Sparse Bayesian graphical models for RPPA time course data

Riten Mitra, Peter Mueller, Yuan Ji, Gordon Mills, Yiling Lu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Advances in functional proteomic technologies have significantly enriched our knowledge of protein functions and their interactions in bio-molecular pathways. We discuss inference for RPPA (reverse phase protein array) data that measure the expression of the protein markers over time. We exploit the dynamical nature of the experiment to build a directed network of protein interactions. For this, we employ a Bayesian graphical model with an informative prior that favors sparsity. Conditional on the network, we model dependence at the level of latent binary indicators rather than the raw expression measurements. One of the key features of the proposed approach is a hierarchical model that allows for the dependence structure to be shared across different experiments, in the case of the motivating application across different drugs and doses. This is critical to facilitate meaningful inference with the limited available sample sizes. The second key feature is a sparsity inducing prior on the dependence structure.

Original languageEnglish (US)
Title of host publicationProceedings 2012 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2012
Pages113-117
Number of pages5
DOIs
StatePublished - Dec 1 2012
Externally publishedYes
Event2012 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2012 - Washington, DC, United States
Duration: Dec 2 2012Dec 4 2012

Other

Other2012 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2012
CountryUnited States
CityWashington, DC
Period12/2/1212/4/12

Fingerprint

Protein Array Analysis
Proteins
Protein Interaction Maps
Sample Size
Proteomics
Technology
Pharmaceutical Preparations
Experiments

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology (miscellaneous)
  • Computational Theory and Mathematics
  • Signal Processing
  • Biomedical Engineering

Cite this

Mitra, R., Mueller, P., Ji, Y., Mills, G., & Lu, Y. (2012). Sparse Bayesian graphical models for RPPA time course data. In Proceedings 2012 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2012 (pp. 113-117). [6507742] https://doi.org/10.1109/GENSIPS.2012.6507742

Sparse Bayesian graphical models for RPPA time course data. / Mitra, Riten; Mueller, Peter; Ji, Yuan; Mills, Gordon; Lu, Yiling.

Proceedings 2012 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2012. 2012. p. 113-117 6507742.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Mitra, R, Mueller, P, Ji, Y, Mills, G & Lu, Y 2012, Sparse Bayesian graphical models for RPPA time course data. in Proceedings 2012 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2012., 6507742, pp. 113-117, 2012 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2012, Washington, DC, United States, 12/2/12. https://doi.org/10.1109/GENSIPS.2012.6507742
Mitra R, Mueller P, Ji Y, Mills G, Lu Y. Sparse Bayesian graphical models for RPPA time course data. In Proceedings 2012 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2012. 2012. p. 113-117. 6507742 https://doi.org/10.1109/GENSIPS.2012.6507742
Mitra, Riten ; Mueller, Peter ; Ji, Yuan ; Mills, Gordon ; Lu, Yiling. / Sparse Bayesian graphical models for RPPA time course data. Proceedings 2012 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2012. 2012. pp. 113-117
@inproceedings{be0a9b9bfea440a4a902566f7c4d2845,
title = "Sparse Bayesian graphical models for RPPA time course data",
abstract = "Advances in functional proteomic technologies have significantly enriched our knowledge of protein functions and their interactions in bio-molecular pathways. We discuss inference for RPPA (reverse phase protein array) data that measure the expression of the protein markers over time. We exploit the dynamical nature of the experiment to build a directed network of protein interactions. For this, we employ a Bayesian graphical model with an informative prior that favors sparsity. Conditional on the network, we model dependence at the level of latent binary indicators rather than the raw expression measurements. One of the key features of the proposed approach is a hierarchical model that allows for the dependence structure to be shared across different experiments, in the case of the motivating application across different drugs and doses. This is critical to facilitate meaningful inference with the limited available sample sizes. The second key feature is a sparsity inducing prior on the dependence structure.",
author = "Riten Mitra and Peter Mueller and Yuan Ji and Gordon Mills and Yiling Lu",
year = "2012",
month = "12",
day = "1",
doi = "10.1109/GENSIPS.2012.6507742",
language = "English (US)",
isbn = "9781467352369",
pages = "113--117",
booktitle = "Proceedings 2012 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2012",

}

TY - GEN

T1 - Sparse Bayesian graphical models for RPPA time course data

AU - Mitra, Riten

AU - Mueller, Peter

AU - Ji, Yuan

AU - Mills, Gordon

AU - Lu, Yiling

PY - 2012/12/1

Y1 - 2012/12/1

N2 - Advances in functional proteomic technologies have significantly enriched our knowledge of protein functions and their interactions in bio-molecular pathways. We discuss inference for RPPA (reverse phase protein array) data that measure the expression of the protein markers over time. We exploit the dynamical nature of the experiment to build a directed network of protein interactions. For this, we employ a Bayesian graphical model with an informative prior that favors sparsity. Conditional on the network, we model dependence at the level of latent binary indicators rather than the raw expression measurements. One of the key features of the proposed approach is a hierarchical model that allows for the dependence structure to be shared across different experiments, in the case of the motivating application across different drugs and doses. This is critical to facilitate meaningful inference with the limited available sample sizes. The second key feature is a sparsity inducing prior on the dependence structure.

AB - Advances in functional proteomic technologies have significantly enriched our knowledge of protein functions and their interactions in bio-molecular pathways. We discuss inference for RPPA (reverse phase protein array) data that measure the expression of the protein markers over time. We exploit the dynamical nature of the experiment to build a directed network of protein interactions. For this, we employ a Bayesian graphical model with an informative prior that favors sparsity. Conditional on the network, we model dependence at the level of latent binary indicators rather than the raw expression measurements. One of the key features of the proposed approach is a hierarchical model that allows for the dependence structure to be shared across different experiments, in the case of the motivating application across different drugs and doses. This is critical to facilitate meaningful inference with the limited available sample sizes. The second key feature is a sparsity inducing prior on the dependence structure.

UR - http://www.scopus.com/inward/record.url?scp=84877806399&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84877806399&partnerID=8YFLogxK

U2 - 10.1109/GENSIPS.2012.6507742

DO - 10.1109/GENSIPS.2012.6507742

M3 - Conference contribution

SN - 9781467352369

SP - 113

EP - 117

BT - Proceedings 2012 IEEE International Workshop on Genomic Signal Processing and Statistics, GENSIPS 2012

ER -