Experimental design of time series data for learning from dynamic Bayesian networks.


Conference Paper

Bayesian networks (BNs) and dynamic Bayesian networks (DBNs) are becoming more widely used as a way to learn various types of networks, including cellular signaling networks, from high-throughput data. Due to the high cost of performing experiments, we are interested in developing an experimental design for time series data generation. Specifically, we are interested in determining properties of time series data that make them more efficient for DBN modeling. We present a theoretical analysis on the ability of DBNs without hidden variables to learn from proteomic time series data. The analysis reveals, among other lessons, that under a reasonable set of assumptions a fixed budget is better spent on collecting many short time series data than on a few long time series data.

Full Text

Duke Authors

Cited Authors

  • Page, D; Ong, IM

Published Date

  • 2006

Published In

  • Pac Symp Biocomput

Start / End Page

  • 267 - 278

PubMed ID

  • 17094245

Pubmed Central ID

  • 17094245

International Standard Serial Number (ISSN)

  • 2335-6928

Conference Location

  • United States