unipept 0.6.4 → 0.7.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 4e2985df7d45eb45a982bb73099e92c001155829
-  data.tar.gz: fc79cba4a15df4511af91a85eb9b09f7172b93e9
+  metadata.gz: d3efe88570b78401e07ba8e33aea86a992249db1
+  data.tar.gz: 89f91e5cf9d921c2e3f332a39bf8fb08d2f41f4f
 SHA512:
-  metadata.gz: 9f0269ffa7a80d490ebf3e85a0a090f5ab89d2d8c75e9f4ca2e904a848ba155b8721d6a0d3fc28289ccab9cf931236074e9ab20d6a1a126a0ddd208cc1240222
-  data.tar.gz: 5381cafb81ac0c32a0f2475e51b0df439e886187ea296a52fb340507763740e4db63918e049434e926f0e360120e4f2609cfbbe80e57518b05be0d951d605637
+  metadata.gz: 94483a52a23563384ccb38a9befd0211d99e829cfa3b1bf71d1a58e760f9cd922b589a83b78d78d444786c70f3f0eaba2adf504bd3b315a33f06dd3f111dc5e6
+  data.tar.gz: 6aa8bd08b5cd97b5ed11841a6f84ece7b7ea4c8cbe62c0d549697658ebcefc36157626a3a1c3e8b1e7d10b44cba2da5e727c485ea4f8705200d978a0364e27e6

data/README.md

@@ -1,6 +1,7 @@
 # unipept-cli
 
 [![Code Climate](https://codeclimate.com/github/unipept/unipept-cli/badges/gpa.svg)](https://codeclimate.com/github/unipept/unipept-cli)
+[![Gem Version](https://badge.fury.io/rb/unipept.svg)](http://badge.fury.io/rb/unipept)
 
 Unipept-cli offers a command line interface to the [Unipept](http://unipept.ugent.be) web service.
 Documentation about the web service can be found at [http://unipept.ugent.be/apidocs](http://unipept.ugent.be/apidocs).
@@ -20,8 +21,8 @@ The Unipept CLI is available as a *gem*. This means it can easily be installed w
 
 ```bash
 $ gem install unipept
-Successfully installed unipept-0.6.0
-Parsing documentation for unipept-0.6.0
+Successfully installed unipept-0.7.0
+Parsing documentation for unipept-0.7.0
 Done installing documentation for unipept after 0 seconds
 1 gem installed
 ```
@@ -30,8 +31,7 @@ After successful installation, the unipept command should be available:
 
 ```bash
 $ unipept -v
-0.6.0
+0.7.0
 ```
 
 The help can be accessed by running `unipept -h`.
-

data/Rakefile

@@ -6,7 +6,7 @@ begin
   Bundler.setup(:default, :development)
 rescue Bundler::BundlerError => e
   $stderr.puts e.message
-  $stderr.puts "Run `bundle install` to install missing gems"
+  $stderr.puts 'Run `bundle install` to install missing gems'
   exit e.status_code
 end
 require 'rake'
@@ -14,14 +14,18 @@ require 'rake'
 require 'jeweler'
 Jeweler::Tasks.new do |gem|
   # gem is a Gem::Specification... see http://guides.rubygems.org/specification-reference/ for more options
-  gem.name = "unipept"
-  gem.executables = ['unipept', 'prot2pept', 'peptfilter', 'uniprot']
-  gem.homepage = "https://github.com/unipept/unipept/"
-  gem.license = "MIT"
-  gem.summary = %Q{Command line interface to Unipept web services.}
-  gem.description = %Q{Command line interface to Unipept web services.}
-  gem.email = "unipept@ugent.be"
-  gem.authors = ["Toon Willems", "Bart Mesuere", "Tom Naessens"]
+  gem.name = 'unipept'
+  gem.executables = %w(unipept prot2pept peptfilter uniprot)
+  gem.homepage = 'https://github.com/unipept/unipept-cli/'
+  gem.license = 'MIT'
+  gem.summary = 'Command line interface to Unipept web services.'
+  gem.description = <<-EOS
+  Command line interface to the Unipept (http://unipept.ugent.be) web services
+  (pept2lca, taxa2lca, pept2taxa and taxonomy) and some utility commands for
+  handling proteins using the command line.
+  EOS
+  gem.email = 'unipept@ugent.be'
+  gem.authors = ['Toon Willems', 'Bart Mesuere', 'Tom Naessens']
   gem.required_ruby_version = '>= 1.9.3'
 end
 Jeweler::RubygemsDotOrgTasks.new
@@ -33,17 +37,17 @@ Rake::TestTask.new(:test) do |test|
   test.verbose = true
 end
 
-desc "Code coverage detail"
+desc 'Code coverage detail'
 task :simplecov do
-  ENV['COVERAGE'] = "true"
+  ENV['COVERAGE'] = 'true'
   Rake::Task['test'].execute
 end
 
-task :default => :test
+task default: :test
 
 require 'rdoc/task'
 Rake::RDocTask.new do |rdoc|
-  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+  version = File.exist?('VERSION') ? File.read('VERSION') : ''
 
   rdoc.rdoc_dir = 'rdoc'
   rdoc.title = "unipept #{version}"

data/VERSION

@@ -1 +1 @@
-0.6.4
+0.7.0

data/bin/peptfilter

@@ -1,20 +1,33 @@
 #!/usr/bin/env ruby
 require 'cri'
 
-Signal.trap("PIPE", "EXIT")
-Signal.trap("INT", "EXIT")
+Signal.trap('PIPE', 'EXIT')
+Signal.trap('INT', 'EXIT')
 root_cmd = Cri::Command.new_basic_root.modify do
   name 'peptfilter'
-  flag :i, :unique, "only output unique peptides"
-  required :l, :minlen, "minimum length (default: 5)"
-  required :u, :maxlen, "minimum length (default: 50)"
-  required :a, :lacks, "a string whose letters represent amino acids that may not occur in the peptide"
-  required :c, :contains, "a string whose letters represent amino acids that must all occur in the peptide"
-  run do |opts, args, cmd|
-    minlen = opts.fetch(:minlen, "5").to_i
-    maxlen = opts.fetch(:maxlen, "50").to_i
-    lacks = opts.fetch(:lacks, "").chars.to_a
-    contains = opts.fetch(:contains, "").chars.to_a
+  summary 'Filter peptides based on specific criteria.'
+  usage 'peptfilter [options]'
+  description <<-EOS
+  The peptfilter command filters a list of peptides according to specific criteria. The command expects a list of peptides that are passed
+
+  - as separate command line arguments
+
+  - in one or more text files that are passed as an argument to the -i option
+
+  - to standard input
+
+  The command will give priority to the first way peptides are passed, in the order as listed above. Text files and standard input should have one peptide per line. FASTA headers are preserved in the output, so that peptides remain bundled.
+  EOS
+  # flag :u, :unique, "filter duplicate peptides."
+  required nil, :minlen, 'only retain tryptic peptides that have at least min (default: 5) amino acids.'
+  required nil, :maxlen, 'only retain tryptic peptides that have at most max (default: 50) amino acids.'
+  required :l, :lacks, 'only retain tryptic peptides that lack all amino acids from the string of residues.'
+  required :c, :contains, 'only retain tryptic peptides that contain all amino acids from the string of residues.'
+  run do |opts, _args, _cmd|
+    minlen = opts.fetch(:minlen, '5').to_i
+    maxlen = opts.fetch(:maxlen, '50').to_i
+    lacks = opts.fetch(:lacks, '').chars.to_a
+    contains = opts.fetch(:contains, '').chars.to_a
     $stdin.each_line do |pept|
       # FASTA headers
       if pept.start_with? '>'

data/bin/prot2pept

@@ -4,8 +4,22 @@ require 'cri'
 Signal.trap("PIPE", "EXIT")
 Signal.trap("INT", "EXIT")
 root_cmd = Cri::Command.new_basic_root.modify do
-  name 'prot2pept'
-  required :p, :pattern, "cleavage pattern to split input protein (default: ([KR])([^P]))"
+  name        'prot2pept'
+  summary     'Split protein sequences into peptides.'
+  usage       'prot2pept [options]'
+  description <<-EOS
+  The prot2pept command splits each protein sequence into a list of peptides according to a given cleavage-pattern. The command expects a list of protein sequences that are passed
+
+  - as separate command line arguments
+
+  - in one or more text files that are passed as an argument to the -i option
+
+  - to standard input
+
+  The command will give priority to the first way protein sequences are passed, in the order as listed above. Text files and standard input should have either one protein sequence per line or contain a FASTA formatted list of protein sequences. FASTA headers are preserved in the output, so that peptides can be bundled per protein sequence.
+
+  EOS
+  required :p, :pattern, 'specify cleavage-pattern (regex) as the pattern after which the next peptide will be cleaved (default: ([KR])([^P]) for tryptic peptides).'
   run do |opts, args, cmd|
     pattern = opts.fetch(:pattern, "([KR])([^P])")
     # decide if we have FASTA input

data/bin/unipept

@@ -9,103 +9,193 @@ require 'fileutils'
 require_relative '../lib/unipept'
 
 # Prevent broken pipe errors
-Signal.trap("PIPE", "EXIT")
-Signal.trap("INT", "EXIT")
+Signal.trap('PIPE', 'EXIT')
+Signal.trap('INT', 'EXIT')
 
 root_cmd = Cri::Command.new_basic_root.modify do
   name 'unipept'
-  flag :v, :version, "print version"
-  flag :q, :quiet, "don't show update messages"
-  option :i, :input, "input file", :argument => :required
-  option :o, :output, "output file", :argument => :required
-  option :f, :format, "output format (available: #{Unipept::Formatter.available.join "," }) (default: #{Unipept::Formatter.default})", :argument => :required
+  summary 'Command line interface to Unipept web services.'
+  usage 'unipept subcommand [options]'
+  description <<-EOS
+  The unipept subcommands are command line wrappers around the Unipept web services.
+
+  Subcommands that start with pept expect a list of tryptic peptides as input. Subcommands that start with tax expect a list of NCBI Taxonomy Identifiers as input. Input is passed
+
+  - as separate command line arguments
+
+  - in one or more text files that are passed as an argument to the -i option
+
+  - to standard input
+
+  The command will give priority to the first way the input is passed, in the order as listed above. Text files and standard input should have one tryptic peptide or one NCBI Taxonomy Identifier per line.
+  EOS
+  flag :v, :version, 'displays the version'
+  flag :q, :quiet, 'disable service messages'
+  option :i, :input, 'read input from file', argument: :required
+  option :o, :output, 'write output to file', argument: :required
+  option :f, :format, "define the output format (available: #{Unipept::Formatter.available.join ', ' }) (default: #{Unipept::Formatter.default})", argument: :required
 
   # Configuration options
-  option nil, "host", "Override host setting", argument: :required
+  option nil, 'host', 'specify the server running the Unipept web service', argument: :required
 
-  run do |opts, args, cmd|
+  run do |opts, _args, _cmd|
     if opts[:version]
-      puts File.read(File.join(File.dirname(__FILE__), "..", "VERSION"))
+      puts File.read(File.join(File.dirname(__FILE__), '..', 'VERSION'))
+    elsif
+      root_cmd.run(['help'])
     end
   end
 end
 
 root_cmd.define_command('config') do
-  usage 'config attr [value]'
+  summary 'Set configuration options.'
+  usage 'config option [value]'
+  description <<-EOS
+  Sets or shows the value for configuration options. All settings are stored in the .unipeptrc file in the home directory of the user.
+
+  Running the command with a value will set that value for the given option, running it without will show the current value.
+
+  These options are currently supported:
+
+  - host: Set the default host for api calls.
+
+  Example: "unipept config host http://api.unipept.ugent.be" will set the default host to the public unipept server.
+  EOS
 
-  run do |opts, args, cmd|
+  run do |_opts, args, _cmd|
     config = Unipept::Configuration.new
     if args.size > 1
       config[args.first] = args[1]
       config.save
     elsif args.size == 1
       puts config[args.first]
+    elsif args.size == 0
+      root_cmd.run(['config', '-h'])
     end
   end
-
 end
 
 root_cmd.define_command('pept2taxa') do
-  usage       'pept2taxa [options]'
-  aliases     :s
-  summary     'Single Peptide Search'
-  description 'Search Unipept for the given peptide and return taxons'
+  usage 'pept2taxa [options]'
+  aliases :pt
+  summary 'Fetch taxa of Uniprot records that match tryptic peptides.'
+  description <<-EOS
+  For each tryptic peptide the unipept pept2taxa command retrieves from Unipept the set of taxa from all Uniprot records whose protein sequence contains an exact matches to the tryptic peptide. The command expects a list of tryptic peptides that are passed
+
+  - as separate command line arguments
+
+  - in one or more text files that are passed as an argument to the -i option
+
+  - to standard input
+
+  The command will give priority to the first way tryptic peptides are passed, in the order as listed above. Text files and standard input should have one tryptic peptide per line.
 
-  flag :e, :equate, "equate I and L"
-  option :s, :select, "select the attributes", :argument => :required, :multiple => true
-  option :a, :extra, "Show full lineage"
-  option :x, :xml, "Download taxonomy from NCBI as xml (specify output filename)", :argument => :required
+  The unipept pept2taxa subcommand yields NCBI Taxonomy records as output.
+  EOS
+
+  flag :e, :equate, 'equate isoleucine (I) and leucine (L) when matching peptides'
+  flag :a, :all, 'report all information fields of NCBI Taxonomy records 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 :x, :xml, 'Download the matched records from the NCBI web service as an xml-formatted file (specify output filename)', argument: :required
 
   runner Unipept::Commands::Pept2taxa
 end
 
 root_cmd.define_command('pept2lca') do
-  usage       'pept2lca [options]'
-  aliases     :l
-  summary     'Give lowest common ancestor for given peptide'
-  description 'Search Unipept for the given peptide and return the lowest common ancestor'
+  usage 'pept2lca [options]'
+  aliases :pl
+  summary 'Fetch taxonomic lowest common ancestor of Uniprot records that match tryptic peptides.'
+  description <<-EOS
+  For each tryptic peptide the unipept pept2lca command retrieves from Unipept the lowest common ancestor of the set of taxa from all Uniprot records whose protein sequence contains an exact matches to the tryptic peptide. The lowest common ancestor is based on the topology of the Unipept Taxonomy -- a cleaned up version of the NCBI Taxonomy -- and is itself a record from the NCBI Taxonomy. The command expects a list of tryptic peptides that are passed
+
+   - as separate command line arguments
+
+   - in one or more text files that are passed as an argument to the -i option
+
+   - to standard input
 
-  flag :e, :equate, "equate I and L"
-  option :s, :select, "select the attributes", :argument => :required, :multiple => true
-  option :a, :extra, "Show full lineage"
+  The command will give priority to the first way tryptic peptides are passed, in the order as listed above. Text files and standard input should have one tryptic peptide per line.
+
+  The unipept pept2lca subcommand yields an NCBI Taxonomy record as output.
+  EOS
+
+  flag :e, :equate, 'equate isoleucine (I) and leucine (L) when matching peptides'
+  flag :a, :all, 'report all information fields of NCBI Taxonomy records 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
 
   runner Unipept::Commands::Pept2lca
 end
 
 root_cmd.define_command('taxa2lca') do
-  usage       'taxa2lca [options]'
-  aliases     :t
-  summary     'Give lowest common ancestor for taxon ids'
-  description 'Search Unipept for the given taxon ids and return the lowest common ancestor'
+  usage 'taxa2lca [options]'
+  aliases :tl
+  summary 'Compute taxonomic lowest common ancestor for given list of taxa.'
+  description <<-EOS
+  The unipept taxa2lca command computes the lowest common ancestor of a given list of NCBI Taxonomy Identifiers. The lowest common ancestor is based on the topology of the Unipept Taxonomy -- a cleaned up version of the NCBI Taxonomy -- and is itself a record from the NCBI Taxonomy. The command expects a list of NCBI Taxonomy Identifiers that are passed
+
+   - as separate command line arguments
+
+   - in one or more text files that are passed as an argument to the -i option
+
+   - to standard input
 
-  option :s, :select, "select the attributes", :argument => :required, :multiple => true
-  option :a, :extra, "Show full lineage"
+  The command will give priority to the first way NCBI Taxonomy Identifiers are passed, in the order as listed above. Text files and standard input should have one NCBI Taxonomy Identifier per line.
+
+  The unipept taxonomy subcommand yields NCBI Taxonomy records as output.
+  EOS
+
+  flag :a, :all, 'report all information fields of NCBI Taxonomy records 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
 
   runner Unipept::Commands::Taxa2lca
 end
 
 root_cmd.define_command('pept2prot') do
-  usage       'pept2prot [options]'
-  aliases     :p
-  summary     'Give protein information for given peptides'
-  description 'Search Unipept for the given peptides and return the lowest common ancestor'
+  usage 'pept2prot [options]'
+  aliases :pp
+  summary 'Fetch Uniprot records that match tryptic peptides.'
+  description <<-EOS
+  For each tryptic peptide the unipept pept2prot command retrieves from Unipept all Uniprot records whose protein sequence contains an exact matches to the tryptic peptide. The command expects a list of tryptic peptides that are passed
+
+  - as separate command line arguments
+
+  - in one or more text files that are passed as an argument to the -i option
 
-  flag :e, :equate, "equate I and L"
-  option :s, :select, "select the attributes", :argument => :required, :multiple => true
-  option :x, :xml, "download uniprot record in specified directory", :argument => :required
-  flag :a, :extra, "include all information. WARNING: will take much longer!"
+  - to standard input
+
+  The command will give priority to the first way tryptic peptides are passed, in the order as listed above. Text files and standard input should have one tryptic peptide per line.
+
+  The unipept pept2prot subcommand yields Uniprot records as output.
+  EOS
+
+  flag :e, :equate, 'equate isoleucine (I) and leucine (L) when matching peptides'
+  flag :a, :all, 'report all information fields of Uniprot records 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 :x, :xml, 'download XML-formatted Uniprot records into the specified download-directory. ', argument: :required
 
   runner Unipept::Commands::Pept2prot
 end
 
 root_cmd.define_command('taxonomy') do
-  usage       'taxonomy [options]'
-  aliases     :tax
-  summary     'Give NCBI taxonomy information on given input taxon ids'
-  description 'Returns information for each input taxon id'
+  usage 'taxonomy [options]'
+  aliases :tax
+  summary 'Fetch taxonomic information from Unipept Taxonomy.'
+  description <<-EOS
+  The unipept taxonomy command yields information from the Unipept Taxonomy records for a given list of NCBI Taxonomy Identifiers. The Unipept Taxonomy is a cleaned up version of the NCBI Taxonomy, and its records are also records of the NCBI Taxonomy. The command expects a list of NCBI Taxonomy Identifiers that are passed
+
+  - as separate command line arguments
+
+  - in one or more text files that are passed as an argument to the -i option
+
+  - to standard input
+
+  The command will give priority to the first way NCBI Taxonomy Identifiers are passed, in the order as listed above. Text files and standard input should have one NCBI Taxonomy Identifier per line.
+
+  The unipept taxonomy subcommand yields NCBI Taxonomy records as output.
+  EOS
 
-  option :s, :select, "select the attributes", :argument => :required, :multiple => true
-  flag :a, :extra, "include all information. WARNING: will take much longer!"
+  flag :a, :all, 'report all information fields of NCBI Taxonomy records 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
 
   runner Unipept::Commands::Taxonomy
 end

data/bin/uniprot

@@ -23,8 +23,22 @@ def get_uniprot_entry(arg, format)
 end
 
 root_cmd = Cri::Command.new_basic_root.modify do
-  name 'uniprot'
-  description 'Download protein sequence from uniprot.org'
+  name        'uniprot'
+  summary     'Command line interface to Uniprot web services.'
+  usage       'uniprot [options]'
+  description <<-EOS
+  The uniprot command is a command line wrapper around the Uniprot web services. The command expects a list of Uniprot Accession Numbers that are passed
+
+  - as separate command line arguments
+
+  - in one or more text files that are passed as an argument to the -i option
+
+  - to standard input
+
+  The command will give priority to the first way Uniprot Accession Numbers are passed, in the order as listed above. Text files and standard input should have one Uniprot Accession Number per line.
+
+  The uniprot command yields Uniprot records as output.
+  EOS
   required :f, :format, "specify output format (available: " + valid_formats.to_a.join(", ") + ")"
   run do |opts, args, cmd|
     if !opts[:format].nil? and !valid_formats.include? opts[:format]

data/unipept.gemspec

@@ -2,17 +2,17 @@
 # DO NOT EDIT THIS FILE DIRECTLY
 # Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
 # -*- encoding: utf-8 -*-
-# stub: unipept 0.6.4 ruby lib
+# stub: unipept 0.7.0 ruby lib
 
 Gem::Specification.new do |s|
   s.name = "unipept"
-  s.version = "0.6.4"
+  s.version = "0.7.0"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.require_paths = ["lib"]
   s.authors = ["Toon Willems", "Bart Mesuere", "Tom Naessens"]
-  s.date = "2015-05-17"
-  s.description = "Command line interface to Unipept web services."
+  s.date = "2015-05-20"
+  s.description = "  Command line interface to the Unipept (http://unipept.ugent.be) web services\n  (pept2lca, taxa2lca, pept2taxa and taxonomy) and some utility commands for\n  handling proteins using the command line.\n"
   s.email = "unipept@ugent.be"
   s.executables = ["unipept", "prot2pept", "peptfilter", "uniprot"]
   s.extra_rdoc_files = [
@@ -47,7 +47,7 @@ Gem::Specification.new do |s|
     "test/test_unipept.rb",
     "unipept.gemspec"
   ]
-  s.homepage = "https://github.com/unipept/unipept/"
+  s.homepage = "https://github.com/unipept/unipept-cli/"
   s.licenses = ["MIT"]
   s.required_ruby_version = Gem::Requirement.new(">= 1.9.3")
   s.rubygems_version = "2.2.2"

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: unipept
 version: !ruby/object:Gem::Version
-  version: 0.6.4
+  version: 0.7.0
 platform: ruby
 authors:
 - Toon Willems
@@ -10,7 +10,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-05-17 00:00:00.000000000 Z
+date: 2015-05-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: cri
@@ -110,7 +110,10 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '0.8'
-description: Command line interface to Unipept web services.
+description: |2
+    Command line interface to the Unipept (http://unipept.ugent.be) web services
+    (pept2lca, taxa2lca, pept2taxa and taxonomy) and some utility commands for
+    handling proteins using the command line.
 email: unipept@ugent.be
 executables:
 - unipept
@@ -148,7 +151,7 @@ files:
 - test/helper.rb
 - test/test_unipept.rb
 - unipept.gemspec
-homepage: https://github.com/unipept/unipept/
+homepage: https://github.com/unipept/unipept-cli/
 licenses:
 - MIT
 metadata: {}