From 0b6ba25a002db710294f36391ffdbe59eeeba270 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bastien=20Mac=C3=A9?= <bastien.mace@agrocampus-ouest.fr>
Date: Fri, 17 Feb 2023 13:35:43 +0000
Subject: [PATCH] correct typo
---
.../dada2_pre-processing.R | 132 +++++++++---------
1 file changed, 66 insertions(+), 66 deletions(-)
diff --git a/I - Pre-processing steps/dada2_pre-processing.R b/I - Pre-processing steps/dada2_pre-processing.R
index 991f065..c7edc36 100644
--- a/I - Pre-processing steps/dada2_pre-processing.R
+++ b/I - Pre-processing steps/dada2_pre-processing.R
@@ -1,66 +1,66 @@
-#STEP 1 : Be prepared
-
-## load the package :
-library("dada2")
-
-## create a path to your ".fastq" files :
-path <- "./edna_intra_pipeline_comparison/samples"
-
-## select the ".fastq" files you want to analyze :
-fns <- sort(list.files(path, pattern = ".fastq", full.names = T))
-
-## the function only extracts files that end with the chosen pattern and
-## they are extracted with their whole path
-
-## then you can only keep the part of your files name you want :
-sample.names <- sapply(strsplit(basename(fns), ".fastq"), '[', 1)
-
-## the function "basename" removes all the path up to the file name
-
-## the function "strsplit" removes the pattern written
-
-########################################################################
-#STEP 2 : Filtering & Trimming
-
-## begin the creation of the new files and folder :
-filts <- file.path(path, "filtered", paste0(sample.names, ".filt.fastq.gz"))
-
-## builds the path to the new folder, which will be located in the path
-## already used and which name will be "filtered"
-
-## the files are named as described before with "sample.names", and
-## the pattern ".filt.fastq.gz" will be added
-
-## from the ".fastq files" of "fns", create the new ".fastq" files of
-## "filts" after filtering and trimming :
-out <- filterAndTrim(fns, filts,
- truncLen = 235,
- maxN = 0,
- maxEE = 1,
- compress = T,
- verbose = T)
-
-## "truncLen" value is chosen considering the marker length and define
-## were the reads will be trimmed (after 235 bp here), and reads which
-## are shortened than this value are filtered
-
-## "maxN" is the number of N tolerated in the sequences after
-## filtering (0 here)
-
-## "maxEE" defines the maximal number of expected errors tolerated in a
-## read (1 here), based on the quality score (EE = sum(10^(-Q/10)))
-
-## "compress = T" means that the files will be gzipped
-
-## "verbose = T" means that information concerning the number of sequences after
-## sequences after filtering will be given
-
-########################################################################
-#STEP 3 : Dereplication
-
-## "derepFastq" function eliminates all the replications of each sequence in the files
-derep <- derepFastq(filts)
-
-## the function annotates each sequence with his abundance
-
-########################################################################
\ No newline at end of file
+#STEP 1 : Be prepared
+
+## load the package :
+library("dada2")
+
+## create a path to your ".fastq" files :
+path <- "./edna_intra_pipeline_comparison/samples"
+
+## select the ".fastq" files you want to analyze :
+fns <- sort(list.files(path, pattern = ".fastq", full.names = T))
+
+## the function only extracts files that end with the chosen pattern and
+## they are extracted with their whole path
+
+## then you can only keep the part of your files name you want :
+sample.names <- sapply(strsplit(basename(fns), ".fastq"), '[', 1)
+
+## the function "basename" removes all the path up to the file name
+
+## the function "strsplit" removes the pattern written
+
+########################################################################
+#STEP 2 : Filtering & Trimming
+
+## begin the creation of the new files and folder :
+filts <- file.path(path, "filtered", paste0(sample.names, ".filt.fastq.gz"))
+
+## builds the path to the new folder, which will be located in the path
+## already used and which name will be "filtered"
+
+## the files are named as described before with "sample.names", and
+## the pattern ".filt.fastq.gz" will be added
+
+## from the ".fastq files" of "fns", create the new ".fastq" files of
+## "filts" after filtering and trimming :
+out <- filterAndTrim(fns, filts,
+ truncLen = 235,
+ maxN = 0,
+ maxEE = 1,
+ compress = T,
+ verbose = T)
+
+## "truncLen" value is chosen considering the marker length and define
+## were the reads will be trimmed (after 235 bp here), and reads which
+## are shorter than this value are filtered
+
+## "maxN" is the number of N tolerated in the sequences after
+## filtering (0 here)
+
+## "maxEE" defines the maximal number of expected errors tolerated in a
+## read (1 here), based on the quality score (EE = sum(10^(-Q/10)))
+
+## "compress = T" means that the files will be gzipped
+
+## "verbose = T" means that information concerning the number of sequences after
+## sequences after filtering will be given
+
+########################################################################
+#STEP 3 : Dereplication
+
+## "derepFastq" function eliminates all the replications of each sequence in the files
+derep <- derepFastq(filts)
+
+## the function annotates each sequence with his abundance
+
+########################################################################
--
GitLab