dadaist2 0.1.05

Author: telatin

bin/dadaist2

@@ -17,7 +17,7 @@ use Digest::MD5 qw(md5_hex);
 use File::Temp;
 
 my $PROGRAM          = basename($0);
-my $VERSION          = '0.1.04';
+my $VERSION          = '0.1.07';
 my $opt_verbose      = 0;
 my $opt_debug        = 0;
 my $opt_id_separator = '_';
@@ -208,6 +208,9 @@ my @dada_paired_args = (
 #                 Special values: 0 - Use all input reads.
 #    Ex: 1000000
      $dada2_min_reads,
+
+# 18) base dir,
+	${temp_dir}
 );
 
 
@@ -224,7 +227,7 @@ if ( $dada2_execution->{'exit'} != 0 ) {
 copy(File::Spec->catfile($dada2_temp, 'stats.tsv'), 
 	 File::Spec->catfile($opt_output_directory, 'dada2_stats.tsv')) || die " ERROR:\n Unable to copy stats.tsv file from $dada2_temp to $opt_output_directory.\n";
 
-my $dada2_tsv  = File::Spec->catfile($dada2_temp, 'dada2.tsv');
+my $dada2_tsv   = File::Spec->catfile($dada2_temp, 'dada2.tsv');
 my $dada2_file  = File::Spec->catfile($opt_output_directory, 'feature-table.tsv');
 my $repseq_file = File::Spec->catfile($opt_output_directory, 'rep-seqs.fasta');
 

bin/run_dada_paired.R

@@ -107,24 +107,24 @@ getN <- function(x) sum(getUniques(x))
 args <- commandArgs(TRUE)
 
 # Assign each of the arguments, in positional order, to an appropriately named R variable
-inp.dirF <- args[[1]]
-inp.dirR <- args[[2]]
-out.path <- args[[3]]
+inp.dirF  <- args[[1]]
+inp.dirR  <- args[[2]]
+out.path  <- args[[3]]
 out.track <- args[[4]]
 filtered.dirF <- args[[5]]
 filtered.dirR <- args[[6]]
 truncLenF <- as.integer(args[[7]])
 truncLenR <- as.integer(args[[8]])
 trimLeftF <- as.integer(args[[9]])
 trimLeftR <- as.integer(args[[10]])
-maxEEF <- as.numeric(args[[11]])
-maxEER <- as.numeric(args[[12]])
-truncQ <- as.integer(args[[13]])
+maxEEF    <- as.numeric(args[[11]])
+maxEER    <- as.numeric(args[[12]])
+truncQ    <- as.integer(args[[13]])
 chimeraMethod <- args[[14]]
 minParentFold <- as.numeric(args[[15]])
-nthreads <- as.integer(args[[16]])
-nreads.learn <- as.integer(args[[17]])
-
+nthreads      <- as.integer(args[[16]])
+nreads.learn  <- as.integer(args[[17]])
+outbasepath   <- args[[18]]
 ### VALIDATE ARGUMENTS ###
 
 # Input directory is expected to contain .fastq.gz file(s)
@@ -178,6 +178,15 @@ cat("DADA2:", as.character(packageVersion("dada2")), "/",
 cat("1) Filtering ")
 filtsF <- file.path(filtered.dirF, basename(unfiltsF))
 filtsR <- file.path(filtered.dirR, basename(unfiltsR))
+
+for (p in c(filtsF,filtsR)) {
+  png(cat(outbasepath,"/",basename(p),".png"));
+  plotQualityProfile(p)
+  dev.off()
+}
+
+
+
 out <- suppressWarnings(filterAndTrim(unfiltsF, filtsF, unfiltsR, filtsR,
                                       truncLen=c(truncLenF, truncLenR), trimLeft=c(trimLeftF, trimLeftR),
                                       maxEE=c(maxEEF, maxEER), truncQ=truncQ, rm.phix=TRUE,
@@ -242,6 +251,6 @@ col.names <- basename(filtsF)
 col.names[[1]] <- paste0("#OTU ID\t", col.names[[1]])
 write.table(seqtab.nochim, out.path, sep="\t",
             row.names=TRUE, col.names=col.names, quote=FALSE)
-saveRDS(seqtab.nochim, gsub("tsv", "rds", out.path)) ### TESTING
+#saveRDS(seqtab.nochim, gsub("tsv", "rds", out.path)) ### TESTING
 
 q(status=0)

meta.yaml

@@ -0,0 +1,43 @@
+{% set name = "dadaist2" %}
+{% set version = "0.1.03" %}
+{% set sha256 = "068a591b9736a3a46f60e4a5af3c40d0c769e8d3b68bc6aa708d17213a876e8d" %}
+{% set user = "quadram-institute-bioscience" %}
+
+package:
+  name: '{{ name }}'
+  version: '{{ version }}'
+
+source:
+  url: 'https://github.com/{{ user }}/{{ name }}/archive/v{{ version }}.tar.gz'
+  sha256: '{{ sha256 }}'
+
+build:
+  number: 0
+  noarch: generic
+
+requirements:
+  run:
+    - perl
+    - perl-fastx-reader >=0.90
+    - vsearch
+    - bioconductor-dada2
+    - fastp
+    - clustalo 
+    - fasttree
+    - sdm
+    - lca
+    - rtk
+    - blast
+
+test:
+  commands:
+    - dadaist2 --version 2>&1 | grep -F '{{ version }}'
+
+
+about:
+  home: 'https://github.com/{{ user }}/{{ name }}'
+  license: MIT
+  summary: Command line wrapper to run DADA2 on a set of paired-end reads
+  description: Command line wrapper to run DADA2 on a set of paired-end reads
+
+