RESUMEN
Next generation sequencing provides an important opportunity for improved diagnosis in epilepsy. To date, the majority of diagnostic genetic testing is conducted in the paediatric arena, while the utility of such testing is less well understood in adults with epilepsy. We conducted whole exome sequencing (WES) and copy number variant analyses in an Irish cohort of 101 people with epilepsy and co-morbid intellectual disability to compare the diagnostic yield of genomic testing between adult and paediatric patients. Variant interpretation followed American College of Medical Genetics and Genomics (ACMG) guidelines. We demonstrate that WES, in combination with array-comparative genomic hybridisation, provides a diagnostic rate of 27% in unrelated adult epilepsy patients and 42% in unrelated paediatric patients. We observe a 2.7% rate of ACMG-defined incidental findings. Our findings indicate that WES has similar utility in both adult and paediatric cohorts and is appropriate for diagnostic testing in both epilepsy patient groups.
Asunto(s)
Epilepsia/genética , Pruebas Genéticas/métodos , Discapacidad Intelectual/genética , Adolescente , Adulto , Niño , Preescolar , Comorbilidad , Hibridación Genómica Comparativa/métodos , Hibridación Genómica Comparativa/normas , Epilepsia/diagnóstico , Epilepsia/epidemiología , Femenino , Pruebas Genéticas/normas , Humanos , Lactante , Discapacidad Intelectual/diagnóstico , Discapacidad Intelectual/epidemiología , Masculino , Persona de Mediana Edad , Mutación , Sensibilidad y Especificidad , Secuenciación del Exoma/métodos , Secuenciación del Exoma/normasRESUMEN
Accurate detection of somatic mutations is still a challenge in cancer analysis. Here we present NeuSomatic, the first convolutional neural network approach for somatic mutation detection, which significantly outperforms previous methods on different sequencing platforms, sequencing strategies, and tumor purities. NeuSomatic summarizes sequence alignments into small matrices and incorporates more than a hundred features to capture mutation signals effectively. It can be used universally as a stand-alone somatic mutation detection method or with an ensemble of existing methods to achieve the highest accuracy.
