Análisis mediante inteligencia computacional de marcadores genéticos en pacientes colombianos con enfermedad de Alzheimer
Cargando...
Archivos
Autores
Tipo de contenido
Document language:
Español
Fecha
Título de la revista
ISSN de la revista
Título del volumen
Documentos PDF
Resumen
Un objetivo principal de la genética humana es comprender la relación entre las variaciones en las secuencias de ADN y la susceptibilidad a ciertas enfermedades. En este trabajo en particular, la información genética se analiza en relación con la enfermedad de Alzheimer (EA), con el fin de mejorar su diagnóstico, prevención y tratamiento. En Colombia, esta enfermedad requiere actualmente una atención especial debido a que su incidencia ha aumentado significativamente en los últimos años. Por esta razón, este trabajo analiza un conjunto de doce marcadores genéticos o polimorfismos de nucleótido simple (SNP) en un grupo de pacientes colombianos con EA a través de un método de inducción constructiva basado en un enfoque de aprendizaje de máquina, denominado reducción de dimensión multifactorial (MDR). Además, se realizaron análisis de epistasia estadística, obteniendo la relación de sinergia entre las variables mediante la ganancia de la información de los genes relacionados con la AD, proporcionando una metodología simple para caracterizar las interacciones en los estudios de asociación genética y determinar los rasgos más importantes que describen el comportamiento de la enfermedad.
Abstract. A main goal of human genetics is to understand the relationship between variations in DNA sequences and the susceptibility to certain illnesses. In this particular work, genetic information is analyzed in relation to the Alzheimer's disease (AD) in order to improve its diagnosis, prevention and treatment. In Colombia, this disease currently requires special attention because its incidence has increased significantly in recent years. Thus, this work analyzes a set of twelve genetic markers or single nucleotide polymorphisms (SNPs) in a set of colombian patients through a constructive induction method based on a machine learning approach, namely, multifactor dimensionality reduction (MDR). Also, some statistical epistasis analysis is carried out. Particularly, epistasis is obtained based on information gain from AD related genes, providing a simple methodology to characterize interactions in genetic association studies and capturing important traits that describe the behavior of the disease.
Abstract. A main goal of human genetics is to understand the relationship between variations in DNA sequences and the susceptibility to certain illnesses. In this particular work, genetic information is analyzed in relation to the Alzheimer's disease (AD) in order to improve its diagnosis, prevention and treatment. In Colombia, this disease currently requires special attention because its incidence has increased significantly in recent years. Thus, this work analyzes a set of twelve genetic markers or single nucleotide polymorphisms (SNPs) in a set of colombian patients through a constructive induction method based on a machine learning approach, namely, multifactor dimensionality reduction (MDR). Also, some statistical epistasis analysis is carried out. Particularly, epistasis is obtained based on information gain from AD related genes, providing a simple methodology to characterize interactions in genetic association studies and capturing important traits that describe the behavior of the disease.