Merge branch 'devel'

.Rbuildignore

@@ -19,3 +19,4 @@ docs
 ^src/main\.cpp$
 ^src/CMakeLists\.txt$
 ^src/cmake-build-debug$
+^CRAN-SUBMISSION$

DESCRIPTION

@@ -2,7 +2,7 @@ Package: tidysq
 Type: Package
 Title: Tidy Processing and Analysis of Biological Sequences
 Version: 1.2.1
-Date: 2022-01-29
+Date: 2024-09-29
 Authors@R: c(person("Dominik", "Rafacz", 
            email = "dominikrafacz@gmail.com",
            comment = c(ORCID = "0000-0003-0925-1909"),

NEWS.md

@@ -3,6 +3,7 @@
 ## Fixed:
 * fixed incorrect codons
 * add explicit casting of alphabet during construction of sequence prototype (fixes issues with new implementation of `union()`) 
+* add skips for tests that use not available packages from "Suggests"
 
 # tidysq 1.2.0
 ## New features:

R/export_sq.R

@@ -1,7 +1,7 @@
 #' Export sq objects into other formats
 #'
 #' @templateVar name_null_ok TRUE
-#' 
+#'
 #' @description Converts object of class \code{\link[=sq-class]{sq}} to a class
 #' from another package. Currently supported packages are \pkg{ape},
 #' \pkg{bioseq}, \pkg{Bioconductor} and \pkg{seqinr}. For exact list of
@@ -13,8 +13,8 @@
 #' @template name
 #' @template three-dots
 #'
-#' @return An object with the format specified in the parameter. To find 
-#' information about the detailed structure of this object, see documentation 
+#' @return An object with the format specified in the parameter. To find
+#' information about the detailed structure of this object, see documentation
 #' of these objects.
 #'
 #' @details
@@ -44,7 +44,7 @@
 #'  }
 #' }
 #'
-#' @examples
+#' @examplesIf all(c(require("Biostrings", quietly = TRUE), require("ape", quietly = TRUE), require("bioseq", quietly = TRUE), require("seqinr", quietly = TRUE)))
 #' # DNA and amino acid sequences can be exported to most packages
 #' sq_ami <- sq(c("MVVGL", "LAVPP"), alphabet = "ami_bsc")
 #' export_sq(sq_ami, "ape::AAbin")
@@ -72,7 +72,7 @@
 export_sq <- function(x, export_format, name = NULL, ...) {
   assert_string(export_format)
   assert_character(name, len = vec_size(x), null.ok = TRUE)
-  
+
   UseMethod("export_sq")
 }
 

R/find_motifs.R

@@ -1,9 +1,9 @@
 #' Find given motifs
 #'
 #' @templateVar name_null_ok FALSE
-#' 
+#'
 #' @description Finds all given motifs in sequences and returns their positions.
-#' 
+#'
 #' @template x
 #' @template name
 #' @param motifs [\code{character}]\cr
@@ -12,20 +12,20 @@
 #' @template dot-name
 #' @template NA_letter
 #' @template three-dots
-#' 
+#'
 #' @return A \code{\link[tibble]{tibble}} with following columns:
 #'  \item{name}{name of the sequence in which a motif was found}
 #'  \item{sought}{sought motif}
 #'  \item{found}{found subsequence, may differ from sought if the motif
 #'   contained ambiguous letters}
 #'  \item{start}{position of first element of found motif}
 #'  \item{end}{position of last element of found motif}
-#' 
+#'
 #' @details
 #' This function allows search of a given motif or motifs in the \code{sq}
 #' object. It returns all motifs found with their start and end positions within
 #' a sequence.
-#' 
+#'
 #' @template motif_details
 #'
 #' @examples
@@ -53,7 +53,7 @@
 #'
 #' # Finding multicharacter motifs:
 #' find_motifs(sq_atp, sq_names, c("nsA", "mYmY$"))
-#' 
+#'
 #' # It can be a part of tidyverse pipeline:
 #' library(dplyr)
 #' fasta_file <- system.file(package = "tidysq", "examples/example_aa.fasta")
@@ -80,7 +80,7 @@ find_motifs.sq <- function(x, name, motifs, ...,
   assert_character(motifs, any.missing = FALSE)
   assert_string(NA_letter, min.chars = 1)
   assert_alph_no_special_chars(alphabet(x))
-  
+
   ret <- CPP_find_motifs(x, name, motifs, NA_letter)
   as_tibble(ret)
 }
@@ -95,6 +95,6 @@ find_motifs.data.frame <- function(x, motifs, ...,
   assert_string(.sq, min.chars = 1)
   assert_string(.name, min.chars = 1)
   assert_subset(c(.sq, .name), colnames(x))
-  
+
   find_motifs(x[[.sq]], x[[.name]], motifs, ..., NA_letter = NA_letter)
 }

R/import_sq.R

@@ -1,20 +1,20 @@
 #' Import sq objects from other objects
-#' 
+#'
 #' @description Creates \code{\link[=sq-class]{sq}} object from object of class
 #' from another package. Currently supported packages are \pkg{ape},
 #' \pkg{bioseq}, \pkg{Bioconductor} and \pkg{seqinr}. For exact list of
 #' supported classes and resulting types, see details.
-#' 
+#'
 #' @param object [\code{any(1)}]\cr
 #'  An object of one of supported classes.
 #' @template three-dots
-#' 
+#'
 #' @return A \code{\link[tibble]{tibble}} with \code{sq} column of
 #' \code{\link[=sq-class]{sq}} type representing the same sequences as given
 #' object; the object has a type corresponding to the input type; if given
 #' sequences have names, output \code{\link[tibble]{tibble}} will also have
 #' another column \code{name} with those names
-#' 
+#'
 #' @details
 #' Currently supported classes are as follows:
 #' \itemize{
@@ -59,22 +59,25 @@
 #'
 #' Providing object of class other than specified will result in an error.
 #'
-#' @examples
+#' @examplesIf require("ape", quietly = TRUE)
 #' # ape example
 #' library(ape)
 #' ape_dna <- as.DNAbin(list(one = c("C", "T", "C", "A"), two = c("T", "G", "A", "G", "G")))
 #' import_sq(ape_dna)
 #'
+#' @examplesIf require("bioseq", quietly = TRUE)
 #' # bioseq example
 #' library(bioseq)
 #' bioseq_rna <- new_rna(c(one = "ANBRY", two = "YUTUGGN"))
 #' import_sq(bioseq_rna)
 #'
+#' @examplesIf require("Biostrings", quietly = TRUE)
 #' # Biostrings example
 #' library(Biostrings)
 #' Biostrings_ami <- AAStringSet(c(one = "FEAPQLIWY", two = "EGITENAK"))
 #' import_sq(Biostrings_ami)
 #'
+#' @examplesIf require("seqinr", quietly = TRUE)
 #' # seqinr example
 #' library(seqinr)
 #' seqinr_dna <- as.SeqFastadna(c("C", "T", "C", "A"), name = "one")
@@ -246,6 +249,6 @@ import_sq.list <- function(object, separate = TRUE, ...) {
 bind_into_sqibble <- function(x, name = NULL) {
   if (is.null(name))
     tibble(sq = x)
-  else 
+  else
     tibble(name = name, sq = x)
 }

R/write_fasta.R

@@ -1,7 +1,7 @@
 #' Save sq to fasta file
 #'
 #' @templateVar name_null_ok FALSE
-#' 
+#'
 #' @description Writes \code{\link[=sq-class]{sq}} objects with their names to
 #' a fasta file.
 #'
@@ -17,7 +17,7 @@
 #' @template three-dots
 #'
 #' @return No value is returned.
-#' 
+#'
 #' @details
 #' Whenever a name has more letters than \code{width} parameter, nothing
 #' happens, as only sequences are split to fit within designated space.
@@ -30,7 +30,7 @@
 #'             c("bat", "cat", "rat", "elephant_swallowed_by_A_snake"),
 #'             tempfile())
 #' }
-#' 
+#'
 #' # It can be a part of tidyverse pipeline:
 #' library(dplyr)
 #' fasta_file <- system.file(package = "tidysq", "examples/example_aa.fasta")
@@ -58,7 +58,7 @@ write_fasta.sq <- function(x, name, file,
   assert_string(file)
   assert_count(width, positive = TRUE)
   assert_string(NA_letter, min.chars = 1)
-  
+
   CPP_write_fasta(x, name, file, width, NA_letter)
 }
 
@@ -73,6 +73,6 @@ write_fasta.data.frame <- function(x, file,
   assert_string(.sq, min.chars = 1)
   assert_string(.name, min.chars = 1)
   assert_subset(c(.sq, .name), colnames(x))
-  
+
   write_fasta(x[[.sq]], x[[.name]], file, width = width, NA_letter = NA_letter)
-}
+}

cran-comments.md

@@ -4,3 +4,4 @@
 
 * This is a resubmission.
 * Fixed issues related to new implementations of set operations on R-devel
+* Added skips to tests that require using packages from "Suggests"

tests/testthat/setup-tests.R

@@ -3,7 +3,7 @@ test_sq_only <- function(.func, ..., .data.frame_ok = FALSE) {
   test_message <- if (.data.frame_ok)
     "the first argument must be of sq or data.frame class" else
       "the first argument must be of sq class"
-  
+
   test_that(test_message, {
     expect_s3_class(rlang::catch_cnd(.func(1:7, ...)),
                     "error_no_method")

tests/testthat/test-casting.R

@@ -44,14 +44,6 @@ str_with_na_1 <- c("!A!T!!TC!", "", "AT!C!G!!", "", "!!A!!T!")
 str_with_na_2 <- c("?A?T??TC?", "", "AT?C?G??", "", "??A??T?")
 str_with_na_3 <- c("<?>A<?>T<?><?>TC<?>", "", "AT<?>C<?>G<?><?>", "", "<?><?>A<?><?>T<?>")
 
-# added because of Biostrings warning
-suppressWarnings({
-  biostr_dna_bsc <- Biostrings::DNAStringSet(str_dna_bsc)
-})
-
-seqinr_ami_bsc <- lapply(str_ami_bsc, function(x)
-  seqinr::as.SeqFastaAA(seqinr::s2c(x)))
-
 # CASTING TO SQ ----
 test_that("character vector is casted to sq with as.sq()", {
   expect_identical(as.sq(str_rna_bsc),
@@ -62,11 +54,25 @@ test_that("character vector is casted to sq with as.sq()", {
                    sq(str_atp))
 })
 
-test_that("non-character objects are passed to import_sq()", {
+test_that("Biostrings objects are passed to import_sq()", {
+  skip_if_not_installed("Biostrings")
+  # suppression because of Biostrings warning
+  suppressWarnings({
+    biostr_dna_bsc <- Biostrings::DNAStringSet(str_dna_bsc)
+  })
   expect_identical(as.sq(biostr_dna_bsc),
                    import_sq(biostr_dna_bsc))
+})
+
+test_that("seqinr objects are passed to import_sq()", {
+  skip_if_not_installed("seqinr")
+  seqinr_ami_bsc <- lapply(str_ami_bsc, function(x)
+    seqinr::as.SeqFastaAA(seqinr::s2c(x)))
   expect_identical(as.sq(seqinr_ami_bsc),
                    import_sq(seqinr_ami_bsc))
+})
+
+test_that("Non-importable objects in import_sq() throw an error", {
   expect_error(as.sq(function(x, y) x + y))
 })
 

tests/testthat/test-export_sq.R

@@ -1,3 +1,5 @@
+skip_if_not_installed("Biostrings")
+
 # SETUP ----
 sq_dna <- sq(c("TACTGGGCATG", "CAGGTCGGA", "TAGTAGTCCG", "", "ACGGT"),
              alphabet = "dna_bsc")

tests/testthat/test-find_motifs.R

@@ -164,6 +164,7 @@ test_that("'found' column can handle both special characters and ambiguous lette
 
 # INDEX COLUMNS ----
 test_that("'start' and 'end' columns have values between 1 and length(sequence)", {
+  skip_if_not_installed("purrr")
   sqibble_1 <- find_motifs(sq_dna_bsc, names_5, "TAG")
   sqibble_1[["found_length"]] <- get_sq_lengths(sqibble_1[["found"]])
   purrr::pwalk(sqibble_1, function(names, sought, found, start, end, found_length) {
@@ -206,6 +207,7 @@ test_that("'start' and 'end' columns have values between 1 and length(sequence)"
 })
 
 test_that("index columns can be used to retrieve found subsequence from original sequence", {
+  skip_if_not_installed("purrr")
   purrr::pwalk(find_motifs(sq_dna_bsc, names_5, "TAG"), function(names, sought, found, start, end) {
     expect_identical(
       bite(sq_dna_bsc[which(names == names_5)], start:end)[[1]],

tests/testthat/test-pkg-Biostrings.R

@@ -1,3 +1,5 @@
+skip_if_not_installed("Biostrings")
+
 # SETUP ----
 str_dna <- c("TACTGGGCATG", "CAGGTCGGA", "TAGTAGTCCG", "", "ACGGT")
 str_1_dna <- "TCYYCAHGGCHA"

tests/testthat/test-pkg-ape.R

@@ -1,3 +1,5 @@
+skip_if_not_installed("ape")
+
 # SETUP ----
 str_dna <- c("TACTGGGCATG", "CAGGTCGGA", "TAGTAGTCCG", "", "ACGGT")
 str_ami <- c("REGENERATED", "TECHNICAL", "FEAT")

tests/testthat/test-pkg-bioseq.R

@@ -1,3 +1,5 @@
+skip_if_not_installed("bioseq")
+
 # SETUP ----
 str_dna <- c("TACTGGGCATG", "CAGGTCGGA", "TAGTAGTCCG", "", "ACGGT")
 str_rna <- c("", "KBS-UVW-AWWWG", "YGHHH-", "-CRASH", "MND-KUUBV-MY-")

tests/testthat/test-pkg-seqinr.R

@@ -1,3 +1,5 @@
+skip_if_not_installed("seqinr")
+
 # SETUP ----
 str_dna <- c("TACTGGGCATG", "CAGGTCGGA", "TAGTAGTCCG", "", "ACGGT")
 str_ami <- c("REGENERATED", "TECHNICAL", "FEAT")