EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AI-driven discovery of novel extracellular matrix biomarkers in pelvic organ prolapse

Yanlin Mi iD, Ben Cahill, Venkata V B Yallapragada, Reut Rotem, Barry A O'Reilly, Sabin Tabirca

PLOS Computational Biology · 07.10.2025 · 21 (10) · e1013483

DOI: 10.1371/journal.pcbi.1013483 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 07.10.2025. Verfasst von Yanlin Mi und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Information Technology, University College Cork, Cork, Ireland. Hauptthemen laut MEDLINE: Pelvic Organ Prolapse, Extracellular Matrix Proteins, Extracellular Matrix. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 82 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Taighde Éireann – Research Ireland, Taighde Éireann-Research Ireland.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning for protein function prediction faces significant challenges in identifying disease-specific proteins. We present Extracellular Matrix Protein Predictor (EPOP), an advanced transfer learning framework leveraging protein language models to decode disease mechanisms. Focusing on pelvic organ prolapse (POP), which affects up to 50% of women worldwide, EPOP demonstrates AI’s power to reveal novel therapeutic targets. We developed a sophisticated fine-tuning protocol for the ESM-2 model, optimized for ECM protein prediction. Our architecture integrates specialized attention mechanisms with interpretability modules, trained on expertly curated and balanced datasets totaling 80,000 proteins (40,000 ECM and 40,000 non-ECM). The framework employs a novel validation strategy using a 16,000-sample independent test set and clinical proteomics data. EPOP achieved unprecedented performance (99.40% accuracy) in ECM protein classification, significantly surpassing traditional deep learning architectures (10.81% improvement over Transformer models, 21.71% over Long Short-Term Memory). Applied to clinical samples, our model revealed a previously unknown pattern of ECM remodeling, identifying 24 novel disease-associated proteins. Model interpretability analysis uncovered specific sequence motifs and structural features critical for ECM protein function, providing mechanistic insights into disease progression. EPOP demonstrates how advanced AI bridges molecular analysis and clinical applications, uncovering novel therapeutic targets. Its success suggests broader applications across ECM-related disorders, potentially transforming approaches to diseases affecting connective tissue architecture.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Pelvic Organ ProlapseExtracellular Matrix ProteinsExtracellular MatrixHumansBiomarkersFemaleComputational BiologyDeep LearningProteomicsArtificial Intelligence

Substanzen

BiomarkersExtracellular Matrix Proteins

Autor:innen und Institutionen

  • School of Computer Science and Information Technology, University College Cork, Cork, Ireland.
  • SFI Centre for Research Training in Artificial Intelligence, University College Cork, Cork, Ireland.
  • Centre for Advanced Photonics and Process Analytics, Munster Technological University, Cork, Ireland.
  • Department of Urogynaecology, Cork University Maternity Hospital, Cork, Ireland.
  • Department of Obstetrics and Gynecology, Shaare Zedek Medical Center, Hebrew University School of Medicine, Jerusalem, Israel.
  • Faculty of Mathematics and Informatics, Transylvania University of Brasov, Brasov, Romania.

ORCID-Profile: Yanlin Mi

Förderung

  • Taighde Éireann – Research Ireland
  • Taighde Éireann-Research Ireland

Zitieren

APA

Mi, Y., Cahill, B., Yallapragada, V. V. B., Rotem, R., O'Reilly, B. A., & Tabirca, S. (2025). AI-driven discovery of novel extracellular matrix biomarkers in pelvic organ prolapse. PLOS Computational Biology, 21(10), e1013483. https://doi.org/10.1371/journal.pcbi.1013483

Vancouver

Mi Y, Cahill B, Yallapragada VVB, Rotem R, O'Reilly BA, Tabirca S. AI-driven discovery of novel extracellular matrix biomarkers in pelvic organ prolapse. PLOS Computational Biology. 2025;21(10):e1013483. doi:10.1371/journal.pcbi.1013483

BibTeX
@article{Mi2025,
  author = {Mi, Yanlin and Cahill, Ben and Yallapragada, Venkata V B and Rotem, Reut and O'Reilly, Barry A and Tabirca, Sabin},
  title = {AI-driven discovery of novel extracellular matrix biomarkers in pelvic organ prolapse},
  journal = {PLOS Computational Biology},
  year = {2025},
  volume = {21},
  number = {10},
  pages = {e1013483},
  doi = {10.1371/journal.pcbi.1013483}
}
Kostenlos starten →