Random walk in machine learning and its applications in biology

Time and location: 11:00-12:00, Building 6 (Nuffield), Room 1129

Speakers: Mahesan Niranjan (School of Electronics and Computer Science, University of Southampton)

Abstract: In recent years we have seen a rapid growth in the amount of biological data available in published repositories in the form of nucleotide and amino acid sequences, macromolecular structures and high throughput experimental measurements of mRNA, protein and metabolite concentrations. Growth of data in this manner has reinforced the view that computational modelling can be useful in uncovering regularities in the data, at least as a way of reducing the search space over which experimental biologists may formulate hypotheses. In this seminar, I will discuss some topics in machine learning, the subject in which we are concerned with the development of algorithms for extracting useful information from large and complex datasets, and how they can be applied to making useful inferences in biology:

• homology detection with protein sequences;
• classification problems in transcriptome analysis and a critique of the precision with which gene expression data is archived in public repositories;
• the relationship between cellular mRNA levels and the corresponding protein levels;
• model-based inference of transcription factor activities during cell cycle regulation

Speaker homepage