add ps_tax_clean function

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: MicEco
 Title: Various functions for microbial community data
-Version: 0.9.11
+Version: 0.9.12
 Authors@R: person("Jakob", "Russel", email = "[email protected]", role = c("aut", "cre"))
 Description: Collection of functions for microbiome analyses. E.g. fitting neutral models and standardized effect sizes of phylogenetic beta diversities, and much more.
 Depends: R (>= 3.2.5)

NAMESPACE

@@ -13,6 +13,7 @@ export(ps_euler)
 export(ps_pheatmap)
 export(ps_prune)
 export(ps_refactor)
+export(ps_tax_clean)
 export(ps_venn)
 export(rarefy_rrna)
 export(rarefy_rrna.matrix)

R/ps_tax_clean.R

@@ -0,0 +1,39 @@
+#' Clean tax_table such that NAs are replaced with names of the most specific known taxonomy prefixed with the rank.
+#'
+#' Example: An OTU is annotated as Proteobacteria in the Phylum rank, but NAs in the more specific ranks.
+#' All annotations below Phylum for this OTU will be replaced with Phylum_Proteobacteria.
+#' @param data \code{phyloseq} or \code{tax_table} object.
+#' @return Similar to input, but with NAs replaced in the tax_table
+#' @export
+
+ps_tax_clean <- function(data){
+
+    # Extract
+    if(is(data, "phyloseq")){
+        tax <- tax_table(data)
+    } else if(is(data, "taxonomyTable")) {
+        tax <- data
+    } else {
+        stop("Input should be a phyloseq or tax_table object")
+    }
+
+    rankn <- rank_names(data)
+
+    # Replace NAs
+    tax <- t(apply(tax, 1, function(x) 
+        if(sum(is.na(x))>0){
+            c(x[!is.na(x)], 
+              paste(rankn[max(which(!is.na(x)))], rep(x[max(which(!is.na(x)))], sum(is.na(x))), sep="_"))} 
+        else{x}))
+
+    # Return
+    colnames(tax) <- rankn
+
+    if(is(data, "phyloseq")){
+        tax_table(data) <- tax_table(tax)
+        return(data)
+    } else if(is(data, "taxonomyTable")) {
+        return(tax_table(tax))
+    }
+
+}

README.md

@@ -35,6 +35,10 @@ Make pretty heatmap directly from a phyloseq object. Built-in agglomoration, fil
 
 Rarefaction curve (theoretical and fast) from a phyloseq object. Output ready for plotting in ggplot2
 
+#### ps_tax_clean
+
+Clean tax_table such that NAs are replaced with names of the most specific known taxonomy prefixed with the rank.
+
 ## Miscellaneous functions
 #### adonis_OmegaSq