miga-base 0.7.25.2 → 0.7.25.3

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

@@ -1,48 +0,0 @@
-#!/usr/bin/env ruby
-
-require "optparse"
-o = {wrap:70}
-ARGV << "-h" if ARGV.empty?
-OptionParser.new do |opts|
-  opts.banner = "
-Wraps sequences in a FastA to a given line length.
-
-Usage: #{$0} [options]"
-  opts.separator ""
-  opts.separator "Options"
-  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("-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?
-
-def wrap_width(txt, len)
-  return "" if txt.empty?
-  return "#{txt}\n" if len==0
-  txt.gsub(/(.{1,#{len}})/,"\\1\n")
-end
-
-ofh = File.open(o[:out], "w")
-File.open(o[:in], "r") do |ifh|
-  bf = ""
-  ifh.each_line do |ln|
-    if ln =~ /^>/
-      ofh.print wrap_width(bf, o[:wrap])
-      ofh.puts ln
-      bf = ""
-    else
-      ln.chomp!
-      bf << ln
-    end
-  end
-  ofh.print wrap_width(bf, o[:wrap])
-end
-ofh.close

data/utils/enveomics/Scripts/FastQ.filter.pl

@@ -1,54 +0,0 @@
-#!/usr/bin/env perl
-#
-# @author: Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
-# @update: Mar-23-2015
-# @license: artistic license 2.0
-#
-
-use warnings;
-use strict;
-use Getopt::Std;
-
-sub HELP_MESSAGE { die "
-.Description:
-   Extracts a subset of sequences from a FastQ file.
-
-.Usage: $0 [options] list.txt seqs.fq > subset.fq
-   
-   [options]
-   -r		Reverse list.  Extracts sequences NOT present in the list.
-   -q		Runs quietly.
-   -h		Prints this message and exits.
-
-   [mandatory]
-   list.txt	List of sequences to extract.
-   seqs.fq	FastQ file containing the superset of sequences.
-   subset.fq	FastQ file to be created.
-
-" }
-
-my %o=();
-getopts('rhq', \%o);
-my($list, $fq) = @ARGV;
-($list and $fq) or &HELP_MESSAGE;
-$o{h} and &HELP_MESSAGE;
-
-print STDERR "Reading list.\n" unless $o{q};
-open LI, "<", $list or die "Cannot read file: $list: $!\n";
-my %li = map { chomp; $_ => 1 } <LI>;
-close LI;
-
-print STDERR "Filtering FastQ.\n" unless $o{q};
-open FQ, "<", $fq or die "Cannot read file: $fq: $!\n";
-my $good = 0;
-while(my $ln = <FQ>){
-   my @ln = ();
-   $ln[$_] = <FQ> for 0 .. 2;
-   chomp $ln;
-   if($ln =~ m/^@((\S+).*)/){ $good = (exists $li{$1} or exists $li{">$1"} or exists $li{"\@$1"} or exists $li{$2} or exists $li{$ln}) }
-   elsif($ln =~ m/^>/){ $good=0; print STDERR "Warning: Non-cannonical defline, line $.: $ln\n" }
-   else{ $good=$o{r}; print STDERR "Warning: Non-cannonical defline, line $.: $ln\n" }
-   print "".join("", "$ln\n", @ln) if (($good and not $o{r}) or ($o{r} and not $good));
-}
-close FQ;
-

data/utils/enveomics/Scripts/FastQ.interpose.pl

@@ -1,90 +0,0 @@
-#!/usr/bin/env perl
-
-# @author Luis M. Rodriguez-R
-# @license artistic license 2.0
-
-use strict;
-use warnings;
-use Symbol;
-
-my $HELP = <<HELP
-
-  Description:
-    Interposes sequences in FastQ format from two files into one output file.
-    If more than two files are provided, the script will interpose all the input
-    files.
-    Note that this script will check for the consistency of the names (assuming
-    a pair of related reads contains the same name varying only in a trailing
-    slash (/) followed by a digit.  If you want to turn this feature off just
-    set the -T option to zero.  If you want to decrease the sampling period (to
-    speed the script up) or increase it (to make it more sensitive to errors)
-    just change the -T option accordingly.
-
-  Usage:
-    $0 [-T <int> ]<output_fastq> <input_fastq_1> <input_fastq_2> [additional input files...]
-
-  Where,
-    -T <int>		: Optional.  Integer indicating the sampling period for
-    			  names evaluation (see Description above).
-			  By default: 1000.
-    output_fastq	: Output file
-    input_fastq_1	: First FastQ file
-    input_fastq_2	: Second FastQ file
-    ... 		: Any additional FastQ files (or none)
-
-HELP
-;
-my $eval_T = 1000;
-if(exists $ARGV[0] and exists $ARGV[1] and $ARGV[0] eq '-T'){
-   $eval_T = $ARGV[1]+0;
-   shift @ARGV;
-   shift @ARGV;
-}
-my $out = shift @ARGV;
-my @in = @ARGV;
-
-
-die $HELP unless $out and $#in >= 1;
-open OUT, ">", $out or die "Unable to write on $out: $!\n";
-print "Output file: $out\n";
-
-my @in_fh = ();
-
-for my $k (0 .. $#in) {
-   $in_fh[$k] = gensym;
-   open $in_fh[$k], "<", $in[$k] or die "Unable to read $in[$k]: $!\n";
-   print "Input file: $in[$k]\n";
-}
-
-my $i = 0;
-my $frl;
-LINE: while(1){
-   my $name = "";
-   print STDERR "\rEntry: $i    " unless $i % 1000;
-   FILE: for my $k (0 .. $#in_fh){
-      my @ln = ();
-      for my $l (0 .. 3){
-	 $ln[$l] = readline($in_fh[$k]);
-	 last LINE if $k==0 and $l==0 and (not defined $ln[$l]);
-	 defined $ln[$l] or die "Impossible to read next entry (line $.) from $in[$k]: $!\n";
-	 chomp $ln[$l];
-      }
-      if($eval_T and not $i % $eval_T){
-	 $ln[0] =~ m/^\@(.*?)\/\d+\s*$/ or die "Impossible to evaluate names!\n offending entry:\n$ln[0]\n";
-	 $name ||= $1;
-	 die "Inconsistent name!\n base name is $name\n offending entry is:\n$ln[0]\n" unless $1 eq $name;
-      }
-      unless($frl){
-	 $ln[0] =~ /^@/ or die "Unexpected format! (missing @)\n offending entry: $ln[0].\n";
-         $ln[2] =~ /^\+/ or die "Unexpected format! (missing +)\n offending entry: $ln[0].\n";
-	 $frl = length $ln[1];
-      }
-      print OUT "".join("\n", @ln, "");
-   }
-   $i++;
-}
-print "\rNumber of entries: $i     \nFirst read length: $frl\n";
-close OUT;
-
-for my $k(0..$#in_fh){print "ALERT: The file $in[$k] contains trailing entries\n" if defined readline($in_fh[$k])}
-

data/utils/enveomics/Scripts/FastQ.offset.pl

@@ -1,90 +0,0 @@
-#!/usr/bin/env perl
-#
-# @author Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
-# @update Mar-23-2015
-# @license artistic license 2.0
-#
-
-use warnings;
-use strict;
-
-my ($in, $off, $force) = @ARGV;
-$in or die "
-.Description:
-   There are several FastQ formats (see http://en.wikipedia.org/wiki/FASTQ_format).
-   This script takes a FastQ in any of them, identifies the type of FastQ (this is,
-   the offset), and generates a FastQ with the given offset.  Note that Solexa+64
-   FastQ can cause problematic values when using the offset 33, since there is no
-   equivalent in Phred+33 for negative values (the range of Solexa+64 is -5 to 40).
-
-.Usage:
-   $0 in.fastq[ offset[ force]] > out.fastq
-
-   in.fastq	Input file in FastQ format (range is automatically detected).
-   offset	(optional) Offset to use for the output.  Use 0 (zero) to detect
-   		the input format and exit.  By default: 33.
-   force	(optional) If true, turns errors into warnings and continues.
-   		Out-of-range values are set to the closest range limit.
-   out.fastq	Output file in FastQ format with the specified offset.
-
-";
-
-$off = 33 unless defined $off;
-
-my $in_off = 0;
-open IN, "<", $in or die "Cannot read file: $in: $!\n";
-GUESS_FORMAT: while(<IN>){
-   unless($.%4){
-      chomp;
-      for my $chr (split //){
-         my $o = ord $chr;
-	 if($o < 55){
-	    $in_off = 33;
-	    last GUESS_FORMAT;
-	 }elsif($o > 80){
-	    $in_off = 64;
-	    last GUESS_FORMAT;
-	 }
-      }
-   }
-}
-close IN;
-print STDERR "Detected input offset: Phred+$in_off\n";
-exit unless $off;
-
-my $Solexa64=0;
-die "Couldn't guess input format.\n" unless $in_off;
-open IN, "<", $in or die "Cannot read file: $in: $!\n";
-while(<IN>){
-   if($in_off==$off or $.%4){
-      print $_;
-   }else{
-      chomp;
-      for my $chr (split //){
-         my $score = ord($chr) - $in_off;
-	 my $err = '';
-	 if($score < -5){
-	    $err = "Out-of-range value $chr ($score) in line $..\n";
-	    $score = $off==64 ? -5 : 0;
-	 }elsif(!$Solexa64 and $score < 0){
-	    if($in_off==64){
-	       print STDERR "Format variant: Solexa+64\n";
-	       $Solexa64 = 1;
-	    }else{
-	       $err = "Out-of-range value $chr ($score) in line $..\n";
-	       $score = 0;
-	    }
-	 }elsif($score>41){
-	    $err = "Out-of-range value $chr ($score) in line $..\n";
-	    $score = 41;
-	 }
-	 if($err){
-	    if($force){ warn $err } else { die $err }
-	 }
-	 print chr( $score + $off );
-      }
-      print "\n";
-   }
-}
-close IN;
-

data/utils/enveomics/Scripts/FastQ.split.pl

@@ -1,53 +0,0 @@
-#!/usr/bin/env perl
-#
-# @author Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
-# @license artistic license 2.0
-# @update Jul-05-2015
-#
-
-use warnings;
-use strict;
-use Symbol;
-
-my ($file, $base, $outN) = @ARGV;
-
-$outN ||= 2;
-($file and $base) or die "
-Usage
-   $0 in_file.fq out_base[ no_files]
-   
-   in_file.fq	Input file in FastA format.
-   out_base	Prefix for the name of the output files.  It will
-   		be appended with .<i>.fastq, where <i> is a consecutive
-		number starting in 1.
-   no_files	Number of files to generate.  By default: 2.
-
-";
-
-
-my @outSym = ();
-for my $i (1 .. $outN){
-   $outSym[$i-1] = gensym;
-   open $outSym[$i-1], ">", "$base.$i.fastq" or die "I can not create the file: $base.$i.fa: $!\n";
-}
-
-
-my($i, $seq) = (-1, '');
-open FILE, "<", $file or die "I can not read the file: $file: $!\n";
-while(my $ln=<FILE>){
-   if($.%4 == 1){
-      print { $outSym[$i % $outN] } $seq if $seq;
-      $i++;
-      $seq = '';
-   }
-   $seq.=$ln;
-}
-print { $outSym[$i % $outN] } $seq if $seq;
-close FILE;
-
-for(my $j=0; $j<$outN; $j++){
-   close $outSym[$j];
-}
-
-print STDERR "Sequences: ".($i+1)."\nFiles: $outN\n";
-

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

@@ -1,63 +0,0 @@
-#!/usr/bin/env ruby
-
-#
-# @author: Luis M. Rodriguez-R
-# @update: Feb-06-2015
-# @license: artistic license 2.0
-#
-
-require 'optparse'
-
-o = {:q=>FALSE, :p=>"", :s=>""}
-ARGV << '-h' if ARGV.size==0
-OptionParser.new do |opts|
-   opts.banner = "
-Generates easy-to-parse tagged reads from FastQ files.
-
-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 ""
-end.parse!
-abort "-i is mandatory" if o[:in].nil?
-abort "-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
-rescue => err
-   $stderr.puts "Exception: #{err}\n\n"
-   err.backtrace.each { |l| $stderr.puts l + "\n" }
-   err
-end
-
-

data/utils/enveomics/Scripts/FastQ.test-error.rb

@@ -1,81 +0,0 @@
-#!/usr/bin/env ruby
-
-require 'optparse'
-
-o = {q:false, key:2}
-ARGV << '-h' if ARGV.empty?
-OptionParser.new do |opts|
-   opts.banner = "
-Compares the estimated error of sequencing reads (Q-score) with
-observed mismatches (identity against a know reference sequence).
-
-Usage: #{$0} [options]"
-  opts.separator ""
-  opts.separator "Mandatory"
-  opts.on("-f", "--fastq FILE",
-       "Path to the FastQ file containing the sequences."){ |v| o[:fastq] = v }
-  opts.on("-b", "--blast FILE",
-       "Path to the tabular BLAST file mapping reads to reference sequences."
-       ){ |v| o[:blast] = v }
-  opts.on("-o", "--out FILE",
-      "Path to the output tab-delimited file to create."){ |v| o[:out] = v }
-  opts.separator ""
-  opts.separator "Other Options"
-  opts.on("-q", "--quiet", "Run quietly (no STDERR output)"){ o[:q] = TRUE }
-  opts.on("-h", "--help", "Display this screen") do
-    puts opts
-    exit
-  end
-  opts.separator ""
-end.parse!
-abort "-f is mandatory" if o[:fastq].nil?
-abort "-b is mandatory" if o[:blast].nil?
-abort "-o is mandatory" if o[:out].nil?
-
-# Read the Q scores and estimate expected mismatches
-mm = {} # <- Hash with read IDs as key, and arrays as values:
-        #    [ expected mismatches, variance of mismatches, length ]
-$stderr.puts "Reading FastQ file" unless o[:q]
-File.open(o[:fastq], "r") do |fh|
-  id = nil
-  fh.each_line do |ln|
-    case $.%4
-    when 1
-      ln =~ /^@(\S+)/ or raise "Unexpected defline format: #{ln}"
-      id = $1
-      $stderr.print " #{mm.size} reads...\r" unless o[:q]
-    when 0
-      ln.chomp!
-      # I'm assuming ALWAYS Phred+33!!!
-      p = ln.split('').map{ |i| (i.ord - 33).to_f }.map{ |q| 10.0**(-q/10.0) }
-      mu = p.inject(:+)
-      var = p.map{ |i| i*(1.0-i) }.inject(:+)
-      mm[id] = [mu, var, p.size]
-    end
-  end
-  $stderr.puts " Found: #{mm.size} reads." unless o[:q]
-end
-
-ofh = File.open(o[:out], "w")
-ofh.puts %w[id obs_subs obs_id aln_len obs_ins obs_del obs_gap mu var len].join("\t")
-
-# Read Identities and compare against expectation
-$stderr.puts "Reading Tabular BLAST file" unless o[:q]
-File.open(o[:blast], "r") do |fh|
-  k = 0
-  fh.each_line do |ln|
-    r = ln.chomp.split("\t")
-    id = r[0]
-    next if mm[id].nil?
-    k += 1
-    $stderr.print " #{k} alignments...\r" unless o[:q]
-    obs_m = r[4].to_i + (r[6].to_i - 1) + (mm[id][2] - r[7].to_i)
-    obs_del = r[3].to_i - (r[7].to_i - r[6].to_i).abs
-    obs_ins = r[3].to_i - (r[9].to_i - r[8].to_i).abs
-    ofh.puts ([id, obs_m, r[2], r[7].to_i - r[6].to_i + 1,
-          obs_ins, obs_del, r[5]] + mm[id]).join("\t")
-  end
-  $stderr.puts " Found #{k} alignments." unless o[:q]
-end
-
-ofh.close