Talk Title: Machine Learning in Genetics
Machine learning involves the creation of computational models from complex data sets, which can be used for predicting outcomes without being explicitly programmed. Now, machine learning is routinely used in applications you encounter every day, such as search engine optimisations and product recommendations. Several applications of machine learning techniques to genetic and genomic data currently exist, including prediction of cellular phenotypes such as drug response, and genomic sequence element annotation. As increasing volumes of genetic and genomic data continue to be generated, machine learning models that can interpret this often complex and noisy data will become more appropriate and accurate than traditional data analysis. In this talk, we will cover the basics of creating and interpreting practical machine learning models from biological data sources, and some of the recent applications in genetics.
Beth Signal, PhD Student, Garvan Institute of Medical Research
Beth is a PhD Student in the Clinical Genome Informatics group at the Garvan Institute. Her current research is focused on developing bioinformatics methods to understand how transcript splicing and expression is controlled. She has a particular interest in using machine learning techniques to study transcriptomic behaviour.