Learning binary threshold networks for gene regulatory network modeling

Gonzalo A. Ruz; Eric Goles

doi:10.1109/CIBCB55180.2022.9863056

Learning binary threshold networks for gene regulatory network modeling

Gonzalo A. Ruz, Eric Goles

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

Abstract

Inspired by the resent trend of binary neural net-works, where weights and activation thresholds are represented using 1 and-1 such that they can be stored in 1-bit instead of full precision, we explore this approach for gene regulatory network modeling. An evolutionary computation approach to learn binary threshold networks is presented. In particular, we consider differential evolution and particle swarm optimization. We test our method by inferring binary threshold networks of a regulatory network of Quorum sensing systems in bacterium Paraburkholderia phytofirmans PsJN. We present results for weights having only 1 and-1 values, and consider different activation thresholds. Full binary threshold networks were found with minimum error (2 bits), whereas when the binary restriction is relaxed for the activation thresholds, networks with 0 bit error were found.

Original language	English
Title of host publication	2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665484626
DOIs	https://doi.org/10.1109/CIBCB55180.2022.9863056
State	Published - 2022
Externally published	Yes
Event	2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2022 - Ottawa, Canada Duration: 14 Aug 2022 → 16 Aug 2022

Publication series

Name	2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2022

Conference

Conference	2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2022
Country/Territory	Canada
City	Ottawa
Period	14/08/22 → 16/08/22

Keywords

Binary threshold networks
Differential evolution
Gene regulatory networks
Particle swarm optimization

Access to Document

10.1109/CIBCB55180.2022.9863056

Cite this

Ruz, G. A., & Goles, E. (2022). Learning binary threshold networks for gene regulatory network modeling. In 2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2022 (2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CIBCB55180.2022.9863056

Ruz, Gonzalo A. ; Goles, Eric. / Learning binary threshold networks for gene regulatory network modeling. 2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2022).

@inproceedings{164bd5113fe2451586752da4c69b83ed,

title = "Learning binary threshold networks for gene regulatory network modeling",

abstract = "Inspired by the resent trend of binary neural net-works, where weights and activation thresholds are represented using 1 and-1 such that they can be stored in 1-bit instead of full precision, we explore this approach for gene regulatory network modeling. An evolutionary computation approach to learn binary threshold networks is presented. In particular, we consider differential evolution and particle swarm optimization. We test our method by inferring binary threshold networks of a regulatory network of Quorum sensing systems in bacterium Paraburkholderia phytofirmans PsJN. We present results for weights having only 1 and-1 values, and consider different activation thresholds. Full binary threshold networks were found with minimum error (2 bits), whereas when the binary restriction is relaxed for the activation thresholds, networks with 0 bit error were found.",

keywords = "Binary threshold networks, Differential evolution, Gene regulatory networks, Particle swarm optimization",

author = "Ruz, {Gonzalo A.} and Eric Goles",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2022 ; Conference date: 14-08-2022 Through 16-08-2022",

year = "2022",

doi = "10.1109/CIBCB55180.2022.9863056",

language = "English",

series = "2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2022",

}

Ruz, GA & Goles, E 2022, Learning binary threshold networks for gene regulatory network modeling. in 2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2022. 2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2022, Institute of Electrical and Electronics Engineers Inc., 2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2022, Ottawa, Canada, 14/08/22. https://doi.org/10.1109/CIBCB55180.2022.9863056

Learning binary threshold networks for gene regulatory network modeling. / Ruz, Gonzalo A.; Goles, Eric.
2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Learning binary threshold networks for gene regulatory network modeling

AU - Ruz, Gonzalo A.

AU - Goles, Eric

PY - 2022

Y1 - 2022

N2 - Inspired by the resent trend of binary neural net-works, where weights and activation thresholds are represented using 1 and-1 such that they can be stored in 1-bit instead of full precision, we explore this approach for gene regulatory network modeling. An evolutionary computation approach to learn binary threshold networks is presented. In particular, we consider differential evolution and particle swarm optimization. We test our method by inferring binary threshold networks of a regulatory network of Quorum sensing systems in bacterium Paraburkholderia phytofirmans PsJN. We present results for weights having only 1 and-1 values, and consider different activation thresholds. Full binary threshold networks were found with minimum error (2 bits), whereas when the binary restriction is relaxed for the activation thresholds, networks with 0 bit error were found.

AB - Inspired by the resent trend of binary neural net-works, where weights and activation thresholds are represented using 1 and-1 such that they can be stored in 1-bit instead of full precision, we explore this approach for gene regulatory network modeling. An evolutionary computation approach to learn binary threshold networks is presented. In particular, we consider differential evolution and particle swarm optimization. We test our method by inferring binary threshold networks of a regulatory network of Quorum sensing systems in bacterium Paraburkholderia phytofirmans PsJN. We present results for weights having only 1 and-1 values, and consider different activation thresholds. Full binary threshold networks were found with minimum error (2 bits), whereas when the binary restriction is relaxed for the activation thresholds, networks with 0 bit error were found.

KW - Binary threshold networks

KW - Differential evolution

KW - Gene regulatory networks

KW - Particle swarm optimization

UR - http://www.scopus.com/inward/record.url?scp=85137875997&partnerID=8YFLogxK

U2 - 10.1109/CIBCB55180.2022.9863056

DO - 10.1109/CIBCB55180.2022.9863056

M3 - Conference contribution

AN - SCOPUS:85137875997

T3 - 2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2022

BT - 2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2022

Y2 - 14 August 2022 through 16 August 2022

ER -

Ruz GA , Goles E. Learning binary threshold networks for gene regulatory network modeling. In 2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2022. Institute of Electrical and Electronics Engineers Inc. 2022. (2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2022). doi: 10.1109/CIBCB55180.2022.9863056

Learning binary threshold networks for gene regulatory network modeling

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this