The aim of this project is to develop methods for analysis of time-series based on count data. For example, detecting significant differences between two count data time series would distinguish between two different models: one in which the two time series are interchangeable, and one in which the second sample is a modification of the first, i.e. the two time series are non-interchangeable. This will broaden the target of my project to general analysis of count time-series data such as clustering, classification, perturbations inference and machine learning over sequential count data. The project will focus on count data sets from ribonucleic acid sequencing (RNA-seq) time course experiments. The method I plan to develop potentially has promising applications in a variety of multidisciplinary fields where event-counting is required, such as economics and biology. In economics, examples include the number of applicants for a job, or the number of labour strikes during a year. In biology, recent examples include high-throughput sequencing, such as RNA-seq and chromatin immunoprecipitation sequencing (ChIP-seq) analyses. These examples are especially relevant to this project because the method I will be developing enables various features of organisms to be compared through tag counts.

The project is sponsored by H2020-EU.1.3.2 Project Ref 660388 and is a collaboration with Magnus Rttray of University of Manchester and Winston Hide of SITraN.

Personnel from ML@SITraN