Methylation and High Dimensional Data Integration

Data integration challenges in bioinformatics are multifaceted. This paper aims to motivate methods and techniques to handle multiple data types and data sources. We integrate multiple sources of data to explore the usefulness of proxy blood methylation as a substitute for brain tissue. We then propose a likelihood based dimension reduction method to handle non-quantitative data. Lastly, we propose a tuning-free method that identifies low-dimensional representations of a target dataset relative to one or more comparison datasets which also is computationally efficient even with large numbers of features.

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Statistics

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2022

Author dc:creator

• Tu, Robin

Contributors dc:contributor

• Zhao, Sihai D
• Foss, Alexander H
• Li, Bo
• Simpson, Douglas G

• Dimension Reduction
• Contrastive
• Methylation
• Bioinformatics
• Statistics
• Methodology

Statement dc:rights

• Copyright 2022 Robin Tu

Language dc:language

en, eng

Handle dc:identifier

https://hdl.handle.net/2142/115367

OAI record oai:identifier

https://www.ideals.illinois.edu/oai-pmh?verb=GetRecord&metadataPrefix=etdms&identifier=oai%3Awww.ideals.illinois.edu%3A2142%2F115367