VIPR: A probabilistic algorithm for analysis of microbial detection microarrays

Adam F. Allred, Guang Wu, Tuya Wulan, Kael F. Fischer, Michael R. Holbrook, Robert B. Tesh, David Wang

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Background: All infectious disease oriented clinical diagnostic assays in use today focus on detecting the presence of a single, well defined target agent or a set of agents. In recent years, microarray-based diagnostics have been developed that greatly facilitate the highly parallel detection of multiple microbes that may be present in a given clinical specimen. While several algorithms have been described for interpretation of diagnostic microarrays, none of the existing approaches is capable of incorporating training data generated from positive control samples to improve performance.Results: To specifically address this issue we have developed a novel interpretive algorithm, VIPR (Viral Identification using a PRobabilistic algorithm), which uses Bayesian inference to capitalize on empirical training data to optimize detection sensitivity. To illustrate this approach, we have focused on the detection of viruses that cause hemorrhagic fever (HF) using a custom HF-virus microarray. VIPR was used to analyze 110 empirical microarray hybridizations generated from 33 distinct virus species. An accuracy of 94% was achieved as measured by leave-one-out cross validation. Conclusions. VIPR outperformed previously described algorithms for this dataset. The VIPR algorithm has potential to be broadly applicable to clinical diagnostic settings, wherein positive controls are typically readily available for generation of training data.

Original languageEnglish (US)
Article number384
JournalBMC Bioinformatics
Volume11
DOIs
StatePublished - Jul 20 2010

Fingerprint

Probabilistic Algorithms
Microarrays
Microarray
Diagnostics
Virus
Viruses
Fever
Infectious Diseases
Bayesian inference
Cross-validation
Well-defined
Optimise
Communicable Diseases
Assays
Distinct
Target
Training

ASJC Scopus subject areas

  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Structural Biology
  • Applied Mathematics

Cite this

Allred, A. F., Wu, G., Wulan, T., Fischer, K. F., Holbrook, M. R., Tesh, R. B., & Wang, D. (2010). VIPR: A probabilistic algorithm for analysis of microbial detection microarrays. BMC Bioinformatics, 11, [384]. https://doi.org/10.1186/1471-2105-11-384

VIPR : A probabilistic algorithm for analysis of microbial detection microarrays. / Allred, Adam F.; Wu, Guang; Wulan, Tuya; Fischer, Kael F.; Holbrook, Michael R.; Tesh, Robert B.; Wang, David.

In: BMC Bioinformatics, Vol. 11, 384, 20.07.2010.

Research output: Contribution to journalArticle

Allred, AF, Wu, G, Wulan, T, Fischer, KF, Holbrook, MR, Tesh, RB & Wang, D 2010, 'VIPR: A probabilistic algorithm for analysis of microbial detection microarrays', BMC Bioinformatics, vol. 11, 384. https://doi.org/10.1186/1471-2105-11-384
Allred, Adam F. ; Wu, Guang ; Wulan, Tuya ; Fischer, Kael F. ; Holbrook, Michael R. ; Tesh, Robert B. ; Wang, David. / VIPR : A probabilistic algorithm for analysis of microbial detection microarrays. In: BMC Bioinformatics. 2010 ; Vol. 11.
@article{b78b176027ec4f4faa8587c5ce94aa72,
title = "VIPR: A probabilistic algorithm for analysis of microbial detection microarrays",
abstract = "Background: All infectious disease oriented clinical diagnostic assays in use today focus on detecting the presence of a single, well defined target agent or a set of agents. In recent years, microarray-based diagnostics have been developed that greatly facilitate the highly parallel detection of multiple microbes that may be present in a given clinical specimen. While several algorithms have been described for interpretation of diagnostic microarrays, none of the existing approaches is capable of incorporating training data generated from positive control samples to improve performance.Results: To specifically address this issue we have developed a novel interpretive algorithm, VIPR (Viral Identification using a PRobabilistic algorithm), which uses Bayesian inference to capitalize on empirical training data to optimize detection sensitivity. To illustrate this approach, we have focused on the detection of viruses that cause hemorrhagic fever (HF) using a custom HF-virus microarray. VIPR was used to analyze 110 empirical microarray hybridizations generated from 33 distinct virus species. An accuracy of 94{\%} was achieved as measured by leave-one-out cross validation. Conclusions. VIPR outperformed previously described algorithms for this dataset. The VIPR algorithm has potential to be broadly applicable to clinical diagnostic settings, wherein positive controls are typically readily available for generation of training data.",
author = "Allred, {Adam F.} and Guang Wu and Tuya Wulan and Fischer, {Kael F.} and Holbrook, {Michael R.} and Tesh, {Robert B.} and David Wang",
year = "2010",
month = "7",
day = "20",
doi = "10.1186/1471-2105-11-384",
language = "English (US)",
volume = "11",
journal = "BMC Bioinformatics",
issn = "1471-2105",
publisher = "BioMed Central",

}

TY - JOUR

T1 - VIPR

T2 - A probabilistic algorithm for analysis of microbial detection microarrays

AU - Allred, Adam F.

AU - Wu, Guang

AU - Wulan, Tuya

AU - Fischer, Kael F.

AU - Holbrook, Michael R.

AU - Tesh, Robert B.

AU - Wang, David

PY - 2010/7/20

Y1 - 2010/7/20

N2 - Background: All infectious disease oriented clinical diagnostic assays in use today focus on detecting the presence of a single, well defined target agent or a set of agents. In recent years, microarray-based diagnostics have been developed that greatly facilitate the highly parallel detection of multiple microbes that may be present in a given clinical specimen. While several algorithms have been described for interpretation of diagnostic microarrays, none of the existing approaches is capable of incorporating training data generated from positive control samples to improve performance.Results: To specifically address this issue we have developed a novel interpretive algorithm, VIPR (Viral Identification using a PRobabilistic algorithm), which uses Bayesian inference to capitalize on empirical training data to optimize detection sensitivity. To illustrate this approach, we have focused on the detection of viruses that cause hemorrhagic fever (HF) using a custom HF-virus microarray. VIPR was used to analyze 110 empirical microarray hybridizations generated from 33 distinct virus species. An accuracy of 94% was achieved as measured by leave-one-out cross validation. Conclusions. VIPR outperformed previously described algorithms for this dataset. The VIPR algorithm has potential to be broadly applicable to clinical diagnostic settings, wherein positive controls are typically readily available for generation of training data.

AB - Background: All infectious disease oriented clinical diagnostic assays in use today focus on detecting the presence of a single, well defined target agent or a set of agents. In recent years, microarray-based diagnostics have been developed that greatly facilitate the highly parallel detection of multiple microbes that may be present in a given clinical specimen. While several algorithms have been described for interpretation of diagnostic microarrays, none of the existing approaches is capable of incorporating training data generated from positive control samples to improve performance.Results: To specifically address this issue we have developed a novel interpretive algorithm, VIPR (Viral Identification using a PRobabilistic algorithm), which uses Bayesian inference to capitalize on empirical training data to optimize detection sensitivity. To illustrate this approach, we have focused on the detection of viruses that cause hemorrhagic fever (HF) using a custom HF-virus microarray. VIPR was used to analyze 110 empirical microarray hybridizations generated from 33 distinct virus species. An accuracy of 94% was achieved as measured by leave-one-out cross validation. Conclusions. VIPR outperformed previously described algorithms for this dataset. The VIPR algorithm has potential to be broadly applicable to clinical diagnostic settings, wherein positive controls are typically readily available for generation of training data.

UR - http://www.scopus.com/inward/record.url?scp=77954680497&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77954680497&partnerID=8YFLogxK

U2 - 10.1186/1471-2105-11-384

DO - 10.1186/1471-2105-11-384

M3 - Article

C2 - 20646301

AN - SCOPUS:77954680497

VL - 11

JO - BMC Bioinformatics

JF - BMC Bioinformatics

SN - 1471-2105

M1 - 384

ER -