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

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

doi:10.1016/j.ijrobp.2018.01.054

Cited by 73 publications

(57 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using this method, several genes implicated in ion transport and vascular regulation were found to be important for rectal bleeding and erectile dysfunction, respectively. This process was also applied to predict genitourinary toxicity and find associated gene ontology terms …”

Section: Radiogenomic Modeling: Mechanistic Data‐driven and Machine mentioning

confidence: 99%

Genomics models in radiotherapy: From mechanistic to machine learning

et al. 2020

View full text Add to dashboard Cite

Machine learning (ML) provides a broad framework for addressing high‐dimensional prediction problems in classification and regression. While ML is often applied for imaging problems in medical physics, there are many efforts to apply these principles to biological data toward questions of radiation biology. Here, we provide a review of radiogenomics modeling frameworks and efforts toward genomically guided radiotherapy. We first discuss medical oncology efforts to develop precision biomarkers. We next discuss similar efforts to create clinical assays for normal tissue or tumor radiosensitivity. We then discuss modeling frameworks for radiosensitivity and the evolution of ML to create predictive models for radiogenomics.

show abstract

Section: Radiogenomic Modeling: Mechanistic Data‐driven and Machine mentioning

confidence: 99%

Genomics models in radiotherapy: From mechanistic to machine learning

et al. 2020

View full text Add to dashboard Cite

show abstract

“…To reduce high-dimensionality burden to predictive model training, a filtering approach was employed where SNPs were removed based on univariate association strength prior to the modeling 35 : SNPs with association p-values < 0.001 and the clinical variables with association pvalues < 0.05 were incorporated into predictive model building. The univariate pvalue cutoff value was taken as in previous studies 29,30 .…”

Section: Univariate Analysis Of Snps and Clinical Variablesmentioning

confidence: 99%

“…The ClueGO software 39 was used to perform a gene set enrichment analysis (GSEA) and to organize the significant processes into relevant groups based on the number of common annotated genes. Details of the GSEA methodology can be found in the Supplementary material of our previous work 30 . GO terms with a false discovery rate (FDR) p ≤ 0.05 were reported.…”

Section: Snp Prioritization and Identification Of Biological Correlatesmentioning

confidence: 99%

“…In the current study, the focus is on a subgroup of women who received scatter and leakage radiation dose > 1 Gy to the contralateral breast at a young age (≤ 40 years) from the Women's Environmental Cancer and Radiation Epidemiology (WECARE) Study 28 . A machine-learning/bioinformatics methodology was employed, which was previously used to model radiation-induced complications of late rectal bleeding and erectile dysfunction 29 , and chronic urinary dysfunction following radiotherapy 30 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Methods to Identify Genetic Correlates of Radiation-Associated Contralateral Breast Cancer in the WECARE Study

Lee

Liang

Woods

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

The purpose of this study is to identify germline single nucleotide polymorphisms (SNPs) that optimally predict radiation-associated contralateral breast cancer (RCBC) and to provide new biological insights into the carcinogenic process.Fifty-two women with contralateral breast cancer and 153 women with unilateral breast cancer were identified within the Women's Environmental Cancer and Radiation Epidemiology (WECARE) Study who were at increased risk of RCBC because they were ≤ 40 years of age at first diagnosis of breast cancer and received a scatter radiation dose > 1 Gy to the contralateral breast. A previously reported algorithm, preconditioned random forest regression, was applied to predict the risk of developing RCBC. The resulting model produced an area under the curve of 0.62 (p=0.04) on hold-out validation data. The biological analysis identified the cyclic AMP-mediated signaling and Ephrin-A as significant biological correlates, which were previously shown to influence cell survival after radiation in an ATM-dependent manner. The key connected genes and proteins that are identified in this analysis were previously identified as relevant to breast cancer, radiation response, or both. In summary, machine learning/bioinformatics methods applied to genome-wide genotyping data have great potential to reveal plausible biological correlates associated with the risk of RCBC.

show abstract

“…In the current study, the focus is on a subgroup of women who received scatter and leakage radiation dose > 1 Gy to the contralateral breast at a young age (� 40 years) from the Women's Environmental Cancer and Radiation Epidemiology (WECARE) Study [5,28]. A machine-learning/bioinformatics methodology was employed, which was previously used to model radiation-induced complications of late rectal bleeding and erectile dysfunction [29], and chronic urinary dysfunction following radiotherapy [30].…”

Section: Introductionmentioning

confidence: 99%

Machine learning on genome-wide association studies to predict the risk of radiation-associated contralateral breast cancer in the WECARE Study

et al. 2020

Self Cite

View full text Add to dashboard Cite

The purpose of this study was to identify germline single nucleotide polymorphisms (SNPs) that optimally predict radiation-associated contralateral breast cancer (RCBC) and to provide new biological insights into the carcinogenic process. Fifty-two women with contralateral breast cancer and 153 women with unilateral breast cancer were identified within the Women's Environmental Cancer and Radiation Epidemiology (WECARE) Study who were at increased risk of RCBC because they were � 40 years of age at first diagnosis of breast cancer and received a scatter radiation dose > 1 Gy to the contralateral breast. A previously reported algorithm, preconditioned random forest regression, was applied to predict the risk of developing RCBC. The resulting model produced an area under the curve (AUC) of 0.62 (p = 0.04) on hold-out validation data. The biological analysis identified the cyclic AMP-mediated signaling and Ephrin-A as significant biological correlates, which were previously shown to influence cell survival after radiation in an ATM-dependent manner. The key connected genes and proteins that are identified in this analysis were previously identified as relevant to breast cancer, radiation response, or both. In summary, machine learning/bioinformatics methods applied to genome-wide genotyping data have great potential to reveal plausible biological correlates associated with the risk of RCBC.

show abstract

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

Abstract: 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.

Cited by 73 publications

References 37 publications

Genomics models in radiotherapy: From mechanistic to machine learning

Genomics models in radiotherapy: From mechanistic to machine learning

Machine Learning Methods to Identify Genetic Correlates of Radiation-Associated Contralateral Breast Cancer in the WECARE Study

Machine learning on genome-wide association studies to predict the risk of radiation-associated contralateral breast cancer in the WECARE Study

Contact Info

Product

Resources

About