PhD defence by Yuhu Liang
In pursuit of gene variation of consequence to human health and disease
The Ph.D. thesis consists of two projects. The first project deals with predicting the nucleotide probability of Human DNA and variants based on sequence context. This is done with the help of a bi-directional Markov model. In the second project, we employed a deep generative decoder model to learn the features of healthy individuals’ gene expression data, and enable differential expression analysis in cancer N-of-1 study.
In this work, we consider several online learning problems. In each case, the learner is faced with different constraints on her behavior and on the feedback she is allowed to observe, which affect the trade-off between exploration and exploitation in different ways. We propose algorithms for each of those problems and analyze them to provide theoretical guarantees against both worst-case and easy data.
Principal Supervisor, professor Anders Krogh, Department of Computer Science, UCPH
Professor Wouter Krogh Boomsma, Department of Computer Science, UCPH
Professor Jakob Skou Pedersen, Aarhus University
Principal Investigator Anders Martin Jacobsen Skanderup, Genome Institute of Singapore (GIS)
Leader of defence: Professor Wouter Krogh Boomsma, Department of Computer Science, UCPH
For an electronic copy of the thesis, please visit the PhD Programme page.