Learning biological networks via bootstrapping with optimized GO-based gene similarity

Ronald Taylor, Bob Baddeley, Antonio Sanfilippo, Rick Riensche, Marc Verhagen, Jason McDermott, Russ Jensen

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

Abstract

Microarray gene expression data provide a unique information resource for learning biological networks using "reverse engineering" methods. However, there are a variety of cases in which we know which genes are involved in a given pathology of interest, but we do not have enough experimental evidence to support the use of fully-supervised/reverse-engineering learning methods. Moreover, corroboration of the reverse engineered networks through independent means such as evidence from the biomedical literature is always desirable. In this paper, we explore a novel semi-supervised approach in which biological networks are learned from a reference list of genes and a partial set of links for these genes extracted automatically from PubMed abstracts, using a knowledge-driven bootstrapping algorithm. We show how new relevant links between genes can be iteratively derived using a gene similarity measure based on the Gene Ontology that is optimized on the input network at each iteration. An initial evaluation indicates the viability of the approach as an alternate or complementary technique to fully supervised methods.

Original languageEnglish
Title of host publication2010 ACM International Conference on Bioinformatics and Computational Biology, ACM-BCB 2010
Pages515-519
Number of pages5
DOIs
Publication statusPublished - 2010
Externally publishedYes
Event2010 ACM International Conference on Bioinformatics and Computational Biology, ACM-BCB 2010 - Niagara Falls, NY
Duration: 2 Aug 20104 Aug 2010

Other

Other2010 ACM International Conference on Bioinformatics and Computational Biology, ACM-BCB 2010
CityNiagara Falls, NY
Period2/8/104/8/10

Fingerprint

Genes
Learning
Reverse engineering
Gene Ontology
PubMed
Pathology
Microarrays
Gene expression
Ontology
Gene Expression

Keywords

  • Biological networks
  • Gene ontology
  • Network inference
  • Simulated annealing
  • Supervised machine learning

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Information Management

Cite this

Taylor, R., Baddeley, B., Sanfilippo, A., Riensche, R., Verhagen, M., McDermott, J., & Jensen, R. (2010). Learning biological networks via bootstrapping with optimized GO-based gene similarity. In 2010 ACM International Conference on Bioinformatics and Computational Biology, ACM-BCB 2010 (pp. 515-519) https://doi.org/10.1145/1854776.1854875

Learning biological networks via bootstrapping with optimized GO-based gene similarity. / Taylor, Ronald; Baddeley, Bob; Sanfilippo, Antonio; Riensche, Rick; Verhagen, Marc; McDermott, Jason; Jensen, Russ.

2010 ACM International Conference on Bioinformatics and Computational Biology, ACM-BCB 2010. 2010. p. 515-519.

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

Taylor, R, Baddeley, B, Sanfilippo, A, Riensche, R, Verhagen, M, McDermott, J & Jensen, R 2010, Learning biological networks via bootstrapping with optimized GO-based gene similarity. in 2010 ACM International Conference on Bioinformatics and Computational Biology, ACM-BCB 2010. pp. 515-519, 2010 ACM International Conference on Bioinformatics and Computational Biology, ACM-BCB 2010, Niagara Falls, NY, 2/8/10. https://doi.org/10.1145/1854776.1854875
Taylor R, Baddeley B, Sanfilippo A, Riensche R, Verhagen M, McDermott J et al. Learning biological networks via bootstrapping with optimized GO-based gene similarity. In 2010 ACM International Conference on Bioinformatics and Computational Biology, ACM-BCB 2010. 2010. p. 515-519 https://doi.org/10.1145/1854776.1854875
Taylor, Ronald ; Baddeley, Bob ; Sanfilippo, Antonio ; Riensche, Rick ; Verhagen, Marc ; McDermott, Jason ; Jensen, Russ. / Learning biological networks via bootstrapping with optimized GO-based gene similarity. 2010 ACM International Conference on Bioinformatics and Computational Biology, ACM-BCB 2010. 2010. pp. 515-519
@inproceedings{e8043325e4854188a610553cf1d5b538,
title = "Learning biological networks via bootstrapping with optimized GO-based gene similarity",
abstract = "Microarray gene expression data provide a unique information resource for learning biological networks using {"}reverse engineering{"} methods. However, there are a variety of cases in which we know which genes are involved in a given pathology of interest, but we do not have enough experimental evidence to support the use of fully-supervised/reverse-engineering learning methods. Moreover, corroboration of the reverse engineered networks through independent means such as evidence from the biomedical literature is always desirable. In this paper, we explore a novel semi-supervised approach in which biological networks are learned from a reference list of genes and a partial set of links for these genes extracted automatically from PubMed abstracts, using a knowledge-driven bootstrapping algorithm. We show how new relevant links between genes can be iteratively derived using a gene similarity measure based on the Gene Ontology that is optimized on the input network at each iteration. An initial evaluation indicates the viability of the approach as an alternate or complementary technique to fully supervised methods.",
keywords = "Biological networks, Gene ontology, Network inference, Simulated annealing, Supervised machine learning",
author = "Ronald Taylor and Bob Baddeley and Antonio Sanfilippo and Rick Riensche and Marc Verhagen and Jason McDermott and Russ Jensen",
year = "2010",
doi = "10.1145/1854776.1854875",
language = "English",
isbn = "9781450304382",
pages = "515--519",
booktitle = "2010 ACM International Conference on Bioinformatics and Computational Biology, ACM-BCB 2010",

}

TY - GEN

T1 - Learning biological networks via bootstrapping with optimized GO-based gene similarity

AU - Taylor, Ronald

AU - Baddeley, Bob

AU - Sanfilippo, Antonio

AU - Riensche, Rick

AU - Verhagen, Marc

AU - McDermott, Jason

AU - Jensen, Russ

PY - 2010

Y1 - 2010

N2 - Microarray gene expression data provide a unique information resource for learning biological networks using "reverse engineering" methods. However, there are a variety of cases in which we know which genes are involved in a given pathology of interest, but we do not have enough experimental evidence to support the use of fully-supervised/reverse-engineering learning methods. Moreover, corroboration of the reverse engineered networks through independent means such as evidence from the biomedical literature is always desirable. In this paper, we explore a novel semi-supervised approach in which biological networks are learned from a reference list of genes and a partial set of links for these genes extracted automatically from PubMed abstracts, using a knowledge-driven bootstrapping algorithm. We show how new relevant links between genes can be iteratively derived using a gene similarity measure based on the Gene Ontology that is optimized on the input network at each iteration. An initial evaluation indicates the viability of the approach as an alternate or complementary technique to fully supervised methods.

AB - Microarray gene expression data provide a unique information resource for learning biological networks using "reverse engineering" methods. However, there are a variety of cases in which we know which genes are involved in a given pathology of interest, but we do not have enough experimental evidence to support the use of fully-supervised/reverse-engineering learning methods. Moreover, corroboration of the reverse engineered networks through independent means such as evidence from the biomedical literature is always desirable. In this paper, we explore a novel semi-supervised approach in which biological networks are learned from a reference list of genes and a partial set of links for these genes extracted automatically from PubMed abstracts, using a knowledge-driven bootstrapping algorithm. We show how new relevant links between genes can be iteratively derived using a gene similarity measure based on the Gene Ontology that is optimized on the input network at each iteration. An initial evaluation indicates the viability of the approach as an alternate or complementary technique to fully supervised methods.

KW - Biological networks

KW - Gene ontology

KW - Network inference

KW - Simulated annealing

KW - Supervised machine learning

UR - http://www.scopus.com/inward/record.url?scp=77958053196&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77958053196&partnerID=8YFLogxK

U2 - 10.1145/1854776.1854875

DO - 10.1145/1854776.1854875

M3 - Conference contribution

AN - SCOPUS:77958053196

SN - 9781450304382

SP - 515

EP - 519

BT - 2010 ACM International Conference on Bioinformatics and Computational Biology, ACM-BCB 2010

ER -