A comparison of batch effect removal methods for enhancement of prediction performance using MAQC-II microarray gene expression data.
A comparison of batch effect removal methods for enhancement of prediction performance using MAQC-II microarray gene expression data.
复制标题
DOI：
10.1038/tpj.2010.57
复制
发表时间：
2010-08
期刊：
影响因子：
--
通讯作者：
Zhang J
中科院分区：
文献类型：
--
作者：
Luo J;Schumacher M;Scherer A;Sanoudou D;Megherbi D;Davison T;Shi T;Tong W;Shi L;Hong H;Zhao C;Elloumi F;Shi W;Thomas R;Lin S;Tillinghast G;Liu G;Zhou Y;Herman D;Li Y;Deng Y;Fang H;Bushel P;Woods M;Zhang J
批次效应是指在微阵列实验中，由于各种原因，如样品制备和杂交方案的不同，样品批次(组)之间的系统性非生物差异。以往的工作主要集中在开发有效去除间歇效应的方法上。然而，它们对跨批次预测性能的影响尚未得到解决，跨批次预测性能是基于微阵列的应用中最重要的目标之一。本文使用来自微阵列质量控制第二阶段(MAQC-II)工作的广泛选择的数据集，这些数据集是在三个具有不同批次效应原因的微阵列平台上产生的，以评估去除它们的效果。还包括来自跨组织和跨平台实验的两个数据集。在使用支持向量机(SVM)和K近邻(KNN)作为分类器，以Matthews相关系数(MCC)作为性能度量的120个案例中，我们发现Ratio-G、Ratio-A、EJLR、Mean-Center和标准化方法分别在89、85、83、79和75%的案例中表现出更好或相当的效果，这表明这些方法的应用通常是可取的，基于比率的方法是首选的。
Batch effects are the systematic non-biological differences between batches (groups) of samples in microarray experiments due to various causes such as differences in sample preparation and hybridization protocols. Previous work focused mainly on the development of methods for effective batch effects removal. However, their impact on cross-batch prediction performance, which is one of the most important goals in microarray-based applications, has not been addressed. This paper uses a broad selection of data sets from the Microarray Quality Control Phase II (MAQC-II) effort, generated on three microarray platforms with different causes of batch effects to assess the efficacy of their removal. Two data sets from cross-tissue and cross-platform experiments are also included. Of the 120 cases studied using Support vector machines (SVM) and K nearest neighbors (KNN) as classifiers and Matthews correlation coefficient (MCC) as performance metric, we find that Ratio-G, Ratio-A, EJLR, mean-centering and standardization methods perform better or equivalent to no batch effect removal in 89, 85, 83, 79 and 75% of the cases, respectively, suggesting that the application of these methods is generally advisable and ratio-based methods are preferred.
登录
查看更多内容
影响因子：
5.8
作者：
Benito, M;Parker, J;Marron, JS
通讯作者：
Marron, JS
DOI：
10.1073/pnas.97.18.10101
发表时间：
2000-08-29
影响因子：
11.1
作者：
Alter, O;Brown, PO;Botstein, D
通讯作者：
Botstein, D
影响因子：
3.8
作者：
Thomas, Russell S.;Pluta, Linda;Halsey, Thomas A.
通讯作者：
Halsey, Thomas A.
影响因子：
3
作者：
Bylesjö M;Eriksson D;Sjödin A;Jansson S;Moritz T;Trygg J
通讯作者：
Trygg J
影响因子：
2.1
作者：
Irizarry, RA;Hobbs, B;Speed, TP
通讯作者：
Speed, TP