unipept 1.1.3 → 1.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 17fb4ae25816764349c1961d48289be0841b3e6a
-  data.tar.gz: b484dc7db887da7172d408c75611083914d34049
+  metadata.gz: 59580ce92eedf89d921c0f37dc980c7a2ac4e2a2
+  data.tar.gz: 064e088ee2208683820c27e5331a8005beeb4753
 SHA512:
-  metadata.gz: b4066aae51893a28a45fcaccb77f847c41ab39d8fa997e7445a16683904a9270a9b663e01e99860c0d65c5dd08cf941ce8d938081e252d677d6c9512d0ecd2b7
-  data.tar.gz: ef1144113dc60261e27b23d90c351f59410bdb7701203b81309e37d2e72aa21f1c7e8c663ef3488d019d9cab763f14b7da437a8a49a2cb034b271490728d084c
+  metadata.gz: 9a8aa82f5cd23581eea54eaae828a96a90055794e39129caf3004c0104b3dfefd57149060b1ace6c50cf85b94dc4a208370186f9b5c5e7fce026bd0658a3ef32
+  data.tar.gz: 326a285c3753138a388c7bfbfce1cd773b9038c2af4c1cd9e3a186989325ebfe983728abb2741c34b044ca33496474953bd1a763470a46f37bd18a9d9c1240f3

data/VERSION

@@ -1 +1 @@
-1.1.3
+1.2.0

data/lib/commands/unipept/pept2prot.rb

@@ -2,6 +2,15 @@ require_relative 'api_runner'
 
 module Unipept::Commands
   class Pept2prot < ApiRunner
+    def initialize(args, opts, cmd)
+      if args[:meganize]
+        args[:all] = true
+        args[:select] = ['peptide,refseq_protein_ids']
+        args[:format] = 'blast'
+      end
+      super
+    end
+
     def required_fields
       ['peptide']
     end

data/lib/commands/unipept.rb

@@ -180,6 +180,7 @@ module Unipept
         flag :e, :equate, 'equate isoleucine (I) and leucine (L) when matching peptides'
         flag :a, :all, 'report all information fields of UniProt entries available in Unipept. Note that this may have a performance penalty.'
         option :s, :select, 'select the information fields to return. Selected fields are passed as a comma separated list of field names. Multiple -s (or --select) options may be used.', argument: :required, multiple: true
+        option nil, :meganize, 'output the results in a BlastTab-like format that MEGAN can understand'
 
         runner Commands::Pept2prot
       end

data/lib/formatters.rb

@@ -254,4 +254,37 @@ module Unipept
       data.map { |row| '<result>' + row.to_xml + '</result>' }.join('')
     end
   end
+
+  class BlastFormatter < Formatter
+    register :blast
+
+    # @return [String] The type of the current formatter: blast
+    def type
+      'blast'
+    end
+
+    def header(_data, _fasta_mapper = nil)
+      ''
+    end
+
+    def footer
+      ''
+    end
+
+    # Converts the given input data to the Blast format.
+    #
+    # @param [Array] data The data we wish to convert
+    #
+    # @param [Boolean] Is this the first output batch?
+    #
+    # @return [String] The converted input data in the Blast format
+    def convert(data, _first)
+      data
+        .reject { |o| o['refseq_protein_ids'].empty? }
+        .map do |o|
+          "#{o['peptide']}\tref|#{o['refseq_protein_ids']}|\t100\t10\t0\t0\t0\t10\t0\t10\t1e-100\t100\n"
+        end
+        .join
+    end
+  end
 end

data/test/commands/unipept/test_api_runner.rb

@@ -166,6 +166,7 @@ module Unipept
       def runner.required_fields
         ['test']
       end
+      runner.required_fields
       assert_equal([], runner.selected_fields)
     end
 

data/test/commands/unipept/test_pept2prot.rb

@@ -16,6 +16,22 @@ module Unipept
       assert_equal(['peptide'], pept2prot.required_fields)
     end
 
+    def test_meganize_options
+      command = Cri::Command.define { name 'pept2prot' }
+      pept2prot = Commands::Pept2prot.new({ meganize: true, host: 'http://api.unipept.ugent.be' }, [], command)
+      assert(pept2prot.options[:all])
+      assert_equal(['peptide,refseq_protein_ids'], pept2prot.options[:select])
+      assert_equal('blast', pept2prot.options[:format])
+    end
+
+    def test_meganize_options_overridecommand
+      command = Cri::Command.define { name 'pept2prot' }
+      pept2prot = Commands::Pept2prot.new({ meganize: true, format: 'xml', all: false, select: ['something'], host: 'http://api.unipept.ugent.be' }, [], command)
+      assert(pept2prot.options[:all])
+      assert_equal(['peptide,refseq_protein_ids'], pept2prot.options[:select])
+      assert_equal('blast', pept2prot.options[:format])
+    end
+
     def test_help
       out, _err = capture_io_while do
         assert_raises SystemExit do

data/test/test_formatters.rb

@@ -7,6 +7,7 @@ module Unipept
       assert(formatters.include?('json'))
       assert(formatters.include?('csv'))
       assert(formatters.include?('xml'))
+      assert(formatters.include?('blast'))
     end
 
     def test_default_formatter
@@ -29,6 +30,9 @@ module Unipept
       formatter = Formatter.new_for_format('csv')
       assert_equal('csv', formatter.type)
 
+      formatter = Formatter.new_for_format('blast')
+      assert_equal('blast', formatter.type)
+
       formatter = Formatter.new_for_format('blah')
       assert_equal('csv', formatter.type)
     end
@@ -121,6 +125,31 @@ module Unipept
     end
   end
 
+  class BlastFormatterTestCase < Unipept::TestCase
+    def formatter
+      Formatter.new_for_format('blast')
+    end
+
+    def test_header
+      assert_equal('', formatter.header(nil, nil))
+    end
+
+    def test_footer
+      assert_equal('', formatter.footer)
+    end
+
+    def test_type
+      assert_equal('blast', formatter.type)
+    end
+
+    def test_convert
+      object = [{ 'peptide' => 'MDGTEYIIVK', 'refseq_protein_ids' => 'WP_008705701.1' }, { 'peptide' => 'ISVAQGASK', 'refseq_protein_ids' => 'NP_003881.2 XP_011547112.1 XP_011547113.1' }, { 'peptide' => 'ISVAQGASK', 'refseq_protein_ids' => '' }]
+      output = "MDGTEYIIVK\tref|WP_008705701.1|\t100\t10\t0\t0\t0\t10\t0\t10\t1e-100\t100\nISVAQGASK\tref|NP_003881.2 XP_011547112.1 XP_011547113.1|\t100\t10\t0\t0\t0\t10\t0\t10\t1e-100\t100\n"
+      assert_equal(output, formatter.convert(object, true))
+      assert_equal(output, formatter.convert(object, false))
+    end
+  end
+
   class CSVFormatterTestCase < Unipept::TestCase
     def formatter
       Formatter.new_for_format('csv')

data/unipept.gemspec

@@ -2,16 +2,16 @@
 # DO NOT EDIT THIS FILE DIRECTLY
 # Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
 # -*- encoding: utf-8 -*-
-# stub: unipept 1.1.3 ruby lib
+# stub: unipept 1.2.0 ruby lib
 
 Gem::Specification.new do |s|
   s.name = "unipept".freeze
-  s.version = "1.1.3"
+  s.version = "1.2.0"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0".freeze) if s.respond_to? :required_rubygems_version=
   s.require_paths = ["lib".freeze]
   s.authors = ["Toon Willems".freeze, "Bart Mesuere".freeze, "Tom Naessens".freeze]
-  s.date = "2017-01-17"
+  s.date = "2017-01-18"
   s.description = "    Command line interface to the Unipept (http://unipept.ugent.be) web services\n    (pept2lca, taxa2lca, pept2taxa, pept2prot and taxonomy) and some utility\n    commands for handling proteins using the command line.\n".freeze
   s.email = "unipept@ugent.be".freeze
   s.executables = ["unipept".freeze, "prot2pept".freeze, "peptfilter".freeze, "uniprot".freeze]

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: unipept
 version: !ruby/object:Gem::Version
-  version: 1.1.3
+  version: 1.2.0
 platform: ruby
 authors:
 - Toon Willems
@@ -10,7 +10,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-01-17 00:00:00.000000000 Z
+date: 2017-01-18 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: cri