miga-base 0.3.0.0 → 0.3.0.1

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

@@ -0,0 +1,60 @@
+#!/usr/bin/env perl
+# 
+# @author  Luis M. Rodriguez-R
+# @update  Oct-07-2015
+# @license artistic license 2.0
+# 
+
+use warnings;
+use strict;
+
+my($file, $content, $stretch) = @ARGV;
+$file or die <<HELP
+
+Description:
+   Filter sequences by N-content and presence of long homopolymers.
+Usage:
+   $0 sequences.fa [content [stretch]] > filtered.fa
+Where:
+   sequences.fa	Input file in FastA format
+   content	A number between 0 and 1 indicating the maximum proportion of Ns
+   		(1 to turn off, 0.5 by default)
+   stretch	A number indicating the maximum number of consecutive identical
+   		nucleotides allowed (0 to turn off, 100 by default)
+   filtered.fa	Filtered set of sequences.
+
+HELP
+;
+($content ||= 0.5)+=0;
+($stretch ||= 100)+=0;
+
+my $good = 0;
+my $N = 0;
+
+FASTA: {
+   local $/ = "\n>";
+   open FILE, "<", $file or die "I can not open the file: $file: $!\n";
+   SEQ: while(<FILE>){
+      $N++;
+      s/^;.*//gm;
+      s/>//g;
+      my($n,$s) = split /\n/, $_, 2;
+      (my $clean = $s) =~ s/[^ACTGN]//g;
+      if($content < 1){
+         (my $Ns = $clean) =~ s/[^N]//g;
+	 next SEQ if length($Ns)>length($clean)*$content;
+      }
+      if($stretch > 0){
+         for my $nuc (qw(A C T G N)){
+	    next SEQ if $clean =~ m/[$nuc]{$stretch}/;
+	 }
+      }
+      print ">$n\n$s\n";
+      $good++;
+   }
+   close FILE;
+   print STDERR "Total sequences: $N\nAfter filtering: $good\n";
+}
+
+
+

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

@@ -0,0 +1,92 @@
+#!/usr/bin/env ruby
+
+# @author  Luis M. Rodriguez-R
+# @license artistic license 2.0
+
+$:.push File.expand_path("../lib", __FILE__)
+require "enveomics_rb/enveomics"
+require "enveomics_rb/stat"
+
+o = {q:false, completeness:nil, minlen:500, shuffle:true}
+OptionParser.new do |opts|
+  opts.banner = "
+Simulates incomplete (fragmented) drafts from complete genomes.
+
+Usage: #{$0} [options]"
+  opts.separator ""
+  opts.separator "Mandatory"
+  opts.on("-i", "--in FILE",
+    "Path to the FastA file containing the complete sequences."
+    ){ |v| o[:in] = v }
+  opts.on("-o", "--out FILE", "Path to the FastA to create."){ |v| o[:out] = v }
+  opts.on("-c", "--completeness FLOAT",
+    "Fraction of genome completeness to simulate from 0 to 1."
+    ){ |v| o[:completeness] = v.to_f }
+  opts.separator ""
+  opts.separator "Options"
+  opts.on("-m", "--minlen INT",
+    "Minimum fragment length to report. By default: #{o[:minlen]}."
+    ){ |v| o[:minlen] = v.to_i }
+  opts.on("-s", "--sorted", "Keep fragments sorted as in the input file. ",
+    "By default, fragments are shuffled."){ |v| o[:shuffle] = !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!
+abort "-i is mandatory" if o[:in].nil?
+abort "-o is mandatory" if o[:out].nil?
+abort "-c is mandatory" if o[:completeness].nil?
+
+begin
+  # Read input sequences
+  g_id  = []
+  g_seq = []
+  File.open(o[:in], "r") do |ifh|
+    id = ""
+    ifh.each_line do |ln|
+      if ln =~ /^>(\S*)/
+        g_id  << $1
+        g_seq << ""
+      else
+        g_seq[g_seq.size-1] += ln.gsub(/[^A-Za-z]/,"")
+      end
+    end
+  end
+  
+  # Fragment genomes
+  f = {}
+  binlen = [1, (o[:minlen].to_f/(1.5**2)).ceil].max
+  p = [0.001, [1.0, 1.0 - (o[:completeness]/1.25 + 0.1)].min].max
+  while not g_seq.empty?
+    id  = g_id.shift
+    seq = g_seq.shift
+    gL  = seq.length
+    while not seq.empty?
+      fL = [0, ((Enve::Stat.r_geom(p).to_f +
+                  Enve::Stat.r_unif(-0.5,0.5))*binlen).round].max
+      f["#{f.size+1}_#{id}"] = seq[0,fL] if fL >= o[:minlen]
+      seq = seq[(fL+1) .. -1]
+      seq = "" if seq.nil?
+    end
+  end
+
+  # Save output
+  k = f.keys
+  k.shuffle! if o[:shuffle]
+  File.open(o[:out], "w") do |ofh|
+    k.each do |id|
+      ofh.puts ">#{id}"
+      ofh.puts f[id].gsub(/(\S{50})/, "\\1\n")
+    end
+  end
+  
+rescue => err
+   $stderr.puts "Exception: #{err}\n\n"
+   err.backtrace.each { |l| $stderr.puts l + "\n" }
+   err
+end
+
+

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 +1,87 @@
+#!/usr/bin/env perl
+
+# Interpose 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.
+# Please 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 $eval_T variable 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 $eval_T accordingly.
+# 
+# @author Luis M. Rodriguez-R
+# @version 1.0
+# @created Nov-27-2012
+# @update Mar-23-2015
+# @license artistic license 2.0
+# 
+# Usage: FastQ.interpose.pl <output_fastq> <input_fastq_1> <input_fastq_2> [additional input files...]
+
+use strict;
+use warnings;
+use Symbol;
+
+my $HELP = <<HELP
+  Usage:
+     $0 <output_fasta> <input_fasta_1> <input_fasta_2> [additional input files...]
+
+  Where,
+     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;	# Period (in number of entries) of evaluation for consistency of the names.
+			# To turn off evaluation set to 0 (zero).
+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.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;
+