miga-base 0.2.1.6 → 0.2.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: ea45f64b95746bcaf6c00a6638edccd66e3873f0
-  data.tar.gz: 83dbe2f728b6affd6122a760736fcd554c491cb8
+  metadata.gz: dd90983aa2e7a7a6653dc1f0456c6801d8cb3baf
+  data.tar.gz: f80a07fad789a82ee7b55ed040c050cecba5b9ca
 SHA512:
-  metadata.gz: 3abc1e0dae50dbd035ca17bc6f3b8e40cea74bd400762f0bce282153f6a5e67f7fc855e6167766700380858d90f38726df5923f68a0fc6104358e0e22a749597
-  data.tar.gz: cb537593f85427b412d8a112ca16748eaf09f35317ff81d5a0f7aa760365d2133c977a05579227fbf7c1f17882596806b79ae8c7df9818fe9947d061185cafaa
+  metadata.gz: 883eaef98d137a956ecbd28bdff15a7c657d84dc1c1dc2f296bd70107924332731f23215507d8d5f60382ebf92cd0a8a6ba2ff746e9d49a1f849615772d05546
+  data.tar.gz: 5124f28088c29a3fc06cac810b6c4e0d2cb702fd6de109b97c35464560b6a3ada73df769a73d87c0594b0d1e8e5400735cd4d11084b8f89b5c959adc0cc3ef07

data/actions/add_result.rb

@@ -6,13 +6,7 @@
 o = {q:true}
 opts = OptionParser.new do |opt|
   opt_banner(opt)
-  opt_object(opt, o, [:project, :dataset_opt])
-  opt.on("-r", "--result STRING",
-    "(Mandatory) Name of the result to add.",
-    "Recognized names for dataset-specific results include:",
-    *MiGA::Dataset.RESULT_DIRS.keys.map{|n| " ~ #{n}"},
-    "Recognized names for project-wide results include:",
-    *MiGA::Project.RESULT_DIRS.keys.map{|n| " ~ #{n}"}){ |v| o[:name]=v }
+  opt_object(opt, o, [:project, :dataset_opt, :result])
   opt_common(opt, o)
 end.parse!
 

data/actions/result_stats.rb

@@ -0,0 +1,75 @@
+#!/usr/bin/env ruby
+
+# @package MiGA
+# @license Artistic-2.0
+
+o = {q:true}
+opts = OptionParser.new do |opt|
+  opt_banner(opt)
+  opt_object(opt, o, [:project, :dataset_opt, :result])
+  opt.on("--compute-and-save",
+    "Computes and saves the statistics."){ |v| o[:compute] = v }
+  opt_common(opt, o)
+end.parse!
+
+##=> Main <=
+opts.parse!
+opt_require(o, project:"-P", name:"-r")
+
+$stderr.puts "Loading project." unless o[:q]
+p = MiGA::Project.load(o[:project])
+raise "Impossible to load project: #{o[:project]}" if p.nil?
+
+$stderr.puts "Loading result." unless o[:q]
+if o[:dataset].nil?
+  r = p.add_result(o[:name], false)
+else
+  d = p.dataset(o[:dataset])
+  r = d.add_result(o[:name], false)
+end
+raise "Cannot load result." if r.nil?
+
+if o[:compute]
+  $stderr.puts "Computing statistics." unless o[:q]
+  stats = {}
+  case o[:name]
+  when :raw_reads
+    scr = "awk 'NR%4==2{L+=length($0)} END{print NR/4, L*4/NR}'"
+    if r[:files][:pair1].nil?
+      s = `#{scr} '#{r.file_path :single}'`.chomp.split(" ")
+      stats = {reads: s[0].to_i, average_length: [s[1].to_f, "bp"]}
+    else
+      s1 = `#{scr} '#{r.file_path :pair1}'`.chomp.split(" ")
+      s2 = `#{scr} '#{r.file_path :pair2}'`.chomp.split(" ")
+      stats = {read_pairs: s1[0].to_i,
+        average_length_forward: [s1[1].to_f, "bp"],
+        average_length_reverse: [s2[1].to_f, "bp"]}
+    end
+  when :trimmed_fasta
+    scr = "awk '{L+=$2} END{print NR, L/NR}'"
+    f = r[:files][:coupled].nil? ? r.file_path(:single) : r.file_path(:coupled)
+    s = `FastA.length.pl '#{f}' | #{scr}`.chomp.split(" ")
+    stats = {reads: s[0].to_i, average_length: [s[1].to_f, "bp"]}
+  when :assembly
+    f = r.file_path :largecontigs
+    s = `FastA.N50.pl '#{f}'`.chomp.split("\n").map{|i| i.gsub(/.*: /,'').to_i}
+    stats = {contigs: s[1], n50: [s[0], "bp"], total_length: [s[2], "bp"]}
+  when :cds
+    scr = "awk '{L+=$2} END{print NR, L/NR}'"
+    f = r.file_path :proteins
+    s = `FastA.length.pl '#{f}' | #{scr}`.chomp.split(" ")
+    stats = {predicted_proteins: s[0].to_i, average_length: [s[1].to_f, "aa"]}
+  else
+    stats = nil
+  end
+  unless stats.nil?
+    r[:stats] = stats
+    r.save
+  end
+end
+
+r[:stats].each do |k,v|
+  puts "#{k.to_s.unmiga_name.capitalize}: #{v.is_a?(Array) ? v.join(" ") : v}."
+end
+
+$stderr.puts "Done." unless o[:q]

data/bin/miga

@@ -11,23 +11,29 @@ require "miga"
 ##=> Global variables <=
 
 $task_desc = {
-  add_result: "Registers a result.",
-  add_taxonomy: "Registers taxonomic information for datasets.",
-  create_dataset: "Creates an empty dataset in a pre-existing MiGA project.",
+  # Projects
   create_project: "Creates an empty MiGA project.",
-  daemon: "Controls the daemon of a MiGA project.",
-  date: "Returns the current date in standard MiGA format.",
+  project_info: "Displays information about a MiGA project.",
+  # Datasets
+  create_dataset: "Creates an empty dataset in a pre-existing MiGA project.",
   download_dataset: "Creates an empty dataset in a pre-existing MiGA project.",
+  unlink_dataset: "Removes a dataset from an MiGA project.",
   find_datasets: "Finds unregistered datasets based on result files.",
   import_datasets: "Link datasets (including results) from one project to "+
     "another.",
-  index_taxonomy: "Creates a taxonomy-indexed list of the datasets.",
   list_datasets: "Lists all registered datasets in an MiGA project.",
+  # Results
+  add_result: "Registers a result.",
+  result_stats: "Extracts statistics for the given result.",
   list_files: "Lists all registered files from the results of a dataset or a "+
     "project.",
-  project_info: "Displays information about a MiGA project.",
+  # System
+  daemon: "Controls the daemon of a MiGA project.",
+  date: "Returns the current date in standard MiGA format.",
+  # Taxonomy
+  add_taxonomy: "Registers taxonomic information for datasets.",
+  index_taxonomy: "Creates a taxonomy-indexed list of the datasets.",
   tax_distributions: "Estimates distributions of distance by taxonomy.",
-  unlink_dataset: "Removes a dataset from an MiGA project."
 }
 
 ##=> Functions <=
@@ -58,6 +64,13 @@ def opt_object(opt, o, what=[:project, :dataset])
     "Type of dataset. Recognized types include:", 
     *MiGA::Project.KNOWN_TYPES.map{ |k,v| "~ #{k}: #{v[:description]}"}
     ){ |v| o[:type]=v.to_sym } if what.include? :project_type
+  opt.on("-r", "--result STRING",
+    "(Mandatory) Name of the result to add.",
+    "Recognized names for dataset-specific results include:",
+    *MiGA::Dataset.RESULT_DIRS.keys.map{|n| " ~ #{n}"},
+    "Recognized names for project-wide results include:",
+    *MiGA::Project.RESULT_DIRS.keys.map{|n| " ~ #{n}"}
+    ){ |v| o[:name]=v.downcase.to_sym } if what.include? :result
 end
 
 # OptParse flags common to all actions.

data/lib/miga/dataset.rb

@@ -30,7 +30,9 @@ class MiGA::Dataset < MiGA::MiGA
     mapping_on_contigs: "08.mapping/01.read-ctg",
     mapping_on_genes: "08.mapping/02.read-gene",
     # Distances (for single-species datasets)
-    distances: "09.distances"
+    distances: "09.distances",
+    # General statistics
+    stats: "90.stats"
   }
 
   ##

data/lib/miga/dataset_result.rb

@@ -59,8 +59,10 @@ module MiGA::DatasetResult
     def add_result_assembly(base)
       return nil unless result_files_exist?(base, ".LargeContigs.fna")
       r = MiGA::Result.new(base + ".json")
-      add_files_to_ds_result(r, name, {:largecontigs=>".LargeContigs.fna",
+      r = add_files_to_ds_result(r, name, {:largecontigs=>".LargeContigs.fna",
         :allcontigs=>".AllContigs.fna"})
+      add_result(:trimmed_fasta) #-> Post interposing
+      r
     end
 
     ##
@@ -133,6 +135,12 @@ module MiGA::DatasetResult
         add_result_distances_multi(base)
       end
     end
+
+    ##
+    # Add result type +:stats+ at +base+.
+    def add_result_stats(base)
+      MiGA::Result.new(base + ".json")
+    end
     
     ##
     # Add result type +:distances+ for _multi_ datasets at +base+.

data/lib/miga/project.rb

@@ -30,6 +30,7 @@ class MiGA::Project < MiGA::MiGA
     10.clades 10.clades/01.find 10.clades/02.ani 10.clades/03.ogs
     10.clades/04.phylogeny 10.clades/04.phylogeny/01.essential
     10.clades/04.phylogeny/02.core 10.clades/05.metadata
+    90.stats
   ]
 
   ##
@@ -45,10 +46,11 @@ class MiGA::Project < MiGA::MiGA
     clade_finding: "10.clades/01.find",
     # Clade analysis
     subclades: "10.clades/02.ani",
-    ogs: "10.clades/03.ogs",
-    ess_phylogeny: "10.clades/04.phylogeny/01.essential",
-    core_phylogeny: "10.clades/04.phylogeny/02.core",
-    clade_metadata: "10.clades/05.metadata"
+    ogs: "10.clades/03.ogs"
+    #ess_phylogeny: "10.clades/04.phylogeny/01.essential",
+    #core_phylogeny: "10.clades/04.phylogeny/02.core",
+    #clade_metadata: "10.clades/05.metadata"
+    #project_stats: "90.stats"
   }
 
   ##

data/lib/miga/result.rb

@@ -62,6 +62,10 @@ class MiGA::Result < MiGA::MiGA
   # Entry with symbol +k+. 
   def [](k) data[k.to_sym] ; end
 
+  ##
+  # Adds value +v+ to entry with symbol +k+.
+  def []=(k,v) data[k.to_sym]=v ; end
+
   ##
   # Register +file+ (path relative to #dir) with the symbol +k+. If the file
   # doesn't exist but the .gz extension does, the gzipped file is registered

data/lib/miga/version.rb

@@ -10,7 +10,7 @@ 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 = [0.2, 1, 6]
+  VERSION = [0.2, 2, 0]
   
   ##
   # Nickname for the current major.minor version.
@@ -18,7 +18,7 @@ module MiGA
   
   ##
   # Date of the current gem release.
-  VERSION_DATE = Date.new(2016, 04, 20)
+  VERSION_DATE = Date.new(2016, 8, 31)
   
   ##
   # Reference of MiGA.

data/scripts/stats.bash

@@ -0,0 +1,22 @@
+#!/bin/bash
+# Available variables: $PROJECT, $RUNTYPE, $MIGA, $CORES, $DATASET
+set -e
+echo "MiGA: $MIGA"
+echo "Project: $PROJECT"
+source "$MIGA/scripts/miga.bash" || exit 1
+DIR="$PROJECT/data/90.stats"
+[[ -d "$DIR" ]] || mkdir -p "$DIR"
+cd "$DIR"
+
+# Initialize
+date "+%Y-%m-%d %H:%M:%S %z" > "$DATASET.start"
+
+# Calculate statistics
+for i in raw_reads trimmed_fasta assembly cds ; do
+  echo "# $i"
+  miga result_stats --compute-and-save -P "$PROJECT" -D "$DATASET" -r $i
+done
+
+# Finalize
+date "+%Y-%m-%d %H:%M:%S %z" > "$DATASET.done"
+miga add_result -P "$PROJECT" -D "$DATASET" -r stats

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: miga-base
 version: !ruby/object:Gem::Version
-  version: 0.2.1.6
+  version: 0.2.2.0
 platform: ruby
 authors:
 - Luis M. Rodriguez-R
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-04-20 00:00:00.000000000 Z
+date: 2016-08-31 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rest-client
@@ -130,6 +130,7 @@ files:
 - scripts/ogs.bash
 - scripts/read_quality.bash
 - scripts/ssu.bash
+- scripts/stats.bash
 - scripts/subclades.bash
 - scripts/trimmed_fasta.bash
 - scripts/trimmed_reads.bash
@@ -154,6 +155,7 @@ files:
 - actions/list_datasets.rb
 - actions/list_files.rb
 - actions/project_info.rb
+- actions/result_stats.rb
 - actions/tax_distributions.rb
 - actions/unlink_dataset.rb
 - Gemfile