Advanced

The projection score - an evaluation criterion for variable subset selection in PCA visualization

Fontes, Magnus LU and Soneson, Charlotte LU (2011) In BMC Bioinformatics 12.
Abstract
Background

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... (More)
Background

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.



Results

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.



Conclusions

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. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
BMC Bioinformatics
volume
12
publisher
BioMed Central
external identifiers
  • wos:000294558200001
  • scopus:79960655875
ISSN
1471-2105
DOI
10.1186/1471-2105-12-307
language
English
LU publication?
yes
id
96a6c4d3-861d-4088-b362-87c44ff7dc9d (old id 2060581)
alternative location
http://www.biomedcentral.com/1471-2105/12/307
date added to LUP
2011-08-23 17:07:02
date last changed
2017-01-01 06:00:23
@article{96a6c4d3-861d-4088-b362-87c44ff7dc9d,
  abstract     = {Background<br/><br>
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.<br/><br>
<br/><br>
Results<br/><br>
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.<br/><br>
<br/><br>
Conclusions<br/><br>
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.},
  articleno    = {307},
  author       = {Fontes, Magnus and Soneson, Charlotte},
  issn         = {1471-2105},
  language     = {eng},
  publisher    = {BioMed Central},
  series       = {BMC Bioinformatics},
  title        = {The projection score - an evaluation criterion for variable subset selection in PCA visualization},
  url          = {http://dx.doi.org/10.1186/1471-2105-12-307},
  volume       = {12},
  year         = {2011},
}