EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PreFold-dG: estimating binding affinity of protein–protein interaction from intermediate representations of protein folding model

Sungjoon Park, Soorin Yim, Dongyun Kim, Kiwoong Yoo, Doyeong Hwang, Kyungwook Lee, Jongseong Jang, Kiyoung Kim

Bioinformatics · 2026

DOI: 10.1093/bioinformatics/btag489 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Sungjoon Park und 7 weiteren Autor:innen. Beteiligte Einrichtung: Bio Intelligence Lab, LG AI Research, Seoul, 07789, Republic of Korea. Hauptthemen laut MEDLINE: Protein Folding, Proteins, Computational Biology, Software. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute of Information & Communications Technology Planning & Evaluation, Ministry of Science and ICT.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Binding affinity governs how proteins interact and underlies essential biological processes. Computational approaches have been developed to simulate and predict protein binding, but the scarcity of high-quality data has imposed significant constraints. One consequence is that most methods focus on predicting mutational changes in binding affinity (ΔΔG), rather than binding affinity (ΔG) itself. This practice risks overfitting to skewed data distributions, limiting the generalizability of predictions. Recent advances in protein structure prediction have enabled computational modeling of protein conformations in mass, providing rich structural information from which binding interactions can be largely explained. However, leveraging these advances for effective prediction of binding affinity has yet to translate into reliable predictions. Results We present PreFold-dG, a model that estimates binding affinities of protein complexes utilizing intermediate embeddings from Boltz-2, an open-source foundation model for protein structure prediction. Our approach aggregates residue-level information weighted by interresidue distance, and predicts ΔG directly rather than its derivative, ΔΔG. PreFold-dG achieved state-of-the-art performance on well-established binding affinity prediction benchmarks and demonstrated robustness on independent test sets. Ablation studies suggest that all intermediate embeddings are utilized in the prediction, whereas their contributions to modeling ΔΔG and ΔG vary. We further validated our model through case studies on real-world broadly neutralizing antibody data with evolutionary relevance. Availability https://github.com/LGAI-Research/PreFold-dG.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Protein FoldingProteinsComputational BiologySoftwareProtein Interaction MappingProtein BindingModels, MolecularProtein Conformation

Substanzen

Proteins

Autor:innen und Institutionen

  • Bio Intelligence Lab, LG AI Research, Seoul, 07789, Republic of Korea.
  • School of Biological Science, Seoul National University, Seoul, 08826, Republic of Korea.

Förderung

  • Institute of Information & Communications Technology Planning & Evaluation
  • Ministry of Science and ICT

Zitieren

APA

Park, S., Yim, S., Kim, D., Yoo, K., Hwang, D., Lee, K., Jang, J., & Kim, K. (2026). PreFold-dG: estimating binding affinity of protein–protein interaction from intermediate representations of protein folding model. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag489

Vancouver

Park S, Yim S, Kim D, Yoo K, Hwang D, Lee K, et al. PreFold-dG: estimating binding affinity of protein–protein interaction from intermediate representations of protein folding model. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag489

BibTeX
@article{Park2026,
  author = {Park, Sungjoon and Yim, Soorin and Kim, Dongyun and Yoo, Kiwoong and Hwang, Doyeong and Lee, Kyungwook and Jang, Jongseong and Kim, Kiyoung},
  title = {PreFold-dG: estimating binding affinity of protein–protein interaction from intermediate representations of protein folding model},
  journal = {Bioinformatics},
  year = {2026},
  doi = {10.1093/bioinformatics/btag489}
}
Kostenlos starten →