From 02892b7b3402952f92c73318e54da4af73767d6c Mon Sep 17 00:00:00 2001
From: Simeon <51403284+simeross@users.noreply.github.com>
Date: Wed, 8 Nov 2023 08:46:31 +0100
Subject: [PATCH] more efficient cluster writing by only reading in
seqtab_nochim once
---
R/per_cluster_abundance.R | 9 +++------
R/read_and_write_cluster_abundance.R | 21 +++------------------
man/per_cluster_abundance.Rd | 4 ++--
3 files changed, 8 insertions(+), 26 deletions(-)
diff --git a/R/per_cluster_abundance.R b/R/per_cluster_abundance.R
index 34b8c80..2348497 100644
--- a/R/per_cluster_abundance.R
+++ b/R/per_cluster_abundance.R
@@ -3,22 +3,19 @@
#' Primarily intended for use inside \code{\link{read_and_write_cluster_abundance}}.
#'
#' @param seqs_of_one_cluster DNAStringSet containing sequences of one cluster
-#' @param seqtab_nochim Path to the seqtab_nochim file (in RDS format)
+#' @param seqtab_nochim seqtab object, as imported by readRDS ("path/to/seqtab_nochim.rds")
#' @param reference_seqs Named vector of reference sequences to exclude (Optional) or NULL (default)
#' @return A table with the abundance of sequences within the cluster
#' @import dplyr readr tibble tidyr
#' @export
per_cluster_abundance <- function(seqs_of_one_cluster = DNAStringSet,
- seqtab_nochim = 'seqtab_nochim.rds',
+ seqtab_nochim = stab,
reference_seqs = NULL){
- stab <- readRDS(seqtab_nochim) %>%
- t() %>% as.data.frame() %>%
- rownames_to_column(var = 'seqs')
seq_tbl <- tibble(seqs = as.data.frame(seqs_of_one_cluster)[[1]],
ID = names(seqs_of_one_cluster))
- named_stab <- left_join(seq_tbl, stab, by = 'seqs')
+ named_stab <- left_join(seq_tbl, seqtab_nochim, by = 'seqs')
if(!is.null(reference_seqs)){
named_stab <- named_stab %>%
diff --git a/R/read_and_write_cluster_abundance.R b/R/read_and_write_cluster_abundance.R
index f6e5595..255b5fe 100644
--- a/R/read_and_write_cluster_abundance.R
+++ b/R/read_and_write_cluster_abundance.R
@@ -22,25 +22,10 @@ read_and_write_cluster_abundance <- function(
seqtab_nochim = 'seqtab_nochim.rds',
outpath = path) {
-# stab <- readRDS(seqtab_nochim) %>%
-# t() %>% as.data.frame() %>%
-# rownames_to_column(var = 'seqs')
+ stab <- readRDS(seqtab_nochim) %>%
+ t() %>% as.data.frame() %>%
+ rownames_to_column(var = 'seqs')
-# per_cluster_abundance <- function(seqs_of_one_cluster = DNAStringSet){
-# seq_tbl <- tibble(seqs = as.data.frame(seqs_of_one_cluster)[[1]],
-# ID = names(seqs_of_one_cluster))
-# named_stab <- left_join(seq_tbl, stab, by = 'seqs')
-
-# if(!is.null(reference_seqs)){
-# named_stab <- named_stab %>%
-# filter(!(ID %in% names(reference_seqs)))
-# }
-
-# stab_tbl <- named_stab %>%
-# select(-seqs) %>%
-# pivot_longer(cols = -ID, names_to = 'Sample', values_to = 'count')
-# }
-#
out <- lapply(cluster_sequence_list, per_cluster_abundance,
seqtab_nochim = seqtab_nochim, reference_seqs = reference_seqs)
diff --git a/man/per_cluster_abundance.Rd b/man/per_cluster_abundance.Rd
index bd02656..f61d293 100644
--- a/man/per_cluster_abundance.Rd
+++ b/man/per_cluster_abundance.Rd
@@ -6,14 +6,14 @@
\usage{
per_cluster_abundance(
seqs_of_one_cluster = DNAStringSet,
- seqtab_nochim = "seqtab_nochim.rds",
+ seqtab_nochim = stab,
reference_seqs = NULL
)
}
\arguments{
\item{seqs_of_one_cluster}{DNAStringSet containing sequences of one cluster}
-\item{seqtab_nochim}{Path to the seqtab_nochim file (in RDS format)}
+\item{seqtab_nochim}{seqtab object, as imported by readRDS ("path/to/seqtab_nochim.rds")}
\item{reference_seqs}{Named vector of reference sequences to exclude (Optional) or NULL (default)}
}
--
GitLab