tspcalc: Estimate top scoring pairs from a gene expression matrix

In tspair: Top Scoring Pairs for Microarray Classification

Description

This function calculates the pair of genes that show the maximum difference in ranking between two user specified groups. The "top scoring pair" (TSP) maximizes the average of sensitivity and specificity over all rank based classifiers using a pair of genes in the data set.

Usage

  tspcalc(dat,grp)

Arguments

dat	Can take two values: (a) an m genes by n arrays matrix of expression data or (b) an eSet object
grp	Can take one of two values: (a) A group indicator in character or numeric form, (b) an integer indicating the column of pData(dat) to use as the group indicator.

Details

tspcalc only works for two group classification. The computation time grows rapidly in the number of genes, so for large gene expression matrices one should be prepared to wait or do a pre-filtering step. The top scoring pairs methodology was originally described in Geman et al. (2004) and the unique TSP idea was described in Tan et al. (2005).

Value

A tsp object with elements:

index	A two-column matrix where each row is a pair of indices from the data matrix achieving the top score
tspscore	The rank based score described in Geman et al. (2004), essentially the empirical average of sensitivity and specificity for the pair.
score	The tie-breaking score described in Tan et al. (2005).
grp	The binary group indicator.
tspdat	Row i and row (i + Number of total TSPs) of this data matrix represent the expression data for the ith TSP pair.
labels	The group labels for the two groups as defined by the grp variable.

Author(s)

Jeffrey T. Leek [e-mail]

References

D. Geman, C. d'Avignon, D. Naiman and R. Winslow, "Classifying gene expression profiles from pairwise mRNA comparisons," Statist. Appl. in Genetics and Molecular Biology, 3, 2004.

A.C. Tan, D.Q. Naiman, L. Xu, R.L. Winslow, D. Geman, "Simple decision rules for classifying human cancers from gene expression profiles," Bioinformatics, 21: 3896-3904, 2005.

See Also

tspplot, ts.pair, tspsig,predict.tsp, summary.tsp

Examples

  ## Not run: 
  ## Load data
  data(tspdata) 

  ## Run tspcalc() on a data matrix and grp vector
  tsp1 <- tspcalc(dat,grp)
  tsp1$index

  ## Run tspcalc() on an expression set and a column of the pData matrix
  tsp2 <- tspcalc(eSet1,1)
  tsp2$index
 
## End(Not run)

Example output

Loading required package: Biobase
Loading required package: BiocGenerics
Loading required package: parallel

Attaching package: 'BiocGenerics'

The following objects are masked from 'package:parallel':

    clusterApply, clusterApplyLB, clusterCall, clusterEvalQ,
    clusterExport, clusterMap, parApply, parCapply, parLapply,
    parLapplyLB, parRapply, parSapply, parSapplyLB

The following objects are masked from 'package:stats':

    IQR, mad, sd, var, xtabs

The following objects are masked from 'package:base':

    Filter, Find, Map, Position, Reduce, anyDuplicated, append,
    as.data.frame, basename, cbind, colMeans, colSums, colnames,
    dirname, do.call, duplicated, eval, evalq, get, grep, grepl,
    intersect, is.unsorted, lapply, lengths, mapply, match, mget,
    order, paste, pmax, pmax.int, pmin, pmin.int, rank, rbind,
    rowMeans, rowSums, rownames, sapply, setdiff, sort, table, tapply,
    union, unique, unsplit, which, which.max, which.min

Welcome to Bioconductor

    Vignettes contain introductory material; view with
    'browseVignettes()'. To cite Bioconductor, see
    'citation("Biobase")', and for packages 'citation("pkgname")'.

     [,1] [,2]
[1,]    5  338
     [,1] [,2]
[1,]    5  338

tspair documentation built on Nov. 8, 2020, 6:51 p.m.