Machine Learning on a Genome-wide Association Study to Predict Late Genitourinary Toxicity After Prostate Radiation Therapy.
Machine Learning on a Genome-wide Association Study to Predict Late Genitourinary Toxicity After Prostate Radiation Therapy.
复制标题
DOI：
10.1016/j.ijrobp.2018.01.054
复制
发表时间：
2018-05-01
期刊：
影响因子：
--
通讯作者：
Oh JH
中科院分区：
文献类型：
--
作者：
Lee S;Kerns S;Ostrer H;Rosenstein B;Deasy JO;Oh JH
放射治疗后的晚期泌尿生殖系统（GU）毒性限制了前列腺癌幸存者的生活质量;然而，使用患者和剂量信息解释GU毒性的努力仍然不成功。我们通过识别和整合全基因组单核苷酸多态性（SNPs）模式来识别具有更大先天性GU毒性风险的患者。我们应用预处理随机森林回归方法从全基因组数据预测风险，以联合收割机结合多个SNP的影响，并克服单SNP分析的统计功效限制。我们研究了一组324例前列腺癌患者，他们在放射治疗后2年使用国际前列腺症状评分对4种泌尿系统症状进行自我评估。该方法的预测准确性因症状而异。仅对于弱流终点，其在保留验证数据上达到了0.70的显著曲线下面积（95%置信区间0.54-0.86; P = .01），优于竞争方法。基因本体分析突出了关键的生物学过程，如神经发生和离子转运，从已知的基因是重要的泌尿道功能。我们将机器学习方法和生物信息学工具应用于全基因组数据，以预测和解释GU毒性。我们的方法能够设计更强大的预测模型，并确定与GU毒性相关的合理生物标志物和生物过程。
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). 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. 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. 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 bio-markers and biological processes associated with GU toxicity.
登录
查看更多内容
DOI：
10.1016/j.ijrobp.2013.10.042
发表时间：
2014-02-01
期刊：
International journal of radiation oncology, biology, physics
影响因子：
--
作者：
Ghadjar P;Zelefsky MJ;Spratt DE;Munck af Rosenschöld P;Oh JH;Hunt M;Kollmeier M;Happersett L;Yorke E;Deasy JO;Jackson A
通讯作者：
Jackson A
影响因子：
4.6
作者：
Oh JH;Kerns S;Ostrer H;Powell SN;Rosenstein B;Deasy JO
通讯作者：
Deasy JO
影响因子：
2
作者：
Hypolite, Joseph A.;Malykhina, Anna P.
通讯作者：
Malykhina, Anna P.
影响因子：
11.1
作者：
Kerns, Sarah L.;Dorling, Leila;Fachal, Laura;Bentzen, Soren;Pharoah, Paul D. P.;Barnes, Daniel R.;Gomez-Caamano, Antonio;Carballo, Ana M.;Dearnaley, David P.;Peleteiro, Paula;Gulliford, Sarah L.;Hall, Emma;Michailidou, Kyriaki;Carracedo, Angel;Sia, Michael;Stock, Richard;Stone, Nelson N.;Sydes, Matthew R.;Tyrer, Jonathan P.;Ahmed, Shahana;Parliament, Matthew;Ostrer, Harry;Rosenstein, Barry S.;Vega, Ana;Burnet, Neil G.;Dunning, Alison M.;Barnett, Gillian C.;West, Catharine M. L.
通讯作者：
West, Catharine M. L.
影响因子：
6.6
作者：
Kerns, Sarah L.;Stone, Nelson N.;Rosenstein, Barry S.
通讯作者：
Rosenstein, Barry S.