Hierarchical Learning for the Analysis of Mass Spectrometry Data

Add to your list(s) Download to your calendar using vCal

• Benjamin Sandford, Doctoral Student, Computer Science, University of Birmingham
• Tuesday 28 June 2016, 11:00-12:00
• Sloman Lounge, Computer Science Building (Y9 in Edgbaston Campus).

If you have a question about this talk, please contact Matthaios Doulgerakis.

This talk has been canceled/deleted

Mass Spectrometry is a technique used to identify the chemical composition of a sample and has been widely used in the biosciences to analyse biological samples. The focus of this talk will be on Mass Spectrometry Imaging (MSI) & Tandem Mass Spectrometry (MS/MS) used in proteomics. The main challenges with Mass Spectrometry data are the complexity and the amount of data generated. Both MSI and MS/MS generate large amounts of complex data that can not be analysed by hand. Current approaches to the analysis of MSI data use standard algorithms such as clustering and component analysis. We propose using an approach that takes advantage of the hierarchical nature of the data to produce an easy to interpret representation of the data based on hierarchical compositions from computer vision. We also present an approach to MS/MS data analysis using some of the recent developments in Deep Learning.

This talk is part of the Medical Imaging Research Seminars series.

This talk is included in these lists:

This talk is not included in any other list

Note that ex-directory lists are not shown.