Dear all，
i have a dataset(n samples containing m dimensions,and n﹤m),and i would like to reduce the dimensionality of this data using PCA method("prcomp" function in R).However,it only returns a n-by-n matrix,So how to perform PCA when the dimensionality is greater than the number of samples in R? Thanks in advance.
•
written
by
LJ
2 answers
If you want to reduce the dimensionality through PCA you should compute the principal components of your data matrix, as you did, and pick the largest n components. Usually the first 2 or 3 contain most of the information (plus if you choose 2 you can easily plot them). The plotting function screeplot can be useful to inspect the variance explained by each component.
From a matrix (genes X samples), you can make a PCA on either the samples or the genes :
- On the samples (as here), the maximal number of dimensions is the number of genes.
- On the genes (as here), the maximal number of dimensions is the number of samples.
Obviously those two PCA highlight very different things from your data. To switch from one to another, you usually have to transpose your matrix.
Log in to answer this question.
-
Error during batch correction/PCA
written by Eduardo Oñate •
-
Dimensionality reduction on data sets with variable dimensions
written by rtrende •
-
How are principal components generated directly from eigendecomposition of a 'sample' covariance ma…
written by didillysquat •
-
R - apply WGCNA pquantile() using margins of array as arguments
written by fabricio_almeidasilva •
-
Eigenvalues from PLINK1.90 pca don't sum to number of variables?
written by c.horscroft •
-
Question about PCA plot using RPKM/FPKM.
written by hxlei613
-
How to interpret these weird plots from find.clusters() function in adegenet package?
written by andre.floresb •
-
Tool: Computational Suite For Bioinformaticians and Biologists -- CSBB [Version 2.1]
written by Praneet Chaturvedi
-
Tool: CSBB-v2.0 [Computational Suite for Bioinformaticians and Biologists version 2]
written by Praneet Chaturvedi
-
Accounting for hidden confounding factors in eQTL analysis
written by Alexander Skates
PCA is working correctly, why would you expect more rows than that?
for example,n=10,m=1000,so the result returns a 10X10 matrix, and the 10 PCs explains 100% variance, but 10 components is far smaller than 1000 features,is it reasonable?
Yes, 10 components is reasonable, since it's impossible for there to be more. In practice, you want fewer than N, as dariober pointed out.
It's because PCs are orthogonal to each other and once you have as many dimensions as datapoints there is no more variation to explain.
Thank you guys for your replies.