Identifying Genes to Predict Cancer Radiotherapy-Related Fatigue with Machine-Learning Methods

Wei Du, Kristin Dickinson, Calvin A. Johnson, Leorey N. Saligan

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

Abstract

While many factors influence the fatigue experienced by patients undergoing radiation therapy (RT), we hypothesize that expression of genes related to oxidative stress can be predictive of RT-related fatigue. In this work, we present a two-phase scheme which first selects a limited subset of genes deemed most predictive by a regularized elastic net, followed by a widely used classifier, the regularized random forest, to discriminate patients having high fatigue from low fatigue during RT. The model predicted 80% accuracy (0.80 AUC) in cross-validation. Initial results suggest that several genes are consistently selected in the proposed scheme, such as PRDX5, FHL2 and GPX4, showing promise as potential predictors for RT-related fatigue, and may provide information of its biologic underpinnings.

Original languageEnglish (US)
Title of host publicationACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics
PublisherAssociation for Computing Machinery, Inc
Number of pages1
ISBN (Electronic)9781450357944
DOIs
StatePublished - Aug 15 2018
Event9th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2018 - Washington, United States
Duration: Aug 29 2018Sep 1 2018

Publication series

NameACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics

Other

Other9th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2018
CountryUnited States
CityWashington
Period8/29/189/1/18

Fingerprint

Radiotherapy
Fatigue
Learning systems
Genes
Fatigue of materials
Neoplasms
Oxidative stress
Area Under Curve
Oxidative Stress
Classifiers
Machine Learning
Gene Expression

Keywords

  • Elastic net
  • Fatigue
  • Gene identification

ASJC Scopus subject areas

  • Computer Science Applications
  • Software
  • Health Informatics
  • Biomedical Engineering

Cite this

Du, W., Dickinson, K., Johnson, C. A., & Saligan, L. N. (2018). Identifying Genes to Predict Cancer Radiotherapy-Related Fatigue with Machine-Learning Methods. In ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics). Association for Computing Machinery, Inc. https://doi.org/10.1145/3233547.3233636

Identifying Genes to Predict Cancer Radiotherapy-Related Fatigue with Machine-Learning Methods. / Du, Wei; Dickinson, Kristin; Johnson, Calvin A.; Saligan, Leorey N.

ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics. Association for Computing Machinery, Inc, 2018. (ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics).

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

Du, W, Dickinson, K, Johnson, CA & Saligan, LN 2018, Identifying Genes to Predict Cancer Radiotherapy-Related Fatigue with Machine-Learning Methods. in ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics. ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, Association for Computing Machinery, Inc, 9th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2018, Washington, United States, 8/29/18. https://doi.org/10.1145/3233547.3233636
Du W, Dickinson K, Johnson CA, Saligan LN. Identifying Genes to Predict Cancer Radiotherapy-Related Fatigue with Machine-Learning Methods. In ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics. Association for Computing Machinery, Inc. 2018. (ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics). https://doi.org/10.1145/3233547.3233636
Du, Wei ; Dickinson, Kristin ; Johnson, Calvin A. ; Saligan, Leorey N. / Identifying Genes to Predict Cancer Radiotherapy-Related Fatigue with Machine-Learning Methods. ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics. Association for Computing Machinery, Inc, 2018. (ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics).
@inproceedings{e2df2acfe1ee450eac903233c3236094,
title = "Identifying Genes to Predict Cancer Radiotherapy-Related Fatigue with Machine-Learning Methods",
abstract = "While many factors influence the fatigue experienced by patients undergoing radiation therapy (RT), we hypothesize that expression of genes related to oxidative stress can be predictive of RT-related fatigue. In this work, we present a two-phase scheme which first selects a limited subset of genes deemed most predictive by a regularized elastic net, followed by a widely used classifier, the regularized random forest, to discriminate patients having high fatigue from low fatigue during RT. The model predicted 80{\%} accuracy (0.80 AUC) in cross-validation. Initial results suggest that several genes are consistently selected in the proposed scheme, such as PRDX5, FHL2 and GPX4, showing promise as potential predictors for RT-related fatigue, and may provide information of its biologic underpinnings.",
keywords = "Elastic net, Fatigue, Gene identification",
author = "Wei Du and Kristin Dickinson and Johnson, {Calvin A.} and Saligan, {Leorey N.}",
year = "2018",
month = "8",
day = "15",
doi = "10.1145/3233547.3233636",
language = "English (US)",
series = "ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics",
publisher = "Association for Computing Machinery, Inc",
booktitle = "ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics",

}

TY - GEN

T1 - Identifying Genes to Predict Cancer Radiotherapy-Related Fatigue with Machine-Learning Methods

AU - Du, Wei

AU - Dickinson, Kristin

AU - Johnson, Calvin A.

AU - Saligan, Leorey N.

PY - 2018/8/15

Y1 - 2018/8/15

N2 - While many factors influence the fatigue experienced by patients undergoing radiation therapy (RT), we hypothesize that expression of genes related to oxidative stress can be predictive of RT-related fatigue. In this work, we present a two-phase scheme which first selects a limited subset of genes deemed most predictive by a regularized elastic net, followed by a widely used classifier, the regularized random forest, to discriminate patients having high fatigue from low fatigue during RT. The model predicted 80% accuracy (0.80 AUC) in cross-validation. Initial results suggest that several genes are consistently selected in the proposed scheme, such as PRDX5, FHL2 and GPX4, showing promise as potential predictors for RT-related fatigue, and may provide information of its biologic underpinnings.

AB - While many factors influence the fatigue experienced by patients undergoing radiation therapy (RT), we hypothesize that expression of genes related to oxidative stress can be predictive of RT-related fatigue. In this work, we present a two-phase scheme which first selects a limited subset of genes deemed most predictive by a regularized elastic net, followed by a widely used classifier, the regularized random forest, to discriminate patients having high fatigue from low fatigue during RT. The model predicted 80% accuracy (0.80 AUC) in cross-validation. Initial results suggest that several genes are consistently selected in the proposed scheme, such as PRDX5, FHL2 and GPX4, showing promise as potential predictors for RT-related fatigue, and may provide information of its biologic underpinnings.

KW - Elastic net

KW - Fatigue

KW - Gene identification

UR - http://www.scopus.com/inward/record.url?scp=85056121407&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056121407&partnerID=8YFLogxK

U2 - 10.1145/3233547.3233636

DO - 10.1145/3233547.3233636

M3 - Conference contribution

AN - SCOPUS:85056121407

T3 - ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics

BT - ACM-BCB 2018 - Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics

PB - Association for Computing Machinery, Inc

ER -