Mi SciELO
Servicios Personalizados
Articulo
Indicadores
Citado por SciELO
Links relacionados
Similares en SciELO
Compartir
Revista Cubana de Informática Médica
versión On-line ISSN 1684-1859
Resumen
DATTA, Neelabh. Unleashing the Power of MutationTaster2 and MutationTaster2021: The Machine Learning Approach to Genetic Variant Analysis. RCIM [online]. 2023, vol.15, n.1 Epub 01-Jun-2023. ISSN 1684-1859.
MutationTaster is a widely used web-based tool that predicts the functional impact of genetic variants. In recent years, the software has undergone significant improvements, leading to the development of MutationTaster2 and MutationTaster2021. The main difference between these two versions is the use of updated reference datasets and an improved algorithm for variant classification. MutationTaster2 utilizes the dbNSFP database, while MutationTaster2021 incorporates gnomAD and ClinVar data. Both versions employ a machine learning approach that combines multiple features to predict variant pathogenicity, including evolutionary conservation, physical properties of amino acid changes, and the potential effect on protein function. The output of MutationTaster is a score indicating the likelihood of a variant being disease causing, with a high score indicating a high likelihood of pathogenicity. Overall, MutationTaster2 and MutationTaster2021 represent valuable tools for researchers and clinicians in the field of genetic variant analysis, providing accurate and efficient predictions of variant pathogenicity.
Palabras clave : MutationTaster2; MutationTaster2021; ExAC.