miga-base 0.7.26.0 → 1.0.0.1

data/utils/enveomics/Scripts/FastA.gc.pl

@@ -0,0 +1,42 @@
+#!/usr/bin/env perl
+#
+# @author  Luis M Rodriguez-R
+# @update  Mar-23-2016
+# @license artistic license 2.0
+#
+
+use warnings;
+use strict;
+
+$#ARGV>=0 or die "
+Usage:
+   $0 seqs.fa... > gc.txt
+
+   seqs.fa	One or more FastA files.
+   gc.txt	A table with the G+C content of the sequences.
+
+";
+
+for my $fa (@ARGV){
+   open FA, "<", $fa or die "Cannot open file: $fa: $!\n";
+   my $def = "";
+   my $len = 0;
+   my $gc  = 0;
+   while(<FA>){
+      next if /^;/;
+      if(m/^>(\S*)/){
+         print "$def\t".($gc/$len)."\n" if $len;
+	 $def = $1;
+	 $len = 0;
+	 $gc  = 0;
+      }else{
+         s/[^ACTGactg]//g;
+	 $len += length $_;
+	 s/[^GC]//g;
+	 $gc  += length $_;
+      }
+   }
+   print "$def\t".($gc/$len)."\n" if $len;
+   close FA;
+}
+

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

@@ -0,0 +1,93 @@
+#!/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 FastA 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_fasta> <input_fasta_1> <input_fasta_2> [additional input files...]
+
+  Where,
+    -T <int>		: Optional.  Integer indicating the sampling period for
+    			  names evaluation (see Description above).
+			  By default: 1000.
+    output_fasta	: Output file
+    input_fasta_1	: First FastA file
+    input_fasta_2	: Second FastA file
+    ... 		: Any additional FastA 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 $out = shift @ARGV;
+my @in = @ARGV;
+$/ = "\n>";
+
+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 $ln = readline($in_fh[$k]);
+      last LINE if $k==0 and not defined $ln;
+      defined $ln or die "Impossible to read next entry ($.) from $in[$k]: $!\n";
+      $ln =~ s/^\>?/>/;
+      $ln =~ s/\>$//;
+      $ln =~ s/^;.*//gm;
+      if($eval_T and not $i % $eval_T){
+	 unless($name){
+	    $ln =~ m/^>(.*?)[\/ \\_]\d+/ or die "Impossible to evaluate names!\n offending entry:\n$ln\n";
+	    $name = $1;
+	 }
+	 die "Inconsistent name!\n base name is $name\n offending entry is:\n$ln\n" unless $ln =~ /^>$name/;
+      }
+      unless($frl){
+         $ln =~ m/^>.*?\n(.*?)\n/ or die "Unexpected format!\n offending entry:\n$ln\n";
+	 my $i = $ln;
+	 $i =~ s/^>.*?\n//;
+	 $i =~ s/\n//g;
+	 $frl = length $i;
+      }
+      print OUT $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/FastA.length.pl

@@ -0,0 +1,38 @@
+#!/usr/bin/env perl
+#
+# @author  Luis M Rodriguez-R
+# @update  Oct-07-2015
+# @license artistic license 2.0
+#
+
+use warnings;
+use strict;
+
+$#ARGV>=0 or die "
+Usage:
+   $0 seqs.fa... > length.txt
+
+   seqs.fa	One or more FastA files.
+   length.txt	A table with the lengths of the sequences.
+
+";
+
+for my $fa (@ARGV){
+   open FA, "<", $fa or die "Cannot open file: $fa: $!\n";
+   my $def = '';
+   my $len = 0;
+   while(<FA>){
+      next if /^;/;
+      if(m/^>(\S+)\s?/){
+         print "$def\t$len\n" if $def;
+	 $def = $1;
+	 $len = 0;
+      }else{
+         s/[^A-Za-z]//g;
+	 $len+= length $_;
+      }
+   }
+   print "$def\t$len\n" if $def;
+   close FA;
+}
+

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.per_file.pl

@@ -0,0 +1,36 @@
+#!/usr/bin/env perl
+#
+# @author  Luis M Rodriguez-R
+# @update  Mar-17-2016
+# @license artistic license 2.0
+#
+
+use warnings;
+use strict;
+
+$#ARGV>=1 or die "
+Usage:
+   $0 outdir seqs.fa...
+
+   outdir	Output directory for the individual files.
+   seqs.fa	One or more FastA files.
+
+";
+
+my $dir = shift @ARGV;
+
+for my $fa (@ARGV){
+   open FA, "<", $fa or die "Cannot open file: $fa: $!\n";
+   my $file = '';
+   while(<FA>){
+      next if /^;/;
+      if(m/^>(\S+)\s?/){
+	 close ONE if $file;
+         $file = $dir."/".$1.".fasta";
+	 open ONE, ">", $file or die "Cannot open file: $file: $!\n";
+      }
+      print ONE $_ if $file;
+   }
+   close ONE if $file;
+}
+

data/utils/enveomics/Scripts/FastA.qlen.pl

@@ -0,0 +1,57 @@
+#!/usr/bin/env perl
+#
+# @author  Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
+# @update  Dec-22-2015
+# @license artistic license 2.0
+#
+use strict;
+use warnings;
+use List::Util qw/sum min max/;
+
+my ($seqs, $minlen) = @ARGV;
+$seqs or die "
+Description:
+   Calculates the quartiles of the length in a set of sequences.  The Q2 is
+   also known as the median.  Q0 is the minimum length, and Q4 is the maximum
+   length.  It also calculates TOTAL, the added length of the sequences in
+   the file, and AVG, the average length.
+   
+Usage:
+   $0 seqs.fa[ minlen]
+
+   seqs.fa	A FastA file containing the sequences.
+   minlen	(optional) The minimum length to take into consideration.
+   		By default: 0.
+
+";
+$minlen ||= 0;
+
+# Read files
+my @len = ();
+open FA, "<", $seqs or die "Cannot open file: $seqs: $!\n";
+my $def = '';
+my $len = 0;
+while(<FA>){
+   next if /^;/;
+   if(m/^>(\S+)\s?/){
+      push(@len, int($len)) if $def and not $len<$minlen;
+      $def = $1;
+      $len = 0;
+   }else{
+      s/[^A-Za-z]//g;
+      $len+= length $_;
+   }
+}
+push(@len, int($len)) if $def and not $len<$minlen;
+close FA;
+
+# Sort and estimates quantiles
+@len = sort { $a <=> $b } @len;
+for my $q (0 .. 4){
+   my $ii = int(my $i = $#len*$q/4);
+   print "Q$q: ".($i==$ii ? $len[$i] : ($len[$ii]+$len[$ii+1])/2 )."\n";
+}
+my $sum = sum @len;
+print "N: ".scalar(@len)."\n";
+print "TOTAL: $sum\n";
+print "AVG: ".($sum/scalar(@len))."\n";

data/utils/enveomics/Scripts/FastA.rename.pl

@@ -0,0 +1,65 @@
+#!/usr/bin/env perl
+#
+# @author  Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
+# @update  Oct-07-2015
+# @license artistic license 2.0
+#
+
+use warnings;
+use strict;
+use Getopt::Std;
+
+sub HELP_MESSAGE { die "
+.Description:
+   Renames a set of sequences in FastA format.
+
+.Usage: $0 [options] list.txt seqs.fa > renamed.fa
+   
+   [options]
+   -f		Filter list.  Ignores sequences NOT present in the list.
+   -q		Runs quietly.
+   -h		Prints this message and exits.
+
+   [mandatory]
+   list.txt	Tab-delimited list of sequences, with the original ID in the
+   		first column and the ID to use in the second.
+   seqs.fa	FastA file containing the superset of sequences.
+   renamed.fa	FastA file to be created.
+
+" }
+
+my %o=();
+getopts('fhq', \%o);
+my($list, $fa) = @ARGV;
+($list and $fa) or &HELP_MESSAGE;
+$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 { my $l=$_; chomp $l; my @r=split(/\t/,$l); $r[0] => $r[1] } <LI>;
+close LI;
+
+print STDERR "Renaming FastA.\n" unless $o{q};
+open FA, "<", $fa or die "Cannot read file: $fa: $!\n";
+my $good = 0;
+while(my $ln = <FA>){
+   next if $ln =~ /^;/;
+   chomp $ln;
+   if($ln =~ m/^>((\S+).*)/){
+      my $rep=0;
+      $rep = ">".$li{$ln} if exists $li{$ln};
+      $rep = ">".$li{$1} if exists $li{$1} and not $rep;
+      $rep = ">".$li{">$1"} if exists $li{">$1"} and not $rep;
+      $rep = ">".$li{$2} if exists $li{$2} and not $rep;
+      if($rep){
+	 $ln = $rep;
+	 $good = 1;
+      }
+   }elsif($ln =~ m/^>/){
+      $good=0;
+      print STDERR "Warning: Non-cannonical defline, line $.: $ln\n";
+   }
+   print "$ln\n" if $good or not $o{f};
+}
+close FA;
+

data/utils/enveomics/Scripts/FastA.revcom.pl

@@ -0,0 +1,23 @@
+#!/usr/bin/env perl
+#
+# @author: Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
+# @update: Dec-25-2015
+# @license: artistic license 2.0
+#
+use strict;
+use warnings;
+use Bio::SeqIO;
+
+($ARGV[0] and $ARGV[0] =~ /--?h(elp)?/) and die "
+Description:
+   Reverse-complement sequences in FastA format.
+
+Usage:
+   $0 < input.fa > output.fa
+
+";
+
+my @len = ();
+my $seqI = Bio::SeqIO->new(-fh => \*STDIN, -format=>"FastA");
+my $seqO = Bio::SeqIO->new(-fh => \*STDOUT, -format=>"FastA");
+while(my $seq = $seqI->next_seq){ $seqO->write_seq($seq->revcom) }