EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Evaluating data partitioning strategies for accurate prediction of protein-ligand binding free energy changes in mutated proteins

Liangxu Xie, Guoming Bao, Dawei Zhang, Lei Xu, Xiaojun Xu, Shan Chang

Computational and Structural Biotechnology Journal · 01.01.2025 · 27 · 4418-4430

DOI: 10.1016/j.csbj.2025.10.020 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computational and Structural Biotechnology Journal, online erschienen am 18.10.2025. Verfasst von Liangxu Xie und 5 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Bioinformatics and Medical Engineering, Jiangsu University of Technology, Changzhou 213001, China. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 82 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Jiangsu Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate prediction of the relative free energy of protein-ligand binding, especially regarding protein mutations, is vital for drug design and interpreting drug resistance. However, machine learning (ML) / deep learning (DL) methods often struggle with generalization due to dataset partitioning strategy. Random data partitioning potentially produces spuriously high correlations that inflate performance estimates. UniProt-based splitting preserves data independence but lacks high prediction accuracy. In this study, we first evaluate six distinct ML/DL models on the MdrDB database using two data partitioning methods. Protein sequences are embedded using the ESM-2 protein large language model, integrating wild-type and mutant features. Although all models show high predictive correlations (Pearson coefficients up to 0.70) under random partitioning, their performance declines with UniProt-based partitioning. To address this issue, we propose a query-anchor pairwise learning framework, utilizing known states as anchor points for predicting unknown query states. The proposed method is validated across three systems, revealing that even a small amount of reference data can significantly enhance prediction accuracy. This enhancement suggests that leveraging known states as anchor points allows for more precise predicting of unknown query states.

Schlagwörter

Stichwörter der Autor:innen

Data partitioning strategyMutant proteinsProtein language modelRelative free energy

Autor:innen und Institutionen

  • Institute of Bioinformatics and Medical Engineering, Jiangsu University of Technology, Changzhou 213001, China.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Jiangsu Province

Zitieren

APA

Xie, L., Bao, G., Zhang, D., Xu, L., Xu, X., & Chang, S. (2025). Evaluating data partitioning strategies for accurate prediction of protein-ligand binding free energy changes in mutated proteins. Computational and Structural Biotechnology Journal, 27, 4418-4430. https://doi.org/10.1016/j.csbj.2025.10.020

Vancouver

Xie L, Bao G, Zhang D, Xu L, Xu X, Chang S. Evaluating data partitioning strategies for accurate prediction of protein-ligand binding free energy changes in mutated proteins. Computational and Structural Biotechnology Journal. 2025;27:4418-4430. doi:10.1016/j.csbj.2025.10.020

BibTeX
@article{Xie2025,
  author = {Xie, Liangxu and Bao, Guoming and Zhang, Dawei and Xu, Lei and Xu, Xiaojun and Chang, Shan},
  title = {Evaluating data partitioning strategies for accurate prediction of protein-ligand binding free energy changes in mutated proteins},
  journal = {Computational and Structural Biotechnology Journal},
  year = {2025},
  volume = {27},
  pages = {4418--4430},
  doi = {10.1016/j.csbj.2025.10.020}
}
Kostenlos starten →