pluripotents.frame: Manually curated list of pluripotent arrays
In pathprint: Pathway fingerprinting for analysis of gene expression arrays

Description Usage Format Source References See Also Examples

A manually compiled list of pluripotent arrays (induced pluripotent cells and embryonic stem cells) together with their GEO IDs and descriptions

1	pluripotents.frame

A data frame with 278 observations on the following 5 variables.

GSM: GEO sample ID
GSE: GEO series ID
GPL: GEO platform ID
source: GEO description - Source
Characteristics: GEO description - Characteristic

http://www.ncbi.nlm.nih.gov/geo/

Altschuler, G. M., O. Hofmann, I. Kalatskaya, R. Payne, S. J. Ho Sui, U. Saxena, A. V. Krivtsov, S. A. Armstrong, T. Cai, L. Stein and W. A. Hide (2013). "Pathprinting: An integrative approach to understand the functional basis of disease." Genome Med 5(7): 68.

consensusDistance, consensusFingerprint

require(pathprintGEOData)
library(SummarizedExperiment)

# load  the data
data(SummarizedExperimentGEO)

ds = c("chipframe", "genesets","pathprint.Hs.gs",
    "platform.thresholds","pluripotents.frame")
data(list = ds)

# extract part of the GEO.fingerprint.matrix and GEO.metadata.matrix
GEO.fingerprint.matrix = assays(geo_sum_data[,300000:350000])$fingerprint
GEO.metadata.matrix = colData(geo_sum_data[,300000:350000])

# Extract common GSMs since we only loaded part of the geo_sum_data object
common_GSMs <- intersect(pluripotents.frame$GSM,colnames(GEO.fingerprint.matrix))

# free up space by removing the geo_sum_data object
remove(geo_sum_data)

head(pluripotents.frame)

# Use pathway fingerprints to search for
# additional pluripotent arrays across GEO
# create consensus pluripotent fingerprint
pluripotent.consensus<-consensusFingerprint(
    GEO.fingerprint.matrix[,common_GSMs], threshold=0.9)

# calculate distance from the pluripotent consensus
geo.pluripotentDistance<-consensusDistance(
    pluripotent.consensus, GEO.fingerprint.matrix)

# plot histograms
par(mfcol = c(2,1), mar = c(0, 4, 4, 2))
geo.pluripotentDistance.hist<-hist(geo.pluripotentDistance[,"distance"],
    nclass = 50, xlim = c(0,1), main = "Distance from pluripotent consensus")
par(mar = c(7, 4, 4, 2))
hist(geo.pluripotentDistance[pluripotents.frame$GSM, "distance"],
        breaks = geo.pluripotentDistance.hist$breaks, xlim = c(0,1), 
    main = "", xlab = "above: all GEO, below: pluripotent samples")