miniTUBA

Medical inference by network integration of temporal data using Bayesian analysis

Zuoshuang Xiang, Rebecca M. Minter, Xiaoming Bi, Peter J. Woolf, Yongqun He

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Motivation: Many biomedical and clinical research problems involve discovering causal relationships between observations gathered from temporal events. Dynamic Bayesian networks are a powerful modeling approach to describe causal or apparently causal relationships, and support complex medical inference, such as future response prediction, automated learning, and rational decision making. Although many engines exist for creating Bayesian networks, most require a local installation and significant data manipulation to be practical for a general biologist or clinician. No software pipeline currently exists for interpretation and inference of dynamic Bayesian networks learned from biomedical and clinical data. Results: miniTUBA is a web-based modeling system that allows clinical and biomedical researchers to perform complex medical/clinical inference and prediction using dynamic Bayesian network analysis with temporal datasets. The software allows users to choose different analysis parameters (e.g. Markov lags and prior topology), and continuously update their data and refine their results. miniTUBA can make temporal predictions to suggest interventions based on an automated learning process pipeline using all data provided. Preliminary tests using synthetic data and laboratory research data indicate that miniTUBA accurately identifies regulatory network structures from temporal data.

Original languageEnglish (US)
Pages (from-to)2423-2432
Number of pages10
JournalBioinformatics
Volume23
Issue number18
DOIs
StatePublished - Sep 15 2007

Fingerprint

Bayes Theorem
Bayesian networks
Bayesian Analysis
Dynamic Bayesian Networks
Software
Pipelines
Learning
Prediction
Research laboratories
Electric network analysis
Biomedical Research
Decision Making
Preliminary Test
Regulatory Networks
Decision making
Research Personnel
Topology
Network Analysis
Synthetic Data
Engines

ASJC Scopus subject areas

  • Statistics and Probability
  • Medicine(all)
  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Computational Theory and Mathematics
  • Computational Mathematics

Cite this

miniTUBA : Medical inference by network integration of temporal data using Bayesian analysis. / Xiang, Zuoshuang; Minter, Rebecca M.; Bi, Xiaoming; Woolf, Peter J.; He, Yongqun.

In: Bioinformatics, Vol. 23, No. 18, 15.09.2007, p. 2423-2432.

Research output: Contribution to journalArticle

Xiang, Zuoshuang ; Minter, Rebecca M. ; Bi, Xiaoming ; Woolf, Peter J. ; He, Yongqun. / miniTUBA : Medical inference by network integration of temporal data using Bayesian analysis. In: Bioinformatics. 2007 ; Vol. 23, No. 18. pp. 2423-2432.
@article{909cd41d726b439586ff31c99198fd08,
title = "miniTUBA: Medical inference by network integration of temporal data using Bayesian analysis",
abstract = "Motivation: Many biomedical and clinical research problems involve discovering causal relationships between observations gathered from temporal events. Dynamic Bayesian networks are a powerful modeling approach to describe causal or apparently causal relationships, and support complex medical inference, such as future response prediction, automated learning, and rational decision making. Although many engines exist for creating Bayesian networks, most require a local installation and significant data manipulation to be practical for a general biologist or clinician. No software pipeline currently exists for interpretation and inference of dynamic Bayesian networks learned from biomedical and clinical data. Results: miniTUBA is a web-based modeling system that allows clinical and biomedical researchers to perform complex medical/clinical inference and prediction using dynamic Bayesian network analysis with temporal datasets. The software allows users to choose different analysis parameters (e.g. Markov lags and prior topology), and continuously update their data and refine their results. miniTUBA can make temporal predictions to suggest interventions based on an automated learning process pipeline using all data provided. Preliminary tests using synthetic data and laboratory research data indicate that miniTUBA accurately identifies regulatory network structures from temporal data.",
author = "Zuoshuang Xiang and Minter, {Rebecca M.} and Xiaoming Bi and Woolf, {Peter J.} and Yongqun He",
year = "2007",
month = "9",
day = "15",
doi = "10.1093/bioinformatics/btm372",
language = "English (US)",
volume = "23",
pages = "2423--2432",
journal = "Bioinformatics",
issn = "1367-4803",
publisher = "Oxford University Press",
number = "18",

}

TY - JOUR

T1 - miniTUBA

T2 - Medical inference by network integration of temporal data using Bayesian analysis

AU - Xiang, Zuoshuang

AU - Minter, Rebecca M.

AU - Bi, Xiaoming

AU - Woolf, Peter J.

AU - He, Yongqun

PY - 2007/9/15

Y1 - 2007/9/15

N2 - Motivation: Many biomedical and clinical research problems involve discovering causal relationships between observations gathered from temporal events. Dynamic Bayesian networks are a powerful modeling approach to describe causal or apparently causal relationships, and support complex medical inference, such as future response prediction, automated learning, and rational decision making. Although many engines exist for creating Bayesian networks, most require a local installation and significant data manipulation to be practical for a general biologist or clinician. No software pipeline currently exists for interpretation and inference of dynamic Bayesian networks learned from biomedical and clinical data. Results: miniTUBA is a web-based modeling system that allows clinical and biomedical researchers to perform complex medical/clinical inference and prediction using dynamic Bayesian network analysis with temporal datasets. The software allows users to choose different analysis parameters (e.g. Markov lags and prior topology), and continuously update their data and refine their results. miniTUBA can make temporal predictions to suggest interventions based on an automated learning process pipeline using all data provided. Preliminary tests using synthetic data and laboratory research data indicate that miniTUBA accurately identifies regulatory network structures from temporal data.

AB - Motivation: Many biomedical and clinical research problems involve discovering causal relationships between observations gathered from temporal events. Dynamic Bayesian networks are a powerful modeling approach to describe causal or apparently causal relationships, and support complex medical inference, such as future response prediction, automated learning, and rational decision making. Although many engines exist for creating Bayesian networks, most require a local installation and significant data manipulation to be practical for a general biologist or clinician. No software pipeline currently exists for interpretation and inference of dynamic Bayesian networks learned from biomedical and clinical data. Results: miniTUBA is a web-based modeling system that allows clinical and biomedical researchers to perform complex medical/clinical inference and prediction using dynamic Bayesian network analysis with temporal datasets. The software allows users to choose different analysis parameters (e.g. Markov lags and prior topology), and continuously update their data and refine their results. miniTUBA can make temporal predictions to suggest interventions based on an automated learning process pipeline using all data provided. Preliminary tests using synthetic data and laboratory research data indicate that miniTUBA accurately identifies regulatory network structures from temporal data.

UR - http://www.scopus.com/inward/record.url?scp=34548709663&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548709663&partnerID=8YFLogxK

U2 - 10.1093/bioinformatics/btm372

DO - 10.1093/bioinformatics/btm372

M3 - Article

VL - 23

SP - 2423

EP - 2432

JO - Bioinformatics

JF - Bioinformatics

SN - 1367-4803

IS - 18

ER -