affxparser (version 1.44.0)

applyCdfGroups: Applies a function over the groups in a CDF structure

Description

Applies a function over the groups in a CDF structure.

Usage

applyCdfGroups(cdf, fcn, ...)

Arguments

cdf
A CDF list structure.
fcn
A function that takes a list structure of group elements and returns an updated list of groups.
...
Arguments passed to the fcn function.

Value

Returns an updated CDF list structure.

Pre-defined restructuring functions

  • Generic:
    • cdfGetFields() - Gets a subset of groups fields in a CDF structure.
    • cdfGetGroups() - Gets a subset of groups in a CDF structure.
    • cdfOrderBy() - Orders the fields according to the value of another field in the same CDF group.
    • cdfOrderColumnsBy() - Orders the columns of fields according to the values in a certain row of another field in the same CDF group.
  • Designed for SNP arrays:
    • cdfAddBaseMmCounts() - Adds the number of allele A and allele B mismatching nucleotides of the probes in a CDF structure.
    • cdfAddProbeOffsets() - Adds probe offsets to the groups in a CDF structure.
    • cdfGtypeCelToPQ() - Function to immitate Affymetrix' gtype_cel_to_pq software.
    • cdfMergeAlleles() - Function to join CDF allele A and allele B groups strand by strand.
    • cdfMergeStrands() - Function to join CDF groups with the same names.
We appreciate contributions.

Examples

Run this code
##############################################################
if (require("AffymetrixDataTestFiles")) {            # START #
##############################################################

cdfFile <- findCdf("Mapping10K_Xba131")

# Identify the unit index from the unit name
unitName <- "SNP_A-1509436"
unit <- which(readCdfUnitNames(cdfFile) == unitName)

# Read the CDF file
cdf0 <- readCdfUnits(cdfFile, units=unit, stratifyBy="pmmm", readType=FALSE, readDirection=FALSE)
cat("Default CDF structure:\n")
print(cdf0)

# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Tabulate the information in each group
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
cdf <- readCdfUnits(cdfFile, units=unit)
cdf <- applyCdfGroups(cdf, lapply, as.data.frame)
print(cdf)

# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Infer the (true or the relative) offset for probe quartets.
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
cdf <- applyCdfGroups(cdf0, cdfAddProbeOffsets)
cat("Probe offsets:\n")
print(cdf)

# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Identify the number of nucleotides that mismatch the
# allele A and the allele B sequences, respectively.
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
cdf <- applyCdfGroups(cdf, cdfAddBaseMmCounts)
cat("Allele A & B target sequence mismatch counts:\n")
print(cdf)



# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Combine the signals from  the sense and the anti-sense
# strands in a SNP CEL files.
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# First, join the strands in the CDF structure.
cdf <- applyCdfGroups(cdf, cdfMergeStrands)
cat("Joined CDF structure:\n")
print(cdf)


# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Rearrange values of group fields into quartets.  This
# requires that the values are already arranged as PMs and MMs.
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
cdf <- applyCdfGroups(cdf0, cdfMergeAlleles)
cat("Probe quartets:\n")
print(cdf)


# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Get the x and y cell locations (note, zero-based)
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
x <- unlist(applyCdfGroups(cdf, cdfGetFields, "x"), use.names=FALSE)
y <- unlist(applyCdfGroups(cdf, cdfGetFields, "y"), use.names=FALSE)

# Validate
ncol <- readCdfHeader(cdfFile)$cols
cells <- as.integer(y*ncol+x+1)
cells <- sort(cells)

cells0 <- readCdfCellIndices(cdfFile, units=unit)
cells0 <- unlist(cells0, use.names=FALSE)
cells0 <- sort(cells0)

stopifnot(identical(cells0, cells))

##############################################################
}                                                     # STOP #
##############################################################

Run the code above in your browser using DataCamp Workspace