Merge pull request #107 from adrientaudiere/dev

v 0.11

Author: adrientaudiere

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: MiscMetabar
 Type: Package
 Title: Miscellaneous Functions for Metabarcoding Analysis
-Version: 0.10.4
+Version: 0.11.0
 Authors@R: person("Adrien", "Taudière", email = "adrien.taudiere@zaclys.net",
   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>.
@@ -74,6 +74,8 @@ Suggests:
     tibble,
     tidyr,
     treemapify,
+    umap,
+    uwot,
     vegan,
     venneuler,
     vctrs,

MiscMetabar.Rproj

@@ -1,4 +1,5 @@
 Version: 1.0
+ProjectId: 3859fc88-3ad3-46d5-8186-259f982e0e31
 
 RestoreWorkspace: No
 SaveWorkspace: No

NAMESPACE

@@ -19,6 +19,8 @@ export(all_object_size)
 export(ancombc_pq)
 export(are_modality_even_depth)
 export(as_binary_otu_table)
+export(assign_sintax)
+export(assign_vsearch_lca)
 export(asv2otu)
 export(biplot_physeq)
 export(biplot_pq)
@@ -39,6 +41,7 @@ export(dist_bycol)
 export(dist_pos_control)
 export(distri_1_taxa)
 export(fac2col)
+export(filt_taxa_pq)
 export(filter_asv_blast)
 export(filter_taxa_blast)
 export(filter_trim)
@@ -54,6 +57,7 @@ export(ggscatt_pq)
 export(ggvenn_pq)
 export(glmutli_pq)
 export(graph_test_pq)
+export(hill_curves_pq)
 export(hill_phyloseq)
 export(hill_pq)
 export(hill_test_rarperm_pq)
@@ -79,6 +83,7 @@ export(multipatt_pq)
 export(multiplot)
 export(multitax_bar_pq)
 export(mumu_pq)
+export(no_legend)
 export(normalize_prop_pq)
 export(otu_circle)
 export(perc)
@@ -88,6 +93,7 @@ export(physeq_or_string_to_dna)
 export(plot_LCBD_pq)
 export(plot_SCBD_pq)
 export(plot_ancombc_pq)
+export(plot_complexity_pq)
 export(plot_deseq2_phyloseq)
 export(plot_deseq2_pq)
 export(plot_edgeR_phyloseq)
@@ -136,6 +142,7 @@ export(track_wkflow_samples)
 export(transp)
 export(treemap_pq)
 export(tsne_pq)
+export(umap_pq)
 export(unique_or_na)
 export(upset_pq)
 export(upset_test_pq)

NEWS.md

@@ -1,4 +1,14 @@
-# MiscMetabar 0.10.5 (in development)
+# MiscMetabar 0.11 (in development)
+
+- 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. 
+- 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()] 
+
 
 # MiscMetabar 0.10.4
 

R/MiscMetabar-package.R

@@ -26,7 +26,8 @@ if (getRversion() >= "2.15.1") {
     "chim_rm", "condition", "physeq", "seq_tab_Pairs", "nb_samp", "silent",
     "X1_lim1", "X1_lim2", "aicc", "variable", "pos_letters", "alluvium",
     "na_remove", "stratum", "to_lodes_form", "clean_fastq", "clean_sam",
-    "samples_names_common", "seq_id"
+    "samples_names_common", "seq_id", "alpha_hill", "Modality", "Type", "complexity",
+    "value_bootstrap"
   ))
 }
 

R/alpha_div_test.R

@@ -122,7 +122,7 @@ hill_tuckey_pq <- function(
 #' @param sample.size (int) A single integer value equal to the number of
 #'   reads being simulated, also known as the depth. See
 #'   [phyloseq::rarefy_even_depth()].
-#' @param verbose (logical). If TRUE, print additional informations.
+#' @param verbose (logical). If TRUE, print additional information.
 #' @param progress_bar (logical, default TRUE) Do we print progress during
 #'   the calculation?
 #' @param p_val_signif (float, `[0:1]`) The mimimum value of p-value to count a

R/beta_div_test.R

@@ -128,10 +128,10 @@ graph_test_pq <- function(physeq,
 #' @param verbose (logical, default TRUE) If TRUE, prompt some messages.
 #' @param ... Other arguments passed on to [vegan::adonis2()] function.
 #'   Note that the parameter `by` is important. If by is set to NULL
-#'   (default) the p-value is computed for the entire model.  
-#' 	 by = NULL will assess the overall significance of all terms together, 
-#'   by = "terms" will assess significance for each term (sequentially from first to last), 
-#'   setting by = "margin" will assess the marginal effects of the terms (each marginal term analysed in a model with all other variables), 
+#'   (default) the p-value is computed for the entire model.
+#' 	 by = NULL will assess the overall significance of all terms together,
+#'   by = "terms" will assess significance for each term (sequentially from first to last),
+#'   setting by = "margin" will assess the marginal effects of the terms (each marginal term analysed in a model with all other variables),
 #'   by = "onedf" will analyse one-degree-of-freedom contrasts sequentially. The argument is passed on to anova.cca.
 #' @return The function returns an anova.cca result object with a
 #'   new column for partial R^2. See help of [vegan::adonis2()] for
@@ -143,7 +143,7 @@ graph_test_pq <- function(physeq,
 #' adonis_pq(enterotype, "SeqTech*Enterotype", na_remove = TRUE, by = "terms")
 #' adonis_pq(enterotype, "SeqTech*Enterotype", na_remove = TRUE, by = "onedf")
 #' adonis_pq(enterotype, "SeqTech*Enterotype", na_remove = TRUE, by = "margin")
-#' 
+#'
 #' adonis_pq(enterotype, "SeqTech", dist_method = "jaccard", by = "terms")
 #' adonis_pq(enterotype, "SeqTech", dist_method = "robust.aitchison", by = "terms")
 #' }
@@ -1048,20 +1048,19 @@ plot_ancombc_pq <-
 #'
 #' @author Adrien Taudière
 #' @examples
-#'  data_fungi_mini_woNA4height <- subset_samples(
-#'     data_fungi_mini,
-#'     !is.na(data_fungi_mini@sam_data$Height)
-#'   )
-#'   taxa_only_in_one_level(data_fungi_mini_woNA4height, "Height", "High")
-#'   #' # Taxa present only in low height samples
-#'   suppressMessages(suppressWarnings(
-#'     taxa_only_in_one_level(data_fungi, "Height", "Low")
-#'   ))
-#'   # Number of taxa present only in sample of time equal to 15
-#'   suppressMessages(suppressWarnings(
-#'     length(taxa_only_in_one_level(data_fungi, "Time", "15"))
-#'   ))
-
+#' data_fungi_mini_woNA4height <- subset_samples(
+#'   data_fungi_mini,
+#'   !is.na(data_fungi_mini@sam_data$Height)
+#' )
+#' taxa_only_in_one_level(data_fungi_mini_woNA4height, "Height", "High")
+#' #' # Taxa present only in low height samples
+#' suppressMessages(suppressWarnings(
+#'   taxa_only_in_one_level(data_fungi, "Height", "Low")
+#' ))
+#' # Number of taxa present only in sample of time equal to 15
+#' suppressMessages(suppressWarnings(
+#'   length(taxa_only_in_one_level(data_fungi, "Time", "15"))
+#' ))
 taxa_only_in_one_level <- function(physeq,
                                    modality,
                                    level,
@@ -1309,7 +1308,7 @@ var_par_pq <-
 #' @param sample.size (int) A single integer value equal to the number of
 #'   reads being simulated, also known as the depth. See
 #'   [phyloseq::rarefy_even_depth()].
-#' @param verbose (logical). If TRUE, print additional informations.
+#' @param verbose (logical). If TRUE, print additional information.
 #' @param progress_bar (logical, default TRUE) Do we print progress during
 #'   the calculation?
 #'

R/controls.R

@@ -7,7 +7,8 @@
 #' <img src="https://img.shields.io/badge/lifecycle-experimental-orange" alt="lifecycle-experimental"></a>
 #'
 #' Search for exact matching of sequences using complement,
-#' reverse and reverse-complement
+#' reverse and reverse-complement. It is useful to check for
+#' primers issues after cutadapt step.
 #'
 #' @inheritParams clean_pq
 #' @param seq2search A DNAStringSet object of sequences to search for.