EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MENDELSEEK: An algorithm that predicts mendelian genes and elucidates what makes them special

Hongyi Zhou, Brice Edelman, Jeffrey Skolnick iD

PLOS Computational Biology · 2026

DOI: 10.1371/journal.pcbi.1013992 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, 2026. Verfasst von Hongyi Zhou und 2 weiteren Autor:innen. Beteiligte Einrichtung: Center for the Study of Systems Biology, School of Biological Sciences, Georgia Institute of Technology, Atlanta, Georgia, United States of America. Hauptthemen laut MEDLINE: Algorithms, Computational Biology, Machine Learning, Genetic Diseases, Inborn. Die Arbeit nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIGMS NIH HHS, Foundation for the National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Although individual Mendelian diseases—those caused by a single gene—are rare, their collective disease burden is substantial. Identifying the causal gene for each condition is essential for accurate diagnosis and effective treatment. Yet, despite decades of research, the genetic basis of more than half of all known Mendelian diseases remains unresolved. To address this gap, we introduce MENDELSEEK , a machine learning framework that predicts Mendelian genes by integrating residue variation scores with pathway participation, Gene Ontology processes, and protein language model features. In benchmarking across 16,946 human genes with 10-fold cross-validation, MENDELSEEK achieved an AUC of 0.869 and an AUPR of 0.737—substantially outperforming the next best methods, ENTPRISE+ENTPRISE-X (AUC 0.781; AUPR 0.626), and REVEL (AUC 0.585; AUPR 0.401). When applied to the full set of 17,858 human genes, MENDELSEEK predicted 1,277 novel Mendelian gene candidates with precision greater than 0.7. Analysis further revealed that Mendelian genes engage in significantly more protein-protein interactions than non-Mendelian genes and are evolutionarily ancient. Together, these results highlight MENDELSEEK as a major advance over existing methods, offering new insights into the biochemical features that distinguish Mendelian from non-Mendelian genes.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsComputational BiologyMachine LearningGenetic Diseases, InbornHumansPrediction AlgorithmsGene OntologyDatabases, GeneticGenetic Predisposition to Disease

Autor:innen und Institutionen

  • Center for the Study of Systems Biology, School of Biological Sciences, Georgia Institute of Technology, Atlanta, Georgia, United States of America.

ORCID-Profile: Jeffrey Skolnick

Förderung

  • NIGMS NIH HHS
  • Foundation for the National Institutes of Health

Zitieren

APA

Zhou, H., Edelman, B., & Skolnick, J. (2026). MENDELSEEK: An algorithm that predicts mendelian genes and elucidates what makes them special. PLOS Computational Biology. https://doi.org/10.1371/journal.pcbi.1013992

Vancouver

Zhou H, Edelman B, Skolnick J. MENDELSEEK: An algorithm that predicts mendelian genes and elucidates what makes them special. PLOS Computational Biology. 2026. doi:10.1371/journal.pcbi.1013992

BibTeX
@article{Zhou2026,
  author = {Zhou, Hongyi and Edelman, Brice and Skolnick, Jeffrey},
  title = {MENDELSEEK: An algorithm that predicts mendelian genes and elucidates what makes them special},
  journal = {PLOS Computational Biology},
  year = {2026},
  doi = {10.1371/journal.pcbi.1013992}
}
Kostenlos starten →