Merge pull request #28 from CCBR/vignette

Create beginnings of introductory vignette

.gitignore

@@ -5,3 +5,4 @@
 .DS_Store
 .quarto
 docs
+inst/doc

CITATION.cff

@@ -1,7 +1,7 @@
-# -----------------------------------------------------------
-# CITATION file created with {cffr} R package, v0.5.0
+# --------------------------------------------
+# CITATION file created with {cffr} R package
 # See also: https://docs.ropensci.org/cffr/
-# -----------------------------------------------------------
+# --------------------------------------------
 
 cff-version: 1.2.0
 message: 'To cite package "reneeTools" in publications use:'
@@ -33,11 +33,10 @@ references:
     url: https://www.R-project.org/
     authors:
       - name: R Core Team
-    location:
-      name: Vienna, Austria
-    year: "2024"
     institution:
       name: R Foundation for Statistical Computing
+      address: Vienna, Austria
+    year: "2024"
     version: ">= 2.10"
   - type: software
     title: DESeq2
@@ -56,7 +55,6 @@ references:
       - family-names: Huber
         given-names: Wolfgang
     year: "2024"
-    doi: 10.18129/B9.bioc.DESeq2
   - type: software
     title: dplyr
     abstract: "dplyr: A Grammar of Data Manipulation"
@@ -125,6 +123,18 @@ references:
       - family-names: Girlich
         given-names: Maximilian
     year: "2024"
+  - type: software
+    title: knitr
+    abstract: "knitr: A General-Purpose Package for Dynamic Report Generation in R"
+    notes: Suggests
+    url: https://yihui.org/knitr/
+    repository: https://CRAN.R-project.org/package=knitr
+    authors:
+      - family-names: Xie
+        given-names: Yihui
+        email: [email protected]
+        orcid: https://orcid.org/0000-0003-0645-5666
+    year: "2024"
   - type: software
     title: readr
     abstract: "readr: Read Rectangular Text Data"
@@ -142,6 +152,49 @@ references:
         email: [email protected]
         orcid: https://orcid.org/0000-0002-6983-2759
     year: "2024"
+  - type: software
+    title: rmarkdown
+    abstract: "rmarkdown: Dynamic Documents for R"
+    notes: Suggests
+    url: https://pkgs.rstudio.com/rmarkdown/
+    repository: https://CRAN.R-project.org/package=rmarkdown
+    authors:
+      - family-names: Allaire
+        given-names: JJ
+        email: [email protected]
+      - family-names: Xie
+        given-names: Yihui
+        email: [email protected]
+        orcid: https://orcid.org/0000-0003-0645-5666
+      - family-names: Dervieux
+        given-names: Christophe
+        email: [email protected]
+        orcid: https://orcid.org/0000-0003-4474-2498
+      - family-names: McPherson
+        given-names: Jonathan
+        email: [email protected]
+      - family-names: Luraschi
+        given-names: Javier
+      - family-names: Ushey
+        given-names: Kevin
+        email: [email protected]
+      - family-names: Atkins
+        given-names: Aron
+        email: [email protected]
+      - family-names: Wickham
+        given-names: Hadley
+        email: [email protected]
+      - family-names: Cheng
+        given-names: Joe
+        email: [email protected]
+      - family-names: Chang
+        given-names: Winston
+        email: [email protected]
+      - family-names: Iannone
+        given-names: Richard
+        email: [email protected]
+        orcid: https://orcid.org/0000-0003-3925-190X
+    year: "2024"
   - type: software
     title: styler
     abstract: "styler: Non-Invasive Pretty Printing of R Code"

DESCRIPTION

@@ -21,13 +21,17 @@ Imports:
     S7,
     tidyr
 Suggests:
+    knitr,
     readr,
+    rmarkdown,
     styler,
     testthat (>= 3.0.0),
     usethis
+VignetteBuilder:
+    knitr
 biocViews:
 Config/testthat/edition: 3
 Encoding: UTF-8
 LazyData: true
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.3.0
+RoxygenNote: 7.3.1

NAMESPACE

@@ -2,10 +2,11 @@
 
 export("%>%")
 export(counts_dat_to_matrix)
+export(create_reneeDataSet_from_dataframes)
+export(create_reneeDataSet_from_files)
 export(filter_low_counts)
 export(meta_tbl_to_dat)
-export(reneeDataSetFromDataFrames)
-export(reneeDataSetFromFiles)
 export(run_deseq2)
 if (getRversion() < "4.3.0") importFrom("S7", "@")
+importFrom(DESeq2,DESeq)
 importFrom(dplyr,"%>%")

NEWS.md

@@ -1,13 +1,13 @@
-# reneeTools development version
+# reneeTools development version 0.0.0.9000
 
 This is the first release of reneeTools 🎉
 
 - Create a `NEWS.md` file to track changes to the package.
 
 ## Main functions & classes
 
-- `reneeDataSet` (#16)
-  - `reneeDataSetFromFiles()` (#16)
-  - `reneeDataSetFromDataFrames()` (#16)
-  - `run_deseq2()` (#16)
-- `filter_low_counts()` (#10)
+- `reneeDataSet` (#16, #28, @kelly-sovacool)
+  - `create_reneeDataSet_from_files()`
+  - `create_reneeDataSet_from_dataframes()`
+  - `run_deseq2()`
+- `filter_low_counts()` (#10, @kelly-sovacool)

R/renee-class.R → R/0_renee-class.R

@@ -1,12 +1,20 @@
+#' reneeDataSet class
+#'
+#' @param count_dat expected gene counts from RSEM as a data frame or tibble.
+#'   Must contain a `gene_id` column and a column for each sample ID in the metadata.
+#' @param sample_meta_dat sample metadata as a data frame or tibble.
+#'   Must contain a `sample_ID` column.
+#'
+#'
 reneeDataSet <- S7::new_class("renee",
   properties = list(
-    counts = S7::new_S3_class("matrix"),
+    counts = S7::class_data.frame,
     sample_meta = S7::class_data.frame,
     analyses = S7::class_list
   ),
-  constructor = function(count_matrix, sample_meta_dat) {
+  constructor = function(count_dat, sample_meta_dat) {
     S7::new_object(S7::S7_object(),
-      counts = count_matrix,
+      counts = count_dat,
       sample_meta = sample_meta_dat,
       analyses = list()
     )
@@ -22,22 +30,19 @@ reneeDataSet <- S7::new_class("renee",
 #' @export
 #'
 #' @examples
-#' reneeDataSetFromFiles(
+#' create_reneeDataSet_from_files(
 #'   system.file("extdata", "RSEM.genes.expected_count.all_samples.txt", package = "reneeTools"),
 #'   system.file("extdata", "sample_metadata.tsv", package = "reneeTools")
 #' )
-reneeDataSetFromFiles <- function(gene_counts_filepath, sample_meta_filepath) {
+create_reneeDataSet_from_files <- function(gene_counts_filepath, sample_meta_filepath) {
   count_dat <- readr::read_tsv(gene_counts_filepath)
   sample_meta_dat <- readr::read_tsv(sample_meta_filepath)
-  return(reneeDataSetFromDataFrames(count_dat, sample_meta_dat))
+  return(create_reneeDataSet_from_dataframes(count_dat, sample_meta_dat))
 }
 
 #' Construct a reneeDataSet object from data frames
 #'
-#' @param gene_counts_dat expected gene counts from RSEM as a data frame or tibble.
-#'   Must contain a `gene_id` column and a column for each sample ID in the metadata.
-#' @param sample_meta_dat sample metadata as a data frame or tibble.
-#'   Must contain a `sample_ID` column.
+#' @inheritParams reneeDataSet
 #'
 #' @return reneeDataSet object
 #' @export
@@ -50,15 +55,16 @@ reneeDataSetFromFiles <- function(gene_counts_filepath, sample_meta_filepath) {
 #'     levels = c("wildtype", "knockout")
 #'   )
 #' )
-#' reneeDataSetFromDataFrames(gene_counts, sample_meta)
-reneeDataSetFromDataFrames <- function(gene_counts_dat, sample_meta_dat) {
-  count_mat <- gene_counts_dat %>% counts_dat_to_matrix()
+#' create_reneeDataSet_from_dataframes(gene_counts, sample_meta)
+create_reneeDataSet_from_dataframes <- function(count_dat, sample_meta_dat) {
+  gene_id <- GeneName <- NULL
+
   sample_meta_dat <- sample_meta_dat %>% meta_tbl_to_dat()
 
   # sample IDs must be in the same order
-  if (!all(colnames(count_mat) == rownames(sample_meta_dat))) {
-    stop("Not all columns in the count matrix equal the rows in the sample metadata. Sample IDs must be in the same order.")
+  if (!all(colnames(count_dat %>% dplyr::select(-gene_id, -GeneName)) == rownames(sample_meta_dat))) {
+    stop("Not all columns in the count data equal the rows in the sample metadata. Sample IDs must be in the same order.")
   }
 
-  return(reneeDataSet(count_mat, sample_meta_dat))
+  return(reneeDataSet(count_dat, sample_meta_dat))
 }

R/deseq2.R

@@ -8,7 +8,7 @@
 #' @export
 #'
 #' @examples
-#' renee_ds <- reneeDataSetFromFiles(
+#' renee_ds <- create_reneeDataSet_from_files(
 #'   system.file("extdata",
 #'     "RSEM.genes.expected_count.all_samples.txt",
 #'     package = "reneeTools"
@@ -18,12 +18,17 @@
 #'   )
 #' )
 #' renee_ds <- run_deseq2(renee_ds, ~condition)
-run_deseq2 <- function(renee_ds, design, ...) {
+run_deseq2 <- S7::new_generic("run_deseq2", "renee_ds", function(renee_ds, design, ...) {
+  S7::S7_dispatch()
+})
+
+S7::method(run_deseq2, reneeDataSet) <- function(renee_ds, design, min_count = 10, ...) {
   dds <- DESeq2::DESeqDataSetFromMatrix(
-    renee_ds@counts,
-    renee_ds@sample_meta,
-    design
+    countData = renee_ds@counts %>% filter_low_counts(min_count = min_count) %>% counts_dat_to_matrix(),
+    colData = renee_ds@sample_meta,
+    design = design
   )
   renee_ds@analyses$deseq2_ds <- DESeq2::DESeq(dds, ...)
+  renee_ds@analyses$deseq2_results <- DESeq2::results(renee_ds@analyses$deseq2_ds)
   return(renee_ds)
 }

R/filter_low_counts.R

@@ -1,25 +1,25 @@
 #' filter_low_counts
 #'
 #' @param counts_dat expected gene counts from RSEM as a data frame or tibble
-#' @param min_counts integer number of minimum counts across all samples (default: 0)
+#' @param min_count integer number of minimum counts across all samples (default: 0)
 #'
 #' @return filtered counts dataframe
 #' @export
 #'
 #' @examples
 #' filter_low_counts(gene_counts) %>% head()
-#' filter_low_counts(gene_counts, min_counts = 100)
+#' filter_low_counts(gene_counts, min_count = 100)
 filter_low_counts <- function(
     counts_dat,
-    min_counts = 0) {
+    min_count = 0) {
   gene_id <- count <- count_sum <- NULL
   genes_above_threshold <- counts_dat %>%
     tidyr::pivot_longer(!c("gene_id", "GeneName"),
       names_to = "sample_id", values_to = "count"
     ) %>%
     dplyr::group_by(gene_id) %>%
     dplyr::summarize(count_sum = sum(count)) %>%
-    dplyr::filter(count_sum >= min_counts) %>%
+    dplyr::filter(count_sum >= min_count) %>%
     dplyr::pull(gene_id)
   return(
     counts_dat %>%

R/zzz.R

@@ -7,3 +7,9 @@
 # source: https://rconsortium.github.io/S7/articles/packages.html#backward-compatibility
 #' @rawNamespace if (getRversion() < "4.3.0") importFrom("S7", "@")
 NULL
+
+
+# Suppress R CMD check note 'All declared Imports should be used'.
+# These packages are used within S7 methods.
+#' @importFrom DESeq2 DESeq
+NULL