Type-1 diabetes risk prediction using multiple kernel learning

This thesis presents an analysis of multiple kernel learning (MKL) for type-1 diabetes risk prediction. MKL combines different models and representation of data to find a linear combination of these representations of the data. MKL has been successfully been implemented in image detection, splice site detection, ribosomal and membrane protein prediction, etc. In this thesis, this method was applied for Genome-wide association study (GWAS) for classifying cases and controls. This thesis has shown that combined kernel does not perform better than the individual kernels and that MKL does not select the best model for this problem. Also, the effect of normalization on MKL as well as risk prediction has also been analyzed.

Name thesis:degree_name

Master of Science in Bioinformatics - (M.S.)

Discipline thesis:degree_discipline

Computer Science

Year

2010

Author dc:creator

• Garg, Paras

Contributors dc:contributor

• Usman W. Roshan
• Jason T. L. Wang
• Zhi Wei

• Diabetes risk prediction
• Multiple kernal learning
• Bioinformatics
• Computer Sciences

Repository record dc:identifier

https://digitalcommons.njit.edu/theses/56

OAI identifier oai:identifier

oai:digitalcommons.njit.edu:theses-1055