Machine learning approaches for extracting genetic medical data information

Bioinformatics is the development and application of computational tools for the field of biological and biomedical research data, including public health informatics and population informatics, in addition to clinical informatics. Bioinformatics represents a promising toolset to move from the standard therapies to tailor medical care to each individual genome, therefore instead of using certain therapy to group of patients suffering of certain disease, they tailor this therapy to each individual genome. Machine learning algorithms and techniques have been used in bioinformatics. There are many methods available to deal with data including DNA sequence, complex gene-gene interactions data, and clinical data. To assess these complex data, there are several approaches such as multifactor dimensionality reduction, generalized multifactor dimensionality reduction, artificial neural networks for example multilayer feedforward neural networks, and feature selection approaches. These approaches provide capabilities to deal with very big data that include an excessive number of features. In this talk, two case studies will be discussed for the use of machine learning for extracting genetic information which includes obesity and diabetes.