EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Deep Learning‐Enabled Engineering of a Hyper‐Stable and Soluble MPB70 ‐83 Antigen for Sensitive Bovine Tuberculosis Surveillance

Wen-Hao Wang, Jia-Zhen Ge, Ying-Ying Xie, Guo-Dong Song, Yijian Liu, Yin-Juan Song, Ren-Ge Li, Rui-Shuang Li, Zi-Qing Wang, Xin-Miao Liu, Shuang-Shuang Guo, Jie Li und 4 weitere

Microbial Biotechnology · 2026-04 · 19 (4)

DOI: 10.1111/1751-7915.70348 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Microbial Biotechnology, online erschienen am 16.04.2026. Verfasst von Wen-Hao Wang und 15 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory for Animal Disease Control and Prevention, College of Veterinary Medicine, Lanzhou Veterinary Research Institute, Chinese Academ…. Hauptthemen laut MEDLINE: Antigens, Bacterial, Deep Learning, Tuberculosis, Bovine, Bacterial Proteins. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Joint Scientific Research Fund Major Project of Gansu Province, Major Science and Technology Project of Gansu Province, Innovation Program of the Chinese Academy of Agricultural Sciences.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Bovine tuberculosis (bTB) diagnostics are frequently hindered by the structural instability and insolubility of recombinant multi‐epitope proteins in prokaryotic expression systems. To address this, we developed an integrated strategy combining immunoinformatics with the ProteinMPNN deep learning framework. We constructed a fusion protein utilizing B‐cell epitopes from MPB70 and MPB83, where ProteinMPNN was employed to redesign non‐epitope scaffolds for optimized thermodynamic stability. The structural integrity was verified via 200‐ns molecular dynamics (MD) simulations. MD analysis revealed the redesigned construct transitions into a rigid, compact native state with a stable hydrophobic core. Validating this in silico design, the optimized protein achieved high‐yield soluble expression in Escherichia coli , eliminating inclusion body formation. The resulting indirect ELISA demonstrated 96.30% sensitivity and 98.61% specificity, showing excellent concordance (Cohen's κ > 0.9) with standard assays. This study demonstrates that deep learning‐based sequence redesign effectively resolves solubility bottlenecks in antigen engineering, providing a robust, scalable tool for precision bTB surveillance.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Antigens, BacterialDeep LearningTuberculosis, BovineBacterial ProteinsProtein EngineeringMembrane ProteinsAnimalsCattleEscherichia coliMolecular Dynamics SimulationRecombinant Fusion ProteinsEpitopes, B-LymphocyteSolubilityEnzyme-Linked Immunosorbent AssayImmunoinformaticsSensitivity and Specificity

Stichwörter der Autor:innen

Mycobacterium bovisProteinMPNNbovine tuberculosis diagnosismolecular dynamics simulationmulti‐epitope fusion proteinsoluble expression

Substanzen

Antigens, BacterialBacterial ProteinsRecombinant Fusion ProteinsMPB83 protein, MycobacteriumEpitopes, B-LymphocyteMembrane Proteins

Autor:innen und Institutionen

  • State Key Laboratory for Animal Disease Control and Prevention, College of Veterinary Medicine, Lanzhou Veterinary Research Institute, Chinese Academy of Agricultural Sciences, Lanzhou University, Lanzhou, China.
  • College of Animal Science and Technology, Shihezi University, Shihezi, China.
  • College of Veterinary Medicine, Gansu Agricultural University, Lanzhou, China.
  • College of Veterinary Medicine, South China Agricultural University, Guangzhou, China.
  • College of Animal Medicine, Xinjiang Agricultural University, Urumqi, China.
  • Gansu Province Research Center for Basic Disciplines of Pathogen Biology, Lanzhou, China.

Förderung

  • Joint Scientific Research Fund Major Project of Gansu Province
  • Major Science and Technology Project of Gansu Province
  • Innovation Program of the Chinese Academy of Agricultural Sciences
  • Key Research and Development Program of Xinjiang

Zitieren

APA

Wang, W. H., Ge, J. Z., Xie, Y. Y., Song, G. D., Liu, Y., Song, Y. J., Li, R. G., Li, R. S., Wang, Z. Q., Liu, X. M., Guo, S. S., Li, J., Chen, S., Li, N., Zheng, F., & Chu, Y. (2026). Deep Learning‐Enabled Engineering of a Hyper‐Stable and Soluble MPB70 ‐83 Antigen for Sensitive Bovine Tuberculosis Surveillance. Microbial Biotechnology, 19(4). https://doi.org/10.1111/1751-7915.70348

Vancouver

Wang WH, Ge JZ, Xie YY, Song GD, Liu Y, Song YJ, et al. Deep Learning‐Enabled Engineering of a Hyper‐Stable and Soluble MPB70 ‐83 Antigen for Sensitive Bovine Tuberculosis Surveillance. Microbial Biotechnology. 2026;19(4). doi:10.1111/1751-7915.70348

BibTeX
@article{Wang2026,
  author = {Wang, Wen-Hao and Ge, Jia-Zhen and Xie, Ying-Ying and Song, Guo-Dong and Liu, Yijian and Song, Yin-Juan and Li, Ren-Ge and Li, Rui-Shuang and Wang, Zi-Qing and Liu, Xin-Miao and Guo, Shuang-Shuang and Li, Jie and Chen, Shengli and Li, Na and Zheng, Fuying and Chu, Yuefeng},
  title = {Deep Learning‐Enabled Engineering of a Hyper‐Stable and Soluble MPB70 ‐83 Antigen for Sensitive Bovine Tuberculosis Surveillance},
  journal = {Microbial Biotechnology},
  year = {2026},
  volume = {19},
  number = {4},
  doi = {10.1111/1751-7915.70348}
}
Kostenlos starten →