miga-base 0.3.9.0 → 0.3.9.1

data/utils/enveomics/Manifest/categories.json

@@ -41,14 +41,17 @@
         "FastQ.test-error.rb"
       ],
       "Manipulation": [
+        "FastA.extract.rb",
         "FastA.filter.pl",
         "FastA.filterLen.pl",
         "FastA.filterN.pl",
         "FastA.fragment.rb",
         "FastA.interpose.pl",
+        "FastA.mask.rb",
         "FastA.per_file.pl",
         "FastA.rename.pl",
         "FastA.revcom.pl",
+        "FastA.sample.rb",
         "FastA.slider.pl",
         "FastA.split.pl",
         "FastA.split.rb",
@@ -143,6 +146,7 @@
         "BlastTab.catsbj.pl",
         "BlastTab.pairedHits.rb",
         "BlastTab.recplot2.R",
+        "GFF.catsbj.pl",
         "RecPlot2.compareIdentities.R"
       ]
     }

data/utils/enveomics/Manifest/examples.json

@@ -57,7 +57,7 @@
       "description": ["Generates recruitment plots for a comparison",
         "between a virome containing HIV and the HIV-1 genome."],
       "values": ["hiv_mix-hiv1.blast.tsv",50,100,null,null,null,null,null,null,
-        null,null,"hiv_mix-hiv1.Rdata","hiv_mix-hiv1.pdf",null,null]
+        null,null,null,"hiv_mix-hiv1.Rdata","hiv_mix-hiv1.pdf",null,null]
     },
     {
       "_": "== Examples of functional annotations ==",

data/utils/enveomics/Pipelines/assembly.pbs/FastA.N50.pl

@@ -1 +1 @@
-../../Scripts/FastA.N50.pl
+utils/enveomics/Pipelines/assembly.pbs/../../Scripts/FastA.N50.pl

data/utils/enveomics/Pipelines/assembly.pbs/FastA.filterN.pl

@@ -1 +1 @@
-../../Scripts/FastA.filterN.pl
+utils/enveomics/Pipelines/assembly.pbs/../../Scripts/FastA.filterN.pl

data/utils/enveomics/Pipelines/assembly.pbs/FastA.length.pl

@@ -1 +1 @@
-../../Scripts/FastA.length.pl
+utils/enveomics/Pipelines/assembly.pbs/../../Scripts/FastA.length.pl

data/utils/enveomics/Pipelines/blast.pbs/FastA.split.pl

@@ -1 +1 @@
-../../Scripts/FastA.split.pl
+utils/enveomics/Pipelines/blast.pbs/../../Scripts/FastA.split.pl

data/utils/enveomics/Scripts/BlastTab.catsbj.pl

@@ -1,9 +1,7 @@
 #!/usr/bin/env perl
-# 
-# @author: Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
-# @updated: Mar-23-2015
-# @license: artistic license 2.0
-# 
+
+# @author: Luis M. Rodriguez-R
+# @license: Artistic-2.0
 
 use warnings;
 use strict;
@@ -13,29 +11,29 @@ use Getopt::Std;
 sub HELP_MESSAGE { die "
 
 Description:
-   Generates a list of hits from a BLAST result concatenating the subject
-   sequences.  This can be used, e.g., to analyze BLAST results against
-   draft genomes.
+  Generates a list of hits from a BLAST result concatenating the subject
+  sequences.  This can be used, e.g., to analyze BLAST results against
+  draft genomes.
 
 Usage:
-   $0 [options] seq.fa map.bls
+  $0 [options] seq.fa map.bls
 
-   seq.fa	Subject sequences (ref) in FastA format.
-   map.bls	Mapping of the reads to the reference in BLAST Tabular
+  seq.fa	Subject sequences (ref) in FastA format.
+  map.bls	Mapping of the reads to the reference in BLAST Tabular
    		format.
    
-   Options:
-   -i <float>	Minimum identity to report a result.  By default: 70.
-   -l <int>	Minimum alignment length to report a result.  By default: 60.
-   -s		The FastA provided is to be treated as a subset of the subject.
-   		By default, it expects all the subjects to be present in the
-		BLAST.
-   -q		Run quietly.
-   -h		Display this message and exit.
+  Options:
+  -i <float>	Minimum identity to report a result.  By default: 70.
+  -l <int>	Minimum alignment length to report a result.  By default: 60.
+  -s		The FastA provided is to be treated as a subset of the subject.
+   		By default, it expects all the BLAST subjects to be present in
+		the FastA.
+  -q		Run quietly.
+  -h		Display this message and exit.
    
-   This script creates two files using <map.bls> as prefix with extensions
-   .rec (for the recruitment plot) and .lim (for the limits of the different
-   sequences in <seq.fa>).
+  This script creates two files using <map.bls> as prefix with extensions
+  .rec (for the recruitment plot) and .lim (for the limits of the different
+  sequences in <seq.fa>).
 
 ";}
 
@@ -51,56 +49,56 @@ my %seq = ();
 my @seq = ();
 my $tot = 0;
 
-SEQ:{
-   print STDERR "== Reading reference sequences\n" unless $o{q};
-   open FA, "<", $fa or die "Cannot read the file: $fa: $!\n";
-   my $cur_seq = '';
-   while(<FA>){
-      chomp;
-      if(m/^>(\S+)/){
-         my $c = $1;
-	 $seq{$c} = exists $seq{$cur_seq} ? $seq{$cur_seq}+1 : 1;
-	 push @seq, $c;
-	 $cur_seq = $c;
-      }else{
-         s/[^A-Za-z]//g;
-	 $seq{$cur_seq} += length $_;
-      }
-   }
-   close FA;
-   print STDERR " Found ".(scalar @seq)." sequences.\n" unless $o{q};
+SEQ: {
+  print STDERR "== Reading reference sequences\n" unless $o{q};
+  open FA, "<", $fa or die "Cannot read the file: $fa: $!\n";
+  my $cur_seq = '';
+  while(<FA>){
+    chomp;
+    if(m/^>(\S+)/){
+      my $c = $1;
+      $seq{$c} = exists $seq{$cur_seq} ? $seq{$cur_seq}+1 : 1;
+      push @seq, $c;
+      $cur_seq = $c;
+    }else{
+      s/[^A-Za-z]//g;
+      $seq{$cur_seq} += length $_;
+    }
+  }
+  close FA;
+  print STDERR " Found ".(scalar @seq)." sequences.\n" unless $o{q};
 }
 
 open LIM, ">", "$map.lim" or die "Cannot create the file: $map.lim: $!\n";
 my $l = 0;
 for my $s (@seq){
-   print LIM "$s\t".(++$l)."\t$seq{$s}\n";
-   ($l, $seq{$s}) = ($seq{$s}, $l);
+  print LIM "$s\t".(++$l)."\t$seq{$s}\n";
+  ($l, $seq{$s}) = ($seq{$s}, $l);
 }
 close LIM;
 
-MAP:{
-   print STDERR "== Reading mapping\n" unless $o{q};
-   open BLS, "<", $map or die "Cannot read the file: $map: $!\n";
-   open REC, ">", "$map.rec" or die "Cannot create the file: $map.rec: $!\n";
-   RESULT:while(<BLS>){
-      chomp;
-      my @ln = split /\t/;
-      $ln[11] or die "Cannot parse line $map:$.: $_\n";
-      next unless $ln[3]>=$o{l};
-      next unless $ln[2]>=$o{i};
-      unless(exists $seq{$ln[1]}){
-         die "Cannot find the subject sequence: $ln[1]\n" unless $o{s};
-	 next RESULT;
-      }
-      my $start = $seq{$ln[1]}+min($ln[8], $ln[9]);
-      my $end   = $seq{$ln[1]}+max($ln[8], $ln[9]);
-      print REC "$start\t$end\t$ln[2]\t$ln[11]\t$ln[0]",
-      		(exists($ln[13])?"\t".($ln[2]*$ln[3]/min($ln[12],$ln[13]))."\t":
-		exists($ln[12])?"\t".($ln[2]*$ln[3]/$ln[12])."\t":""),"\n";
-   }
-   close BLS;
-   close REC;
-   print STDERR " done.\n" unless $o{q};
+MAP: {
+  print STDERR "== Reading mapping\n" unless $o{q};
+  open BLS, "<", $map or die "Cannot read the file: $map: $!\n";
+  open REC, ">", "$map.rec" or die "Cannot create the file: $map.rec: $!\n";
+  RESULT: while(<BLS>){
+    chomp;
+    my @ln = split /\t/;
+    $ln[11] or die "Cannot parse line $map:$.: $_\n";
+    next unless $ln[3]>=$o{l};
+    next unless $ln[2]>=$o{i};
+    unless(exists $seq{$ln[1]}){
+      die "Cannot find the subject sequence: $ln[1]\n" unless $o{s};
+      next RESULT;
+    }
+    my $start = $seq{$ln[1]}+min($ln[8], $ln[9]);
+    my $end   = $seq{$ln[1]}+max($ln[8], $ln[9]);
+    print REC "$start\t$end\t$ln[2]\t$ln[11]\t$ln[0]",
+          (exists($ln[13])?"\t".($ln[2]*$ln[3]/min($ln[12],$ln[13]))."\t":
+          exists($ln[12])?"\t".($ln[2]*$ln[3]/$ln[12])."\t":""),"\n";
+  }
+  close BLS;
+  close REC;
+  print STDERR " done.\n" unless $o{q};
 }
 

data/utils/enveomics/Scripts/BlastTab.recplot2.R

@@ -1,7 +1,7 @@
 #!/usr/bin/env Rscript
 
 # @author  Luis M. Rodriguez-R
-# @license artistic license 2.0
+# @license Artistic-2.0
 
 #= Load stuff
 suppressPackageStartupMessages(library(enveomics.R))
@@ -17,6 +17,7 @@ opt <- enve.cliopts(enve.recplot2,
   usage="usage: %prog [options] output.Rdata [output.pdf [width height]]",
   mandatory=c("prefix"),
   o_desc=list(pos.breaks="Breaks in the positions histogram.",
+    pos.breaks.tsv="File with (absolute) coordinates of breaks in the position histogram",
     id.breaks="Breaks in the identity histogram.",
     id.summary="Function summarizing the identity bins. By default: sum.",
     peaks.col="Color of peaks, mandatory for peak-finding (e.g., darkred).",
@@ -24,7 +25,8 @@ opt <- enve.cliopts(enve.recplot2,
   p_desc=paste("","Produce recruitment plot objects provided that",
     "BlastTab.catsbj.pl has been previously executed.", sep="\n\t"),
   ignore=c("plot"),
-  defaults=c(id.metric="identity", peaks.col=NA, peaks.method="emauto"))
+  defaults=c(pos.breaks.tsv=NA, id.metric="identity", peaks.col=NA,
+    peaks.method="emauto"))
 
 #= Run it!
 if(length(opt$args)>1){

data/utils/enveomics/Scripts/FastA.extract.rb

@@ -0,0 +1,152 @@
+#!/usr/bin/env ruby
+
+#
+# @author Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
+# @license Artistic-2.0
+#
+
+require 'optparse'
+
+o = {q: false}
+ARGV << '-h' if ARGV.size==0
+
+OptionParser.new do |opt|
+  opt.banner = "
+Extracts a list of sequences and/or coordinates from multi-FastA files.
+
+Usage: #{$0} [options]"
+  opt.separator ''
+  opt.separator 'Mandatory'
+  opt.on('-i', '--in PATH', 'Input FastA file.'){ |v| o[:i] = v }
+  opt.on('-o', '--out PATH', 'Output FastA file.'){ |v| o[:o] = v }
+  opt.on('-c', '--coords STRING',
+    'Comma-delimited list of coordinates (mandatory unless -C is passed).',
+    'The format of the coordinates is "SEQ:FROM..TO" or "SEQ:FROM~LEN":',
+    'SEQ: Sequence ID, or * (asterisk) to extract range from all sequences',
+    'FROM: Integer, position of the first base to include (can be negative)',
+    'TO: Integer, last base to include (can be negative)',
+    'LEN: Length of the range to extract'
+    ){ |v| o[:c] = v }
+  opt.separator ''
+  opt.separator 'Options'
+  opt.on('-C', '--coords-file PATH',
+    'File containing the coordinates, one per line.',
+    'Each line must follow the format described for -c.'){ |v| o[:C] = v }
+  opt.on('-q', '--quiet', 'Run quietly (no STDERR output).'){ o[:q] = true }
+  opt.on('-h', '--help', 'Display this screen.') do
+    puts opt
+    exit
+  end
+  opt.separator ''
+end.parse!
+abort '-i is mandatory.' if o[:i].nil?
+abort '-o is mandatory.' if o[:o].nil?
+abort '-c is mandatory.' if o[:c].nil? and o[:C].nil?
+
+# Classses to parse coordinates
+class SeqCoords
+  attr :id, :from, :to, :length, :str
+  def initialize(str)
+    @str = str
+    m = /(\S+):(-?\d+)(~|\.\.)(-?\d+)/.match str
+    raise "Cannot parse coordinates: #{str}" if m.nil?
+    @id = m[1]
+    @from = m[2].to_i
+    if m[3] == '~'
+      @length = m[4].to_i
+    else
+      @to = m[4].to_i
+    end
+  end
+
+  def extract(id, seq)
+    return nil unless concerns? id
+    from_i = from > 0 ? from : seq.length + 1 + from
+    if to.nil?
+      seq[from_i, length]
+    else
+      to_i = to > 0 ? to : seq.length + 1 + to
+      seq[from_i .. to_i]
+    end
+  end
+
+  def concerns?(seq_id)
+    return true if id == '*'
+    return id == seq_id
+  end
+end
+
+class SeqCoordsCollection
+  class << self
+    def from_str(str)
+      c = new
+      str.split(',').each { |i| c << SeqCoords.new(i) }
+      c
+    end
+    def from_file(path)
+      c = new
+      File.open(path, 'r') do |fh|
+        fh.each{ |i| c << SeqCoords.new(i.chomp) }
+      end
+      c
+    end
+  end
+
+  attr :collection
+
+  def initialize
+    @collection = []
+  end
+
+  def <<(coords)
+    @collection << coords
+  end
+
+  def extract(id, seq)
+    @collection.map{ |c| c.extract(id, seq) }.compact
+  end
+end
+
+# Functions to parse sequences
+def do_stuff(id, sq)
+  return if id.nil? or sq.empty?
+  @n_in += 1
+  sq.gsub!(/[^A-Za-z]/, '')
+  i = 0
+  @coll.extract(id, sq).each do |new_sq|
+    @ofh.puts ">#{id}:#{i += 1}"
+    @ofh.puts new_sq
+    @n_out += 1
+  end
+end
+
+# Parse coordinates
+$stderr.puts 'Parsing coordinates' unless o[:q]
+@coll = o[:c].nil? ? SeqCoordsCollection.from_file(o[:C]) :
+  SeqCoordsCollection.from_str(o[:c])
+$stderr.puts "  Coordinates found: #{@coll.collection.size}"
+
+# Parse sequences
+$stderr.puts 'Parsing sequences' unless o[:q]
+@n_in = 0
+@n_out = 0
+@ofh = File.open(o[:o], 'w')
+File.open(o[:i], 'r') do |fh|
+  id = nil
+  sq = ''
+  fh.each do |ln|
+    next if ln =~ /^;/
+    if ln =~ /^>(\S+)/
+      id = $1
+      do_stuff(id, sq)
+      sq = ''
+    else
+      sq << ln
+    end
+  end
+  do_stuff(id, sq)
+end
+@ofh.close
+$stderr.puts "  Input sequences: #{@n_in}"
+$stderr.puts "  Output fragments: #{@n_out}"
+

data/utils/enveomics/Scripts/FastA.mask.rb

@@ -0,0 +1,89 @@
+#!/usr/bin/env ruby
+
+require 'optparse'
+o = {x: 'N', trim: false, wrap: 70}
+ARGV << '-h' if ARGV.empty?
+OptionParser.new do |opts|
+  opts.banner = "
+Mask sequence region(s) in a FastA file.
+
+Usage: #{$0} [options]"
+  opts.separator ''
+  opts.separator 'Mandatory'
+  opts.on('-i', '--in FILE', 'Input FastA file.'){ |v| o[:in] = v }
+  opts.on('-o', '--out FILE', 'Output FastA file.'){ |v| o[:out] = v }
+  opts.on('-r', '--regions REG1,REG2,...', Array,
+    'Regions to mask separated by commas.',
+    'Each region must be in the format "sequence_id:from..to"'
+    ){ |v| o[:reg] = v }
+  opts.separator ''
+  opts.separator 'Options'
+  opts.on('-x', '--symbol CHAR',
+    'Character used to mask the region(s)',
+    "By default: #{o[:x]}."){ |v| o[:x] = v }
+  opts.on('-t', '--trim',
+    'Trim masked regions extending to the edge of a sequence'
+    ){ |v| o[:trim] = v }
+  opts.on('-w', '--wrap INT',
+    'Line length to wrap sequences. Use 0 to generate 1-line sequences.',
+    "By default: #{o[:wrap]}."){ |v| o[:wrap] = v.to_i }
+  opts.on('-h', '--help', 'Display this screen.') do
+    puts opts
+    exit
+  end
+  opts.separator ''
+end.parse!
+abort '-i is mandatory' if o[:in].nil?
+abort '-o is mandatory' if o[:out].nil?
+abort '-r is mandatory' if o[:reg].nil?
+
+def wrap_width(txt, len)
+  return "" if txt.empty?
+  return "#{txt}\n" if len==0
+  txt.gsub(/(.{1,#{len}})/,"\\1\n")
+end
+
+# Read input sequences
+sq = {}
+File.open(o[:in], 'r') do |ifh|
+  bf = ''
+  ifh.each('>') do |i|
+    (dln, seq) = i.split(/[\n\r]+/, 2)
+    next if seq.nil?
+    id = dln.gsub(/\s.*/,  '')
+    seq.gsub!(/[\s>]/, '')
+    sq[id] = [dln, seq]
+  end
+end
+
+# Parse coordinates and mask regions
+last_id = nil
+o[:reg].each do |i|
+  m = i.match(/^(?:(.+):)?(\d+)\.\.(\d+)$/) or
+    abort "Unexpected region format: #{i}"
+  r = [m[1], m[2].to_i-1, m[3].to_i-1]
+  if r[0].nil?
+    abort "Region missing sequence ID: #{i}" if last_id.nil?
+    r[0] = last_id
+  end
+  last_id = r[0]
+  sq[r[0]] or abort "Cannot find sequence #{r[0]}"
+  r[1] <= r[2] or abort "Malformed range: #{i}"
+  if r[1] < 0 or r[2] > sq[r[0]][1].size
+    abort "Range extends beyond the edge of the sequence: #{i}"
+  end
+  sq[r[0]][1][r[1] .. r[2]] = o[:x]*(1+r[2]-r[1])
+end
+
+# Trim sequences and generate output
+ofh = File.open(o[:out], 'w')
+sq.each do |_k,v|
+  ofh.puts ">#{v[0]}"
+  if o[:trim]
+    v[1].gsub!(/^#{o[:x]}+/,'')
+    v[1].gsub!(/#{o[:x]}+$/,'')
+  end
+  ofh.print wrap_width(v[1], o[:wrap])
+end
+ofh.close
+

data/utils/enveomics/Scripts/FastA.sample.rb

@@ -0,0 +1,83 @@
+#!/usr/bin/env ruby
+
+#
+# @author Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
+# @license Artistic-2.0
+#
+
+require 'optparse'
+
+o = {q: false, rep: false}
+ARGV << '-h' if ARGV.size==0
+
+OptionParser.new do |opt|
+  opt.banner = "
+Samples a random set of sequences from a multi-FastA file.
+
+Usage: #{$0} [options]"
+  opt.separator ''
+  opt.separator 'Mandatory'
+  opt.on('-i', '--in PATH', 'Input FastA file.'){ |v| o[:i] = v }
+  opt.on('-o', '--out PATH', 'Output FastA file.'){ |v| o[:o] = v }
+  opt.on('-f', '--fraction FLOAT',
+    'Fraction of sequences to sample [0-1].',
+    'Mandatory unless -n is provided.'){ |v| o[:f] = v.to_f }
+  opt.separator ''
+  opt.separator 'Options'
+  opt.on('-c', '--number INT',
+    'Number of sequences to sample.',
+    'Mandatory unless -f is provided.'){ |v| o[:n] = v.to_i }
+  opt.on('-r', '--replacement','Sample with replacement'){ |v| o[:rep] = v }
+  opt.on('-q', '--quiet', 'Run quietly (no STDERR output).'){ o[:q] = true }
+  opt.on('-h', '--help', 'Display this screen.') do
+    puts opt
+    exit
+  end
+  opt.separator ''
+end.parse!
+abort '-i is mandatory.' if o[:i].nil?
+abort '-o is mandatory.' if o[:o].nil?
+abort '-f or -n is mandatory.' if o[:f].nil? and o[:n].nil?
+
+# Functions to parse sequences
+def do_stuff(id, sq)
+  return if id.nil? or sq.empty?
+  @n_in += 1
+  sq.gsub!(/[^A-Za-z]/, '')
+  i = 0
+  @coll.extract(id, sq).each do |new_sq|
+    @ofh.puts ">#{id}:#{i += 1}"
+    @ofh.puts new_sq
+    @n_out += 1
+  end
+end
+
+# Parse sequences
+$stderr.puts 'Parsing sequences' unless o[:q]
+seq = []
+File.open(o[:i], 'r') do |fh|
+  id = nil
+  sq = ''
+  fh.each do |ln|
+    next if ln =~ /^;/
+    if ln =~ /^>(.+)/
+      seq << [id, sq] unless id.nil?
+      id = $1
+      sq = ''
+    else
+      sq << ln
+    end
+  end
+  seq << [id, sq] unless id.nil?
+end
+$stderr.puts "  Input sequences: #{seq.size}"
+o[:n] ||= (seq.size * o[:f]).round
+seq_o = o[:rep] ? o[:n].times.map{ seq.sample } : seq.sample(o[:n])
+File.open(o[:o], 'w') do |fh|
+  seq_o.each do |i|
+    fh.puts ">#{i[0]}"
+    fh.puts i[1]
+  end
+end
+$stderr.puts "  Output sequences: #{seq_o.size}"
+