EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MAKA-Map: Real-Valued Distance Prediction for Protein Folding Mechanisms via a Hybrid Neural Framework Integrating the Mamba and Kolmogorov–Arnold Networks

Benzhi Dong, Yumeng Hua iD, Chang Hou, Dali Xu, Guohua Wang

Biomolecules · 2026

DOI: 10.3390/biom16020194 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biomolecules, 2026. Verfasst von Benzhi Dong und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, China. Hauptthemen laut MEDLINE: Protein Folding, Proteins, Computational Biology, Neural Networks, Computer. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Real-valued inter-residue distance maps provide essential spatial information for understanding protein folding mechanisms and guiding downstream applications such as function annotation, drug discovery, and structural modeling. However, existing prediction methods often struggle to capture long-range dependencies and to maintain topological consistency across different structural scales. To address these challenges, we propose a novel prediction framework that integrates a Mamba architecture, based on a selective state space model, to effectively model global interactions, and incorporates the Kolmogorov–Arnold Network (KAN) to enhance nonlinear structural representation. Extensive experiments on standard benchmark datasets, including CASP13, CASP14, and CASP15, demonstrate prediction accuracies of 86.53%, 85.44%, and 82.77%, respectively, outperforming state-of-the-art approaches. These results indicate that the proposed framework substantially improves the fidelity of real-valued distance prediction and offers a promising tool for downstream structural and functional studies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Protein FoldingProteinsComputational BiologyNeural Networks, ComputerPrediction AlgorithmsModels, MolecularProtein ConformationAlgorithms

Stichwörter der Autor:innen

KANMambaproteinreal-valued distance prediction

Substanzen

Proteins

Autor:innen und Institutionen

  • College of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, China.
  • Faculty of Computing, Harbin Institute of Technology, Harbin 150001, China.

ORCID-Profile: Yumeng Hua

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Dong, B., Hua, Y., Hou, C., Xu, D., & Wang, G. (2026). MAKA-Map: Real-Valued Distance Prediction for Protein Folding Mechanisms via a Hybrid Neural Framework Integrating the Mamba and Kolmogorov–Arnold Networks. Biomolecules. https://doi.org/10.3390/biom16020194

Vancouver

Dong B, Hua Y, Hou C, Xu D, Wang G. MAKA-Map: Real-Valued Distance Prediction for Protein Folding Mechanisms via a Hybrid Neural Framework Integrating the Mamba and Kolmogorov–Arnold Networks. Biomolecules. 2026. doi:10.3390/biom16020194

BibTeX
@article{Dong2026,
  author = {Dong, Benzhi and Hua, Yumeng and Hou, Chang and Xu, Dali and Wang, Guohua},
  title = {MAKA-Map: Real-Valued Distance Prediction for Protein Folding Mechanisms via a Hybrid Neural Framework Integrating the Mamba and Kolmogorov–Arnold Networks},
  journal = {Biomolecules},
  year = {2026},
  doi = {10.3390/biom16020194}
}
Kostenlos starten →