miga-base 0.3.6.0 → 0.3.6.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 8b285b9906876a9f1b5366f929a4776d1689dbc1
-  data.tar.gz: 83b6843d00417fef4a8de18e4a102ad4d1899f0d
+SHA256:
+  metadata.gz: c629b49cedd42f76fd8c466ecbc561e915dcaeef9dbbc2140f66300ac21c4e86
+  data.tar.gz: 2174cd7e010340ea865b7ec251a9d8b2823a059bbcec782924052a5da0c0a247
 SHA512:
-  metadata.gz: acfa6eb243f7fa8985cb649ab3b701db68515e8a18c221d94cb149e51cddeec49642b6176da46956765cca8f1961aa88d71b5cb9625131cf64f9287e79e173c6
-  data.tar.gz: 4ac1f2f81854959679b53d4865efba3a36ddca14216ff9f2aef06e1c27b7b415b47c833387e73ddf3cae41369f382146f1041b9a833743d58d3aad0a954bd1ab
+  metadata.gz: f20e4c7312402beec67de7a458356f76bd932edbeadffdee83061d040c8eaaddf31ada6304873638237ca299b806054e7de9656ecfebaeaa7e8e5ddb83710a93
+  data.tar.gz: 5dcae9006b7b84d75ce05019f9ac3f6defe4305c52f574a7c3426a3f8ee098ee4cd0ecf0968d5669066886fbc77185cd477ea265df5509eaf66733e2d4dfb421

data/actions/stats.rb

@@ -127,8 +127,6 @@ if o[:compute]
       end
       d.save
     end
-  when :distances
-    d.cleanup_distances! unless d.nil?
   else
     stats = nil
   end

data/lib/miga/version.rb

@@ -1,5 +1,5 @@
 
-require "date"
+require 'date'
 
 ##
 # High-level minimal requirements for the MiGA::MiGA class.
@@ -10,11 +10,11 @@ module MiGA
   # - Float representing the major.minor version.
   # - Integer representing gem releases of the current version.
   # - Integer representing minor changes that require new version number.
-  VERSION = [0.3, 6, 0]
+  VERSION = [0.3, 6, 1]
   
   ##
   # Nickname for the current major.minor version.
-  VERSION_NAME = "tinge"
+  VERSION_NAME = 'tinge'
   
   ##
   # Date of the current gem release.

data/scripts/clade_finding.bash

@@ -11,6 +11,9 @@ cd "$PROJECT/data/10.clades/01.find"
 # Initialize
 miga date > "miga-project.start"
 
+# Cleanup databases
+ruby -I "$MIGA/lib" "$MIGA/utils/cleanup-databases.rb" "$PROJECT" "$CORES"
+
 # Run
 ruby -I "$MIGA/lib" "$MIGA/utils/subclades.rb" "$PROJECT" "$SCRIPT"
 

data/utils/cleanup-databases.rb

@@ -0,0 +1,25 @@
+#!/usr/bin/env ruby
+
+require 'thread'
+require 'miga'
+
+ARGV[1] or abort "Usage: #{$0} path/to/project threads"
+
+$stderr.puts "Cleaning databases..."
+ds_list = MiGA::Project.load(ARGV[0]).datasets.
+  select(&:is_ref?).select(&:is_active?)
+
+thr = ARGV[1].to_i
+
+(0 .. thr-1).each do |t|
+  fork do
+    k = -1
+    ds_list.each do |i|
+      k = (k+1) % thr
+      next unless k == t
+      i.cleanup_distances!
+    end
+  end
+end
+Process.waitall
+

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

@@ -0,0 +1 @@
+utils/enveomics/Pipelines/assembly.pbs/../../Scripts/FastA.N50.pl

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

@@ -0,0 +1 @@
+utils/enveomics/Pipelines/assembly.pbs/../../Scripts/FastA.filterN.pl

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

@@ -0,0 +1 @@
+utils/enveomics/Pipelines/assembly.pbs/../../Scripts/FastA.length.pl

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

@@ -0,0 +1 @@
+utils/enveomics/Pipelines/blast.pbs/../../Scripts/FastA.split.pl

data/utils/enveomics/Scripts/lib/enveomics.R

@@ -0,0 +1 @@
+utils/enveomics/Scripts/lib/../../enveomics.R

data/utils/subclade/pipeline.rb

@@ -26,16 +26,18 @@ module MiGA::SubcladeRunner::Pipeline
       `ogs.mcl.rb -o '#{ogs_file}.tmp' --abc '#{abc_path}' -t '#{opts[:thr]}'`
       File.open(ogs_file, 'w') do |fh|
         File.foreach("#{ogs_file}.tmp").with_index do |ln, lno|
-          fh.puts ln if lno != 0
+          fh.puts ln if lno > 0
         end
       end
       File.unlink "#{ogs_file}.tmp"
     end
 
     # Find species medoids
-    src = File.expand_path('utils/find-medoid.R', MiGA::MiGA.root_path)
-    `Rscript '#{src}' miga-project.dist.rdata \
-      miga-project.ani95-medoids miga-project.ani95-clades`
+    if File.size? 'miga-project.dist.rdata'
+      src = File.expand_path('utils/find-medoid.R', MiGA::MiGA.root_path)
+      `Rscript '#{src}' miga-project.dist.rdata \
+        miga-project.ani95-medoids miga-project.ani95-clades`
+    end
 
     # Propose clades
     ofh = File.open('miga-project.proposed-clades', 'w')

data/utils/subclades.R

@@ -22,11 +22,11 @@ subclades <- function(ani_file, out_base, thr = 1, ani.d = dist(0), sel = NA) {
     if(length(ani.d) == 0 && !file.exists(dist_rdata)){
       # Read from ani_file
       a <- read.table(gzfile(ani_file), sep = '\t', header = TRUE, as.is = TRUE)
-      if(nrow(a)==0){
+      if(nrow(a) == 0){
         generate_empty_files(out_base)
         return(NULL)
       }
-      if(!is.na(sel) and file.exists(sel)){
+      if(!is.na(sel) && file.exists(sel)){
         say('Filter selection')
         lab <- read.table(sel, sep='\t', head=FALSE, as.is=TRUE)[,1]
         a <- a[a$a %in% lab & a$b %in% lab, ]

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: miga-base
 version: !ruby/object:Gem::Version
-  version: 0.3.6.0
+  version: 0.3.6.1
 platform: ruby
 authors:
 - Luis M. Rodriguez-R
@@ -188,6 +188,7 @@ files:
 - test/test_helper.rb
 - utils/adapters.fa
 - utils/arch-ess-genes.rb
+- utils/cleanup-databases.rb
 - utils/core-pan-plot.R
 - utils/distance/base.rb
 - utils/distance/commands.rb
@@ -341,6 +342,7 @@ files:
 - utils/enveomics/Scripts/gi2tax.rb
 - utils/enveomics/Scripts/in_silico_GA_GI.pl
 - utils/enveomics/Scripts/lib/data/essential.hmm.gz
+- utils/enveomics/Scripts/lib/enveomics.R
 - utils/enveomics/Scripts/lib/enveomics_rb/enveomics.rb
 - utils/enveomics/Scripts/lib/enveomics_rb/jplace.rb
 - utils/enveomics/Scripts/lib/enveomics_rb/og.rb
@@ -495,7 +497,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.2.2
+rubygems_version: 2.7.7
 signing_key: 
 specification_version: 4
 summary: MiGA

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

@@ -1,56 +0,0 @@
-#!/usr/bin/env perl
-#
-# @author: Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
-# @update: Oct 07 2015
-# @license: artistic license 2.0
-#
-use strict;
-use warnings;
-use List::Util qw/sum min max/;
-
-my ($seqs, $minlen, $n__) = @ARGV;
-$seqs or die "
-Description:
-   Calculates the N50 value of a set of sequences.  Alternatively, it
-   can calculate other N** values.  It also calculates the total number
-   of sequences and the total added length.
-   
-Usage:
-   $0 seqs.fa[ minlen[ **]]
-
-   seqs.fa	A FastA file containing the sequences.
-   minlen	(optional) The minimum length to take into consideration.
-   		By default: 0.
-   **		Value N** to calculate.  By default: 50 (N50).
-";
-$minlen ||= 0;
-$n__    ||= 50;
-
-my @len = ();
-open SEQ, "<", $seqs or die "Cannot open file: $seqs: $!\n";
-while(<SEQ>){
-   if(/^>/){
-      push @len, 0;
-   }else{
-      next if /^;/;
-      chomp;
-      s/\W//g;
-      $len[-1]+=length $_;
-   }
-}
-close SEQ;
-@len = sort { $a <=> $b } map { $_>=$minlen?$_:() } @len;
-my $tot = (sum(@len) || 0);
-
-my $thr = $n__*$tot/100;
-my $pos = 0;
-for(@len){
-   $pos+= $_;
-   if($pos>=$thr){
-      print "N$n__: $_\n";
-      last;
-   }
-}
-print "Sequences: ".scalar(@len)."\n";
-print "Total length: $tot\n";
-

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

@@ -1,60 +0,0 @@
-#!/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/Pipelines/assembly.pbs/FastA.length.pl

@@ -1,38 +0,0 @@
-#!/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/Pipelines/blast.pbs/FastA.split.pl

@@ -1,55 +0,0 @@
-#!/usr/bin/env perl
-#
-# @author Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
-# @update Oct-13-2015
-# @license artistic license 2.0
-#
-
-use warnings;
-use strict;
-use Symbol;
-
-my ($file, $base, $outN) = @ARGV;
-
-$outN ||= 12;
-($file and $base) or die "
-Usage
-   $0 in_file.fa out_base[ no_files]
-   
-   in_file.fa	Input file in FastA format.
-   out_base	Prefix for the name of the output files.  It will
-   		be appended with .<i>.fa, where <i> is a consecutive
-		number starting in 1.
-   no_files	Number of files to generate.  By default: 12.
-
-";
-
-
-my @outSym = ();
-for my $i (1 .. $outN){
-   $outSym[$i-1] = gensym;
-   open $outSym[$i-1], ">", "$base.$i.fa" 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>){
-   next if $ln=~/^;/;
-   if($ln =~ m/^>/){
-      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";
-