Machine Learning on a Genome-wide Association Study to Predict Late Genitourinary Toxicity After Prostate Radiation Therapy

Sangkyu Lee, Sarah Kerns, Harry Ostrer, Barry Rosenstein, Joseph O. Deasy, Jung Hun Oh

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Purpose: Late genitourinary (GU) toxicity after radiation therapy limits the quality of life of prostate cancer survivors; however, efforts to explain GU toxicity using patient and dose information have remained unsuccessful. We identified patients with a greater congenital GU toxicity risk by identifying and integrating patterns in genome-wide single nucleotide polymorphisms (SNPs). Methods and Materials: We applied a preconditioned random forest regression method for predicting risk from the genome-wide data to combine the effects of multiple SNPs and overcome the statistical power limitations of single-SNP analysis. We studied a cohort of 324 prostate cancer patients who were self-assessed for 4 urinary symptoms at 2 years after radiation therapy using the International Prostate Symptom Score. Results: The predictive accuracy of the method varied across the symptoms. Only for the weak stream endpoint did it achieve a significant area under the curve of 0.70 (95% confidence interval 0.54-0.86; P = 01) on hold-out validation data that outperformed competing methods. Gene ontology analysis highlighted key biological processes, such as neurogenesis and ion transport, from the genes known to be important for urinary tract functions. Conclusions: We applied machine learning methods and bioinformatics tools to genome-wide data to predict and explain GU toxicity. Our approach enabled the design of a more powerful predictive model and the determination of plausible biomarkers and biological processes associated with GU toxicity.

Original languageEnglish (US)
JournalInternational Journal of Radiation Oncology Biology Physics
DOIs
StateAccepted/In press - Jan 1 2018

Fingerprint

machine learning
genome
Genome-Wide Association Study
toxicity
Prostate
radiation therapy
Radiotherapy
polymorphism
nucleotides
Single Nucleotide Polymorphism
Biological Phenomena
Genome
genes
Prostatic Neoplasms
cancer
Gene Ontology
biomarkers
Neurogenesis
Ion Transport
Computational Biology

ASJC Scopus subject areas

  • Radiation
  • Oncology
  • Radiology Nuclear Medicine and imaging
  • Cancer Research

Cite this

Machine Learning on a Genome-wide Association Study to Predict Late Genitourinary Toxicity After Prostate Radiation Therapy. / Lee, Sangkyu; Kerns, Sarah; Ostrer, Harry; Rosenstein, Barry; Deasy, Joseph O.; Oh, Jung Hun.

In: International Journal of Radiation Oncology Biology Physics, 01.01.2018.

Research output: Contribution to journalArticle

@article{d1ab9f409be742d8b45800bdb096d9c2,
title = "Machine Learning on a Genome-wide Association Study to Predict Late Genitourinary Toxicity After Prostate Radiation Therapy",
abstract = "Purpose: Late genitourinary (GU) toxicity after radiation therapy limits the quality of life of prostate cancer survivors; however, efforts to explain GU toxicity using patient and dose information have remained unsuccessful. We identified patients with a greater congenital GU toxicity risk by identifying and integrating patterns in genome-wide single nucleotide polymorphisms (SNPs). Methods and Materials: We applied a preconditioned random forest regression method for predicting risk from the genome-wide data to combine the effects of multiple SNPs and overcome the statistical power limitations of single-SNP analysis. We studied a cohort of 324 prostate cancer patients who were self-assessed for 4 urinary symptoms at 2 years after radiation therapy using the International Prostate Symptom Score. Results: The predictive accuracy of the method varied across the symptoms. Only for the weak stream endpoint did it achieve a significant area under the curve of 0.70 (95{\%} confidence interval 0.54-0.86; P = 01) on hold-out validation data that outperformed competing methods. Gene ontology analysis highlighted key biological processes, such as neurogenesis and ion transport, from the genes known to be important for urinary tract functions. Conclusions: We applied machine learning methods and bioinformatics tools to genome-wide data to predict and explain GU toxicity. Our approach enabled the design of a more powerful predictive model and the determination of plausible biomarkers and biological processes associated with GU toxicity.",
author = "Sangkyu Lee and Sarah Kerns and Harry Ostrer and Barry Rosenstein and Deasy, {Joseph O.} and Oh, {Jung Hun}",
year = "2018",
month = "1",
day = "1",
doi = "10.1016/j.ijrobp.2018.01.054",
language = "English (US)",
journal = "International Journal of Radiation Oncology Biology Physics",
issn = "0360-3016",
publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Machine Learning on a Genome-wide Association Study to Predict Late Genitourinary Toxicity After Prostate Radiation Therapy

AU - Lee, Sangkyu

AU - Kerns, Sarah

AU - Ostrer, Harry

AU - Rosenstein, Barry

AU - Deasy, Joseph O.

AU - Oh, Jung Hun

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Purpose: Late genitourinary (GU) toxicity after radiation therapy limits the quality of life of prostate cancer survivors; however, efforts to explain GU toxicity using patient and dose information have remained unsuccessful. We identified patients with a greater congenital GU toxicity risk by identifying and integrating patterns in genome-wide single nucleotide polymorphisms (SNPs). Methods and Materials: We applied a preconditioned random forest regression method for predicting risk from the genome-wide data to combine the effects of multiple SNPs and overcome the statistical power limitations of single-SNP analysis. We studied a cohort of 324 prostate cancer patients who were self-assessed for 4 urinary symptoms at 2 years after radiation therapy using the International Prostate Symptom Score. Results: The predictive accuracy of the method varied across the symptoms. Only for the weak stream endpoint did it achieve a significant area under the curve of 0.70 (95% confidence interval 0.54-0.86; P = 01) on hold-out validation data that outperformed competing methods. Gene ontology analysis highlighted key biological processes, such as neurogenesis and ion transport, from the genes known to be important for urinary tract functions. Conclusions: We applied machine learning methods and bioinformatics tools to genome-wide data to predict and explain GU toxicity. Our approach enabled the design of a more powerful predictive model and the determination of plausible biomarkers and biological processes associated with GU toxicity.

AB - Purpose: Late genitourinary (GU) toxicity after radiation therapy limits the quality of life of prostate cancer survivors; however, efforts to explain GU toxicity using patient and dose information have remained unsuccessful. We identified patients with a greater congenital GU toxicity risk by identifying and integrating patterns in genome-wide single nucleotide polymorphisms (SNPs). Methods and Materials: We applied a preconditioned random forest regression method for predicting risk from the genome-wide data to combine the effects of multiple SNPs and overcome the statistical power limitations of single-SNP analysis. We studied a cohort of 324 prostate cancer patients who were self-assessed for 4 urinary symptoms at 2 years after radiation therapy using the International Prostate Symptom Score. Results: The predictive accuracy of the method varied across the symptoms. Only for the weak stream endpoint did it achieve a significant area under the curve of 0.70 (95% confidence interval 0.54-0.86; P = 01) on hold-out validation data that outperformed competing methods. Gene ontology analysis highlighted key biological processes, such as neurogenesis and ion transport, from the genes known to be important for urinary tract functions. Conclusions: We applied machine learning methods and bioinformatics tools to genome-wide data to predict and explain GU toxicity. Our approach enabled the design of a more powerful predictive model and the determination of plausible biomarkers and biological processes associated with GU toxicity.

UR - http://www.scopus.com/inward/record.url?scp=85042565518&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042565518&partnerID=8YFLogxK

U2 - 10.1016/j.ijrobp.2018.01.054

DO - 10.1016/j.ijrobp.2018.01.054

M3 - Article

JO - International Journal of Radiation Oncology Biology Physics

JF - International Journal of Radiation Oncology Biology Physics

SN - 0360-3016

ER -