miga-base 0.3.1.6 → 0.3.1.7

data/utils/enveomics/Scripts/aai.rb

@@ -73,7 +73,7 @@ Usage: #{$0} [options]"
     "Path to the directory containing the binaries of the search program."
     ){ |v| o[:bin] = v }
   opts.on("-p", "--program STR",
-    "Search program to be used.  One of: blast+ (default), blast, blat."
+    "Search program to be used. One of: blast+ (default), blast, blat, diamond."
     ){ |v| o[:program] = v }
   opts.on("-t", "--threads INT",
     "Number of parallel threads to be used.  By default: #{o[:thr]}."
@@ -128,6 +128,7 @@ Usage: #{$0} [options]"
 end.parse!
 abort "-1 is mandatory" if o[:seq1].nil?
 abort "-2 is mandatory" if o[:seq2].nil?
+abort "-p diamond is incompatible with -N" if o[:program]=="diamond" && o[:nucl]
 abort "SQLite3 requested (-S) but sqlite3 not supported.  First install gem " +
   "sqlite3." unless o[:sqlite3].nil? or has_sqlite3
 o[:bin] = o[:bin]+"/" if o[:bin].size > 0
@@ -213,7 +214,7 @@ Dir.mktmpdir do |dir|
         o[ "#{seq}name".to_sym ])
     else
       seq_names << ( o[ "#{seq}name".to_sym ].nil? ?
-        File.basename(o[seq], ".faa") :
+        File.basename(o[seq], ".*") :
         o[ "#{seq}name".to_sym ])
     end
     $stderr.puts "  Reading FastA file: #{o[seq]}" unless o[:q]
@@ -236,7 +237,7 @@ Dir.mktmpdir do |dir|
       else
         fo.puts ln
         seq_len[seq][seqs] += ln.chomp.gsub(/[^A-Za-z]/,"").length
-        actg_cnt[seq] += ln.chomp.gsub(/[^ACTGN]/,"").length
+        actg_cnt[seq] += ln.chomp.gsub(/[^ACTGNactgn]/,"").length
       end
     end
     fi.close
@@ -251,13 +252,16 @@ Dir.mktmpdir do |dir|
     minfrg = seqs if minfrg > seqs
     case o[:program].downcase
     when "blast"
-      `"#{o[:bin]}formatdb" -i "#{dir}/#{seq.to_s}.fa" \
+      `"#{o[:bin]}formatdb" -i "#{dir}/#{seq}.fa" \
       -p #{o[:nucl] ? "F" : "T"}`
     when "blast+"
-      `"#{o[:bin]}makeblastdb" -in "#{dir}/#{seq.to_s}.fa" \
+      `"#{o[:bin]}makeblastdb" -in "#{dir}/#{seq}.fa" \
       -dbtype #{o[:nucl] ? "nucl" : "prot"}`
     when "blat"
       # Nothing to do
+    when "diamond"
+      `"#{o[:bin]}diamond" makedb --in "#{dir}/#{seq}.fa" \
+      --db "#{dir}/#{seq}.fa.dmnd" --threads "#{o[:thr]}"`
     else
       abort "Unsupported program: #{o[:program]}."
     end
@@ -288,9 +292,12 @@ Dir.mktmpdir do |dir|
       -max_target_seqs 1 -num_threads #{o[:thr]} -outfmt 6 \
       -out "#{dir}/#{i}.tab"`
     when "blat"
-      `#{o[:bin]}blat "#{s}" "#{q}" #{"-prot" unless o[:nucl]} -out=blast8 \
+      `"#{o[:bin]}blat" "#{s}" "#{q}" #{"-prot" unless o[:nucl]} -out=blast8 \
       "#{dir}/#{i}.tab.uns"`
       `sort -k 1 "#{dir}/#{i}.tab.uns" > "#{dir}/#{i}.tab"`
+    when "diamond"
+      `"#{o[:bin]}diamond" blastp --threads "#{o[:thr]}" --outfmt 6 \
+      --db "#{s}.dmnd" --query "#{q}" --out "#{dir}/#{i}.tab" --more-sensitive`
     else
       abort "Unsupported program: #{o[:program]}."
     end

data/utils/enveomics/Scripts/ani.rb

@@ -193,7 +193,7 @@ Dir.mktmpdir do |dir|
         "ncbi:#{acc[1]}" : o[ "#{seq}name".to_sym ] )
     else
       seq_names << ( o[ "#{seq}name".to_sym ].nil? ?
-        File.basename(o[seq], ".fna") : o[ "#{seq}name".to_sym ] )
+        File.basename(o[seq], ".*") : o[ "#{seq}name".to_sym ] )
     end
     $stderr.puts "  Reading FastA file: #{o[seq]}" unless o[:q]
     sqlite_db.execute("delete from regions where seq=?",
@@ -218,7 +218,7 @@ Dir.mktmpdir do |dir|
       else
         ln.gsub!(/[^A-Za-z]/, '')
         seq_len[seq]  += ln.length
-        actg_cnt[seq] += ln.gsub(/[^ACTGN]/,"").length
+        actg_cnt[seq] += ln.gsub(/[^ACTGNactgn]/,"").length
         buffer = buffer + ln
         while buffer.size > o[:win]
           seq_i = buffer[0, o[:win]]

data/utils/enveomics/Scripts/clust.rand.rb

@@ -0,0 +1,102 @@
+#!/usr/bin/env ruby
+
+#
+# @author: Luis M. Rodriguez-R
+# @license: artistic license 2.0
+#
+
+require "optparse"
+
+o = { q:false, prec:6 }
+ARGV << "-h" if ARGV.empty?
+OptionParser.new do |opts|
+   opts.banner = "
+Calculates the Rand Index and the Adjusted Rand Index between two clusterings.
+
+The clustering format is a raw text file with one cluster per line, each
+defined as comma-delimited members, and a header line (ignored). Note that this
+is equivalent to the OGs format for 1 genome.
+
+Usage: #{$0} [options]"
+  opts.separator ""
+  opts.separator "Mandatory"
+  opts.on("-1", "--clust1 FILE", "First input file."){ |v| o[:clust1]=v }
+  opts.on("-2", "--clust2 FILE", "Second input file."){ |v| o[:clust2]=v }
+  opts.separator ""
+  opts.separator "Other options"
+  opts.on("-p", "--prec INT",
+    "Precision to report. By default: #{o[:prec]}"){ |v| o[:prec]=v.to_i }
+  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 "-1 is mandatory" if o[:clust1].nil?
+abort "-2 is mandatory" if o[:clust2].nil?
+
+def load_clust(file, q)
+  $stderr.puts "Reading clusters in '#{file}'." unless q
+  out = []
+  File.open(file, "r") do |fh|
+    fh.each_line do |ln|
+      next if $.==1
+      out[$.-2] = ln.chomp.split(",")
+    end
+  end
+  $stderr.puts " Loaded clusters: #{out.size}." unless q
+  out
+end
+
+def choose_2(n)
+  return 0 if n<2
+  n*(n-1)/2
+end
+
+##### MAIN:
+begin
+  # Read the pre-computed OGs
+  clust1 = load_clust(o[:clust1], o[:q])
+  clust2 = load_clust(o[:clust2], o[:q])
+  
+  # Contingency table
+  $stderr.puts "Estimating the contingency table." unless o[:q]
+  cont = []
+  b_sums = []
+  clust1.each_with_index do |x_i, i|
+    cont[i] = []
+    clust2.each_with_index do |y_j, j|
+      cont[i][j] = (x_i & y_j).size
+      b_sums[j]||= 0
+      b_sums[j] += cont[i][j]
+    end
+  end
+  a_sums = cont.map{ |i| i.inject(:+) }
+
+  # Calculate variables
+  # - see http://i11www.iti.kit.edu/extra/publications/ww-cco-06.pdf
+  $stderr.puts "Estimating indexes." unless o[:q]
+  n = clust1.map{ |i| i.size }.inject(:+)
+  pairs = choose_2(n)
+  n11 = clust1.each_index.map do |i|
+    clust2.each_index.map do |j|
+      choose_2(cont[i][j])
+    end.inject(:+)
+  end.inject(:+).to_f
+  t1 = a_sums.map{ |a_i| choose_2(a_i) }.inject(:+).to_f
+  t2 = b_sums.map{ |b_j| choose_2(b_j) }.inject(:+).to_f
+  t3 = 2*t1*t2/(n*(n-1))
+  n00 = pairs + n11 - t1 - t2
+  r_index = (n11 + n00)/pairs
+  r_adjusted = (n11 - t3)/((t1+t2)/2 - t3)
+  
+  # Report
+  puts "Rand Index = %.#{o[:prec]}f" % r_index
+  puts "Adjusted Rand Index = %.#{o[:prec]}f" % r_adjusted
+rescue => err
+  $stderr.puts "Exception: #{err}\n\n"
+  err.backtrace.each { |l| $stderr.puts l + "\n" }
+  err
+end
+

data/utils/enveomics/Scripts/lib/enveomics_rb/enveomics.rb

@@ -1,7 +1,6 @@
 
 #
 # @author: Luis M. Rodriguez-R
-# @update: Oct-21-2015
 # @license: artistic license 2.0
 #
 
@@ -9,18 +8,17 @@ require "optparse"
 ARGV << "-h" if ARGV.size==0
 
 def use(gems, mandatory=true)
-   gems = [gems] unless gems.is_a? Array
-   begin
-      require "rubygems"
-      while ! gems.empty?
-         require gems.first
-	 gems.shift
-      end
-      return true
-   rescue LoadError
-      abort "\nUnmet requirements, please install required gems:" +
-	 gems.map{ |gem| "\n   gem install #{gem}" }.join + "\n\n" if mandatory
-      return false
-   end
+  gems = [gems] unless gems.is_a? Array
+  begin
+    require "rubygems"
+    while ! gems.empty?
+      require gems.shift
+    end
+    return true
+  rescue LoadError
+    abort "\nUnmet requirements, please install required gems:" +
+      gems.map{ |gem| "\n   gem install #{gem}" }.join + "\n\n" if mandatory
+    return false
+  end
 end
 

data/utils/enveomics/Scripts/lib/enveomics_rb/jplace.rb

@@ -124,7 +124,7 @@ module JPlace
 	 @nwk = nwk
 	 @parent = parent
 	 @placements = []
-	 @collapsed = FALSE
+	 @collapsed = false
 	 # Find index
 	 index_m = /^(?<pre>.*){(?<idx>[0-9]+)}(?<post>[^\(\),;]*);?$/.match(nwk)
 	 if index_m.nil? and parent.nil? and nwk[nwk.length-1]==';'
@@ -239,7 +239,7 @@ module JPlace
 	       end
 	    end
 	 end
-	 @collapsed = TRUE
+	 @collapsed = true
       end
       def add_placement!(placement)
 	 @placements << placement

data/utils/enveomics/Scripts/rbm.rb

@@ -29,17 +29,17 @@ Usage: #{$0} [options]"
       "Sequences are assumed to be nucleotides (proteins by default)."
       ){ |v| o[:nucl] = true }
    opts.on("-l", "--len INT",
-      "Minimum alignment length (in residues).  By default: #{o[:len].to_s}."
+      "Minimum alignment length (in residues).  By default: #{o[:len]}."
       ){ |v| o[:len] = v.to_i }
    opts.on("-f", "--fract FLOAT",
-      "Minimum alignment length (as a fraction of the query). If set, " +
-      "requires BLAST+ (see -p).  By default: #{o[:fract].to_s}."
+      "Minimum alignment length (as a fraction of the query).",
+      "If set, requires BLAST+ or Diamond (see -p).  By default: #{o[:fract]}."
       ){ |v| o[:fract] = v.to_i }
    opts.on("-i", "--id NUM",
       "Minimum alignment identity (in %).  By default: #{o[:id].to_s}."
       ){ |v| o[:id] = v.to_f }
    opts.on("-s", "--score NUM",
-      "Minimum alignment score (in bits).  By default: #{o[:score].to_s}."
+      "Minimum alignment score (in bits).  By default: #{o[:score]}."
       ){ |v| o[:score] = v.to_f }
    opts.separator ""
    opts.separator "Software Options"
@@ -47,7 +47,7 @@ Usage: #{$0} [options]"
       "Path to the directory containing the binaries of the search program."
       ){ |v| o[:bin] = v }
    opts.on("-p", "--program STR",
-      "Search program to be used.  One of: blast+ (default), blast."
+      "Search program to be used.  One of: blast+ (default), blast, diamond."
       ){ |v| o[:program] = v }
    opts.on("-t", "--threads INT",
       "Number of parallel threads to be used.  By default: #{o[:thr]}."
@@ -63,8 +63,9 @@ Usage: #{$0} [options]"
 end.parse!
 abort "-1 is mandatory" if o[:seq1].nil?
 abort "-2 is mandatory" if o[:seq2].nil?
-abort "Argument -f/--fract requires -p blast+" if
-   o[:fract]>0 and o[:program]!="blast+"
+abort '-p diamond is incompatible with -n' if o[:program]=='diamond' && o[:nucl]
+abort 'Argument -f/--fract requires -p blast+ or -p diamond' if
+   o[:fract]>0 and o[:program]!='blast+' and o[:program]!='diamond'
 o[:bin] = o[:bin]+"/" if o[:bin].size > 0
 
 Dir.mktmpdir do |dir|
@@ -74,12 +75,15 @@ Dir.mktmpdir do |dir|
    $stderr.puts "Creating databases." unless o[:q]
    [:seq1, :seq2].each do |seq|
       case o[:program].downcase
-      when "blast"
-         `"#{o[:bin]}formatdb" -i "#{o[seq]}" -n "#{dir}/#{seq.to_s}" \
+      when 'blast'
+         `"#{o[:bin]}formatdb" -i "#{o[seq]}" -n "#{dir}/#{seq}" \
 	 -p #{(o[:nucl]?"F":"T")}`
-      when "blast+"
-         `"#{o[:bin]}makeblastdb" -in "#{o[seq]}" -out "#{dir}/#{seq.to_s}" \
+      when 'blast+'
+         `"#{o[:bin]}makeblastdb" -in "#{o[seq]}" -out "#{dir}/#{seq}" \
 	 -dbtype #{(o[:nucl]?"nucl":"prot")}`
+      when 'diamond'
+         `"#{o[:bin]}diamond" makedb --in "#{dir}/#{seq}.fa" \
+         --db "#{dir}/#{seq}.fa.dmnd" --threads "#{o[:thr]}"`
       else
          abort "Unsupported program: #{o[:program]}."
       end
@@ -95,14 +99,19 @@ Dir.mktmpdir do |dir|
       s = "#{dir}/seq#{i==1?2:1}"
       $stderr.puts "  Query: #{q}." unless o[:q]
       case o[:program].downcase
-      when "blast"
+      when 'blast'
 	 `"#{o[:bin]}blastall" -p #{o[:nucl]?"blastn":"blastp"} -d "#{s}" \
 	 -i "#{q}" -v 1 -b 1 -a #{o[:thr]} -m 8 -o "#{dir}/#{i}.tab"`
-      when "blast+"
+      when 'blast+'
 	 `"#{o[:bin]}#{o[:nucl]?"blastn":"blastp"}" -db "#{s}" -query "#{q}" \
 	 -max_target_seqs 1 -num_threads #{o[:thr]} -out "#{dir}/#{i}.tab" \
 	 -outfmt "6 qseqid sseqid pident length mismatch gapopen qstart qend \
 	 sstart send evalue bitscore qlen slen"`
+      when 'diamond'
+         `"#{o[:bin]}diamond" blastp --threads "#{o[:thr]}" \
+         --outfmt "6 qseqid sseqid pident length mismatch gapopen qstart qend \
+         sstart send evalue bitscore qlen slen" --db "#{s}.dmnd" \
+         --query "#{q}" --out "#{dir}/#{i}.tab" --more-sensitive`
       else
 	 abort "Unsupported program: #{o[:program]}."
       end
@@ -111,7 +120,7 @@ Dir.mktmpdir do |dir|
       fh.each_line do |ln|
 	 ln.chomp!
 	 row = ln.split(/\t/)
-	 row[12] = "1" if o[:program]!="blast+"
+	 row[12] = "1" unless %w[blast+ diamond].include? o[:program]
 	 if qry_seen[ row[0] ].nil? and row[3].to_i >= o[:len] and
 	       row[2].to_f >= o[:id] and row[11].to_f >= o[:score] and
 	       row[3].to_f/row[12].to_i >= o[:fract]

data/utils/enveomics/enveomics.R/DESCRIPTION

@@ -1,5 +1,5 @@
 Package: enveomics.R
-Version: 1.1.5
+Version: 1.1.6
 Authors@R: c(person("Luis M.","Rodriguez-R",role=c("aut","cre"),
 	   email="lmrodriguezr@gmail.com"))
 Title: Various Utilities for Microbial Genomics and Metagenomics

data/utils/enveomics/enveomics.R/R/barplot.R

@@ -82,7 +82,7 @@ enve.barplot <- structure(function(
           rainbow(min(colors.per.group*2, top)-colors.per.group, s=3/4, v=3/5))
     if(top > colors.per.group*2) color.col <- c(color.col,
           rainbow(top-colors.per.group*2, s=1, v=1.25/4))
-  }else if(length(col)==1 & col=='coto'){
+  }else if(length(col)==1 & col[1]=="coto"){
     color.col <- c("#5BC0EB","#FDE74C","#9BC53D","#E55934","#FA7921","#EF476F",
                     "#FFD166","#06D6A0","#118AB2","#073B4C","#264653","#2A9D8F",
                     "#E9C46A","#F4A261","#E76F51")
@@ -102,7 +102,7 @@ enve.barplot <- structure(function(
     col=rev(c(color.col, rep(other.col, nrow(p)-length(color.col)))),
     border=NA,space=ifelse(add.trend,ifelse(organic.trend,0.75,0.5),0.2), ...)
   if(add.trend || min.report < max(p)){
-    color.alpha <- paste(c(substr(color.col, 1, 7), other.col), '40', sep='')
+    color.alpha <- enve.col.alpha(c(color.col, other.col), 1/4)
     if(top < nrow(p)){
       cf <- colSums(p[1:(nrow(p)-top), ])
     }else{

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: miga-base
 version: !ruby/object:Gem::Version
-  version: 0.3.1.6
+  version: 0.3.1.7
 platform: ruby
 authors:
 - Luis M. Rodriguez-R
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-01-23 00:00:00.000000000 Z
+date: 2018-03-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rest-client
@@ -157,6 +157,8 @@ files:
 - lib/miga/project/result.rb
 - lib/miga/remote_dataset.rb
 - lib/miga/result.rb
+- lib/miga/result/base.rb
+- lib/miga/result/dates.rb
 - lib/miga/tax_dist.rb
 - lib/miga/tax_index.rb
 - lib/miga/taxonomy.rb
@@ -209,6 +211,7 @@ files:
 - utils/enveomics/Manifest/Tasks/fasta.json
 - utils/enveomics/Manifest/Tasks/fastq.json
 - utils/enveomics/Manifest/Tasks/graphics.json
+- utils/enveomics/Manifest/Tasks/mapping.json
 - utils/enveomics/Manifest/Tasks/ogs.json
 - utils/enveomics/Manifest/Tasks/other.json
 - utils/enveomics/Manifest/Tasks/remote.json
@@ -259,6 +262,7 @@ files:
 - utils/enveomics/Scripts/Aln.cat.rb
 - utils/enveomics/Scripts/Aln.convert.pl
 - utils/enveomics/Scripts/AlphaDiversity.pl
+- utils/enveomics/Scripts/BedGraph.tad.rb
 - utils/enveomics/Scripts/BlastPairwise.AAsubs.pl
 - utils/enveomics/Scripts/BlastTab.addlen.rb
 - utils/enveomics/Scripts/BlastTab.advance.bash
@@ -294,6 +298,7 @@ files:
 - utils/enveomics/Scripts/FastA.revcom.pl
 - utils/enveomics/Scripts/FastA.slider.pl
 - utils/enveomics/Scripts/FastA.split.pl
+- utils/enveomics/Scripts/FastA.split.rb
 - utils/enveomics/Scripts/FastA.subsample.pl
 - utils/enveomics/Scripts/FastA.tag.rb
 - utils/enveomics/Scripts/FastA.wrap.rb
@@ -302,6 +307,7 @@ files:
 - utils/enveomics/Scripts/FastQ.offset.pl
 - utils/enveomics/Scripts/FastQ.split.pl
 - utils/enveomics/Scripts/FastQ.tag.rb
+- utils/enveomics/Scripts/FastQ.test-error.rb
 - utils/enveomics/Scripts/FastQ.toFastA.awk
 - utils/enveomics/Scripts/GenBank.add_fields.rb
 - utils/enveomics/Scripts/HMM.essential.rb
@@ -331,6 +337,7 @@ files:
 - utils/enveomics/Scripts/VCF.SNPs.rb
 - utils/enveomics/Scripts/aai.rb
 - utils/enveomics/Scripts/ani.rb
+- utils/enveomics/Scripts/clust.rand.rb
 - utils/enveomics/Scripts/gi2tax.rb
 - utils/enveomics/Scripts/in_silico_GA_GI.pl
 - utils/enveomics/Scripts/lib/data/essential.hmm.gz