Machine learning methods for mRNA alternative splicing
Supervisor: Heejung Shim
Available for: MSc/PhD and undergraduate research projects.
Location: Melbourne Integrative Genomics, University of Melbourne
Project title: Machine learning methods for mRNA alternative splicing
Background: Alternative splicing of pre-mRNA allows a single gene to produce different proteins in eukaryotes, and they have been shown to affect various gene functions, and eventually disease. We have developed a method for inference of the underlying splicing processes using RNA-seq data and produced the software package, McSplicer (https://github.com/shimlab/McSplicer). Currently, we are building on the proposed method to develop new machine learning methods for identification of differential splicing events.
Proposed projects: The specific project will depend on the student’s interest and background. Options are 1) benchmarking currently available methods against McSplicer and analyzing RNA-seq data to better understand splicing processes, 2) contributing to the development of new machine learning methods, or 3) software development for the new machine learning methods.
Learning outcomes: software development, statistics / machine learning, programming and analysis using Python (optionally R), statistical analysis of complex and large-scale genomic data, data visualization.