Merge pull request #108 from adrientaudiere/dev

v 0.12

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: MiscMetabar
 Type: Package
 Title: Miscellaneous Functions for Metabarcoding Analysis
-Version: 0.11.0
+Version: 0.12.0
 Authors@R: person("Adrien", "Taudière", email = "[email protected]",
   role = c("aut", "cre", "cph"), comment = c(ORCID = "0000-0003-1088-1182"))
 Description: Facilitate the description, transformation, exploration, and reproducibility of metabarcoding analyses. 'MiscMetabar' is mainly built on top of the 'phyloseq', 'dada2' and 'targets' R packages. It helps to build reproducible and robust bioinformatics pipelines in R. 'MiscMetabar' makes ecological analysis of alpha and beta-diversity easier, more reproducible and more powerful by integrating a large number of tools. Important features are described in Taudière A. (2023) <doi:10.21105/joss.06038>.
@@ -55,10 +55,11 @@ Suggests:
     networkD3,
     pak,
     patchwork,
+    pbapply,
     permute,
     phangorn,
     phyloseqGraphTest,
-    pbapply,
+    pkgnet,
     plotly,
     plyr,
     reshape2,

NAMESPACE

@@ -19,6 +19,7 @@ export(all_object_size)
 export(ancombc_pq)
 export(are_modality_even_depth)
 export(as_binary_otu_table)
+export(assign_idtaxa)
 export(assign_sintax)
 export(assign_vsearch_lca)
 export(asv2otu)
@@ -71,6 +72,7 @@ export(is_mumu_installed)
 export(is_swarm_installed)
 export(is_vsearch_installed)
 export(krona)
+export(learn_idtaxa)
 export(list_fastq_files)
 export(lulu)
 export(lulu_phyloseq)
@@ -137,6 +139,7 @@ export(taxa_as_columns)
 export(taxa_as_rows)
 export(taxa_only_in_one_level)
 export(tbl_sum_samdata)
+export(tbl_sum_taxtable)
 export(track_wkflow)
 export(track_wkflow_samples)
 export(transp)

NEWS.md

@@ -1,11 +1,26 @@
-# MiscMetabar 0.11 (in development)
+# MiscMetabar 0.2.0 (in development) 
+
+- Add function [assign_idtaxa()] and [learn_idtaxa()] to facilitate the taxonomic assignation using the idtaxa algorithm from the  DECIPHER R package.
+- Add option `idtaxa` to method in [add_new_taxonomy_pq()]
+- Add function [tbl_sum_taxtable()] to summarize tax_table from a phyloseq object 
+- In function [assign_sintax()], add params `too_few` (default value "align_start") and `too_many` (default "merge") to authorize db with variable numbers of rank and parenthesis in taxonomic name, 
+
+
+# MiscMetabar 0.11.1 (in development) 
+
+- Add param `suffix` to `add_blast_info()` allowing multiple use of the function on the same phyloseq object (e.g. in order to used different database)
+- Add param `return_DNAStringSet` to `write_temp_fasta()` function to return a DNAStringSet object in place of a temporary file. 
+- Add a vignette pkgnet-report.
+- Add the possibility to send fasta.gz file to `count_seq()`
+
+# MiscMetabar 0.11 
 
 - Add function `filt_taxa_pq()` to filter taxa based on the number of sequences/occurences
 - Add functions `no_legend()` and `hill_curves_pq()` to plot hill diversity accumulation curves for phyloseq
 - Add function `umap_pq()` to compute Dimensionality Reduction with UMAP
 - Add function `plot_complexity_pq()` to plot kmer complexity of references sequences of a phyloseq object
 - Add param `type` to `ridge_pq()` to plot a cumulative version (type="ecdf") version of ridge
-- Introduce the idea of a pq-verse: some other packages will complete the MiscMetabar packages to make package maintenance easier. The [comparpq](https://github.com/adrientaudiere/comparpq) package will facilitate the comparison of phyloseq object with different taxonomy, different clustering method, different samples with same modality or different primers. 
+- Introduce the idea of a pq-verse: some other packages will complete the MiscMetabar packages to make package maintenance easier. The [comparpq](https://github.com/adrientaudiere/comparpq) package will facilitate the comparison of phyloseq object with different taxonomy, different clustering methods, different samples with same modality or different primers. 
 - Add functions [assign_vsearch_lca()], [assign_sintax()] and internal function [write_temp_fasta()]
 - Add param `method` to `add_new_taxonomy_pq()` to allow the use of [dada2::assign_taxonomy()] (default, precedent only method available), [assign_sintax()] or [assign_vsearch_lca()] 
 

R/MiscMetabar-package.R

@@ -27,7 +27,8 @@ if (getRversion() >= "2.15.1") {
     "X1_lim1", "X1_lim2", "aicc", "variable", "pos_letters", "alluvium",
     "na_remove", "stratum", "to_lodes_form", "clean_fastq", "clean_sam",
     "samples_names_common", "seq_id", "alpha_hill", "Modality", "Type", "complexity",
-    "value_bootstrap"
+    "value_bootstrap", "LearnTaxa", "OrientNucleotides", "RemoveGaps",
+    "method", "readDNAStringSet"
   ))
 }
 

R/blast.R

@@ -630,6 +630,8 @@ blast_to_derep <- function(derep,
 #' @inheritParams clean_pq
 #' @param fasta_for_db path to a fasta file to make the blast database
 #' @param silent (logical) If true, no message are printing.
+#' @param suffix (character) The suffix to name the new columns.
+#'   Set the suffix to "" in order to remove any suffix.
 #' @param ... Other arguments passed on to [blast_pq()] function.
 #' @return A new \code{\link[phyloseq]{phyloseq-class}} object with more information in tax_table based on a
 #'   blast on a given database
@@ -638,21 +640,27 @@ blast_to_derep <- function(derep,
 #'
 #' @author Adrien Taudière
 
-add_blast_info <- function(physeq, fasta_for_db, silent = FALSE, ...) {
+add_blast_info <- function(physeq, fasta_for_db, silent = FALSE, suffix = "blast_info", ...) {
   verify_pq(physeq)
   res_blast <- blast_pq(physeq,
     fasta_for_db = fasta_for_db,
-    unique_per_seq = TRUE, score_filter = FALSE, ...
+    unique_per_seq = TRUE,
+    score_filter = FALSE,
+    ...
   )
   new_physeq <- physeq
 
-  new_physeq@tax_table <- tax_table(cbind(
+  new_taxtab <- cbind(
     new_physeq@tax_table,
     as.matrix(res_blast[match(
       taxa_names(new_physeq),
       res_blast$`Query name`
     ), ])
-  ))
+  )
+
+  # colnames(new_taxtab) <- c(colnames(new_physeq@tax_table), paste0(colnames(physeq), suffix))
+
+  new_physeq@tax_table <- tax_table(new_taxtab)
 
   verify_pq(new_physeq)
   if (!silent) {