An integrative model of chromatin and expression variation across human cell types
Abstract/Contents
- Abstract
- Although all cells in our body contain the same genetic material, they can perform vastly different functions by selectively expressing subsets of their genes. Cell-type-specific gene regulation is achieved through interactions between regulatory proteins and epigenetic mechanisms, which affect the structural organization of the genome. Characterizing these interactions is important for understanding the causes of genetic diseases and for identifying potential targets for medical intervention. The amount and complexity of genomic data being generated nowadays imply that many of the challenges that the field of genomics is currently facing are purely computational. The goal of this thesis is to demonstrate how machine learning approaches that account for the inherent heterogeneity and combinatorial complexity of gene regulatory mechanisms can be successfully used to provide novel biological insights. This thesis starts by presenting two studies that use computational techniques to investigate the variation in epigenetic state across genomic contexts and individuals. These studies demonstrate that the effects of epigenetic variation on gene regulation are highly combinatorial. Motivated by these results, and by the wealth of data generated by the ENCODE and Roadmap Epigenomics projects, I present a machine learning framework for discovering cell-type-specific regulatory mechanisms. This framework integrates several data sources including gene expression, DNA sequence information, cell-type-specific epigenetic state, and information regarding protein interactions. The proposed model achieves high predictive power and discovers novel cell-type-specific regulatory features and context-specific interactions between them.
Description
| Type of resource | text |
|---|---|
| Form | electronic; electronic resource; remote |
| Extent | 1 online resource. |
| Publication date | 2014 |
| Issuance | monographic |
| Language | English |
Creators/Contributors
| Associated with | Kyriazopoulou-Panagiotopoulou, Sofia |
|---|---|
| Associated with | Stanford University, Department of Computer Science. |
| Primary advisor | Batzoglou, Serafim |
| Thesis advisor | Batzoglou, Serafim |
| Thesis advisor | Kundaje, Anshul, 1980- |
| Thesis advisor | Snyder, Michael, Ph. D |
| Advisor | Kundaje, Anshul, 1980- |
| Advisor | Snyder, Michael, Ph. D |
Subjects
| Genre | Theses |
|---|
Bibliographic information
| Statement of responsibility | Sofia Kyriazopoulou-Panagiotopoulou. |
|---|---|
| Note | Submitted to the Department of Computer Science. |
| Thesis | Thesis (Ph.D.)--Stanford University, 2014. |
| Location | electronic resource |
Access conditions
- Copyright
- © 2014 by Sofia Kyriazopoulou Panagiotopoulou
- License
- This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).
Also listed in
Loading usage metrics...