miga-base 0.7.26.2 → 1.0.3.0

data/utils/enveomics/Scripts/FastQ.maskQual.rb

@@ -0,0 +1,89 @@
+#!/usr/bin/env ruby
+
+$VERSION = 1.2
+$:.push File.expand_path('../lib', __FILE__)
+require 'enveomics_rb/enveomics'
+
+o = { q: false, offset: 33, qual: 15, fasta: false }
+OptionParser.new do |opts|
+  opts.version = $VERSION
+  Enveomics.opt_banner(
+    opts, 'Masks low-quality bases in a FastQ file',
+    "#{File.basename($0)} -i in.fastq -o out.fastq [options]"
+  )
+
+  opts.separator 'Mandatory'
+  opts.on(
+    '-i', '--input FILE',
+    'Path to the FastQ file containing the sequences',
+    'Supports compression with .gz extension, use - for STDIN'
+  ) { |v| o[:in] = v }
+  opts.on(
+    '-o', '--out FILE',
+    'Path to the output FastQ file',
+    'Supports compression with .gz extension, use - for STDOUT'
+  ) { |v| o[:out] = v }
+
+  opts.separator ''
+  opts.separator 'Quality Options'
+  opts.on(
+    '-q', '--qual INT', Integer,
+    "Minimum quality score to allow a base, by default: #{o[:qual]}"
+  ) { |v| o[:qual] = v }
+  opts.on(
+    '--offset INT', Integer,
+    "Q-score offset, by default: #{o[:offset]}"
+  ) { |v| o[:offset] = v }
+
+  opts.separator ''
+  opts.separator 'Other Options'
+  opts.on(
+    '-a', '--fasta', 'Output sequences in FastA format'
+  ) { |v| o[:fasta] = v }
+  opts.on('-q', '--quiet', 'Run quietly (no STDERR output)') { o[:q] = true }
+  opts.on('-h', '--help', 'Display this screen') do
+    puts opts
+    exit
+  end
+  opts.separator ''
+end.parse!
+
+raise Enveomics::OptionError.new('-i is mandatory') if o[:in].nil?
+raise Enveomics::OptionError.new('-o is mandatory') if o[:out].nil?
+$QUIET = o[:q]
+
+# Open in/out files
+say 'Reading FastQ file'
+ifh = reader(o[:in])
+ofh = writer(o[:out])
+
+# Parse and mask
+entry = []
+lno = 0
+ifh.each_line do |ln|
+  lno += 1 # <- Gzip doesn't support $.
+  case lno % 4
+  when 1
+    ln =~ /^@(\S+)/ or
+      raise Enveomics::ParseError.new("Unexpected defline format: #{ln}")
+    entry << ln
+  when 2, 3
+    entry << ln
+  when 0
+    entry << ln
+    q = entry[3].chomp.split('').map { |i| (i.ord - o[:offset]) }
+    q.map { |i| i < o[:qual] }.each_with_index { |i, k| entry[1][k] = 'N' if i }
+    ofh.puts(o[:fasta] ? [entry[0].gsub(/^@/, '>'), entry[1]] : entry)
+    entry = []
+  end
+end
+
+# Finalize
+say "  Lines: #{lno}"
+unless entry.empty?
+  raise Enveomics::ParseError.new('Unexpected trailing lines in FastQ')
+end
+say "  Sequences: #{lno / 4}"
+ifh.close
+ofh.close
+

data/utils/enveomics/Scripts/FastQ.tag.rb

@@ -1,63 +1,70 @@
 #!/usr/bin/env ruby
 
-#
-# @author: Luis M. Rodriguez-R
-# @update: Feb-06-2015
-# @license: artistic license 2.0
-#
+# frozen_string_literal: true
 
-require 'optparse'
+$:.push File.expand_path('../lib', __FILE__)
+require 'enveomics_rb/enveomics'
+$VERSION = 1.1
 
-o = {:q=>FALSE, :p=>"", :s=>""}
-ARGV << '-h' if ARGV.size==0
+o = { q: false, p: '', s: '' }
 OptionParser.new do |opts|
-   opts.banner = "
-Generates easy-to-parse tagged reads from FastQ files.
+  opts.version = $VERSION
+  Enveomics.opt_banner(
+    opts, 'Generates easy-to-parse tagged reads from FastQ files',
+    "#{File.basename($0)} -i in.fasta -o out.fasta [options]"
+  )
 
-Usage: #{$0} [options]"
-   opts.separator ""
-   opts.separator "Mandatory"
-   opts.on("-i", "--in FILE", "Path to the FastQ file containing the sequences."){ |v| o[:in] = v }
-   opts.on("-o", "--out FILE", "Path to the FastQ to create."){ |v| o[:out] = v }
-   opts.separator ""
-   opts.separator "ID options"
-   opts.on("-p", "--prefix STR", "Prefix to use in all IDs."){ |v| o[:p] = v }
-   opts.on("-s", "--suffix STR", "Suffix to use in all IDs."){ |v| o[:s] = v }
-   opts.separator ""
-   opts.separator "Other Options"
-   opts.on("-q", "--quiet", "Run quietly (no STDERR output)"){ o[:q] = TRUE }
-   opts.on("-h", "--help", "Display this screen") do
-      puts opts
-      exit
-   end
-   opts.separator ""
+  opts.separator 'Mandatory'
+  opts.on(
+    '-i', '--in FILE',
+    'Path to the FastQ file containing the sequences',
+    'Supports compression with .gz extension, use - for STDIN'
+  ) { |v| o[:in] = v }
+  opts.on(
+    '-o', '--out FILE', 'Path to the FastQ to create',
+    'Supports compression with .gz extension, use - for STDOUT'
+  ) { |v| o[:out] = v }
+  opts.separator ''
+  opts.separator 'ID options'
+  opts.on('-p', '--prefix STR', 'Prefix to use in all IDs') { |v| o[:p] = v }
+  opts.on('-s', '--suffix STR', 'Suffix to use in all IDs') { |v| o[:s] = v }
+  opts.separator ''
+  opts.separator 'Other Options'
+  opts.on('-q', '--quiet', 'Run quietly (no STDERR output)') { o[:q] = true }
+  opts.on('-h', '--help', 'Display this screen') { puts opts ; exit }
+  opts.separator ''
 end.parse!
-abort "-i is mandatory" if o[:in].nil?
-abort "-o is mandatory" if o[:out].nil?
-   
+
+raise Enveomics::OptionError.new('-i is mandatory') if o[:in].nil?
+raise Enveomics::OptionError.new('-o is mandatory') if o[:out].nil?
+
 begin
-   ifh = File.open(o[:in], 'r');
-   ofh = File.open(o[:out], 'w');
-   i=0
-   while ln=ifh.gets
-      ln.chomp!
-      if $.%4==1 and not /^@/.match(ln).nil?
-	 i+=1
-	 ofh.puts "@#{o[:p]}#{i}#{o[:s]}"
-      elsif $.%4==2 or $.%4==0
-         ofh.puts ln
-      elsif $.%4==3 and not /^\+/.match(ln).nil?
-         ofh.puts "+"
-      else
-         abort "Impossible to parse line #{$.}: #{ln}.\n"
-      end
-   end
-   ifh.close
-   ofh.close
+  ifh = reader(o[:in])
+  ofh = writer(o[:out])
+  i = 0
+  lno = 0
+  ifh.each do |ln|
+    ln.chomp!
+    lno += 1
+    case lno % 4
+    when 1
+      ln =~ /^@/ or
+        raise Enveomics::ParseError.new("Cannot parse line #{$.}: #{ln}")
+      i += 1
+      ofh.puts "@#{o[:p]}#{i}#{o[:s]}"
+    when 3
+      ln =~ /^\+/ or
+        raise Enveomics::ParseError.new("Cannot parse line #{$.}: #{ln}")
+      ofh.puts '+'
+    else
+      ofh.puts ln
+    end
+  end
+  ifh.close
+  ofh.close
 rescue => err
-   $stderr.puts "Exception: #{err}\n\n"
-   err.backtrace.each { |l| $stderr.puts l + "\n" }
-   err
+  $stderr.puts "Exception: #{err}\n\n"
+  err.backtrace.each { |l| $stderr.puts l + "\n" }
+  err
 end
 
-

data/utils/enveomics/Scripts/SRA.download.bash

@@ -1,21 +1,19 @@
 #!/bin/bash
 
-#
-# @author  Luis M. Rodriguez-R
-# @license artistic license 2.0
-#
-
-DATA_LINK="https://www.ebi.ac.uk/ena/data/warehouse/filereport"
+DATA_LINK="https://www.ebi.ac.uk/ena/portal/api/filereport"
 DATA_OPS="result=read_run&fields=run_accession,fastq_ftp,fastq_md5"
 SRX=$1
 DIR=${2:-$SRX}
+VERSION=1.0
 
 if [[ "$SRX" == "" ]] ; then
 echo "
+[Enveomics Collection: $(basename "$0" .bash) $VERSION]
+
 Downloads the set of runs from a project, sample, or experiment in SRA.
 
 Usage:
-$0 <SRA-ID>[ <dir>]
+$(basename "$0") <SRA-ID>[ <dir>]
 
 <SRA-ID>	ID of the SRA Project, Sample, or Experiment.
 <dir>		Directory where the files are to be downladed. By default,
@@ -34,7 +32,7 @@ function md5value {
   echo "$o"
 }
 
-curl -s "$DATA_LINK?$DATA_OPS&accession=$SRX" -o "$DIR/srr_list.txt"
+curl -Ls "$DATA_LINK?$DATA_OPS&accession=$SRX" -o "$DIR/srr_list.txt"
 tail -n +2 "$DIR/srr_list.txt" | while read ln ; do
   srr=$(echo "$ln"|cut -f 1)
   ftp=$(echo "$ln"|cut -f 2)

data/utils/enveomics/Scripts/Table.prefScore.R

@@ -0,0 +1,60 @@
+#!/usr/bin/env Rscript
+
+#= Load stuff
+args <- commandArgs(trailingOnly = FALSE)  
+enveomics_R <- file.path(
+  dirname(sub('^--file=', '', args[grep('^--file=', args)])),
+  'lib',
+  'enveomics.R'
+)
+for(file in c('cliopts.R','utils.R','prefscore.R'))
+  source(file.path(enveomics_R, 'R', file))
+
+#= Generate interface
+opt <- enve.cliopts(
+  enve.prefscore,
+  file.path(enveomics_R, 'man', 'enve.prefscore.Rd'),
+  positional_arguments = c(1, 4),
+  usage = 'usage: %prog [options] output.tsv [output.pdf [width height]]',
+  mandatory = c('x', 'set'),
+  number = c('signif.thr'),
+  ignore = c('plot'),
+  o_desc = list(
+    x = 'A tab-delimited table of presence/absence (1/0) with species as rows and samples as columns.',
+    set = 'A list of sample names that constitute the test set, one per line',
+    ignore = 'A list of species to exclude from the analysis, one per line'
+  )
+)
+
+#= Set output files
+opt$options[['x']] <- read.table(
+  opt$options[['x']],
+  header = TRUE,
+  row.names = 1,
+  sep = '\t'
+)
+opt$options[['set']] <- read.table(
+  opt$options[['set']],
+  header = FALSE,
+  sep = '\t',
+  as.is = TRUE
+)[,1]
+if(!is.null(opt$options[['ignore']]))
+  opt$options[['ignore']] <- read.table(
+    opt$options[['ignore']],
+    header = FALSE,
+    sep = '\t',
+    as.is = TRUE
+  )[,1]
+if(length(opt$args) > 1) {
+  args <- as.list(opt$args[-1])
+  for(i in 2:3) if(length(args) >= i) args[[i]] <- as.numeric(args[[i]])
+  do.call('pdf', args)
+} else {
+  opt$options[['plot']] <- FALSE
+}
+
+#= Run it!
+y <- do.call('enve.prefscore', opt$options)
+write.table(y, opt$args[1], quote = FALSE, sep = '\t', col.names = FALSE)
+if(length(opt$args)>1) ttt <- dev.off()

data/utils/enveomics/Scripts/aai.rb

@@ -236,8 +236,9 @@ Dir.mktmpdir do |dir|
         end
       end
       response = RestClient.post(
-        "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi",
-        db:"nuccore",rettype:"fasta",id:protIds.join(","),idtype:"acc")
+        'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi',
+        db: 'protein', rettype: 'fasta', id: protIds.join(','), idtype: 'acc'
+      )
       abort "Unable to reach NCBI EUtils, error code " +
         response.code.to_s + "." unless response.code == 200
       fo.puts response.to_str

data/utils/enveomics/Scripts/anir.rb

@@ -0,0 +1,137 @@
+#!/usr/bin/env ruby
+
+# frozen_string_literal: true
+
+$:.push File.expand_path('../lib', __FILE__)
+require 'enveomics_rb/enveomics'
+require 'enveomics_rb/anir'
+$VERSION = 1.0
+
+o = {
+  q: false, threads: 2,
+  r_format: :fastq, g_format: :fasta, m_format: :sam, r_type: :single,
+  identity: 95.0, algorithm: :auto, bimodality: 0.5, bin_size: 1.0,
+  coefficient: :sarle
+}
+
+OptionParser.new do |opt|
+  cmd = File.basename($0)
+  opt.banner = <<~BANNER
+
+    [Enveomics Collection: #{cmd} v#{$VERSION}]
+
+    Estimates ANIr: the Average Nucleotide Identity of reads against a genome
+
+    Usage
+        # [ Input/output modes ]
+        # Run mapping and (optionally) save it as SAM
+        # Requires bowtie2
+        #{cmd} -r reads.fastq -g genome.fasta -m out_map.sam [options]
+
+        # Read mapping from BAM file
+        # Requires samtools
+        #{cmd} -m map.bam --m-format bam [options]
+
+        # Read mapping from other formats: SAM or Tabular BLAST
+        #{cmd} -m map.blast --m-format tab [options]
+
+        # Read a list of identities as percentage (contig filtering off)
+        #{cmd} -m identities.txt --m-format list [options]
+
+        # [ Identity threshold modes ]
+        #{cmd} -i 95 -a fix [options] # Set fixed identity threshold
+        #{cmd} -a gmm [options]       # Find valley by EM of GMM
+        #{cmd} -a auto [options]      # Pick method by bimodality (default)"
+
+  BANNER
+
+  opt.separator 'Input/Output'
+  opt.on('-r', '--reads PATH', 'Metagenomic reads') { |v| o[:r] = v }
+  opt.on('-g', '--genome PATH', 'Genome assembly') { |v| o[:g] = v }
+  opt.on('-m', '--mapping PATH', 'Mapping file') { |v| o[:m] = v }
+  opt.on('-L', '--list PATH', 'Output file with identities') { |v| o[:L] = v }
+  opt.on('-H', '--hist PATH', 'Output file with histogram') { |v| o[:H] = v }
+  opt.on(
+    '-T', '--tab PATH', 'Output file with results in tabular format'
+  ) { |v| o[:T] = v }
+  opt.separator ''
+
+  opt.separator 'Formats'
+  opt.on(
+    '--r-format STRING',
+    'Metagenomic reads format: fastq (default) or fasta',
+    'Both options support compression with .gz file extension'
+  ) { |v| o[:r_format] = v.downcase.to_sym }
+  opt.on(
+    '--r-type STRING', 'Type of metagenomic reads:',
+    '~ single (default): Single reads',
+    '~ coupled: Coupled reads in separate files (-m must be comma-delimited)',
+    '~ interleaved: Coupled reads in a single interposed file'
+  ) { |v| o[:r_type] = v.downcase.to_sym }
+  opt.on(
+    '--g-format STRING',
+    'Genome assembly format: fasta (default) or list',
+    'Both options support compression with .gz file extension',
+    'If passed in mapping-read mode, filters only matches to these contigs'
+  ) { |v| o[:g_format] = v.downcase.to_sym }
+  opt.on(
+    '--m-format STRING',
+    'Mapping file format: sam (default), bam, tab, or list',
+    'sam, tab, and list options support compression with .gz file extension'
+  ) { |v| o[:m_format] = v.downcase.to_sym }
+  opt.separator ''
+
+  opt.separator 'Identity threshold'
+  opt.on(
+    '-i', '--identity FLOAT', Float,
+    "Set a fixed threshold of percent identity (default: #{o[:identity]})"
+  ) { |v| o[:identity] = v }
+  opt.on(
+    '-a', '--algorithm STRING',
+    'Set an algorithm to automatically detect identity threshold:',
+    '~ gmm: Valley detection by E-M of Gaussian Mixture Model',
+    '~ fix: Fixed threshold, see -i',
+    '~ auto (default): Pick gmm or fix depending on bimodality, see -b'
+  ) { |v| o[:algorithm] = v.downcase.to_sym }
+  opt.on(
+    '-b', '--bimodality FLOAT', Float,
+    'Threshold of bimodality below which the algorithm is set to fix',
+    'The coefficient used is the de Michele & Accantino (2014) B index',
+    "By default: #{o[:bimodality]}"
+  ) { |v| o[:bimodality] = v }
+  opt.on(
+    '--coefficient STRING',
+    'Coefficient of bimodality for -a auto:',
+    '~ sarle (default): Sarle\'s bimodality coefficient b',
+    '~ dma: de Michele and Accatino (2014 PLoS ONE) B index, use with -b 0.1'
+  ) { |v| o[:coefficient] = v.downcase.to_sym }
+  opt.on(
+    '--bin-size FLOAT', Float,
+    "Width of histogram bins (in percent identity). By default: #{o[:bin_size]}"
+  ) { |v| o[:bin_size] = v }
+  opt.separator ''
+
+  opt.separator 'General'
+  opt.on(
+    '-t', '--threads INT', Integer, 'Threads to use'
+  ) { |v| o[:threads] = v }
+  opt.on('-l', '--log PATH', 'Log file to save output') { |v| o[:log] = v }
+  opt.on('-q', '--quiet', 'Run quietly') { |v| o[:q] = v }
+  opt.on('-h', '--help', 'Display this screen') do
+    puts opt
+    exit
+  end
+  opt.separator ''
+end.parse!
+
+anir = Enveomics::ANIr.new(o)
+anir.go!
+if o[:T]
+  File.open(o[:T], 'w') do |fh|
+    fh.puts "anir\tsd\treads\tid_threshold"
+    fh.puts [
+      anir.sample.mean, anir.sample.sd, anir.sample.n, anir.opts[:identity]
+    ].join("\t")
+  end
+end
+