An evolutionary approach to the discretization of gene expression profiles to predict the severity of COVID-19

Nisrine Mouhrim; Alberto Tonda; Itzel Rodríguez-Guerra; Aletta D. Kraneveld; Alejandro Lopez Rincon

doi:10.1145/3520304.3529001

An evolutionary approach to the discretization of gene expression profiles to predict the severity of COVID-19

Nisrine Mouhrim, Alberto Tonda, Itzel Rodríguez-Guerra, Aletta D. Kraneveld, Alejandro Lopez Rincon

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

Abstract

In this work, we propose to use a state-of-the-art evolutionary algorithm to set the discretization thresholds for gene expression profiles, using feedback from a classifier in order to maximize the accuracy of the predictions based on the discretized gene expression levels, while at the same time minimizing the number of different profiles obtained, to ease the understanding of the expert. The methodology is applied to a dataset containing COVID-19 patients that developed either mild or severe symptoms. The results show that the evolutionary approach performs better than a traditional discretization based on statistical analysis, and that it does preserve the sense-making necessary for practitioners to trust the results.

Original language	English
Title of host publication	GECCO '22: Proceedings of the Genetic and Evolutionary Computation Conference Companion
Editors	Jonathan E. Fieldsend
Publisher	Association for Computing Machinery
Pages	731-734
Number of pages	4
ISBN (Electronic)	9781450392686
DOIs	https://doi.org/10.1145/3520304.3529001
Publication status	Published - 9 Jul 2022
Event	2022 Genetic and Evolutionary Computation Conference, GECCO 2022 - Virtual, Online, United States Duration: 9 Jul 2022 → 13 Jul 2022

Conference

Conference	2022 Genetic and Evolutionary Computation Conference, GECCO 2022
Country/Territory	United States
City	Virtual, Online
Period	9/07/22 → 13/07/22

Keywords

covid-19
discretization
evolutionary optimization
gene expression profiles
prognosis

Access to Document

10.1145/3520304.3529001

3520304.3529001Final published version, 952 KBLicence: Taverne

Cite this

Mouhrim, N., Tonda, A., Rodríguez-Guerra, I., Kraneveld, A. D., & Rincon, A. L. (2022). An evolutionary approach to the discretization of gene expression profiles to predict the severity of COVID-19. In J. E. Fieldsend (Ed.), GECCO '22: Proceedings of the Genetic and Evolutionary Computation Conference Companion (pp. 731-734). Association for Computing Machinery. https://doi.org/10.1145/3520304.3529001

@inproceedings{1cce3a3d7a244e66835648173f085d05,

title = "An evolutionary approach to the discretization of gene expression profiles to predict the severity of COVID-19",

abstract = "In this work, we propose to use a state-of-the-art evolutionary algorithm to set the discretization thresholds for gene expression profiles, using feedback from a classifier in order to maximize the accuracy of the predictions based on the discretized gene expression levels, while at the same time minimizing the number of different profiles obtained, to ease the understanding of the expert. The methodology is applied to a dataset containing COVID-19 patients that developed either mild or severe symptoms. The results show that the evolutionary approach performs better than a traditional discretization based on statistical analysis, and that it does preserve the sense-making necessary for practitioners to trust the results.",

keywords = "covid-19, discretization, evolutionary optimization, gene expression profiles, prognosis",

author = "Nisrine Mouhrim and Alberto Tonda and Itzel Rodr{\'i}guez-Guerra and Kraneveld, {Aletta D.} and Rincon, {Alejandro Lopez}",

note = "Publisher Copyright: {\textcopyright} 2022 Owner/Author.; 2022 Genetic and Evolutionary Computation Conference, GECCO 2022 ; Conference date: 09-07-2022 Through 13-07-2022",

year = "2022",

month = jul,

day = "9",

doi = "10.1145/3520304.3529001",

language = "English",

pages = "731--734",

editor = "Fieldsend, {Jonathan E.}",

booktitle = "GECCO '22: Proceedings of the Genetic and Evolutionary Computation Conference Companion",

publisher = "Association for Computing Machinery",

address = "United States",

}

Mouhrim, N, Tonda, A, Rodríguez-Guerra, I, Kraneveld, AD & Rincon, AL 2022, An evolutionary approach to the discretization of gene expression profiles to predict the severity of COVID-19. in JE Fieldsend (ed.), GECCO '22: Proceedings of the Genetic and Evolutionary Computation Conference Companion. Association for Computing Machinery, pp. 731-734, 2022 Genetic and Evolutionary Computation Conference, GECCO 2022, Virtual, Online, United States, 9/07/22. https://doi.org/10.1145/3520304.3529001

An evolutionary approach to the discretization of gene expression profiles to predict the severity of COVID-19. / Mouhrim, Nisrine; Tonda, Alberto; Rodríguez-Guerra, Itzel et al.
GECCO '22: Proceedings of the Genetic and Evolutionary Computation Conference Companion. ed. / Jonathan E. Fieldsend. Association for Computing Machinery, 2022. p. 731-734.

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

TY - GEN

T1 - An evolutionary approach to the discretization of gene expression profiles to predict the severity of COVID-19

AU - Mouhrim, Nisrine

AU - Tonda, Alberto

AU - Rodríguez-Guerra, Itzel

AU - Kraneveld, Aletta D.

AU - Rincon, Alejandro Lopez

PY - 2022/7/9

Y1 - 2022/7/9

N2 - In this work, we propose to use a state-of-the-art evolutionary algorithm to set the discretization thresholds for gene expression profiles, using feedback from a classifier in order to maximize the accuracy of the predictions based on the discretized gene expression levels, while at the same time minimizing the number of different profiles obtained, to ease the understanding of the expert. The methodology is applied to a dataset containing COVID-19 patients that developed either mild or severe symptoms. The results show that the evolutionary approach performs better than a traditional discretization based on statistical analysis, and that it does preserve the sense-making necessary for practitioners to trust the results.

AB - In this work, we propose to use a state-of-the-art evolutionary algorithm to set the discretization thresholds for gene expression profiles, using feedback from a classifier in order to maximize the accuracy of the predictions based on the discretized gene expression levels, while at the same time minimizing the number of different profiles obtained, to ease the understanding of the expert. The methodology is applied to a dataset containing COVID-19 patients that developed either mild or severe symptoms. The results show that the evolutionary approach performs better than a traditional discretization based on statistical analysis, and that it does preserve the sense-making necessary for practitioners to trust the results.

KW - covid-19

KW - discretization

KW - evolutionary optimization

KW - gene expression profiles

KW - prognosis

UR - http://www.scopus.com/inward/record.url?scp=85136320034&partnerID=8YFLogxK

U2 - 10.1145/3520304.3529001

DO - 10.1145/3520304.3529001

M3 - Conference contribution

AN - SCOPUS:85136320034

SP - 731

EP - 734

BT - GECCO '22: Proceedings of the Genetic and Evolutionary Computation Conference Companion

A2 - Fieldsend, Jonathan E.

PB - Association for Computing Machinery

T2 - 2022 Genetic and Evolutionary Computation Conference, GECCO 2022

Y2 - 9 July 2022 through 13 July 2022

ER -

Mouhrim N, Tonda A, Rodríguez-Guerra I, Kraneveld AD , Rincon AL. An evolutionary approach to the discretization of gene expression profiles to predict the severity of COVID-19. In Fieldsend JE, editor, GECCO '22: Proceedings of the Genetic and Evolutionary Computation Conference Companion. Association for Computing Machinery. 2022. p. 731-734 doi: 10.1145/3520304.3529001

An evolutionary approach to the discretization of gene expression profiles to predict the severity of COVID-19

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this