From ce91d689f086fea6f0eb03e1062d34f11774c5d3 Mon Sep 17 00:00:00 2001
From: brendanf <brendan.furneaux@gmail.com>
Date: Sun, 27 Oct 2019 14:20:47 +0100
Subject: [PATCH] bug fix for chimeras again.

---
 DESCRIPTION                     |  2 +-
 R/tzara.R                       | 12 ++++++++++--
 man/find_all_region_chimeras.Rd |  5 ++++-
 man/find_region_chimeras.Rd     |  6 +++++-
 4 files changed, 20 insertions(+), 5 deletions(-)

diff --git a/DESCRIPTION b/DESCRIPTION
index 5b9cccb..092b02f 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -1,7 +1,7 @@
 Package: tzara
 Type: Package
 Title: Cluster long amplicons using dada2 denoising on variable regions
-Version: 0.0.7.2
+Version: 0.0.7.3
 Authors@R: person(given = "Brendan", family = "Furneaux",
                   email = "brendan.furneaux@gmail.com",
                   role = c("aut", "cre"))
diff --git a/R/tzara.R b/R/tzara.R
index 366b6e6..832f514 100644
--- a/R/tzara.R
+++ b/R/tzara.R
@@ -906,6 +906,7 @@ reconstruct <- function(
       region_table = region_table,
       order = order,
       sample_column = sample_column,
+      read_column = read_column,
       chimera_offset = chimera_offset)
 
    if (!is.null(raw_column)) {
@@ -1090,6 +1091,8 @@ assemble_region_table <- function(
 #'        which identifies different samples; if present, use
 #'        \code{\link[dada2]{isBimeraDenovoTable}} instead of
 #'        \code{\link[dada2]{isBimeraDenovo}}.
+#' @param read_column (\code{character} scalar) column in region_table
+#'        which identifies different reads.
 #' @param chimera_offset (\code{integer} scalar) use \code{1} if the first
 #'        region is conserved.
 #' @param ... passed to \code{find_region_chimeras}.
@@ -1105,6 +1108,7 @@ find_all_region_chimeras <- function(
    region_table,
    order,
    sample_column = NULL,
+   read_column = "read_id",
    chimera_offset = 0,
    ...
 ) {
@@ -1117,6 +1121,7 @@ find_all_region_chimeras <- function(
          find_region_chimeras,
          region_table = region_table,
          sample_column = sample_column,
+         read_column = read_column,
          ...
       )
    )
@@ -1134,12 +1139,15 @@ find_all_region_chimeras <- function(
 #'        which identifies different samples; if present, use
 #'        \code{\link[dada2]{isBimeraDenovoTable}} instead of
 #'        \code{\link[dada2]{isBimeraDenovo}}.
+#' @param read_column (\code{character} scalar) column in region_table
+#'        which identifies different reads.
 #' @param ... passed on to \code{\link[dada2]{isBimeraDenovoTable}} or
 #'        \code{\link[dada2]{isBimeraDenovo}}.
 #'
 #' @return an \code{character} vector giving the read IDs of
 #'        \code{region_table} which were detected as bimeras.
-find_region_chimeras <- function(region_table, chimset, sample_column, ...) {
+find_region_chimeras <- function(region_table, chimset, sample_column,
+                                 read_column, ...) {
    seqs <- do.call(str_c, region_table[, chimset])
    chimset_name <- paste(chimset, collapse = "--")
    flog.trace("Searching for bimeras in regions %s.", chimset_name)
@@ -1167,7 +1175,7 @@ find_region_chimeras <- function(region_table, chimset, sample_column, ...) {
               sum(seqs %in% names(chims)[chims], na.rm = TRUE),
               sum(!is.na(seqs)),
               chimset_name)
-   names(chims)[chims]
+   region_table[[read_column]][seqs %in% names(chims)[chims]]
 }
 
 block_consensus <- function(.x, .y, reg, reg2, reg2_raw, read_column, ...) {
diff --git a/man/find_all_region_chimeras.Rd b/man/find_all_region_chimeras.Rd
index a89230d..8e30d2c 100644
--- a/man/find_all_region_chimeras.Rd
+++ b/man/find_all_region_chimeras.Rd
@@ -5,7 +5,7 @@
 \title{Find chimeras in adjacent variable-conserved-variable domain triplets}
 \usage{
 find_all_region_chimeras(region_table, order, sample_column = NULL,
-  chimera_offset = 0, ...)
+  read_column = "read_id", chimera_offset = 0, ...)
 }
 \arguments{
 \item{region_table}{(\code{data.frame} containing all the regions in
@@ -18,6 +18,9 @@ which identifies different samples; if present, use
 \code{\link[dada2]{isBimeraDenovoTable}} instead of
 \code{\link[dada2]{isBimeraDenovo}}.}
 
+\item{read_column}{(\code{character} scalar) column in region_table
+which identifies different reads.}
+
 \item{chimera_offset}{(\code{integer} scalar) use \code{1} if the first
 region is conserved.}
 
diff --git a/man/find_region_chimeras.Rd b/man/find_region_chimeras.Rd
index 9137897..db046ad 100644
--- a/man/find_region_chimeras.Rd
+++ b/man/find_region_chimeras.Rd
@@ -4,7 +4,8 @@
 \alias{find_region_chimeras}
 \title{Check for bimeras in a subset of regions}
 \usage{
-find_region_chimeras(region_table, chimset, sample_column, ...)
+find_region_chimeras(region_table, chimset, sample_column, read_column,
+  ...)
 }
 \arguments{
 \item{region_table}{(\code{data.frame} containing all the regions in
@@ -18,6 +19,9 @@ which identifies different samples; if present, use
 \code{\link[dada2]{isBimeraDenovoTable}} instead of
 \code{\link[dada2]{isBimeraDenovo}}.}
 
+\item{read_column}{(\code{character} scalar) column in region_table
+which identifies different reads.}
+
 \item{...}{passed on to \code{\link[dada2]{isBimeraDenovoTable}} or
 \code{\link[dada2]{isBimeraDenovo}}.}
 }