MLe-KCNQ2: An Artificial Intelligence Model for the Prognosis of Missense KCNQ2 Gene Variants
International Journal of Molecular Sciences · 2024
DOI: 10.3390/ijms25052910 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Molecular Sciences, 2024. Verfasst von Alba Saez-Matia und 13 weiteren Autor:innen. Beteiligte Einrichtung: Instituto Biofisika, CSIC-UPV/EHU, 48940 Leioa, Spain. Hauptthemen laut MEDLINE: Epilepsy, Benign Neonatal, Epilepsy, Generalized. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Basque Government, Ministerio de Ciencia e Innovación, Government of the Autonomous Community of the Basque Country.
Abstract (Originalsprache)
Despite the increasing availability of genomic data and enhanced data analysis procedures, predicting the severity of associated diseases remains elusive in the absence of clinical descriptors. To address this challenge, we have focused on the KV7.2 voltage-gated potassium channel gene (KCNQ2), known for its link to developmental delays and various epilepsies, including self-limited benign familial neonatal epilepsy and epileptic encephalopathy. Genome-wide tools often exhibit a tendency to overestimate deleterious mutations, frequently overlooking tolerated variants, and lack the capacity to discriminate variant severity. This study introduces a novel approach by evaluating multiple machine learning (ML) protocols and descriptors. The combination of genomic information with a novel Variant Frequency Index (VFI) builds a robust foundation for constructing reliable gene-specific ML models. The ensemble model, MLe-KCNQ2, formed through logistic regression, support vector machine, random forest and gradient boosting algorithms, achieves specificity and sensitivity values surpassing 0.95 (AUC-ROC > 0.98). The ensemble MLe-KCNQ2 model also categorizes pathogenic mutations as benign or severe, with an area under the receiver operating characteristic curve (AUC-ROC) above 0.67. This study not only presents a transferable methodology for accurately classifying KCNQ2 missense variants, but also provides valuable insights for clinical counseling and aids in the determination of variant severity. The research context emphasizes the necessity of precise variant classification, especially for genes like KCNQ2, contributing to the broader understanding of gene-specific challenges in the field of genomic research. The MLe-KCNQ2 model stands as a promising tool for enhancing clinical decision making and prognosis in the realm of KCNQ2-related pathologies.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Instituto Biofisika, CSIC-UPV/EHU, 48940 Leioa, Spain.
- Physics Department, Universidad del País Vasco, UPV/EHU, 48940 Leioa, Spain.
- Donostia International Physics Center, 20018 Donostia, Spain.
- Centro de Física de Materiales CFM, CSIC-UPV/EHU, 20018 Donostia, Spain.
- Pediatric Neurology Department, Sant Joan de Déu Hospital, Institut de Recerca Sant Joan de Déu, Barcelona University, 08950 Barcelona, Spain.
- Departamento de Fisiología, Universidad del País Vasco, UPV/EHU, 01006 Vitoria-Gasteiz, Spain.
ORCID-Profile: Alba Saez-Matia, Arantza Muguruza-Montero, Eider Nuñez, Oscar R Ballesteros, Mónica Gallego, Oscar Casis, Aritz Leonardo, Aitor Bergara
Förderung
- Basque Government
- Ministerio de Ciencia e Innovación
- Government of the Autonomous Community of the Basque Country
- Spanish Ministry of Science and Innovation
- Basque Government and administered by the University of the Basque Country
Zitieren
APA
Saez-Matia, A., Ibarluzea, M. G., M-Alicante, S., Muguruza-Montero, A., Nuñez, E., Ramis, R., Ballesteros, O. R., Lasa-Goicuria, D., Fons, C., Gallego, M., Casis, O., Leonardo, A., Bergara, A., & Villarroel, A. (2024). MLe-KCNQ2: An Artificial Intelligence Model for the Prognosis of Missense KCNQ2 Gene Variants. International Journal of Molecular Sciences. https://doi.org/10.3390/ijms25052910
Vancouver
Saez-Matia A, Ibarluzea MG, M-Alicante S, Muguruza-Montero A, Nuñez E, Ramis R, et al. MLe-KCNQ2: An Artificial Intelligence Model for the Prognosis of Missense KCNQ2 Gene Variants. International Journal of Molecular Sciences. 2024. doi:10.3390/ijms25052910
BibTeX
@article{SaezMatia2024,
author = {Saez-Matia, Alba and Ibarluzea, Markel G and M-Alicante, Sara and Muguruza-Montero, Arantza and Nuñez, Eider and Ramis, Rafael and Ballesteros, Oscar R and Lasa-Goicuria, Diego and Fons, Carmen and Gallego, Mónica and Casis, Oscar and Leonardo, Aritz and Bergara, Aitor and Villarroel, Alvaro},
title = {MLe-KCNQ2: An Artificial Intelligence Model for the Prognosis of Missense KCNQ2 Gene Variants},
journal = {International Journal of Molecular Sciences},
year = {2024},
doi = {10.3390/ijms25052910}
}
EUVIMED