Merge revamp-tests (#31)

Update tests to testthat 3rd edition, amongst many 
other small changes.

.github/workflows/check-bioc.yml

@@ -56,9 +56,9 @@ jobs:
       fail-fast: false
       matrix:
         config:
-          - { os: ubuntu-latest, r: '4.0', bioc: '3.12', cont: "bioconductor/bioconductor_docker:RELEASE_3_12", rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest" }
-          - { os: macOS-latest, r: '4.0', bioc: '3.12'}
-          - { os: windows-latest, r: '4.0', bioc: '3.12'}
+          - { os: ubuntu-latest, r: '4.1', bioc: '3.13', cont: "bioconductor/bioconductor_docker:RELEASE_3_13", rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest" }
+          - { os: macOS-latest, r: '4.1', bioc: '3.13'}
+          - { os: windows-latest, r: '4.1', bioc: '3.13'}
     env:
       R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
       RSPM: ${{ matrix.config.rspm }}
@@ -106,16 +106,16 @@ jobs:
         uses: actions/cache@v2
         with:
           path: ${{ env.R_LIBS_USER }}
-          key: ${{ env.cache-version }}-${{ runner.os }}-biocversion-RELEASE_3_12-r-4.0-${{ hashFiles('.github/depends.Rds') }}
-          restore-keys: ${{ env.cache-version }}-${{ runner.os }}-biocversion-RELEASE_3_12-r-4.0-
+          key: ${{ env.cache-version }}-${{ runner.os }}-biocversion-RELEASE_3_13-r-4.1-${{ hashFiles('.github/depends.Rds') }}
+          restore-keys: ${{ env.cache-version }}-${{ runner.os }}-biocversion-RELEASE_3_13-r-4.1-
 
       - name: Cache R packages on Linux
         if: "!contains(github.event.head_commit.message, '/nocache') && runner.os == 'Linux' "
         uses: actions/cache@v2
         with:
           path: /home/runner/work/_temp/Library
-          key: ${{ env.cache-version }}-${{ runner.os }}-biocversion-RELEASE_3_12-r-4.0-${{ hashFiles('.github/depends.Rds') }}
-          restore-keys: ${{ env.cache-version }}-${{ runner.os }}-biocversion-RELEASE_3_12-r-4.0-
+          key: ${{ env.cache-version }}-${{ runner.os }}-biocversion-RELEASE_3_13-r-4.1-${{ hashFiles('.github/depends.Rds') }}
+          restore-keys: ${{ env.cache-version }}-${{ runner.os }}-biocversion-RELEASE_3_13-r-4.1-
 
       - name: Install Linux system dependencies
         if: runner.os == 'Linux'
@@ -182,11 +182,12 @@ jobs:
         run: |
           ## Pass #2 at installing dependencies
           message(paste('****', Sys.time(), 'pass number 2 at installing dependencies: any remaining dependencies ****'))
-          remotes::install_local(dependencies = TRUE, repos = BiocManager::repositories(), build_vignettes = TRUE, upgrade = TRUE)
+          remotes::install_local(dependencies = TRUE, repos = BiocManager::repositories(), build_vignettes = TRUE, upgrade = TRUE, force = TRUE)
 
           ## For running the checks
-          message(paste('****', Sys.time(), 'installing rcmdcheck ****'))
+          message(paste('****', Sys.time(), 'installing rcmdcheck and BiocCheck ****'))
           remotes::install_cran("rcmdcheck")
+          ## BiocManager::install("BiocCheck")
         shell: Rscript {0}
 
       - name: Install BiocGenerics
@@ -264,7 +265,7 @@ jobs:
         if: failure()
         uses: actions/upload-artifact@master
         with:
-          name: ${{ runner.os }}-biocversion-RELEASE_3_12-r-4.0-results
+          name: ${{ runner.os }}-biocversion-RELEASE_3_13-r-4.1-results
           path: check
 
       - uses: docker/build-push-action@v1

DESCRIPTION

@@ -12,7 +12,7 @@ License: MIT + file LICENSE
 Encoding: UTF-8
 LazyData: true
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.1.1
+RoxygenNote: 7.1.2
 VignetteBuilder: knitr
 Remotes: moodymudskipper/cutr
 biocViews:
@@ -39,4 +39,7 @@ Imports:
 Suggests: 
     knitr,
     rmarkdown,
-    testthat
+    testthat (>= 3.0.0),
+    vdiffr (>= 1.0.0),
+    withr
+Config/testthat/edition: 3

R/download_ccp_crap.R

@@ -1,3 +1,30 @@
+#' Get the UniProt sequences in CCP cRAP
+#'
+#' @description This function take no inputs and simply outputs a vector of the
+#' UniProt accessions for the sequences in the CCP cRAP FASTA.
+#'
+#' @return Returns a `character vector` of UniProt accessions.
+#' @export
+get_ccp_crap <- function() {
+  # load ccp crap and extract accessions
+  input <- Biostrings::readAAStringSet(
+    filepath = system.file("extdata", "cRAP_20190401.fasta.gz", package = "camprotR")
+  ) %>%
+    names()
+
+  accessions <- regmatches(
+    input,
+    gregexpr("(?<=\\|)[A-Z,0-9]{6}(?=\\|)", input, perl = TRUE)
+  ) %>%
+    unlist()
+
+  accessions[!accessions %in% "000000"]
+
+  # deal with alpha amylase proteins specifically
+  accessions[4:6] <- c("P0DUB6", "P0DTE7", "P0DTE8")
+  accessions
+}
+
 #' Download CCP cRAP FASTA file
 #'
 #' @description This function is used to download the Cambridge Centre for

R/make_fasta.R

@@ -1,30 +1,3 @@
-#' Get the UniProt sequences in CCP cRAP
-#'
-#' @description This function take no inputs and simply outputs a vector of the
-#' UniProt accessions for the sequences in the CCP cRAP FASTA.
-#'
-#' @return Returns a `character vector` of UniProt accessions.
-#' @export
-get_ccp_crap <- function() {
-  # load ccp crap and extract accessions
-  input <- Biostrings::readAAStringSet(
-    filepath = system.file("extdata", "cRAP_20190401.fasta", package = "camprotR")
-  ) %>%
-    names()
-
-  accessions <- regmatches(
-    input,
-    gregexpr("(?<=\\|)[A-Z,0-9]{6}(?=\\|)", input, perl = TRUE)
-  ) %>%
-    unlist()
-
-  accessions[!accessions %in% "000000"]
-
-  # deal with alpha amylase proteins specifically
-  accessions[4:6] <- c("P0DUB6", "P0DTE7", "P0DTE8")
-  accessions
-}
-
 #' Make a FASTA using UniProt accessions
 #'
 #' @description Given a vector of UniProt accessions, this function will:
@@ -63,10 +36,21 @@ make_fasta <- function(accessions, file, is_crap = FALSE, overwrite = FALSE, ver
   )
 
   # query uniprot and save FASTA to disk
-  response <- httr::GET(
-    url = "https://www.uniprot.org/uploadlists/",
-    query = payload,
-    config = httr::write_disk(path = file, overwrite = overwrite)
+  # security level fix for Ubuntu 20.04
+  # see https://msmith.de/2020/10/02/httr-curl-ubuntu-20-04.html
+  httr_config <- switch(
+    Sys.info()["sysname"],
+    "Linux" = httr::config(ssl_cipher_list = "DEFAULT@SECLEVEL=1"),
+    httr::config()
+  )
+
+  response <- httr::with_config(
+    config = httr_config,
+    httr::GET(
+      url = "https://www.uniprot.org/uploadlists/",
+      query = payload,
+      config = httr::write_disk(path = file, overwrite = overwrite)
+    )
   )
 
   # basic http error handling
@@ -146,7 +130,20 @@ sub_crap <- function(x, start = 1, width = 3) {
 #' @export
 check_uniprot_release <- function() {
   # query H. sapiens actin
-  response <- httr::GET(url = "https://www.uniprot.org/uniprot/P60709")
+  # security level fix for Ubuntu 20.04
+  # see https://msmith.de/2020/10/02/httr-curl-ubuntu-20-04.html
+  httr_config <- switch(
+    Sys.info()["sysname"],
+    "Linux" = httr::config(ssl_cipher_list = "DEFAULT@SECLEVEL=1"),
+    httr::config()
+  )
+
+  response <- httr::with_config(
+    config = httr_config,
+    httr::GET(
+      url = "https://www.uniprot.org/uniprot/P60709"
+    )
+  )
 
   # basic http error handling
   httr::stop_for_status(response, "query UniProt")

R/pep_silac_p0.R

@@ -0,0 +1,12 @@
+#' PeptideGroups PD output for SILAC labelled MOLM-13 cells
+#'
+#' @description Passage 0, 100% light (R0K0).
+#'
+#' \describe{
+#'   \item{column name}{`class`. Description.}
+#' }
+#'
+#' @references Insert reference here when published.
+#'
+#' @keywords datasets
+"pep_silac_p0"

R/pep_silac_p4.R

@@ -0,0 +1,12 @@
+#' PeptideGroups PD output for SILAC labelled MOLM-13 cells
+#'
+#' @description Passage 4, 1:1 light:heavy mixture (R0K0:R10K8).
+#'
+#' \describe{
+#'   \item{column name}{`class`. Description.}
+#' }
+#'
+#' @references Insert reference here when published.
+#'
+#' @keywords datasets
+"pep_silac_p4"

R/psm_silac_p4.R

@@ -0,0 +1,12 @@
+#' PSMs PD output for SILAC labelled MOLM-13 cells
+#'
+#' @description Passage 4, 1:1 light:heavy mixture (R0K0:R10K8).
+#'
+#' \describe{
+#'   \item{column name}{`class`. Description.}
+#' }
+#'
+#' @references Insert reference here when published.
+#'
+#' @keywords datasets
+"psm_silac_p4"

R/ptm.R

@@ -144,12 +144,14 @@ parse_PTM_scores <- function(obj,
 #' to add 'filtered_pos' column
 #'
 #' @param obj `data.frame` with PD output at PSM/peptide level
-#' @param proteome_fasta `character` Filepath for proteome fasta
-#' @param master_protein_col `character` Column name for master protein
+#' @param proteome_fasta `string` Filepath for proteome fasta
+#' @param master_protein_col `string` Name of column containing master protein IDs
+#' @param sequence_col `string`. Name of column containing peptide sequences
 #'
 #' @return `data.frame`
 #' @export
-add_PTM_positions <- function(obj, proteome_fasta, master_protein_col = "Master.Protein.Accessions") {
+add_PTM_positions <- function(obj, proteome_fasta, master_protein_col = "Master.Protein.Accessions",
+                              sequence_col = "Sequence") {
   proteome <- Biostrings::readAAStringSet(proteome_fasta)
   names(proteome) <- sapply(base::strsplit(names(proteome), split = "\\|"), "[[", 2)
 
@@ -182,7 +184,7 @@ add_PTM_positions <- function(obj, proteome_fasta, master_protein_col = "Master.
   obj$ptm_position <- apply(
     obj,
     MARGIN = 1, function(x) combine_peptide_ptm_positions(
-      proteome, x[[master_protein_col]], x[["Sequence"]], x[["filtered_pos"]]
+      proteome, x[[master_protein_col]], x[[sequence_col]], x[["filtered_pos"]]
     )
   )
 

data-raw/pep_silac_p0.R

@@ -0,0 +1,20 @@
+library(dplyr)
+
+# Read in SILAC passage 0 peptide data
+# 100% light cells (R0K0)
+pepg <- read.delim(
+  here::here("data-raw/Molm_13_P0_PeptideGroups.txt")
+)
+
+# Remove extraneous periods from colnames
+colnames(pepg) <- remove_dots(colnames(pepg))
+
+# Set seed for reproducible sampling
+set.seed(2021)
+
+# Get all peptides for a random sample of 100 Master proteins
+pep_silac_p0 <- pepg %>%
+  filter(Master.Protein.Accessions %in% sample(unique(Master.Protein.Accessions), 100))
+
+# Output .rda file
+usethis::use_data(pep_silac_p0, overwrite = TRUE)

data-raw/pep_silac_p4.R

@@ -0,0 +1,20 @@
+library(dplyr)
+
+# Read in SILAC passage 4 peptide data
+# 50:50 mix of light:heavy cells (R0K0:R10K8)
+pepg <- read.delim(
+  here::here("data-raw/Molm_13_P4_PeptideGroups.txt")
+)
+
+# Remove extraneous periods from colnames
+colnames(pepg) <- remove_dots(colnames(pepg))
+
+# Set seed for reproducible sampling
+set.seed(2021)
+
+# Get all peptides for a random sample of 100 Master proteins
+pep_silac_p4 <- pepg %>%
+  filter(Master.Protein.Accessions %in% sample(unique(Master.Protein.Accessions), 100))
+
+# Output .rda file
+usethis::use_data(pep_silac_p4, overwrite = TRUE)

data-raw/psm_silac_p4.R

@@ -0,0 +1,17 @@
+library(dplyr)
+
+# Read in SILAC passage 4 peptide data
+# 50:50 mix of light:heavy cells (R0K0:R10K8)
+silac_p4 <- read.delim(
+  here::here("data-raw/Molm_13_P4_PSMs.txt")
+)
+
+# Set seed for reproducible sampling
+set.seed(2021)
+
+# Get all PSMs for a random sample of 100 Master proteins
+psm_silac_p4 <- silac_p4 %>%
+  filter(Master.Protein.Accessions %in% sample(unique(Master.Protein.Accessions), 100))
+
+# Output .rda file
+usethis::use_data(psm_silac_p4, overwrite = TRUE)