Merge pull request #80 from adrientaudiere/dev

Improve test and examples for CRAN submission

DESCRIPTION

@@ -1,10 +1,10 @@
 Package: MiscMetabar
 Type: Package
 Title: Miscellaneous Functions for Metabarcoding Analysis
-Version: 0.7.3
+Version: 0.7.4
 Authors@R: person("Adrien", "Taudière", email = "[email protected]",
   role = c("aut", "cre", "cph"), comment = c(ORCID = "0000-0003-1088-1182"))
-Description: The MiscMetabar package aims to facilitate the description, transformation, exploration, and reproducibility of metabarcoding analysis. Mainly build on the top of phyloseq, dada2 R packages. MiscMetabar help to build reproducible and robust bioinformatic pipeline in R. MiscMetabar make ecological analysis of alpha and beta-diversity simple and powerfull by integrating a large number of analysis, some of them from other R packages.  
+Description: The MiscMetabar package aims to facilitate the description, transformation, exploration, and reproducibility of metabarcoding analysis. Mainly build on the top of phyloseq, dada2 R packages. MiscMetabar help to build reproducible and robust bioinformatic pipeline in R. MiscMetabar make ecological analysis of alpha and beta-diversity simple and powerful by integrating a large number of analysis, some of them from other R packages.  
 License: AGPL-3
 Encoding: UTF-8
 LazyData: true

NEWS.md

@@ -6,6 +6,10 @@
 - Add functions `swarm_clustering()` and `vsearch_clustering()` and add `swarm` method in the function `asv2otu()`
 - Add function `physeq_or_string_to_dna()` mostly for internal use
 - Add function `cutadapt_remove_primers()` to remove primers using [cutadapt](https://github.com/marcelm/cutadapt/)
+- Add internal functions `is_swarm_installed()`, `is_cutadapt_installed()`, `is_vsearch_installed()` and `is_falco_installed()` to test for the availability of external software in order to run examples and test from testthat.
+
+- Submit to CRAN and change code to comply with their rules (patch 0.7.1 to 0.7.4)
+
 
 ## BREAKING CHANGES
 

R/Deseq2_edgeR.R

@@ -21,12 +21,15 @@
 #' @export
 #' @examples
 #' data("GlobalPatterns", package = "phyloseq")
-#' plot_edgeR_pq(GlobalPatterns, c("SampleType", "Soil", "Feces"),
+#' GP_archae <- subset_taxa(GlobalPatterns, GlobalPatterns@tax_table[, 1] == "Archaea")
+#' plot_edgeR_pq(GP_archae, c("SampleType", "Soil", "Feces"),
 #'   color_tax = "Kingdom"
 #' )
-#' plot_edgeR_pq(GlobalPatterns, c("SampleType", "Soil", "Feces"),
+#' \dontrun{
+#' plot_edgeR_pq(GP_archae, c("SampleType", "Soil", "Feces"),
 #'   taxolev = "Class", color_tax = "Kingdom"
 #' )
+#' }
 #' @author Adrien Taudière
 #'
 #' @return A \code{\link{ggplot}}2 plot representing edgeR results

R/beta_div_test.R

@@ -230,12 +230,11 @@ adonis_pq <- function(physeq,
 #' @export
 #' @seealso [plot_LCBD_pq], [adespatial::beta.div()]
 #' @examples
-#' data(data_fungi_sp_known)
-#' res <- LCBD_pq(data_fungi_sp_known, nperm = 50)
+#' res <- LCBD_pq(data_fungi_sp_known, nperm = 5)
 #' str(res)
 #' length(res$LCBD)
 #' length(res$SCBD)
-#' LCBD_pq(data_fungi_sp_known, nperm = 50, method = "jaccard")
+#' LCBD_pq(data_fungi_sp_known, nperm = 5, method = "jaccard")
 #'
 #' @author Adrien Taudière
 #' This function is mainly a wrapper of the work of others.
@@ -288,20 +287,20 @@ LCBD_pq <- function(physeq,
 #'
 #' @examples
 #' data(data_fungi)
-#' plot_LCBD_pq(data_fungi,
+#' plot_LCBD_pq(data_fungi_mini,
 #'   nperm = 100, only_plot_significant = FALSE,
 #'   pval = 0.2
 #' )
-#' plot_LCBD_pq(data_fungi,
+#' plot_LCBD_pq(data_fungi_mini,
 #'   nperm = 100, only_plot_significant = TRUE,
 #'   pval = 0.2
 #' )
 #' library("patchwork")
-#' plot_LCBD_pq(data_fungi,
+#' plot_LCBD_pq(data_fungi_mini,
 #'   nperm = 100, only_plot_significant = FALSE,
 #'   sam_variables = c("Time", "Height")
 #' )
-#' plot_LCBD_pq(data_fungi,
+#' plot_LCBD_pq(data_fungi_mini,
 #'   nperm = 100, only_plot_significant = TRUE, pval = 0.2,
 #'   sam_variables = c("Time", "Height", "Tree_name")
 #' ) &
@@ -563,12 +562,8 @@ multipatt_pq <- function(physeq,
 #' @export
 #'
 #' @examples
-#' data(data_fungi_sp_known)
 #' res_height <- ancombc_pq(
-#'   subset_taxa_pq(
-#'     data_fungi_sp_known,
-#'     taxa_sums(data_fungi_sp_known) > 5000
-#'   ),
+#'   data_fungi_mini,
 #'   fact = "Height",
 #'   levels_fact = c("Low", "High"),
 #'   verbose = TRUE
@@ -590,10 +585,7 @@ multipatt_pq <- function(physeq,
 #'   geom_point()
 #'
 #' res_time <- ancombc_pq(
-#'   subset_taxa_pq(
-#'     data_fungi_sp_known,
-#'     taxa_sums(data_fungi_sp_known) > 5000
-#'   ),
+#'   data_fungi_mini,
 #'   fact = "Time",
 #'   levels_fact = c("0", "15"),
 #'   tax_level = "Family",

R/dada_phyloseq.R

@@ -481,7 +481,7 @@ track_wkflow_samples <- function(list_pq_obj, ...) {
 #' @param method (default: clusterize)
 #'   Set the clustering method.
 #'   - `clusterize` use the [DECIPHER::Clusterize()] fonction,
-#'   - `vsearch` use the vsearch software (https://github.com/torognes/vsearch/)
+#'   - `vsearch` use the vsearch software (https://github.com/torognes/vsearch)
 #'     with arguments `--cluster_size` by default (see args `vsearch_cluster_method`)
 #'     and `-strand both` (see args `vsearch_args`)
 #'   - `swarm` use the swarm
@@ -493,7 +493,7 @@ track_wkflow_samples <- function(list_pq_obj, ...) {
 #'   set tax_adjust to 0 (default). For the moment only tax_adjust = 0 is
 #'   robust
 #' @param vsearch_cluster_method (default: "--cluster_size) See other possible
-#'   methods in the [vsearch pdf manual](https://github.com/torognes/vsearch/releases/download/v2.23.0/vsearch_manual.pdf) (e.g. `--cluster_size` or `--cluster_smallmem`)
+#'   methods in the [vsearch manual](https://github.com/torognes/vsearch/) (e.g. `--cluster_size` or `--cluster_smallmem`)
 #'   - `--cluster_fast` : Clusterize the fasta sequences in filename, automatically sort by decreasing sequence length beforehand.
 #'   - `--cluster_size` : Clusterize the fasta sequences in filename, automatically sort by decreasing sequence abundance beforehand.
 #'   - `--cluster_smallmem` : Clusterize the fasta sequences in filename without automatically modifying their order beforehand. Sequence are expected to be sorted by decreasing sequence length, unless *--usersort* is used.
@@ -520,6 +520,15 @@ track_wkflow_samples <- function(list_pq_obj, ...) {
 #' @return A new object of class `physeq` or a list of cluster if dna_seq
 #'   args was used.
 #'
+#' @examples
+#' asv2otu(data_fungi_mini)
+#' asv2otu(data_fungi_mini, method_clusterize = "longest")
+#' if (MiscMetabar:::is_swarm_installed()) {
+#'   d_swarm <- asv2otu(data_fungi_mini, method = "swarm")
+#' }
+#' if (MiscMetabar:::is_vsearch_installed()) {
+#'   d_vs <- asv2otu(data_fungi_mini, method = "vsearch")
+#' }
 #' @references
 #'   VSEARCH can be downloaded from
 #'   \url{https://github.com/torognes/vsearch}.
@@ -1917,8 +1926,8 @@ plot_guild_pq <-
 #' @examples
 #' library("phangorn")
 #'
-#' df <- subset_taxa_pq(data_fungi, taxa_sums(data_fungi) > 9000)
-#' df_tree <- build_phytree_pq(df, nb_bootstrap = 5)
+#' df <- subset_taxa_pq(data_fungi_mini, taxa_sums(data_fungi_mini) > 9000)
+#' df_tree <- build_phytree_pq(df, nb_bootstrap = 2)
 #' plot(df_tree$UPGMA)
 #' plotBS(df_tree$UPGMA, df_tree$UPGMA_bs, main = "UPGMA")
 #' plot(df_tree$NJ, "unrooted")

R/data.R

@@ -32,6 +32,39 @@
 #' @usage data(data_fungi_sp_known)
 "data_fungi_sp_known"
 
+
+#' Fungal OTU in phyloseq format
+#'
+#' It is a subset of the data_fungi dataset including only Basidiomycota
+#'   with more than 5000 sequences.
+#'
+#' Obtain using `data_fungi_mini <- subset_taxa(data_fungi, Phylum == "Basidiomycota")`
+#' and then `data_fungi_mini <-   subset_taxa_pq(data_fungi_mini, colSums(data_fungi_mini@otu_table) > 5000)`
+#'
+#'
+#' @format A physeq object containing 45 taxa with references sequences
+#' described by 14 taxonomic ranks and 137 samples described by 7 sample variables:
+#' - *X*: the name of the fastq-file
+#' - *Sample_names*: the names of ... the samples
+#' - *Treename*: the name of an tree
+#' - *Sample_id*: identifier for each sample
+#' - *Height*: height of the sample in the tree
+#' - *Diameter*: diameter of the trunk
+#' - *Time*: time since the dead of the tree
+#' @usage data(data_fungi_mini)
+#' @format A physeq object containing 45 taxa with references sequences
+#' described by 14 taxonomic ranks and 137 samples described by 7 sample variables:
+#' - *X*: the name of the fastq-file
+#' - *Sample_names*: the names of ... the samples
+#' - *Treename*: the name of an tree
+#' - *Sample_id*: identifier for each sample
+#' - *Height*: height of the sample in the tree
+#' - *Diameter*: diameter of the trunk
+#' - *Time*: time since the dead of the tree
+#' @usage data(data_fungi_mini)
+"data_fungi_mini"
+
+
 #' This tutorial explore the dataset from Tengeler et al. (2020) available in the `mia` package.
 #' obtain using `mia::makePhyloseqFromTreeSE(Tengeler2020)`
 #'

R/miscellanous.R

@@ -359,3 +359,100 @@ install_pkg_needed <- function(pkg, use_pak = TRUE, bioconductor_pkg = FALSE,
     }
   }
 }
+
+################################################################################
+#' Test if cutadapt is installed.
+#'
+#' @description
+#'  `r lifecycle::badge("maturing")`
+#'
+#' Useful for testthat and examples compilation for R CMD CHECK and
+#'   test coverage
+#'
+#' @param args_before_cutadapt : (String) A one line bash command to run before
+#' to run cutadapt. For examples, "source ~/miniconda3/etc/profile.d/conda.sh && conda activate cutadaptenv &&" allow to bypass the conda init which asks to restart the shell
+#' @keywords internal
+#' @noRd
+#' @return A logical that say if cutadapt is install in
+#'
+#' @examples
+#' MiscMetabar:::is_cutadapt_installed()
+#' @author Adrien Taudière
+
+is_cutadapt_installed <- function(args_before_cutadapt = "source ~/miniconda3/etc/profile.d/conda.sh && conda activate cutadaptenv && ") {
+  writeLines(paste0(args_before_cutadapt, " cutadapt -h"), paste0(tempdir(), "/script_cutadapt.sh"))
+  cutadapt_error_or_not <- try(system(paste0("bash ", tempdir(), "/script_cutadapt.sh 2>&1"), intern = TRUE), silent = T)
+  unlink(paste0(tempdir(), "/script_cutadapt.sh"))
+
+  return(class(cutadapt_error_or_not) != "try-error")
+}
+
+#' Test if falco is installed.
+#'
+#' @description
+#'  `r lifecycle::badge("maturing")`
+#'
+#' Useful for testthat and examples compilation for R CMD CHECK and
+#'   test coverage
+#'
+#' @param path (default: falco) Path to falco
+#' @keywords internal
+#' @noRd
+#' @return A logical that say if falco is install in
+#'
+#' @examples
+#' MiscMetabar:::is_falco_installed()
+#' @author Adrien Taudière
+
+is_falco_installed <- function(path = "falco") {
+  return(class(try(system(paste0(path, " 2>&1"), intern = TRUE),
+    silent = TRUE
+  )) != "try-error")
+}
+
+#' Test if swarm is installed.
+#'
+#' @description
+#'  `r lifecycle::badge("maturing")`
+#'
+#' Useful for testthat and examples compilation for R CMD CHECK and
+#'   test coverage
+#'
+#' @param path (default: swarm) Path to falco
+#' @keywords internal
+#' @noRd
+#' @return A logical that say if swarm is install in
+#'
+#' @examples
+#' MiscMetabar:::is_swarm_installed()
+#' @author Adrien Taudière
+
+is_swarm_installed <- function(path = "swarm") {
+  return(class(try(system(paste0(path, " -h 2>&1"), intern = TRUE),
+    silent = TRUE
+  )) != "try-error")
+}
+
+#' Test if vsearch is installed.
+#'
+#' @description
+#'  `r lifecycle::badge("maturing")`
+#'
+#' Useful for testthat and examples compilation for R CMD CHECK and
+#'   test coverage
+#'
+#' @param path (default: vsearch) Path to vsearch
+#' @keywords internal
+#' @noRd
+#' @return A logical that say if vsearch is install in
+#'
+#' @examples
+#' MiscMetabar:::is_vsearch_installed()
+#' @author Adrien Taudière
+
+is_vsearch_installed <- function(path = "vsearch") {
+  return(class(try(system(paste0(path, " 2>&1"), intern = TRUE),
+    silent = TRUE
+  )) != "try-error")
+}
+################################################################################