PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Whole Genome Association Studies in Autistic Spectrum Disorders Revisited: A Support Vector Machine Approach
P Johnston, David Hardoon, C Ecker, T Clarke, J Powell and D Murphy
In: 8th Annual International Meeting for Autism Research(2008).

Abstract

Autistic spectrum disorders (ASDs) are moderately common, highly heritable neurodevelopmental conditions with a strong genetic basis. Several lines of evidence support genetic factors as a predominant cause of ASDs. However, investigations’ using conventional genetic approaches has been slow. To date no single biological or clinical markers have yet been identified. Recent years has seen an increase use of whole genome association studies (WGAS), specifically through the establishment of collaborative efforts such as Autism Genetic Resource Exchange (AGRE) and the Autism Genome Project. Still very little light has been shed on the complex aetiology of this polygenic disorder. Support vector machines (SVM), one method of machine learning, has the ability to classify data using a mathematical function which best discriminates two groups - also highlighting the most influential discriminatory factors. However nobody has yet applied a SVM approach on WGAS.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Poster)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Brain Computer Interfaces
ID Code:4670
Deposited By:David Hardoon
Deposited On:13 March 2009