The projection score--an evaluation criterion for variable subset selection in PCA visualization.
The projection score--an evaluation criterion for variable subset selection in PCA visualization.
复制标题
DOI：
10.1186/1471-2105-12-307
复制
发表时间：
2011-07-28
影响因子：
3
通讯作者：
Soneson C
中科院分区：
文献类型：
--
作者：
Fontes M;Soneson C
在许多科学领域，收集高维数据集（通常具有探索性目的）以生成新的相关假设变得越来越普遍。探索性的观点往往使统计指导的可视化方法，如主成分分析（PCA），选择的方法。然而，所获得的可视化的清晰度，从而使用它们来制定相关的假设的潜力，可能会混淆的存在下，许多非信息变量。对于微阵列数据，更容易解释的可视化通常通过过滤变量集来获得，例如通过去除具有最小方差的变量或通过仅包括与特定响应最高度相关的变量。所得到的可视化可能在很大程度上取决于纳入标准，即有效地保留变量的数量。据我们所知，不存在客观的方法来确定可视化的背景下的最佳纳入标准。我们提出的投影得分，这是一个简单的，直观的吸引力的衡量变量子集的信息量相对于PCA可视化。该测量可以普遍应用于为任何类型的变量过滤找到合适的包含标准。我们应用所提出的度量在微阵列数据集和合成数据集中找到不同过滤方法的最佳变量子集。我们还注意到，投影得分可以应用于一般情况下，比较任何变量子集的信息量相对于PCA的可视化。我们的结论是，投影得分提供了一个易于解释和普遍适用的措施，一个变量子集的信息量方面的可视化PCA，可以用来系统地找到最可解释的PCA可视化在实际的探索性分析。
In many scientific domains, it is becoming increasingly common to collect high-dimensional data sets, often with an exploratory aim, to generate new and relevant hypotheses. The exploratory perspective often makes statistically guided visualization methods, such as Principal Component Analysis (PCA), the methods of choice. However, the clarity of the obtained visualizations, and thereby the potential to use them to formulate relevant hypotheses, may be confounded by the presence of the many non-informative variables. For microarray data, more easily interpretable visualizations are often obtained by filtering the variable set, for example by removing the variables with the smallest variances or by only including the variables most highly related to a specific response. The resulting visualization may depend heavily on the inclusion criterion, that is, effectively the number of retained variables. To our knowledge, there exists no objective method for determining the optimal inclusion criterion in the context of visualization. We present the projection score, which is a straightforward, intuitively appealing measure of the informativeness of a variable subset with respect to PCA visualization. This measure can be universally applied to find suitable inclusion criteria for any type of variable filtering. We apply the presented measure to find optimal variable subsets for different filtering methods in both microarray data sets and synthetic data sets. We note also that the projection score can be applied in general contexts, to compare the informativeness of any variable subsets with respect to visualization by PCA. We conclude that the projection score provides an easily interpretable and universally applicable measure of the informativeness of a variable subset with respect to visualization by PCA, that can be used to systematically find the most interpretable PCA visualization in practical exploratory analysis.
登录
查看更多内容
影响因子：
56.9
作者：
Golub, TR;Slonim, DK;Lander, ES
通讯作者：
Lander, ES
影响因子：
3.7
作者：
Bungaro, Silvia;Dell'Orto, Marta Campo;Cazzaniga, Giovanni
通讯作者：
Cazzaniga, Giovanni
影响因子：
1.8
作者：
Peres-Neto, PR;Jackson, DA;Somers, KM
通讯作者：
Somers, KM
影响因子：
11.5
作者：
Modlich, O;Prisack, HB;Bojar, H
通讯作者：
Bojar, H
在儿童白血病中翻译微阵列数据以进行诊断测试。
影响因子：
3.8
作者：
Hoffmann, Katrin;Firth, Martin J.;Beesley, Alex H.;de Klerk, Nicholas H.;Kees, Ursula R.
通讯作者：
Kees, Ursula R.