A pattern mining based integrative framework for biomarker discovery

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

2 Citations (Scopus)

Abstract

Recent advances in high throughput data collection and imaging technologies have resulted in the availability of diverse biomedical datasets that capture complementary information pertaining to the biological processes in an organism. Biomarkers that are discovered by integrating such datasets obtained from case-control studies have the potential to elucidate the biological mechanisms behind complex human diseases. Of particular importance are interaction-type integrative biomarker, which are biomarkers whose features can explain the disease when taken together, but not when considered individually. We propose a pattern mining based integrative framework (PAMIN) to discover these interactiontype integrative biomarkers from diverse case control datasets. PAMIN first finds patterns from individual datasets to capture the available information separately and then combines these patterns to find integrated patterns (IPs) consisting of variables from multiple datasets. We also use several interestingness measures to characterize the IPs into specific categories. Using synthetic and real data we compare the IPs found using our approach with those found by CCA and discriminative-CCA (dCCA). Our results indicate that PAMIN is able to discover interaction type integrated patterns that these competing approaches cannot find.

Original languageEnglish (US)
Title of host publication2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012
Pages498-505
Number of pages8
DOIs
StatePublished - Nov 26 2012
Event2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012 - Orlando, FL, United States
Duration: Oct 7 2012Oct 10 2012

Publication series

Name2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012

Other

Other2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012
CountryUnited States
CityOrlando, FL
Period10/7/1210/10/12

Fingerprint

Biomarkers
Biological Phenomena
Throughput
Availability
Case-Control Studies
Imaging techniques
Datasets
Technology

Keywords

  • Algorithms

Cite this

Dey, S., Atluri, G., Steinbach, M. S., Lim, K. O., MacDonald, A., & Kumar, V. (2012). A pattern mining based integrative framework for biomarker discovery. In 2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012 (pp. 498-505). (2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012). https://doi.org/10.1145/2382936.2383000

A pattern mining based integrative framework for biomarker discovery. / Dey, Sanjoy; Atluri, Gowtham; Steinbach, Michael S; Lim, Kelvin O; MacDonald, Angus; Kumar, Vipin.

2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012. 2012. p. 498-505 (2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012).

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

Dey, S, Atluri, G, Steinbach, MS, Lim, KO, MacDonald, A & Kumar, V 2012, A pattern mining based integrative framework for biomarker discovery. in 2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012. 2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012, pp. 498-505, 2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012, Orlando, FL, United States, 10/7/12. https://doi.org/10.1145/2382936.2383000
Dey S, Atluri G, Steinbach MS, Lim KO, MacDonald A, Kumar V. A pattern mining based integrative framework for biomarker discovery. In 2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012. 2012. p. 498-505. (2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012). https://doi.org/10.1145/2382936.2383000
Dey, Sanjoy ; Atluri, Gowtham ; Steinbach, Michael S ; Lim, Kelvin O ; MacDonald, Angus ; Kumar, Vipin. / A pattern mining based integrative framework for biomarker discovery. 2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012. 2012. pp. 498-505 (2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012).
@inproceedings{61a2c8f22f7e47b992f07d7048804be9,
title = "A pattern mining based integrative framework for biomarker discovery",
abstract = "Recent advances in high throughput data collection and imaging technologies have resulted in the availability of diverse biomedical datasets that capture complementary information pertaining to the biological processes in an organism. Biomarkers that are discovered by integrating such datasets obtained from case-control studies have the potential to elucidate the biological mechanisms behind complex human diseases. Of particular importance are interaction-type integrative biomarker, which are biomarkers whose features can explain the disease when taken together, but not when considered individually. We propose a pattern mining based integrative framework (PAMIN) to discover these interactiontype integrative biomarkers from diverse case control datasets. PAMIN first finds patterns from individual datasets to capture the available information separately and then combines these patterns to find integrated patterns (IPs) consisting of variables from multiple datasets. We also use several interestingness measures to characterize the IPs into specific categories. Using synthetic and real data we compare the IPs found using our approach with those found by CCA and discriminative-CCA (dCCA). Our results indicate that PAMIN is able to discover interaction type integrated patterns that these competing approaches cannot find.",
keywords = "Algorithms",
author = "Sanjoy Dey and Gowtham Atluri and Steinbach, {Michael S} and Lim, {Kelvin O} and Angus MacDonald and Vipin Kumar",
year = "2012",
month = "11",
day = "26",
doi = "10.1145/2382936.2383000",
language = "English (US)",
isbn = "9781450316705",
series = "2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012",
pages = "498--505",
booktitle = "2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012",

}

TY - GEN

T1 - A pattern mining based integrative framework for biomarker discovery

AU - Dey, Sanjoy

AU - Atluri, Gowtham

AU - Steinbach, Michael S

AU - Lim, Kelvin O

AU - MacDonald, Angus

AU - Kumar, Vipin

PY - 2012/11/26

Y1 - 2012/11/26

N2 - Recent advances in high throughput data collection and imaging technologies have resulted in the availability of diverse biomedical datasets that capture complementary information pertaining to the biological processes in an organism. Biomarkers that are discovered by integrating such datasets obtained from case-control studies have the potential to elucidate the biological mechanisms behind complex human diseases. Of particular importance are interaction-type integrative biomarker, which are biomarkers whose features can explain the disease when taken together, but not when considered individually. We propose a pattern mining based integrative framework (PAMIN) to discover these interactiontype integrative biomarkers from diverse case control datasets. PAMIN first finds patterns from individual datasets to capture the available information separately and then combines these patterns to find integrated patterns (IPs) consisting of variables from multiple datasets. We also use several interestingness measures to characterize the IPs into specific categories. Using synthetic and real data we compare the IPs found using our approach with those found by CCA and discriminative-CCA (dCCA). Our results indicate that PAMIN is able to discover interaction type integrated patterns that these competing approaches cannot find.

AB - Recent advances in high throughput data collection and imaging technologies have resulted in the availability of diverse biomedical datasets that capture complementary information pertaining to the biological processes in an organism. Biomarkers that are discovered by integrating such datasets obtained from case-control studies have the potential to elucidate the biological mechanisms behind complex human diseases. Of particular importance are interaction-type integrative biomarker, which are biomarkers whose features can explain the disease when taken together, but not when considered individually. We propose a pattern mining based integrative framework (PAMIN) to discover these interactiontype integrative biomarkers from diverse case control datasets. PAMIN first finds patterns from individual datasets to capture the available information separately and then combines these patterns to find integrated patterns (IPs) consisting of variables from multiple datasets. We also use several interestingness measures to characterize the IPs into specific categories. Using synthetic and real data we compare the IPs found using our approach with those found by CCA and discriminative-CCA (dCCA). Our results indicate that PAMIN is able to discover interaction type integrated patterns that these competing approaches cannot find.

KW - Algorithms

UR - http://www.scopus.com/inward/record.url?scp=84869424548&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84869424548&partnerID=8YFLogxK

U2 - 10.1145/2382936.2383000

DO - 10.1145/2382936.2383000

M3 - Conference contribution

AN - SCOPUS:84869424548

SN - 9781450316705

T3 - 2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012

SP - 498

EP - 505

BT - 2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012

ER -