From 16bcb844774ddaed1678d6a0edb7475984f69f24 Mon Sep 17 00:00:00 2001 From: OganM Date: Wed, 9 Oct 2024 16:03:50 -0700 Subject: [PATCH] add documentation for the output --- DESCRIPTION | 4 ++-- R/ermineR.R | 21 ++++++++++++++++++++- R/testWrappers.R | 11 +++++++++++ man/corr.Rd | 21 +++++++++++++++++++++ man/ermineR.Rd | 20 +++++++++++++++++++- man/gsr.Rd | 21 +++++++++++++++++++++ man/ora.Rd | 21 +++++++++++++++++++++ man/precRecall.Rd | 21 +++++++++++++++++++++ man/roc.Rd | 21 +++++++++++++++++++++ 9 files changed, 157 insertions(+), 4 deletions(-) diff --git a/DESCRIPTION b/DESCRIPTION index 2a4c82f..f8c6a8f 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -1,6 +1,6 @@ Package: ermineR Title: Gene set analysis with multifunctionality assessment -Version: 1.0.2.9000 +Version: 1.0.3.9000 Authors@R: person("Ogan", "Mancarci", email = "ogan.mancarci@gmail.com", role = c("aut", "cre")) Description: ErmineR is an interface to the ermineJ gene set analysis software (http://erminej.msl.ubc.ca). Depends: R (>= 3.4.0) @@ -26,4 +26,4 @@ Suggests: tools Remotes: PavlidisLab/gemma.R -RoxygenNote: 7.2.1 +RoxygenNote: 7.3.2 diff --git a/R/ermineR.R b/R/ermineR.R index 967527a..a3991fd 100644 --- a/R/ermineR.R +++ b/R/ermineR.R @@ -17,7 +17,26 @@ #' @inheritParams geneSetOpts #' @inheritParams returnOpts #' -#' @return A list +#' @return A list containing a "results" component and a "details" component. +#' "results" is a data.frame containing the main output. The columns of this table are +#' +#' \itemize{ +#' \item \code{Name}: the name of the gene set +#' \item \code{ID}: the id of the gene set +#' \item \code{NumProbes}: the number of elements (e.g. probes) in the gene set. +#' \item \code{NumGenes}: the number of genes in the gene set. +#' \item \code{RawScore}: the raw statistic for the gene set. For explanations see this page +#' \item \code{Pval}: the p value for the gene set. +#' \item \code{CorrectedPvalue}: the corrected p pvalue. See this page for more information. +#' \item \code{MFPvalue}: pvalue after multifunctionality correction. Might be missing if correction was not performed. +#' \item \code{CorrectedMFPvalue}: Like CorrectedPvalue, but for the multifunctionality “corrected” pvalue. +#' \item \code{Multifunctionality}: How biased the genes in the set are towards multifunctional genes. +#' \item \code{Same as}: a list of gene sets which have the exact same members as this one. Such gene sets are not listed anywhere else. +#' \item \code{GeneMembers}: If you selected the “Include genes” option when saving, this will contain a list of the genes that are in the gene set, separated by “|”. +#' } +#' +#' "details" section contain settings that were used to run the analysis. +#' #' @export #' ermineR = function(annotation = NULL, diff --git a/R/testWrappers.R b/R/testWrappers.R index 67e1d7e..d463c4d 100644 --- a/R/testWrappers.R +++ b/R/testWrappers.R @@ -29,6 +29,9 @@ #' @inheritParams generalStats #' @inheritParams geneSetOpts #' @inheritParams returnOpts +#' +#' @inherit ermineR return +#' #' @export ora = function(scores = NULL, hitlist = NULL, @@ -88,6 +91,8 @@ ora = function(scores = NULL, #' @inheritParams geneSetOpts #' @inheritParams returnOpts #' +#' @inherit ermineR return +#' #' @export gsr = function(scores, scoreColumn = 1, @@ -143,6 +148,8 @@ gsr = function(scores, #' @inheritParams geneSetOpts #' @inheritParams returnOpts #' +#' @inherit ermineR return +#' #' @export precRecall = function(scores, scoreColumn = 1, @@ -204,6 +211,8 @@ precRecall = function(scores, #' @inheritParams geneSetOpts #' @inheritParams returnOpts #' +#' @inherit ermineR return +#' #' @export corr = function(expression, annotation = NULL, @@ -268,6 +277,8 @@ corr = function(expression, #' @inheritParams geneSetOpts #' @inheritParams returnOpts #' +#' @inherit ermineR return +#' #' @export roc = function(scores, scoreColumn = 1, diff --git a/man/corr.Rd b/man/corr.Rd index 40ffce1..1b1281b 100644 --- a/man/corr.Rd +++ b/man/corr.Rd @@ -78,6 +78,27 @@ symbols are accepted.} \item{return}{If results should be returned. Set to FALSE if you only want a file} } +\value{ +A list containing a "results" component and a "details" component. +"results" is a data.frame containing the main output. The columns of this table are + +\itemize{ + \item \code{Name}: the name of the gene set + \item \code{ID}: the id of the gene set + \item \code{NumProbes}: the number of elements (e.g. probes) in the gene set. + \item \code{NumGenes}: the number of genes in the gene set. + \item \code{RawScore}: the raw statistic for the gene set. For explanations see this page + \item \code{Pval}: the p value for the gene set. + \item \code{CorrectedPvalue}: the corrected p pvalue. See this page for more information. + \item \code{MFPvalue}: pvalue after multifunctionality correction. Might be missing if correction was not performed. + \item \code{CorrectedMFPvalue}: Like CorrectedPvalue, but for the multifunctionality “corrected” pvalue. + \item \code{Multifunctionality}: How biased the genes in the set are towards multifunctional genes. + \item \code{Same as}: a list of gene sets which have the exact same members as this one. Such gene sets are not listed anywhere else. + \item \code{GeneMembers}: If you selected the “Include genes” option when saving, this will contain a list of the genes that are in the gene set, separated by “|”. +} + +"details" section contain settings that were used to run the analysis. +} \description{ This method examines the gene expression profiles themselves, not the gene scores for each gene (which is how the other methods like ORA diff --git a/man/ermineR.Rd b/man/ermineR.Rd index bb5eaec..f2a6b4d 100644 --- a/man/ermineR.Rd +++ b/man/ermineR.Rd @@ -117,7 +117,25 @@ for details.} \item{maxClassSize}{maximum class size} } \value{ -A list +A list containing a "results" component and a "details" component. +"results" is a data.frame containing the main output. The columns of this table are + +\itemize{ + \item \code{Name}: the name of the gene set + \item \code{ID}: the id of the gene set + \item \code{NumProbes}: the number of elements (e.g. probes) in the gene set. + \item \code{NumGenes}: the number of genes in the gene set. + \item \code{RawScore}: the raw statistic for the gene set. For explanations see this page + \item \code{Pval}: the p value for the gene set. + \item \code{CorrectedPvalue}: the corrected p pvalue. See this page for more information. + \item \code{MFPvalue}: pvalue after multifunctionality correction. Might be missing if correction was not performed. + \item \code{CorrectedMFPvalue}: Like CorrectedPvalue, but for the multifunctionality “corrected” pvalue. + \item \code{Multifunctionality}: How biased the genes in the set are towards multifunctional genes. + \item \code{Same as}: a list of gene sets which have the exact same members as this one. Such gene sets are not listed anywhere else. + \item \code{GeneMembers}: If you selected the “Include genes” option when saving, this will contain a list of the genes that are in the gene set, separated by “|”. +} + +"details" section contain settings that were used to run the analysis. } \description{ The monolith function that wraps the emrineJ cli. It is recommended to use diff --git a/man/gsr.Rd b/man/gsr.Rd index 7d266aa..f8ce360 100644 --- a/man/gsr.Rd +++ b/man/gsr.Rd @@ -94,6 +94,27 @@ symbols are accepted.} \item{return}{If results should be returned. Set to FALSE if you only want a file} } +\value{ +A list containing a "results" component and a "details" component. +"results" is a data.frame containing the main output. The columns of this table are + +\itemize{ + \item \code{Name}: the name of the gene set + \item \code{ID}: the id of the gene set + \item \code{NumProbes}: the number of elements (e.g. probes) in the gene set. + \item \code{NumGenes}: the number of genes in the gene set. + \item \code{RawScore}: the raw statistic for the gene set. For explanations see this page + \item \code{Pval}: the p value for the gene set. + \item \code{CorrectedPvalue}: the corrected p pvalue. See this page for more information. + \item \code{MFPvalue}: pvalue after multifunctionality correction. Might be missing if correction was not performed. + \item \code{CorrectedMFPvalue}: Like CorrectedPvalue, but for the multifunctionality “corrected” pvalue. + \item \code{Multifunctionality}: How biased the genes in the set are towards multifunctional genes. + \item \code{Same as}: a list of gene sets which have the exact same members as this one. Such gene sets are not listed anywhere else. + \item \code{GeneMembers}: If you selected the “Include genes” option when saving, this will contain a list of the genes that are in the gene set, separated by “|”. +} + +"details" section contain settings that were used to run the analysis. +} \description{ The goal of this method is the same as for \code{\link{ora}}: to provide a p value for each gene set. The key difference lies in that ORA diff --git a/man/ora.Rd b/man/ora.Rd index 0d3ccfe..b468bd4 100644 --- a/man/ora.Rd +++ b/man/ora.Rd @@ -95,6 +95,27 @@ symbols are accepted.} \item{return}{If results should be returned. Set to FALSE if you only want a file} } +\value{ +A list containing a "results" component and a "details" component. +"results" is a data.frame containing the main output. The columns of this table are + +\itemize{ + \item \code{Name}: the name of the gene set + \item \code{ID}: the id of the gene set + \item \code{NumProbes}: the number of elements (e.g. probes) in the gene set. + \item \code{NumGenes}: the number of genes in the gene set. + \item \code{RawScore}: the raw statistic for the gene set. For explanations see this page + \item \code{Pval}: the p value for the gene set. + \item \code{CorrectedPvalue}: the corrected p pvalue. See this page for more information. + \item \code{MFPvalue}: pvalue after multifunctionality correction. Might be missing if correction was not performed. + \item \code{CorrectedMFPvalue}: Like CorrectedPvalue, but for the multifunctionality “corrected” pvalue. + \item \code{Multifunctionality}: How biased the genes in the set are towards multifunctional genes. + \item \code{Same as}: a list of gene sets which have the exact same members as this one. Such gene sets are not listed anywhere else. + \item \code{GeneMembers}: If you selected the “Include genes” option when saving, this will contain a list of the genes that are in the gene set, separated by “|”. +} + +"details" section contain settings that were used to run the analysis. +} \description{ Over-representation analysis (ORA) examines the genes that meet a selection criterion and determines if there are gene sets which are diff --git a/man/precRecall.Rd b/man/precRecall.Rd index 1c6b53d..4c76137 100644 --- a/man/precRecall.Rd +++ b/man/precRecall.Rd @@ -94,6 +94,27 @@ symbols are accepted.} \item{return}{If results should be returned. Set to FALSE if you only want a file} } +\value{ +A list containing a "results" component and a "details" component. +"results" is a data.frame containing the main output. The columns of this table are + +\itemize{ + \item \code{Name}: the name of the gene set + \item \code{ID}: the id of the gene set + \item \code{NumProbes}: the number of elements (e.g. probes) in the gene set. + \item \code{NumGenes}: the number of genes in the gene set. + \item \code{RawScore}: the raw statistic for the gene set. For explanations see this page + \item \code{Pval}: the p value for the gene set. + \item \code{CorrectedPvalue}: the corrected p pvalue. See this page for more information. + \item \code{MFPvalue}: pvalue after multifunctionality correction. Might be missing if correction was not performed. + \item \code{CorrectedMFPvalue}: Like CorrectedPvalue, but for the multifunctionality “corrected” pvalue. + \item \code{Multifunctionality}: How biased the genes in the set are towards multifunctional genes. + \item \code{Same as}: a list of gene sets which have the exact same members as this one. Such gene sets are not listed anywhere else. + \item \code{GeneMembers}: If you selected the “Include genes” option when saving, this will contain a list of the genes that are in the gene set, separated by “|”. +} + +"details" section contain settings that were used to run the analysis. +} \description{ Precision-recall curves are a standard way to analyze the quality of a classifier, as are \code{\link{roc}} curves. The difference diff --git a/man/roc.Rd b/man/roc.Rd index 07581b5..272a1ea 100644 --- a/man/roc.Rd +++ b/man/roc.Rd @@ -87,6 +87,27 @@ symbols are accepted.} \item{return}{If results should be returned. Set to FALSE if you only want a file} } +\value{ +A list containing a "results" component and a "details" component. +"results" is a data.frame containing the main output. The columns of this table are + +\itemize{ + \item \code{Name}: the name of the gene set + \item \code{ID}: the id of the gene set + \item \code{NumProbes}: the number of elements (e.g. probes) in the gene set. + \item \code{NumGenes}: the number of genes in the gene set. + \item \code{RawScore}: the raw statistic for the gene set. For explanations see this page + \item \code{Pval}: the p value for the gene set. + \item \code{CorrectedPvalue}: the corrected p pvalue. See this page for more information. + \item \code{MFPvalue}: pvalue after multifunctionality correction. Might be missing if correction was not performed. + \item \code{CorrectedMFPvalue}: Like CorrectedPvalue, but for the multifunctionality “corrected” pvalue. + \item \code{Multifunctionality}: How biased the genes in the set are towards multifunctional genes. + \item \code{Same as}: a list of gene sets which have the exact same members as this one. Such gene sets are not listed anywhere else. + \item \code{GeneMembers}: If you selected the “Include genes” option when saving, this will contain a list of the genes that are in the gene set, separated by “|”. +} + +"details" section contain settings that were used to run the analysis. +} \description{ The receiver operator characteristic (ROC) method is a fast, non-parametric alternative to the ORA and resampling methods for generating gene set scores