FDR for PLPE

Share:

Description

This computes FDR for PLPE.

Usage

1
2
## Default S3 method:
lpe.paired.fdr(x, obj, n.iter=5, lambda=0.9, ...) 

Arguments

x

data matrix

obj

object created from lpe.paired

n.iter

number of iterations

lambda

numeric vector of probabilities with values in [0,1]

...

other argument

Value

design

design matrix; condition index in the first column and pair index in the sceond column

data.type

data type: 'ms' for mass spectrometry data, 'cdna' for cDNA microarray data

estimator

specification for the estimator: 'median', 'mean' and 'huber'

w.estimator

two approaches to estimate the weight: 'random' or 'fixed'

w

weight paramter between individual variance estimate and pooling variance estimate, 0<= w <=1

pi0

estimated proportion of non-null peptides

FDR

matrix for test results including FDRs

...

other arguments

Author(s)

HyungJun Cho and Jae K. Lee

References

Cho H, Smalley DM, Ross MM, Theodorescu D, Ley K and Lee JK (2007). Statistical Identification of Differentially Labelled Peptides from Liquid Chromatography Tandem Mass Spectrometry, Proteomics, 7:3681-3692.

See Also

lpe.paired.fdr

Examples

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
#LC-MS/MS proteomic data for platelets MPs
library(PLPE)
data(plateletSet)
x <- exprs(plateletSet)
x <- log2(x) 

cond <- c(1, 2, 1, 2, 1, 2)
pair <- c(1, 1, 2, 2, 3, 3)
design <- cbind(cond, pair)

out <- lpe.paired(x, design, q=0.1, data.type="ms")
out.fdr <- lpe.paired.fdr(x,obj=out)
out.fdr$FDR[1:10,]