Merge pull request #59 from uclahs-cds/nzeltser-cran-fixes

cran fixes

Author: alkaZeltser

DESCRIPTION

@@ -4,7 +4,7 @@ Title: Utilities for the Application of a Polygenic Score to a VCF
 Version: 1.0.0
 Authors@R: c(
     person('Paul', 'Boutros', role = 'cre', email = '[email protected]'),
-    person('Nicole', 'Zeltser', role = 'aut', comment = c(ORCID = '000-0001-7246-2771')),
+    person('Nicole', 'Zeltser', role = 'aut', comment = c(ORCID = '0000-0001-7246-2771')),
     person('Rachel', 'Dang', role = 'ctb'))
 Description: This tool is intended to simply and transparently parse
     genotype/dosage data from an input VCF, match genotype coordinates

NAMESPACE

@@ -35,15 +35,15 @@ importFrom(
 
 export(
     apply.polygenic.score,
+    combine.pgs.bed,
+    combine.vcf.with.pgs,
     convert.alleles.to.pgs.dosage,
     convert.allele.frequency.to.dosage,
     convert.pgs.to.bed,
     format.chromosome.notation,
     get.pgs.percentiles,
     import.pgs.weight.file,
     import.vcf,
-    merge.pgs.bed,
-    merge.vcf.with.pgs,
     parse.pgs.input.header,
     create.pgs.density.plot,
     create.pgs.rank.plot,

NEWS.md

@@ -1,3 +1,8 @@
+# ApplyPolygenicScore Unreleased
+
+## Changed
+* Renamed functions starting with reserved vocabulary for S3 generic methods merge. -> combine.
+
 # ApplyPolygenicScore 1.0.0 (2024-07-25)
 
 * First release

R/apply-pgs.R

@@ -278,7 +278,7 @@ apply.polygenic.score <- function(
     ### End Input Validation ###
 
     # merge VCF and PGS data
-    merged.vcf.with.pgs.data <- merge.vcf.with.pgs(
+    merged.vcf.with.pgs.data <- combine.vcf.with.pgs(
         vcf.data = vcf.data,
         pgs.weight.data = pgs.weight.data
         )$merged.vcf.with.pgs.data;

R/merge-vcf-with-pgs.R R/combine-vcf-with-pgs.RR/merge-vcf-with-pgs.R renamed to R/combine-vcf-with-pgs.R

@@ -1,4 +1,4 @@
-#' @title Merge VCF with PGS
+#' @title Combine VCF with PGS
 #' @description Match PGS SNPs to corresponding VCF information by genomic coordinates using a merge operation.
 #' @param vcf.data A data.frame containing VCF data. Required columns: \code{CHROM, POS}.
 #' @param pgs.weight.data A data.frame containing PGS data. Required columns: \code{CHROM, POS}.
@@ -26,12 +26,12 @@
 #'     );
 #' pgs.import <- import.pgs.weight.file(pgs.weight.path);
 #'
-#' merge.data <- merge.vcf.with.pgs(
+#' merge.data <- combine.vcf.with.pgs(
 #'     vcf.data = vcf.import$dat,
 #'     pgs.weight.data = pgs.import$pgs.weight.data
 #'     );
 #' @export
-merge.vcf.with.pgs <- function(vcf.data, pgs.weight.data) {
+combine.vcf.with.pgs <- function(vcf.data, pgs.weight.data) {
 
     # check that inputs are data.frames
     if (!is.data.frame(vcf.data)) {

R/convert-pgs-to-bed.R

@@ -78,7 +78,7 @@ convert.pgs.to.bed <- function(pgs.weight.data, chr.prefix = TRUE, numeric.sex.c
     return(pgs.bed);
     }
 
-#' @title Merge PGS BED files
+#' @title Combine PGS BED files
 #' @description Merge overlapping PGS coordinates in multiple BED files.
 #' @param pgs.bed.list A named list of data.frames containing PGS coordinates in BED format.
 #' @param add.annotation.data A logical indicating whether an additional annotation data column should be added to the annotation column.
@@ -99,9 +99,9 @@ convert.pgs.to.bed <- function(pgs.weight.data, chr.prefix = TRUE, numeric.sex.c
 #'     annotation = c('d', 'e', 'f')
 #'     );
 #' bed.input <- list(bed1 = bed1, bed2 = bed2);
-#' merge.pgs.bed(bed.input);
+#' combine.pgs.bed(bed.input);
 #' @export
-merge.pgs.bed <- function(pgs.bed.list, add.annotation.data = FALSE, annotation.column.index = 4, slop = 0) {
+combine.pgs.bed <- function(pgs.bed.list, add.annotation.data = FALSE, annotation.column.index = 4, slop = 0) {
 
     # check that pgs.bed.list is a named list
     if (!is.list(pgs.bed.list) | is.null(names(pgs.bed.list))) {

R/plot-pgs.R

@@ -71,34 +71,45 @@ split.pgs.by.phenotype <- function(pgs, phenotype.data) {
 #' @param border.padding numeric padding for plot borders
 #' @return If no output directory is provided, a multipanel lattice plot object is returned, otherwise a plot is written to the indicated path and \code{NULL} is returned.
 #' @examples
-#' set.seed(200);
+#' set.seed(100);
 #' pgs.data <- data.frame(
-#'     PGS = rnorm(200, 0, 1)
+#'     PGS = rnorm(100, 0, 1)
 #'     );
 #'  temp.dir <- tempdir();
 #'
 #' # Basic Plot
-#' create.pgs.density.plot(pgs.data, output.dir = temp.dir, filename.prefix = 'basic-plot');
+#' create.pgs.density.plot(
+#'     pgs.data,
+#'     output.dir = temp.dir,
+#'     filename.prefix = 'basic-plot',
+#'     width = 6,
+#'     height = 6
+#'     );
 #'
 #' # Plot multiple PGS outputs
-#' pgs.data$PGS.with.normalized.missing <- rnorm(200, 1, 1);
-#' create.pgs.density.plot(pgs.data, output.dir = temp.dir);
+#' pgs.data$PGS.with.normalized.missing <- rnorm(100, 1, 1);
+#' \donttest{create.pgs.density.plot(pgs.data, output.dir = temp.dir);}
 #'
 #' # Plot phenotype categories
-#' pgs.data$sex <- sample(c('male', 'female', 200, replace = TRUE));
+#' \donttest{
+#' pgs.data$sex <- sample(c('male', 'female', 100, replace = TRUE));
 #' create.pgs.density.plot(
-#'     pgs.data, output.dir = temp.dir,
+#'     pgs.data,
+#'     output.dir = temp.dir,
 #'     filename.prefix = 'multiple-pgs',
 #'     phenotype.columns = 'sex'
 #'     );
-#'
+#'}
 #' # Plot multiple phenotypes
-#' pgs.data$letters <- sample(letters[1:5], 200, replace = TRUE);
+#' \donttest{
+#' pgs.data$letters <- sample(letters[1:5], 100, replace = TRUE);
 #' create.pgs.density.plot(
-#'     pgs.data, output.dir = temp.dir,
+#'     pgs.data,
+#'     output.dir = temp.dir,
 #'     filename.prefix = 'multiple-phenotypes',
 #'     phenotype.columns = c('sex', 'letters')
 #'     );
+#' }
 #' @export
 create.pgs.density.plot <- function(
     pgs.data,
@@ -370,11 +381,11 @@ create.pgs.density.plot <- function(
 #' @param border.padding numeric padding for plot borders
 #' @return If no output directory is provided, a multipanel lattice plot object is returned, otherwise a plot is written to the indicated path and \code{NULL} is returned.
 #' @examples
-#' set.seed(200);
+#' set.seed(100);
 #'
 #' pgs.data <- data.frame(
-#'     PGS = rnorm(200, 0, 1),
-#'     continuous.phenotype = rnorm(200, 2, 1)
+#'     PGS = rnorm(100, 0, 1),
+#'     continuous.phenotype = rnorm(100, 2, 1)
 #'     );
 #'  temp.dir <- tempdir();
 #'
@@ -383,26 +394,32 @@ create.pgs.density.plot <- function(
 #'     pgs.data,
 #'     output.dir = temp.dir,
 #'     filename.prefix = 'basic-plot',
-#'     phenotype.columns = 'continuous.phenotype'
+#'     phenotype.columns = 'continuous.phenotype',
+#'     width = 6,
+#'     height = 6
 #'     );
 #'
 #' # Plot multiple PGS outputs
-#' pgs.data$PGS.with.normalized.missing <- rnorm(200, 1, 1);
+#' \donttest{
+#' pgs.data$PGS.with.normalized.missing <- rnorm(100, 1, 1);
 #' create.pgs.with.continuous.phenotype.plot(
 #'     pgs.data,
 #'     output.dir = temp.dir,
 #'     filename.prefix = 'multiple-pgs',
 #'     phenotype.columns = 'continuous.phenotype'
 #'     );
+#'}
 #'
 #' # Plot multiple phenotypes
-#' pgs.data$continuous.phenotype2 <- rnorm(200, 10, 1);
+#' \donttest{
+#' pgs.data$continuous.phenotype2 <- rnorm(100, 10, 1);
 #' create.pgs.with.continuous.phenotype.plot(
 #'     pgs.data,
 #'     output.dir = temp.dir,
 #'     filename.prefix = 'multiple-phenotypes',
 #'     phenotype.columns = c('continuous.phenotype', 'continuous.phenotype2')
 #'     );
+#' }
 #' @export
 create.pgs.with.continuous.phenotype.plot <- function(
     pgs.data,

README.md

@@ -57,7 +57,7 @@ If you wish to apply a PGS to a cohort, we recommend that genotypes for the whol
     We recommend starting by filtering your input VCF for just the variants in your PGS weight files. Several software tools are available to do this, and most all require a coordinate BED file. A description of BED format can be found [here](https://bedtools.readthedocs.io/en/latest/content/general-usage.html).
 
     The function `import.pgs.weight.file` can be used to import your PGS weight files into R.
-    The functions `convert.pgs.to.bed` and `merge.pgs.bed` can be used to make the conversion, and merge several BED dataframes into one, respectively.
+    The functions `convert.pgs.to.bed` and `combine.pgs.bed` can be used to make the conversion, and merge several BED dataframes into one, respectively.
 
 2. Import your VCF file.
 
@@ -67,7 +67,7 @@ If you wish to apply a PGS to a cohort, we recommend that genotypes for the whol
 3. Apply your PGS.
 
     Provide your imported VCF and PGS weight files to `apply.polygenic.score`. It's as simple as that.
-    Under the hood, this function begins by calling `merge.vcf.with.pgs`. The merge function also outputs a list of variants in your PGS that could not be found in your VCF data, which you can obtain by calling the function independently.
+    Under the hood, this function begins by calling `combine.vcf.with.pgs`. The merge function also outputs a list of variants in your PGS that could not be found in your VCF data, which you can obtain by calling the function independently.
     `apply.polygenic.score` outputs lots of useful information along with the score and provides various customizeable options, such as methods for handling missing sites (see [this discussion](https://github.com/uclahs-cds/package-ApplyPolygenicScore/discussions/17) for more) and basic analyses with phenotype data.
 
 4. Create summary plots.