promise.genestat {PROMISE} | R Documentation |
a function to calculate individual gene and PROMISE statistics for a defined pattern of association
promise.genestat(Y, ph.data, ph.pattern, strat = NULL, proj0=FALSE)
Y |
a data frame with row corresponding to probe set and column corresponding to subjects, the order of column should match order of row in ph.data. |
ph.data |
a data frame with rows corresponding to subjects and columns corresponding to endpoint variables. |
ph.pattern |
a data frame with column headers: stat.coef, stat.func, endpt.vars. The stat.coeff column gives the coefficients for combining the statistics of association of genomic variable with individual endpoint variable into the ultimate PROMISE statistic. If proj0=TRUE, the stat.coeff is ignored. The stat.func column gives the name of the R routine that computes the test statistic of association of the end point variables. jung.rstat and spearman.rstat are provided. Users can provide their own routines accordingly. The endpt.vars column gives the name(s) of variable(s) in ph.data needed to compute each term of the PROMISE statistic. A comma without a space should be used to separate multiple variables that correspond to the same term in the association pattern definition. |
strat |
a vector of stratum to calculate stratified statistics. The default is NULL. |
proj0 |
indicator of whether projection to 0 is performed. It takes two valid values: TRUE or FALSE. If proj0=TRUE, PROMISE statistics is the sum of squares of individual statitics. The default is FALSE. |
a matrix of statistics. Each row gives gene's statistics of each individual endpoint and the PROMISE statistics defined in ph.pattern.
a function internally called by PROMISE.
Stan Pounds stanley.pounds@stjude.org; Xueyuan Cao xueyuan.cao@stjude.org
Pounds S, Cheng C, Cao X, Crews KR, Plunkett W, Gandhi V, Rubnitz J, Ribeiro RC, Downing JR, and Lamba J (2009) PROMISE: a tool to identify genomic features with a specific biologically interesting pattern of associations with multiple endpoint variables. Bioinformatics 25: 2013-2019
## load sampExprSet, phPatt. data(sampExprSet) data(phPatt) Y <- exprs(sampExprSet) ph.data <- pData(phenoData(sampExprSet)) test <- promise.genestat(Y, ph.data, phPatt, strat=ph.data[, 5]) test2 <- promise.genestat(Y, ph.data, phPatt, strat=ph.data[, 5], proj0=TRUE)