MLe-KCNQ2: An Artificial Intelligence Model for the Prognosis of Missense KCNQ2 Gene Variants
Authors:
- Alba Saez-MatiaASAlba Saez-Matia
- Markel G. IbarluzeaMIMarkel G. Ibarluzea
- Sara M-AlicanteSMSara M-Alicante
- Arantza Muguruza-MonteroAMArantza Muguruza-Montero
- Eider NuñezENEider Nuñez
- Rafael RamisRRRafael Ramis
- Oscar R. BallesterosOBOscar R. Ballesteros
- Diego Lasa-GoicuriaDLDiego Lasa-Goicuria
- Carmen FonsCFCarmen Fons
- Mónica GallegoMGMónica Gallego
- Oscar CasisOCOscar Casis
- Aritz LeonardoALAritz Leonardo
Open Access
- 2 March 2024
- journal article
- research article
- Published by MDPI AG in International Journal of Molecular Sciences
- Vol. 25 (5) , 2910
Abstract
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.Keywords
Funding Information
- Eusko Jaurlaritza (IT1707-22, PID2022-139230NB-I00, PID2021-128286NB-100, PID2020-118814RB-I00, PRE_2021_1_0101, POS_2021_1_0017)
- Ministerio de Ciencia e Innovación (IT1707-22, PID2022-139230NB-I00, PID2021-128286NB-100, PID2020-118814RB-I00, PRE_2021_1_0101, POS_2021_1_0017)
- Eusko Jaurlaritza (IT1707-22, PID2022-139230NB-I00, PID2021-128286NB-100, PID2020-118814RB-I00, PRE_2021_1_0101, POS_2021_1_0017)
This publication has 65 references indexed in Scilit:
- Variant interpretation using population databases: Lessons from gnomADHuman Mutation, 2021
- Opportunities and challenges for the computational interpretation of rare variation in clinically important genesThe American Journal of Human Genetics, 2021
- The Human Gene Mutation Database (HGMD®): optimizing its use in a clinical diagnostic or research settingHuman Genetics, 2020
- Clinical Implications and Challenges of Artificial Intelligence and Deep LearningJAMA, 2018
- The Complementarity Between Protein-Specific and General Pathogenicity Predictors for Amino Acid SubstitutionsHuman Mutation, 2016
- Using ClinVar as a Resource to Support Variant InterpretationCurrent Protocols in Human Genetics, 2016
- Variable clinical expression in patients with mosaicism for KCNQ2 mutationsAmerican Journal of Medical Genetics Part A, 2015
- The Evaluation of Tools Used to Predict the Impact of Missense Variants Is Hindered by Two Types of CircularityHuman Mutation, 2015
- KCNQ2 encephalopathy: Emerging phenotype of a neonatal epileptic encephalopathyAnnals of Neurology, 2011
- Performance of mutation pathogenicity prediction methods on missense variantsHuman Mutation, 2011