Publication: Aplicación de métodos de aprendizaje automático para el estudio de la comorbilidad inversa entre cáncer y trastornos del sistema nervioso central
Loading...
Files
Official URL
Full text at PDC
Publication Date
2016-07-01
Authors
Advisors (or tutors)
Editors
Journal Title
Journal ISSN
Volume Title
Publisher
Universidad Complutense de Madrid
Citations
Exportar
Abstract
La cantidad de datos biológicos y médicos que se produce hoy en día es enorme, y se podría decir que el campo de las ciencias de la vida forma parte ya del club del Big Data. Estos datos contienen información crucial que pueden ayudar a comprender mejor los mecanismos moleculares en los sistemas biológicos. Este conocimiento es fundamental para el progreso en el diagnóstico y en el tratamiento de las enfermedades. La Bioinformática, junto con la Biología Computacional, son disciplinas que se encargan de organizar, analizar e interpretar los datos procedentes de la Biología Molecular. De hecho, la complejidad y la heterogeneidad de los problemas biológicos requieren de un continuo diseño, implementación y aplicación de nuevos métodos y algoritmos. La minería de datos biológicos es una tarea complicada debido a la naturaleza heterogénea y compleja de dichos datos, siendo éstos muy dependientes de detalles específicos experimentales. Esta tesis se basa en el estudio de un problema biomédico complejo: la menor probabilidad de desarrollar algunos tipos de cáncer en pacientes con ciertos trastornos del sistema nervioso central (SNC) u otros trastornos neurológicos, y viceversa. Denominamos a esta condición como comorbilidad inversa. Desde el punto de vista médico, entender mejor las conexiones e interacciones entre cáncer y trastornos neurológicos podría mejorar la calidad de vida y el efecto de la asistencia médica de millones de personas en todo el mundo. Aunque la comorbilidad inversa ha sido estudiada a nivel médico, a través de estudios epidemiológicos, no se ha investigado en profundidad a nivel molecular...
Large-scale biological and medical data is continuously produced, making by now Life Sciences part of Big Data sciences. Such data contain acute information that can enable a better understanding of themolecular mechanisms behind biological systems. This information is essential for the progress in the diagnosis and the treatment of diseases. Bioinformatics and Computational Biology are the disciplines dedicated to the organization, analysis, and interpretation of the data produced by Life Sciences. Indeed, biological data mining is complicated by the heterogeneous and complex nature of the data, that are very dependent on the specific experimental details. The complexity and variety of biological problems require the continuous design, implementation, and application of newmethods and algorithms. This thesis deals with one specific complex biomedical problem, i.e. the lower than expected probability of cancer patients develop some central nervous system (CNS) or neurological disorder and viceversa. This condition is known as inverse comorbidity. At the medical level, a better understanding of the connections and interactions between cancer and neurological disorders could potentially improve the quality of life and healthcare outcome of millions of people worldwide. Even if this is a well characterized phenomenon, based on solid population and epidemiological studies, very little is known about the molecular basis of inverse comorbidity...
Large-scale biological and medical data is continuously produced, making by now Life Sciences part of Big Data sciences. Such data contain acute information that can enable a better understanding of themolecular mechanisms behind biological systems. This information is essential for the progress in the diagnosis and the treatment of diseases. Bioinformatics and Computational Biology are the disciplines dedicated to the organization, analysis, and interpretation of the data produced by Life Sciences. Indeed, biological data mining is complicated by the heterogeneous and complex nature of the data, that are very dependent on the specific experimental details. The complexity and variety of biological problems require the continuous design, implementation, and application of newmethods and algorithms. This thesis deals with one specific complex biomedical problem, i.e. the lower than expected probability of cancer patients develop some central nervous system (CNS) or neurological disorder and viceversa. This condition is known as inverse comorbidity. At the medical level, a better understanding of the connections and interactions between cancer and neurological disorders could potentially improve the quality of life and healthcare outcome of millions of people worldwide. Even if this is a well characterized phenomenon, based on solid population and epidemiological studies, very little is known about the molecular basis of inverse comorbidity...
Description
Tesis inédita de la Universidad Complutense de Madrid, Facultad de Informática, Departamento de Ingeniería del Software e Inteligencia Artificial, leída el 27-11-2015