Merge pull request #22 from SchlossLab/iss-14

Parse taxonomy file to dataframe

NAMESPACE

@@ -3,5 +3,6 @@
 export("%>%")
 export(.data)
 export(read_dist)
+export(read_tax)
 importFrom(dplyr,"%>%")
 importFrom(rlang,.data)

R/read_tax.R

@@ -0,0 +1,64 @@
+#' Convert taxonomy strings into dataframe of labels based on taxnomic classification
+#'
+#' @param taxonomy_filename filename of taxonomy file
+#'
+#' @return dataframe of taxonomic labels
+#' @export
+#' @author Nick Lesniak, \email{nlesniak@@umich.edu}
+#'
+#' @examples
+#' taxonomy_filepath <- system.file("extdata",
+#'   "test.taxonomy",
+#'   package = "mothuR"
+#' )
+#' taxonomy_tbl <- read_tax(taxonomy_filepath)
+#' head(taxonomy_tbl)
+read_tax <- function(taxonomy_filename) {
+  levels <- c("Kingdom", "Phylum", "Class", "Order", "Family", "Genus")
+  taxonomy_df <- utils::read.table(taxonomy_filename,
+    sep = "\t",
+    header = T,
+    stringsAsFactors = F
+  ) %>%
+    dplyr::mutate(Taxonomy = gsub("_", " ", .data[["Taxonomy"]])) %>%
+    tidyr::separate(.data[["Taxonomy"]], levels, sep = "\\(\\d{2,3}\\);", extra = "drop") %>%
+    dplyr::select(-.data[["Size"]])
+  # in older version of mothur unclassified are listed as unclassified
+  # without information from higher level classification
+  # for those cases, append with lowest identified classification
+  if (any(taxonomy_df$Genus == "unclassified")) {
+    taxonomy_df <- taxonomy_df %>%
+      tidyr::pivot_longer(
+        cols = -.data[["OTU"]],
+        names_to = "Level",
+        values_to = "Classification"
+      ) %>%
+      # order classification level
+      dplyr::mutate(Level = factor(.data[["Level"]], levels)) %>%
+      dplyr::left_join(dplyr::group_by(., .data[["OTU"]]) %>%
+        dplyr::filter(.data[["Classification"]] != "unclassified") %>%
+        # select lowest level classification
+        dplyr::filter(.data[["Level"]] == levels[max(as.numeric(.data[["Level"]]))]) %>%
+        dplyr::select(.data[["OTU"]], Lowest_classified = .data[["Classification"]]),
+      by = "OTU"
+      ) %>%
+      dplyr::mutate(Classification = ifelse(.data[["Classification"]] == "unclassified",
+        # append unclassified with lowest classification
+        paste(.data[["Lowest_classified"]], .data[["Classification"]], sep = " "),
+        .data[["Classification"]]
+      )) %>%
+      dplyr::select(-.data[["Lowest_classified"]]) %>%
+      tidyr::pivot_wider(
+        names_from = "Level",
+        values_from = "Classification"
+      )
+  }
+  # create label options for OTU and lowest taxonomic classification with the OTU
+  taxonomy_df <- taxonomy_df %>%
+    dplyr::mutate(
+      tax_otu_label = paste0(.data[["Genus"]], " (", gsub("tu0*", "TU ", .data[["OTU"]]), ")"),
+      tax_otu_label = gsub(" unclassified", "", .data[["tax_otu_label"]]),
+      otu_label = paste0(gsub("tu0*", "TU ", .data[["OTU"]]))
+    )
+  return(taxonomy_df)
+}

R/utils.R

@@ -0,0 +1,8 @@
+#' dplyr pipe
+#' @importFrom dplyr %>%
+#' @export
+dplyr::`%>%`
+
+## make R CMD CHECK shut up about the dot `.``
+## See: \url{https://github.com/tidyverse/magrittr/issues/29}
+utils::globalVariables(c("."))

docs/pkgdown.css

@@ -244,14 +244,14 @@ nav[data-toggle='toc'] .nav .nav > .active:focus > a {
 
 .ref-index th {font-weight: normal;}
 
-.ref-index td {vertical-align: top;}
+.ref-index td {vertical-align: top; min-width: 100px}
 .ref-index .icon {width: 40px;}
 .ref-index .alias {width: 40%;}
 .ref-index-icons .alias {width: calc(40% - 40px);}
 .ref-index .title {width: 60%;}
 
 .ref-arguments th {text-align: right; padding-right: 10px;}
-.ref-arguments th, .ref-arguments td {vertical-align: top;}
+.ref-arguments th, .ref-arguments td {vertical-align: top; min-width: 100px}
 .ref-arguments .name {width: 20%;}
 .ref-arguments .desc {width: 80%;}
 

docs/pkgdown.yml

@@ -1,7 +1,7 @@
 pandoc: 2.7.3
-pkgdown: 1.5.1
+pkgdown: 1.6.1
 pkgdown_sha: ~
 articles:
   introduction: introduction.html
-last_built: 2020-09-03T20:18Z
+last_built: 2020-10-06T16:27Z