IGP.clusterRepro {clusterRepro}

In-group proportion calculation

Description

This function classifies gene expression (microarray) data using centroids and calculates the in-group proportions of the resulting groups.

Usage

IGP.clusterRepro(Data, Centroids)

Arguments

Data

The matrix of gene expression data with annotated rows. For gene clusters, the labeled rows are samples and the columns are genes. For sample clusters, the labeled rows are genes and the columns are samples.

Centroids

The matrix of centroids with annotated rows. The labeled rows are either genes (for gene clusters) or samples (for sample clusters) and the columns are the centroids.

Details

The Pearson's centered correlation coefficient between each datum and each centroid is calculated. The datum is then classified to the group whose centroid had the highest correlation with the datum. The in-group proportion is defined to be the proportion of data in a group whose nearest neighbors (Pearson's centered correlation) are also classified to the same group.

Value

Class

The data classification made using the centroids

IGP

The in-group proportions for the groups found in the data

Size

The number of data classified to each of the groups

Author(s)

Amy Kapp and Robert Tibshirani

References

Amy Kapp and Robert Tibshirani. Are clusters in one dataset present in another dataset? To be published.

Examples

### Make centroid matrix with annotated rows
C <- matrix(rnorm(30), 10)
rownames(C) <- letters[1:nrow(C)]

### Make data matrix with annotated rows
D <- matrix(rnorm(100), 10)
rownames(D) <- letters[1:nrow(C)]

### Classify data and calculate in-group proportions
Result <- IGP.clusterRepro(D, C)

### If the number of rows in the centroid matrix does not match the
### number of rows in the data matrix and the row labels are unique, this
### function will only use the rows that the two matrices have in common.
D <- matrix(rnorm(200), 20)
rownames(D) <- letters[(nrow(D)+6):7]
Result <- IGP.clusterRepro(D, C)