Knowledge-driven genomic interactions

An application in ovarian cancer

Dokyoon Kim, Ruowang Li, Scott M. Dudek, Alex T. Frase, Sarah A. Pendergrass, Marylyn Deriggi Ritchie

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Background: Effective cancer clinical outcome prediction for understanding of the mechanism of various types of cancer has been pursued using molecular-based data such as gene expression profiles, an approach that has promise for providing better diagnostics and supporting further therapies. However, clinical outcome prediction based on gene expression profiles varies between independent data sets. Further, single-gene expression outcome prediction is limited for cancer evaluation since genes do not act in isolation, but rather interact with other genes in complex signaling or regulatory networks. In addition, since pathways are more likely to co-operate together, it would be desirable to incorporate expert knowledge to combine pathways in a useful and informative manner.

Methods: Thus, we propose a novel approach for identifying knowledge-driven genomic interactions and applying it to discover models associated with cancer clinical phenotypes using grammatical evolution neural networks (GENN). In order to demonstrate the utility of the proposed approach, an ovarian cancer data from the Cancer Genome Atlas (TCGA) was used for predicting clinical stage as a pilot project.

Results: We identified knowledge-driven genomic interactions associated with cancer stage from single knowledge bases such as sources of pathway-pathway interaction, but also knowledge-driven genomic interactions across different sets of knowledge bases such as pathway-protein family interactions by integrating different types of information. Notably, an integration model from different sources of biological knowledge achieved 78.82% balanced accuracy and outperformed the top models with gene expression or single knowledge-based data types alone. Furthermore, the results from the models are more interpretable because they are framed in the context of specific biological pathways or other expert knowledge.

Conclusions: The success of the pilot study we have presented herein will allow us to pursue further identification of models predictive of clinical cancer survival and recurrence. Understanding the underlying tumorigenesis and progression in ovarian cancer through the global view of interactions within/between different biological knowledge sources has the potential for providing more effective screening strategies and therapeutic targets for many types of cancer.

Original languageEnglish (US)
Article number20
JournalBioData Mining
Volume7
Issue number1
DOIs
StatePublished - Sep 9 2014

Fingerprint

Ovarian Cancer
Ovarian Neoplasms
Genomics
Cancer
Gene expression
Pathway
Interaction
Genes
Neoplasms
Gene Expression Profile
Knowledge Bases
Transcriptome
Knowledge Base
Gene Expression
Prediction
Grammatical Evolution
Gene
Identification (control systems)
Screening
Model

All Science Journal Classification (ASJC) codes

  • Biochemistry
  • Molecular Biology
  • Genetics
  • Computer Science Applications
  • Computational Theory and Mathematics
  • Computational Mathematics

Cite this

Kim, D., Li, R., Dudek, S. M., Frase, A. T., Pendergrass, S. A., & Ritchie, M. D. (2014). Knowledge-driven genomic interactions: An application in ovarian cancer. BioData Mining, 7(1), [20]. https://doi.org/10.1186/1756-0381-7-20
Kim, Dokyoon ; Li, Ruowang ; Dudek, Scott M. ; Frase, Alex T. ; Pendergrass, Sarah A. ; Ritchie, Marylyn Deriggi. / Knowledge-driven genomic interactions : An application in ovarian cancer. In: BioData Mining. 2014 ; Vol. 7, No. 1.
@article{508666efcfcb4a17ba562adfbe6f8dc9,
title = "Knowledge-driven genomic interactions: An application in ovarian cancer",
abstract = "Background: Effective cancer clinical outcome prediction for understanding of the mechanism of various types of cancer has been pursued using molecular-based data such as gene expression profiles, an approach that has promise for providing better diagnostics and supporting further therapies. However, clinical outcome prediction based on gene expression profiles varies between independent data sets. Further, single-gene expression outcome prediction is limited for cancer evaluation since genes do not act in isolation, but rather interact with other genes in complex signaling or regulatory networks. In addition, since pathways are more likely to co-operate together, it would be desirable to incorporate expert knowledge to combine pathways in a useful and informative manner.Methods: Thus, we propose a novel approach for identifying knowledge-driven genomic interactions and applying it to discover models associated with cancer clinical phenotypes using grammatical evolution neural networks (GENN). In order to demonstrate the utility of the proposed approach, an ovarian cancer data from the Cancer Genome Atlas (TCGA) was used for predicting clinical stage as a pilot project.Results: We identified knowledge-driven genomic interactions associated with cancer stage from single knowledge bases such as sources of pathway-pathway interaction, but also knowledge-driven genomic interactions across different sets of knowledge bases such as pathway-protein family interactions by integrating different types of information. Notably, an integration model from different sources of biological knowledge achieved 78.82{\%} balanced accuracy and outperformed the top models with gene expression or single knowledge-based data types alone. Furthermore, the results from the models are more interpretable because they are framed in the context of specific biological pathways or other expert knowledge.Conclusions: The success of the pilot study we have presented herein will allow us to pursue further identification of models predictive of clinical cancer survival and recurrence. Understanding the underlying tumorigenesis and progression in ovarian cancer through the global view of interactions within/between different biological knowledge sources has the potential for providing more effective screening strategies and therapeutic targets for many types of cancer.",
author = "Dokyoon Kim and Ruowang Li and Dudek, {Scott M.} and Frase, {Alex T.} and Pendergrass, {Sarah A.} and Ritchie, {Marylyn Deriggi}",
year = "2014",
month = "9",
day = "9",
doi = "10.1186/1756-0381-7-20",
language = "English (US)",
volume = "7",
journal = "BioData Mining",
issn = "1756-0381",
publisher = "BioMed Central",
number = "1",

}

Kim, D, Li, R, Dudek, SM, Frase, AT, Pendergrass, SA & Ritchie, MD 2014, 'Knowledge-driven genomic interactions: An application in ovarian cancer', BioData Mining, vol. 7, no. 1, 20. https://doi.org/10.1186/1756-0381-7-20

Knowledge-driven genomic interactions : An application in ovarian cancer. / Kim, Dokyoon; Li, Ruowang; Dudek, Scott M.; Frase, Alex T.; Pendergrass, Sarah A.; Ritchie, Marylyn Deriggi.

In: BioData Mining, Vol. 7, No. 1, 20, 09.09.2014.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Knowledge-driven genomic interactions

T2 - An application in ovarian cancer

AU - Kim, Dokyoon

AU - Li, Ruowang

AU - Dudek, Scott M.

AU - Frase, Alex T.

AU - Pendergrass, Sarah A.

AU - Ritchie, Marylyn Deriggi

PY - 2014/9/9

Y1 - 2014/9/9

N2 - Background: Effective cancer clinical outcome prediction for understanding of the mechanism of various types of cancer has been pursued using molecular-based data such as gene expression profiles, an approach that has promise for providing better diagnostics and supporting further therapies. However, clinical outcome prediction based on gene expression profiles varies between independent data sets. Further, single-gene expression outcome prediction is limited for cancer evaluation since genes do not act in isolation, but rather interact with other genes in complex signaling or regulatory networks. In addition, since pathways are more likely to co-operate together, it would be desirable to incorporate expert knowledge to combine pathways in a useful and informative manner.Methods: Thus, we propose a novel approach for identifying knowledge-driven genomic interactions and applying it to discover models associated with cancer clinical phenotypes using grammatical evolution neural networks (GENN). In order to demonstrate the utility of the proposed approach, an ovarian cancer data from the Cancer Genome Atlas (TCGA) was used for predicting clinical stage as a pilot project.Results: We identified knowledge-driven genomic interactions associated with cancer stage from single knowledge bases such as sources of pathway-pathway interaction, but also knowledge-driven genomic interactions across different sets of knowledge bases such as pathway-protein family interactions by integrating different types of information. Notably, an integration model from different sources of biological knowledge achieved 78.82% balanced accuracy and outperformed the top models with gene expression or single knowledge-based data types alone. Furthermore, the results from the models are more interpretable because they are framed in the context of specific biological pathways or other expert knowledge.Conclusions: The success of the pilot study we have presented herein will allow us to pursue further identification of models predictive of clinical cancer survival and recurrence. Understanding the underlying tumorigenesis and progression in ovarian cancer through the global view of interactions within/between different biological knowledge sources has the potential for providing more effective screening strategies and therapeutic targets for many types of cancer.

AB - Background: Effective cancer clinical outcome prediction for understanding of the mechanism of various types of cancer has been pursued using molecular-based data such as gene expression profiles, an approach that has promise for providing better diagnostics and supporting further therapies. However, clinical outcome prediction based on gene expression profiles varies between independent data sets. Further, single-gene expression outcome prediction is limited for cancer evaluation since genes do not act in isolation, but rather interact with other genes in complex signaling or regulatory networks. In addition, since pathways are more likely to co-operate together, it would be desirable to incorporate expert knowledge to combine pathways in a useful and informative manner.Methods: Thus, we propose a novel approach for identifying knowledge-driven genomic interactions and applying it to discover models associated with cancer clinical phenotypes using grammatical evolution neural networks (GENN). In order to demonstrate the utility of the proposed approach, an ovarian cancer data from the Cancer Genome Atlas (TCGA) was used for predicting clinical stage as a pilot project.Results: We identified knowledge-driven genomic interactions associated with cancer stage from single knowledge bases such as sources of pathway-pathway interaction, but also knowledge-driven genomic interactions across different sets of knowledge bases such as pathway-protein family interactions by integrating different types of information. Notably, an integration model from different sources of biological knowledge achieved 78.82% balanced accuracy and outperformed the top models with gene expression or single knowledge-based data types alone. Furthermore, the results from the models are more interpretable because they are framed in the context of specific biological pathways or other expert knowledge.Conclusions: The success of the pilot study we have presented herein will allow us to pursue further identification of models predictive of clinical cancer survival and recurrence. Understanding the underlying tumorigenesis and progression in ovarian cancer through the global view of interactions within/between different biological knowledge sources has the potential for providing more effective screening strategies and therapeutic targets for many types of cancer.

UR - http://www.scopus.com/inward/record.url?scp=84907058092&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84907058092&partnerID=8YFLogxK

U2 - 10.1186/1756-0381-7-20

DO - 10.1186/1756-0381-7-20

M3 - Article

VL - 7

JO - BioData Mining

JF - BioData Mining

SN - 1756-0381

IS - 1

M1 - 20

ER -

Kim D, Li R, Dudek SM, Frase AT, Pendergrass SA, Ritchie MD. Knowledge-driven genomic interactions: An application in ovarian cancer. BioData Mining. 2014 Sep 9;7(1). 20. https://doi.org/10.1186/1756-0381-7-20