes dissimilar to the test set already outperform classical counterparts on a blind benchmark. Brief Bioinform. 2021; 22(6). PMC: 8575004. DOI: 10.1093/bib/bbab225. View

15.

Vassura M, Di Lena P, Margara L, Mirto M, Aloisio G, Fariselli P . Blurring contact maps of thousands of proteins: what we can learn by reconstructing 3D structure. BioData Min. 2011; 4(1):1. PMC: 3033854. DOI: 10.1186/1756-0381-4-1. View

16.

Meng Z, Xia K . Persistent spectral-based machine learning (PerSpect ML) for protein-ligand binding affinity prediction. Sci Adv. 2021; 7(19). PMC: 8104863. DOI: 10.1126/sciadv.abc5329. View

17.

Hawkins P, Skillman A, Nicholls A . Comparison of shape-matching and docking as virtual screening tools. J Med Chem. 2007; 50(1):74-82. DOI: 10.1021/jm0603365. View

18.

Cang Z, Mu L, Wei G . Representability of algebraic topology for biomolecules in machine learning based scoring and virtual screening. PLoS Comput Biol. 2018; 14(1):e1005929. PMC: 5774846. DOI: 10.1371/journal.pcbi.1005929. View