The method predicting interaction between protein targets and small-molecular ligands with the wide applicability domain. (June 2022)

• Record Type: Journal Article
• Authors: Karasev, Dmitry A.; Sobolev, Boris N.; Lagunin, Alexey A.; Filimonov, Dmitry A.; Poroikov, Vladimir V.
• Is Part Of: Computational biology and chemistry. Volume 98(2022)
• Publication Date: 2022-06
• Subjects: Proteochemometrics -- Protein-ligand interaction -- Drug design -- Datasets' heterogeneity; Chemistry -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; Biochemistry -- Data processing; Biology -- Data processing; Molecular biology -- Data processing; Periodicals; Electronic journals; 542.85
• DOI: 10.1016/j.compbiolchem.2022.107674
• Languages: English
• ISSNs: 1476-9271

Abstract

Abstract: Prediction of protein-ligand interaction is necessary for drug design, gene regulatory networks investigation, and chemical probes detection. The existing methods commonly demonstrate high prediction accuracy for the particular groups of protein and their ligands. We developed an approach suited for the wider applicability and tested it on three dataset types significantly differing by protein homology. The study included three typical scenarios of assessing the target-ligand interaction: 1 st - predicting protein targets by ligand structures' comparisons; 2 nd - predicting ligands by target sequences' comparisons; 3 rd - predicting both the uncharacterized targets and ligands with the fuzzy coefficients based on ligand comparisons. The 1 st scenario implemented showed a high prediction accuracy of 0.96–0.99, providing fuzzy coefficients of target-ligand interactions in the 3 rd scenario. Testing by 2 nd scenario displayed the accuracy of 0.97–0.99 for predicting within the particular protein families, sets non-ordered by protein homology, and accuracy higher than 0.90 for most HIV sets, each presenting the close mutant proteins differing by point substitutions. The 3 rd scenario displayed that fuzzy classification can reveal reasonable accuracy 0.86–0.94 at simulated data incompleteness. Thus, our approach provides high prediction accuracy with the wide applicability domain, including data differing in heterogeneity and completeness. Graphical Abstract: ga1 Highlights: The developed method enables predicting protein-ligand interactions within the vast applicability domain. Our approach provides in silico assessment of the protein-ligand interaction under the three typical scenarios. The approach accurately predicts target-ligand binding for protein groups differing in phylogenetic relations.