PLATYPUS: A Multiple–View Learning Predictive Framework for Cancer Drug Sensitivity Prediction
PLATYPUS: A Multiple–View Learning Predictive Framework for Cancer Drug Sensitivity Prediction
复制标题
PLATYPUS：用于癌症药物敏感性预测的多视图学习预测框架
DOI：
10.1142/9789813279827_0013
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Joshua M. Stuart
中科院分区：
文献类型：
--
作者：
Kiley Graim;V. Friedl;Kathleen E. Houlahan;Joshua M. Stuart
癌症是一种复杂的疾病集合，在某种程度上每个患者都是独特的。精准肿瘤学旨在利用肿瘤样本的分子数据确定最佳药物治疗方案。虽然omics级别的数据越来越广泛地用于肿瘤标本，但可以训练协同学习方法的数据集在样本和数据类型之间的覆盖范围不同。能够“连接点”以利用这些研究提供的更多信息的方法可以为最大化预测潜力提供主要优势。我们引入了一种名为PLATYPUS的多视图机器学习策略，该策略从多个数据源构建“视图”，这些数据源都用作预测患者结局的特征。我们表明，在未标记数据的观点之间找到一致性的学习策略可以提高学习方法在任何单一观点上的性能。我们通过在大型癌细胞系数据库中推导药物敏感性的签名来说明该方法的强大功能。代码和其他信息可从PLATYPUS网站https://sysbiowiki.soe.ucsc.edu/platypus获得。
Cancer is a complex collection of diseases that are to some degree unique to each patient. Precision oncology aims to identify the best drug treatment regime using molecular data on tumor samples. While omics-level data is becoming more widely available for tumor specimens, the datasets upon which co learning methods can be trained vary in coverage from sample to sample and from data type to data type. Methods that can ‘connect the dots’ to leverage more of the information provided by these studies could offer major advantages for maximizing predictive potential. We introduce a multi-view machine-learning strategy called PLATYPUS that builds ‘views’ from multiple data sources that are all used as features for predicting patient outcomes. We show that a learning strategy that finds agreement across the views on unlabeled data increases the performance of the learning methods over any single view. We illustrate the power of the approach by deriving signatures for drug sensitivity in a large cancer cell line database. Code and additional information are available from the PLATYPUS website https://sysbiowiki.soe.ucsc.edu/platypus.