Defence of dissertation in the field of computer science, Huibin Shen, M.Sc.
Title of the dissertation is: Machine Learning for Small Molecule Identification
Map © OpenStreetMap. Some rights reserved.
Huibin Shen, M.Sc., will defend the dissertation "Machine Learning for Small Molecule Identification" on 30 March 2017 at 12 noon in Aalto University School of Science, lecture hall T2, Konemiehentie 2, Espoo.
Metabolites are small molecules, such as sugars, fatty acids and amino acids that serve as sources of energy in the cells and as building materials for cell walls. Accurate identification of the metabolites of a biological sample is a requisite step for subsequent analyses such as anti-doping, drug control or other medical diagnostics.
In this dissertation, a series of machine learning methods are proposed to automatically identify metabolites. A special family of the machine learning algorithms, known as kernel methods, are used to handle the non-tabular nature of the data in this application. These methods are currently the most accurate ones as demonstrated in a recent small molecule identification challenge (CASMI 2016).
Dissertation release (pdf)
Opponent: Professor François Laviolette, Université Laval, Canada
Custos: Professor Juho Rousu, Aalto University School of Science, Department of Computer Science
Electronic dissertation: http://urn.fi/URN:ISBN:978-952-60-7292-0