miga-base 0.3.1.6 → 0.3.1.7

data/utils/enveomics/Manifest/Tasks/trees.json

@@ -10,58 +10,58 @@
       "help_arg": "--help",
       "options": [
         {
-	  "name": "Input tree",
-	  "opt": "--t",
-	  "arg": "in_file",
-	  "mandatory": true,
-	  "description": "A tree to prune in Newick format."
-	},
-	{
-	  "opt": "--dist-quantile",
-	  "arg": "float",
-	  "default": 0.25,
-	  "description": "The quantile of edge lengths."
-	},
-	{
-	  "opt": "--min_dist",
-	  "arg": "float",
-	  "description": ["The minimum distance to allow between two tips. If",
-	    "not set, dist.quantile is used instead to calculate it."]
-	},
-	{
-	  "opt": "--quiet",
-	  "description": ["Boolean indicating if the function must run without",
-	    "output."]
-	},
-	{
-	  "opt": "--max_iters",
-	  "arg": "integer",
-	  "default": 1000,
-	  "description": "Maximum number of iterations."
-	},
-	{
-	  "opt": "--min_nodes_random",
-	  "arg": "integer",
-	  "default": 40000,
-	  "description": ["Minimum number of nodes to trigger 'tip-pairs'",
-	    "nodes sampling. This sampling is less reproducible and more",
-	    "computationally expensive, but it's the only solution if the",
-	    "cophenetic matrix exceeds 2^31-1 entries; above that, it cannot",
-	    "be represented in R."]
-	},
-	{
-	  "opt": "--random_nodes_frx",
-	  "arg": "float",
-	  "default": 1.0,
-	  "description": ["Fraction of the nodes to be sampled if more than",
-	    "'Min nodes random'."]
-	},
-	{
-	  "arg": "out_file",
-	  "mandatory": true,
-	  "description": ["Output file in Newick format containing the pruned",
-	    "tree."]
-	}
+          "name": "Input tree",
+          "opt": "--t",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "A tree to prune in Newick format."
+        },
+        {
+          "opt": "--dist-quantile",
+          "arg": "float",
+          "default": 0.25,
+          "description": "The quantile of edge lengths."
+        },
+        {
+          "opt": "--min_dist",
+          "arg": "float",
+          "description": ["The minimum distance to allow between two tips. If",
+            "not set, dist.quantile is used instead to calculate it."]
+        },
+        {
+          "opt": "--quiet",
+          "description": ["Boolean indicating if the function must run without",
+            "output."]
+        },
+        {
+          "opt": "--max_iters",
+          "arg": "integer",
+          "default": 1000,
+          "description": "Maximum number of iterations."
+        },
+        {
+          "opt": "--min_nodes_random",
+          "arg": "integer",
+          "default": 40000,
+          "description": ["Minimum number of nodes to trigger 'tip-pairs'",
+            "nodes sampling. This sampling is less reproducible and more",
+            "computationally expensive, but it's the only solution if the",
+            "cophenetic matrix exceeds 2^31-1 entries; above that, it cannot",
+            "be represented in R."]
+        },
+        {
+          "opt": "--random_nodes_frx",
+          "arg": "float",
+          "default": 1.0,
+          "description": ["Fraction of the nodes to be sampled if more than",
+            "'Min nodes random'."]
+        },
+        {
+          "arg": "out_file",
+          "mandatory": true,
+          "description": ["Output file in Newick format containing the pruned",
+            "tree."]
+        }
       ]
     }
   ]

data/utils/enveomics/Manifest/Tasks/variants.json

@@ -58,10 +58,10 @@
           "description": "Minimum information content (in bits, from 0 to 1).",
           "default": 0.0
         },
-	{
-	  "opt": "--indels",
-	  "description": "Process indels."
-	}
+        {
+          "opt": "--indels",
+          "description": "Process indels."
+        }
       ]
     },
     {

data/utils/enveomics/Manifest/categories.json

@@ -2,13 +2,15 @@
   "categories": {
     "Sequence similarity search": {
       "Statistics": [
+        "BedGraph.tad.rb",
         "BlastPairwise.AAsubs.pl",
         "BlastTab.advance.bash",
         "BlastTab.recplot2.R",
         "BlastTab.seqdepth.pl",
         "BlastTab.seqdepth_nomedian.pl",
         "BlastTab.seqdepth_ZIP.pl",
-        "BlastTab.sumPerHit.pl"
+        "BlastTab.sumPerHit.pl",
+        "FastQ.test-error.rb"
       ],
       "Manipulation": [
         "BlastTab.addlen.rb",
@@ -33,7 +35,8 @@
         "FastA.gc.pl",
         "FastA.length.pl",
         "FastA.N50.pl",
-        "FastA.qlen.pl"
+        "FastA.qlen.pl",
+        "FastQ.test-error.rb"
       ],
       "Manipulation": [
         "FastA.filter.pl",
@@ -41,11 +44,12 @@
         "FastA.filterN.pl",
         "FastA.fragment.rb",
         "FastA.interpose.pl",
-	"FastA.per_file.pl",
+        "FastA.per_file.pl",
         "FastA.rename.pl",
         "FastA.revcom.pl",
         "FastA.slider.pl",
         "FastA.split.pl",
+        "FastA.split.rb",
         "FastA.subsample.pl",
         "FastA.tag.rb",
         "FastA.wrap.rb",
@@ -86,7 +90,7 @@
         "Table.df2dist.R",
         "Table.filter.pl",
         "Table.merge.pl",
-	"Table.replace.rb",
+        "Table.replace.rb",
         "Table.round.rb",
         "Table.split.pl"
       ],
@@ -126,6 +130,10 @@
         "Aln.cat.rb",
         "Aln.convert.pl",
         "BlastPairwise.AAsubs.pl"
+      ],
+      "Clustering": [
+        "ogs.mcl.rb",
+        "clust.rand.rb"
       ]
     }
   }

data/utils/enveomics/Manifest/examples.json

@@ -56,7 +56,7 @@
       "task": "BlastTab.recplot2.R",
       "description": ["Generates recruitment plots for a comparison",
         "between a virome containing HIV and the HIV-1 genome."],
-      "values": ["hiv_mix-hiv1.blast.tsv",50,100,null,null,null,null,null,
+      "values": ["hiv_mix-hiv1.blast.tsv",50,100,null,null,null,null,null,"NA",
         "hiv_mix-hiv1.Rdata","hiv_mix-hiv1.pdf",null,null]
     },
     {

data/utils/enveomics/Scripts/BedGraph.tad.rb

@@ -0,0 +1,71 @@
+#!/usr/bin/env ruby
+
+require "optparse"
+
+o = {range:0.5}
+ARGV << "-h" if ARGV.empty?
+OptionParser.new do |opt|
+  opt.banner = "
+  Estimates the truncated average sequencing depth (TAD) from a BedGraph file.
+
+  IMPORTANT: This script doesn't consider zero-coverage positions if missing
+  from the file. If you produce your BedGraph file with bedtools genomecov and
+  want to consider zero-coverage position, be sure to use -bga (not -bg).
+
+  Usage: #{$0} [options]"
+  opt.separator ""
+  opt.on("-i", "--input PATH",
+    "Input BedGraph file (mandatory)."){ |v| o[:i]=v }
+  opt.on("-r", "--range FLOAT",
+    "Central range to consider, between 0 and 1.",
+    "By default: #{o[:range]} (inter-quartile range)."
+    ){ |v| o[:range]=v.to_f }
+  opt.on("-h", "--help", "Display this screen.") do
+    puts opt
+    exit
+  end
+  opt.separator ""
+end.parse!
+abort "-i is mandatory." if o[:i].nil?
+
+def pad(d, idx, r)
+  idx.each do |i|
+    next if d[i].nil?
+    d[i] -= r
+    break unless d[i] < 0
+    r = -d[i]
+    d[i] = nil
+  end
+  d
+end
+
+# Read BedGraph
+d = []
+ln = 0
+File.open(o[:i], "r") do |ifh|
+  ifh.each_line do |i|
+    next if i =~ /^#/
+    r = i.chomp.split("\t")[1 .. -1].map{ |j| j.to_i }
+    l = r[1]-r[0]
+    d[ r[2] ] ||= 0
+    d[ r[2] ] += l
+    ln += l
+  end
+end
+
+# Estimate padding ranges
+pad = (1.0-o[:range])/2.0
+r = (pad*ln).round
+
+# Pad
+d = pad(d, d.each_index.to_a, r+0)
+d = pad(d, d.each_index.to_a.reverse, r+0)
+
+# Average
+if d.compact.empty?
+  p 0.0
+else
+  s = d.each_with_index.to_a.map{ |v,i| v.nil? ? 0 : i*v }.inject(0,:+)
+  p s.to_f/d.compact.inject(:+)
+end
+

data/utils/enveomics/Scripts/BlastTab.recplot2.R

@@ -1,40 +1,41 @@
 #!/usr/bin/env Rscript
-#
+
 # @author  Luis M. Rodriguez-R
-# @update  Jan-05-2016
 # @license artistic license 2.0
-#
 
 #= Load stuff
 suppressPackageStartupMessages(library(enveomics.R))
-args <- commandArgs(trailingOnly = F)  
+args <- commandArgs(trailingOnly = FALSE)
 enveomics_R <- file.path(dirname(
-   sub("^--file=", "", args[grep("^--file=", args)])),
-   "lib", "enveomics.R")
+  sub("^--file=", "", args[grep("^--file=", args)])),
+  "lib", "enveomics.R")
 
 #= Generate interface
 opt <- enve.cliopts(enve.recplot2,
-   file.path(enveomics_R, "man", "enve.recplot2.Rd"),
-   positional_arguments=c(1,4),
-   usage="usage: %prog [options] output.Rdata [output.pdf [width height]]",
-   mandatory=c("prefix"),
-   o_desc=list(pos.breaks="Breaks in the positions histogram.",
-     id.breaks="Breaks in the identity histogram.",
-     id.summary="Function summarizing the identity bins. By default: sum."),
-   p_desc=paste("","Produce recruitment plot objects provided that",
-     "BlastTab.catsbj.pl has been previously executed.", sep="\n\t"),
-   ignore=c("plot"),
-
-   defaults=c(id.metric="identity"))
+  file.path(enveomics_R, "man", "enve.recplot2.Rd"),
+  positional_arguments=c(1,4),
+  usage="usage: %prog [options] output.Rdata [output.pdf [width height]]",
+  mandatory=c("prefix"),
+  o_desc=list(pos.breaks="Breaks in the positions histogram.",
+    id.breaks="Breaks in the identity histogram.",
+    id.summary="Function summarizing the identity bins. By default: sum.",
+    peaks.col="Color of peaks, mandatory for peak-finding (e.g., darkred)."),
+  p_desc=paste("","Produce recruitment plot objects provided that",
+    "BlastTab.catsbj.pl has been previously executed.", sep="\n\t"),
+  ignore=c("plot"),
+  defaults=c(id.metric="identity", peaks.col=NA))
 
 #= Run it!
 if(length(opt$args)>1){
-   args = as.list(opt$args[-1])
-   for(i in 2:3) if(length(args)>=i) args[[i]] <- as.numeric(args[[i]])
-   do.call("pdf", args)
+  args = as.list(opt$args[-1])
+  for(i in 2:3) if(length(args)>=i) args[[i]] <- as.numeric(args[[i]])
+  do.call("pdf", args)
 }else{
-   opt$options[["plot"]] <- FALSE
+  opt$options[["plot"]] <- FALSE
 }
+pc <- opt$options[["peaks.col"]]
+if(!is.na(pc) && pc=="NA") opt$options[["peaks.col"]] <- NA
 rp <- do.call("enve.recplot2", opt$options)
 save(rp, file=opt$args[1])
 if(length(opt$args)>1) dev.off()
+

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

@@ -0,0 +1,79 @@
+#!/usr/bin/env ruby
+#
+# @author Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
+# @license Artistic-2.0
+#
+
+require "optparse"
+
+o = {q:false, n:12, lett:false, dc:false, z:false, out:"%s.%s.fa"}
+ARGV << "-h" if ARGV.size==0
+
+OptionParser.new do |opt|
+  opt.banner = "
+  Evenly splits a multi-FastA file into multiple multi-FastA files.
+  
+  Usage: #{$0} [options]"
+  opt.separator ""
+  opt.separator "Mandatory"
+  opt.on("-i", "--input PATH", "Input FastA file."){ |v| o[:i] = v}
+  opt.on("-p", "--prefix PATH", "Prefix of output FastA files."){ |v| o[:p] = v}
+  opt.separator ""
+  opt.separator "Options"
+  opt.on("-n", "--number INT",
+    "Number of output files to produce. By default: #{o[:n]}."
+    ){ |v| o[:n] = v.to_i }
+  opt.on("-z", "--zero-padded",
+    "Use zero-padded numbers as output index."){ o[:lett]=false; o[:z]=true }
+  opt.on("-l", "--lowercase-letters",
+    "Use lowercase letters as output index."){ o[:lett]=true ; o[:dc]=true }
+    opt.on("-u", "--uppercase-letters",
+    "Use uppercase letters as output index."){ o[:lett]=true }
+  opt.on("-o", "--out STR",
+    "Format of output filenames, where %s are replaced by prefix and index.",
+    "By default: #{o[:out]}."){ |v| o[:out] = v }
+  opt.on("-q", "--quiet", "Run quietly (no STDERR output)."){ o[:q] = TRUE }
+  opt.on("-h", "--help", "Display this screen.") do
+    puts opt
+    exit
+  end
+  opt.separator ""
+end.parse!
+abort "-i is mandatory." if o[:i].nil?
+abort "-p is mandatory." if o[:p].nil?
+
+ofh = []
+idx = if o[:lett]
+  k = Math::log(o[:n], 26).ceil
+  r = o[:dc] ? ["a","z"] : ["A","Z"]
+  ((r[0]*k) .. (r[1]*k)).first(o[:n])
+elsif o[:z]
+  k = Math::log(o[:n], 10).ceil
+  (1 .. o[:n]).map{ |i| "%0#{k}d" % i }
+else
+  (1 .. o[:n]).map{ |i| i.to_s }
+end
+idx.each do |i|
+  fn = o[:out] % [o[:p], i]
+  ofh << File.open(fn, "w")
+end
+
+i = -1
+seq = ""
+File.open(o[:i], "r") do |ifh|
+  ifh.each_line do |ln|
+    next if ln =~ /^;/
+    if ln =~ /^>/
+      ofh[i % o[:n]].print seq
+      i += 1
+      seq = ""
+    end
+    seq << ln
+  end
+  ofh[i % o[:n]].print seq
+end
+
+ofh.each{ |i| i.close }
+
+$stderr.puts "Sequences: #{i+1}.", "Files: #{o[:n]}." unless o[:q]
+

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

@@ -0,0 +1,81 @@
+#!/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