Single-cell characterization of human immune cell histone modification profiles using machine learning
Abstract/Contents
- Abstract
- Histone post-translational modifications (HPTMs) regulate gene expression through coordinated interactions known as histone crosstalk. Variations in HPTM abundances or histone crosstalk are associated with cancer, infectious diseases, autoimmune disorders and mental illness. EpiTOF, a high-dimensional mass cytometry-based platform, measures abundances of HPTMs and histone variants across multiple immune cell sub-types at a single-cell resolution. However, the direct study of histone crosstalk in vivo in higher eukaryotes is very difficult due to experimental limitations in inhibiting or knocking-out HPTMs. In this thesis, we develop computational methods to infer directed associations between HPTMs from their abundances measured using EpiTOF. Leveraging the large number of immune cells from healthy human subjects profiled using EpiTOF, we first develop a neural network-based subject-specific method and train models to accurately predict HPTM abundances. We then infer directed associations between HPTMs from these models using a novel, perturbation-based interpretation algorithm. Lastly, we apply our trained models and interpretation algorithm and identify changes in HPTM associations due to the influenza vaccine and the cluster of cells that drive these changes. Our results provide insights into the histone crosstalk landscape in immune cells from human beings. The trained models and the interpretation framework can be applied to identify changes in the HPTM and histone crosstalk landscape due to a disease or external stimuli like vaccination. Our methods can also be applied to proteomic or transcriptomic datasets to infer directed interactions between proteins or gene expression respectively.
Description
Type of resource | text |
---|---|
Form | electronic resource; remote; computer; online resource |
Extent | 1 online resource. |
Place | California |
Place | [Stanford, California] |
Publisher | [Stanford University] |
Copyright date | 2022; ©2022 |
Publication date | 2022; 2022 |
Issuance | monographic |
Language | English |
Creators/Contributors
Author | Ganesan, Ananthakrishnan |
---|---|
Degree supervisor | Khatri, Purvesh |
Thesis advisor | Khatri, Purvesh |
Thesis advisor | Hastie, Trevor |
Thesis advisor | Utz, PJ |
Degree committee member | Hastie, Trevor |
Degree committee member | Utz, PJ |
Associated with | Stanford University, Institute for Computational and Mathematical Engineering |
Subjects
Genre | Theses |
---|---|
Genre | Text |
Bibliographic information
Statement of responsibility | Ananthakrishnan Ganesan. |
---|---|
Note | Submitted to the Institute for Computational and Mathematical Engineering. |
Thesis | Thesis Ph.D. Stanford University 2022. |
Location | https://purl.stanford.edu/pn703nv2237 |
Access conditions
- Copyright
- © 2022 by Ananthakrishnan Ganesan
- License
- This work is licensed under a Creative Commons Attribution 3.0 Unported license (CC BY).
Also listed in
Loading usage metrics...