bio-gff3 0.8.0 → 0.8.2

data/Gemfile

@@ -2,6 +2,7 @@ source "http://rubygems.org"
 # Add dependencies required to use your gem here.
 # Example:
 #   gem "activesupport", ">= 2.3.5"
+gem "bio", ">= 1.3.1"
 
 # Add dependencies to develop your gem here.
 # Include everything needed to run rake, tests, features, etc.
@@ -10,6 +11,6 @@ group :development do
   gem "bundler", "~> 1.0.0"
   gem "jeweler", "~> 1.5.2"
   gem "rcov", ">= 0"
-  gem "bio", ">= 1.4.1"
-	gem "rspec"
+  gem "bio", ">= 1.3.1"
+	gem "rspec", ">= 2.0.0"
 end

data/Gemfile.lock

@@ -24,9 +24,9 @@ PLATFORMS
   ruby
 
 DEPENDENCIES
-  bio (>= 1.4.1)
+  bio (>= 1.3.1)
   bundler (~> 1.0.0)
   jeweler (~> 1.5.2)
   rcov
-  rspec
+  rspec (>= 2.0.0)
   shoulda

data/README.rdoc

@@ -1,69 +1,60 @@
 = bio-gff3
 
-GFF3 plugin for BioRuby, aimed at parsing big data
+GFF3 parser, aimed at parsing big data GFF3 to return sequences of any type, 
+including assembled mRNA, protein and CDS sequences.
 
 Features:
 
-# Take GFF (genome browser) information and digest mRNA and CDS sequences
+# Take GFF3 (genome browser) information of any type, and assemble sequences, e.g. mRNA and CDS
 # Options for low memory use and caching of records
-# Support for external FASTA files
+# Support for external FASTA input files
+# Use of multi-cores (NYI)
+
+Currently the output is a FASTA file.
 
 You can use this plugin in two ways. First as a standalone program, next as a
 plugin library to BioRuby.
 
-For example, fetch mRNA and CDS information from GFF3 files and output to FASTA:
-
-  ./bin/gff3-fetch mrna test/data/gff/test.gff3
-  ./bin/gff3-fetch cds test/data/gff/test.gff3
-
-Or clone this repository and add the 'lib' dir to the Ruby search path and 
-
-  require 'bio/db/gff/gffdb'
-
-You can also run RSpec with something like
-
-  rspec -I ../bioruby/lib/ spec/*.rb 
-
-This implementation depends on BioRuby's basic GFF3 parser, with the possible
-advantage that the plugin is faster and does not consume all memory. The Gff3
-specs are based on the output of the Wormbase genome browser.
+== Install and run gff3-fetch
 
-For a write-up see http://thebird.nl/bioruby/BioRuby_GFF3.html 
+After installing ruby 1.9, or later, you can use rubygems
 
--------------------------------------------------------------------------------
+  gem install bio-gff3
 
+Then, fetch mRNA and CDS information from GFF3 files and output to FASTA:
 
-  Fetch and assemble mRNAs, or CDS and print in FASTA format. 
+  gff3-fetch mrna test/data/gff/test.gff3
+  gff3-fetch cds test/data/gff/test.gff3
 
-    gff3-fetch [--no-cache] mRNA|CDS [filename.fa] filename.gff
+== Development
 
-  Where:
+To use the library
 
-    --no-cache      : do not load everything in memory (slower)
-    mRNA            : assemble mRNA
-    CDS             : assemble CDS 
+  require 'bio-gff3'
 
-  Multiple GFF3 files can be used. For external FASTA files, always the last
-  one before the GFF file is used.
+For coding examples see ./bin/gff3-fetch and the ./spec/*rb
 
-  Examples:
+You can run RSpecs with something like
 
-    Find mRNA and CDS information from test.gff3 (which includes sequence information)
+  rspec -I ../bioruby/lib/ spec/*.rb 
 
-      gff3-fetch mRNA test/data/gff/test.gff3
-      gff3-fetch CDS test/data/gff/test.gff3
+(supposing you are referring a bioruby source repository)
 
-    Find CDS from external FASTA file
+This implementation depends on BioRuby's basic GFF3 parser, with the possible
+advantage that the plugin can assemble sequences, is faster and does not
+consume all memory. The Gff3 specs are based on the output of the Wormbase
+genome browser.
 
-      gff3-fetch CDS test/data/gff/MhA1_Contig1133.fa test/data/gff/MhA1_Contig1133.gff3
+== See also
 
-    Find mRNA from external FASTA file, without loading everything in RAM
+  gff3-fetch --help
 
-      gff3-fetch --no-cache mRNA test/data/gff/test-ext-fasta.fa test/data/gff/test-ext-fasta.gff3   
+For a write-up see http://thebird.nl/bioruby/BioRuby_GFF3.html 
 
-  If you use this software, please cite http://dx.doi.org/10.1093/bioinformatics/btq475
+-------------------------------------------------------------------------------
 
 == Copyright
 
 Copyright (C) 2010,2011 Pjotr Prins <pjotr.prins@thebird.nl> 
 
+

data/VERSION

@@ -1 +1 @@
-0.8.0
+0.8.2

data/bin/gff3-fetch

@@ -6,37 +6,89 @@
 #
 # Copyright (C) 2010,2011 Pjotr Prins <pjotr.prins@thebird.nl>
 
-
 USAGE = <<EOM
-  Fetch and assemble mRNAs, or CDS and print in FASTA format. 
 
-    gff3-fetch [--no-cache] mRNA|CDS [filename.fa] filename.gff
+  Fetch and assemble GFF3 types (e.g. ORF, mRNA, CDS) + print in FASTA format. 
+
+    gff3-fetch [--low-mem] [--validate] type [filename.fa] filename.gff3
 
-  Where:
+  Where (NYI == Not Yet Implemented):
+
+    --translate     : output as amino acid sequence 
+    --validate      : validate GFF3 file by translating
+    --no-assemble   : output each record as a sequence -- NYI
+    --add-phase     : output records using phase (useful w. no-assemble CDS to AA) --NYI
+    --fix           : check 3-frame translation and fix, if possible -- NYI
+  
+  type is any valid type in the GFF3 definition. For example:
 
-    --no-cache      : do not load everything in memory (slower)
     mRNA            : assemble mRNA
     CDS             : assemble CDS 
+    exon            : list all exons
+    gene/ORF        : list gene ORFs -- NYI
+    other           : use any type from GFF3 definition, e.g. 'Terminate' -- NYI
+
+  and the following performance options:
 
-  Multiple GFF3 files can be used. For external FASTA files, always the last
-  one before the GFF file is used.
+    --cache full    : load all in RAM (fast)
+    --cache none    : do not load anything in memory (slow)
+    --low-mem       : use LRU cache (limit RAM use, fast) -- NYI
+    --max-cpus num  : use num threads -- NYI
+    --emboss        : use EMBOSS translation (fast) -- NYI
+
+  Multiple GFF3 files can be used. With external FASTA files, always the last
+  one before the GFF3 filename is matched.
+
+  Note that above switches are only partially implemented at this stage. Full
+  feature support is projected Feb. 2011.
 
   Examples:
 
-    Find mRNA and CDS information from test.gff3 (which includes sequence information)
+    Assemble mRNA and CDS information from test.gff3 (which includes sequence information)
 
       gff3-fetch mRNA test/data/gff/test.gff3
       gff3-fetch CDS test/data/gff/test.gff3
 
-    Find CDS from external FASTA file
+    Find CDS records from external FASTA file, adding phase and translate to protein sequence
 
-      gff3-fetch CDS test/data/gff/MhA1_Contig1133.fa test/data/gff/MhA1_Contig1133.gff3
+      gff3-fetch --no-assemble --add-phase --translate CDS test/data/gff/MhA1_Contig1133.fa test/data/gff/MhA1_Contig1133.gff3
 
     Find mRNA from external FASTA file, without loading everything in RAM
 
-      gff3-fetch --no-cache mRNA test/data/gff/test-ext-fasta.fa test/data/gff/test-ext-fasta.gff3   
+      gff3-fetch --cache none mRNA test/data/gff/test-ext-fasta.fa test/data/gff/test-ext-fasta.gff3   
+      gff3-fetch --cache none mRNA test/data/gff/test-ext-fasta.fa test/data/gff/test-ext-fasta.gff3   
+
+    Validate GFF3 file using EMBOSS translation and validation
+
+      gff3-fetch --cache none --validate --emboss mRNA test/data/gff/test-ext-fasta.fa test/data/gff/test-ext-fasta.gff3   
+
+    Find GENEID predicted terminal exons
+
+      gff3-fetch terminal chromosome1.fa geneid.gff3
+
+== Performance
+
+time gff3-fetch cds m_hapla.WS217.dna.fa m_hapla.WS217.gff3 > test.fa
+
+  Cache      real     user     sys
+  ----------------------------------------------------
+  full       12m41s   12m28s   0m09s (0.8.0 Jan. 2011)
+  none      504m39s  477m49s  26m50s (0.8.0 Jan. 2011)
+  ----------------------------------------------------
+
+where
 
-  If you use this software, please cite http://dx.doi.org/10.1093/bioinformatics/btq475
+   52M m_hapla.WS217.dna.fa
+  456M m_hapla.WS217.gff3
+
+ruby 1.9.2p136 (2010-12-25 revision 30365) [x86_64-linux]
+on an 8 CPU, 2.6 GHz (6MB cache), 16 GB RAM machine. 
+
+== Cite
+
+  If you use this software, please cite 
+  
+    http://dx.doi.org/10.1093/bioinformatics/btq475
 
 == Copyright
 
@@ -44,58 +96,104 @@ Copyright (C) 2010,2011 Pjotr Prins <pjotr.prins@thebird.nl>
 
 EOM
 
-rootpath = File.dirname(File.dirname(__FILE__))
-$: << rootpath+'/lib'
-$: << rootpath+'/../bioruby/lib'
+SEP = File::SEPARATOR
+rootpath = File.dirname(File.dirname(__FILE__))+SEP
+$: << rootpath+'lib'
+GFF3_VERSION = File.new(rootpath+'VERSION').read.chomp
 
 require 'bio-gff3'
+require 'optparse'
+require 'ostruct'
+require 'bio/output/gfffastawriter'
 
-$stderr.print "BioRuby GFF3 Plugin Copyright (C) 2010,2011 Pjotr Prins <pjotr.prins@thebird.nl>\n\n"
+$stderr.print "BioRuby GFF3 Plugin "+GFF3_VERSION+" Copyright (C) 2010,2011 Pjotr Prins <pjotr.prins@thebird.nl>\n\n"
 
 if ARGV.size == 0
   print USAGE
 end
 
+options = OpenStruct.new()
+opts = OptionParser.new() { |opts|
+  opts.on_tail("-h", "--help", "Show help and examples") {
+    print(opts)
+    print USAGE
+    exit()
+  }
+
+  opts.on("--cache [none,full]", String, "Caching (default full)") do |cache|
+    case cache.downcase
+      when 'none'
+        options.cache = :cache_none
+      # when 'lru'
+      #   options.cache = :cache_lru
+      when 'full'
+        options.cache = :cache_full
+      else
+        raise 'Unknown --cache option'
+    end
+  end
+
+  opts.on("--translate", "output as amino acid sequence") do |b|
+    options.translate = b
+  end
+
+  opts.on("--validate", "validate GFF3 file by translating") do |v|
+    options.validate = v
+    $stop_on_error = true  # replace global in near future
+  end
+
+  # opts.on("-q", "--quiet", "Run quietly") do |q|
+  #   options.quiet = q
+  # end
+
+  # opts.on("-v", "--[no-]verbose", "Run verbosely") do |v|
+  #   options.verbose = v
+  # end
+
+  # opts.on("-t", "--[no-]trace", "Debug") do |t|
+  #   options.trace = t
+  # end
+}
+opts.parse!(ARGV)
+
 gfftype = ARGV.shift
-caching = true
-if gfftype == "--no-cache"
-  caching = false
-  gfftype = ARGV.shift
-end
+
 raise "Unknown GFF type '#{gfftype}'" if gfftype !~ /mrna|cds|exon/i
 
 fastafn = nil
 
 ARGV.each do | fn |
-  if File.extname(fn) =~ /fa|fas|fasta/i
+  if File.extname(fn) =~ /fa|fas|fasta$/i
+    raise "Only one fasta file allowed per GFF3" if fastafn != nil
     fastafn = fn
     next
   end
-  options = {:validate => false}
-  options = {:validate => false, :cache_components => :cache_none, :cache_records => :cache_none} if caching == false
-  options[:fasta_filename] = fastafn if fastafn
 
-  gffdb = Bio::GFFbrowser::GFFdb.new(fn,options)
+  opts = {}
+  opts[:validate] = options.validate
+  opts[:cache_components] = options.cache
+  opts[:cache_records]    = options.cache
+  opts[:fasta_filename] = fastafn if fastafn
+  gffdb = Bio::GFFbrowser::GFFdb.new(fn,opts)
   gff = gffdb.assembler
+  writer = Bio::GFFbrowser::FastaWriter.new(options.translate, options.validate)
   case gfftype.downcase
     when 'mrna' 
           gff.each_mRNA_seq do | id, seq |
-            puts ">"+id
-            puts seq
+            writer.put(id,seq)
           end
     when 'exon'
           gff.each_exon_seq do | id, seq |
-            puts ">"+id
-            puts seq
+            writer.put(id,seq)
           end
     when 'cds'
           gff.each_CDS_seq do | id, seq |
-            puts ">"+id
-            puts seq
+            writer.put(id,seq)
           end
     else
       raise "Unknown action <#{gfftype}>"
   end
+  fastafn = nil
 end
 
 

data/bio-gff3.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{bio-gff3}
-  s.version = "0.8.0"
+  s.version = "0.8.2"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Pjotr Prins"]
-  s.date = %q{2010-12-31}
+  s.date = %q{2011-01-03}
   s.default_executable = %q{gff3-fetch}
   s.description = %q{GFF3 (genome browser) information and digest mRNA and CDS sequences.
 Options for low memory use and caching of records.
@@ -38,6 +38,7 @@ Support for external FASTA files.
     "lib/bio/db/gff/gffinmemory.rb",
     "lib/bio/db/gff/gffnocache.rb",
     "lib/bio/db/gff/gffparser.rb",
+    "lib/bio/output/gfffastawriter.rb",
     "lib/bio/system/lruhash.rb",
     "spec/gff3_assemble2_spec.rb",
     "spec/gff3_assemble3_spec.rb",
@@ -76,27 +77,30 @@ Support for external FASTA files.
     s.specification_version = 3
 
     if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
+      s.add_runtime_dependency(%q<bio>, [">= 1.3.1"])
       s.add_development_dependency(%q<shoulda>, [">= 0"])
       s.add_development_dependency(%q<bundler>, ["~> 1.0.0"])
       s.add_development_dependency(%q<jeweler>, ["~> 1.5.2"])
       s.add_development_dependency(%q<rcov>, [">= 0"])
-      s.add_development_dependency(%q<bio>, [">= 1.4.1"])
-      s.add_development_dependency(%q<rspec>, [">= 0"])
+      s.add_development_dependency(%q<bio>, [">= 1.3.1"])
+      s.add_development_dependency(%q<rspec>, [">= 2.0.0"])
     else
+      s.add_dependency(%q<bio>, [">= 1.3.1"])
       s.add_dependency(%q<shoulda>, [">= 0"])
       s.add_dependency(%q<bundler>, ["~> 1.0.0"])
       s.add_dependency(%q<jeweler>, ["~> 1.5.2"])
       s.add_dependency(%q<rcov>, [">= 0"])
-      s.add_dependency(%q<bio>, [">= 1.4.1"])
-      s.add_dependency(%q<rspec>, [">= 0"])
+      s.add_dependency(%q<bio>, [">= 1.3.1"])
+      s.add_dependency(%q<rspec>, [">= 2.0.0"])
     end
   else
+    s.add_dependency(%q<bio>, [">= 1.3.1"])
     s.add_dependency(%q<shoulda>, [">= 0"])
     s.add_dependency(%q<bundler>, ["~> 1.0.0"])
     s.add_dependency(%q<jeweler>, ["~> 1.5.2"])
     s.add_dependency(%q<rcov>, [">= 0"])
-    s.add_dependency(%q<bio>, [">= 1.4.1"])
-    s.add_dependency(%q<rspec>, [">= 0"])
+    s.add_dependency(%q<bio>, [">= 1.3.1"])
+    s.add_dependency(%q<rspec>, [">= 2.0.0"])
   end
 end
 

data/lib/bio/db/gff/gffassemble.rb

@@ -17,9 +17,14 @@ module Bio
           $stderr.print "Info: "+str+" <#{id}>\n"
         end
 
-        def warn str,id=''
+        def warn str, id=''
           Kernel.warn "Warning: "+str+" <#{id}>"
         end
+
+        def error str, id=''
+          Kernel.warn "Error: "+str+" <#{id}>"
+          exit(1) if $stop_on_error
+        end
       end
 
       # Helper class for counting IDs

data/lib/bio/db/gff/gffnocache.rb

@@ -15,6 +15,8 @@ module Bio
 
       module NoCacheHelpers 
 
+        # Module to fetch a line from GFF3 file and returns a parsed 
+        # record
         module SeekRec
           # Fetch a record using fh and file seek position
           def SeekRec::fetch(fh,fpos)
@@ -24,7 +26,8 @@ module Bio
           end
         end
 
-        # The hardwired to file RecList
+        # Helper class which gives Hash-like access to the 
+        # no-cache GFF3 file
         class SeekRecList 
           def initialize fh
             @fh = fh
@@ -49,6 +52,7 @@ module Bio
           end
         end
 
+        # List of ids
         class SeekLinkedRecs < Hash
           include Helpers::Error
           def add id, rec

data/lib/bio/db/gff/gffparser.rb

@@ -107,7 +107,7 @@ module Bio
               if sequence
                 yield description(id,component,reclist), assemble(sequence,component.start,reclist)
               else 
-                warn "No sequence information for",id
+                error "No sequence information for",id
               end
             end
           end
@@ -128,7 +128,7 @@ module Bio
                 end
                 yield description(id,component,reclist), seq
               else 
-                warn "No sequence information for",id
+                error "No sequence information for",id
               end
             end
           end
@@ -143,7 +143,7 @@ module Bio
                 seq = assemble(sequence,component.start,reclist)
                 yield description(id,component,reclist), seq
               else 
-                warn "No sequence information for",id
+                error "No sequence information for",id
               end
             end
           end

data/lib/bio/output/gfffastawriter.rb

@@ -0,0 +1,31 @@
+
+module Bio
+  module GFFbrowser
+
+    class FastaWriter
+      def initialize translate, validate
+        @do_translate = translate
+        @do_validate = validate
+      end
+
+      def put id, seq
+        puts '>'+id
+        put_seq seq
+      end
+      private
+
+      def put_seq seq
+        if @do_translate or @do_validate
+          ntseq = Bio::Sequence::NA.new(seq)
+          aaseq = ntseq.translate
+          puts aaseq if @do_translate
+          if @do_validate
+            raise 'Validation problem of '+id if aaseq.count('*') > 1
+          end
+          return if @do_translate
+        end
+        puts seq
+      end
+    end
+  end
+end

metadata

@@ -5,8 +5,8 @@ version: !ruby/object:Gem::Version
   segments: 
   - 0
   - 8
-  - 0
-  version: 0.8.0
+  - 2
+  version: 0.8.2
 platform: ruby
 authors: 
 - Pjotr Prins
@@ -14,12 +14,27 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-12-31 00:00:00 +01:00
+date: 2011-01-03 00:00:00 +01:00
 default_executable: gff3-fetch
 dependencies: 
 - !ruby/object:Gem::Dependency 
-  name: shoulda
+  name: bio
   requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        segments: 
+        - 1
+        - 3
+        - 1
+        version: 1.3.1
+  type: :runtime
+  prerelease: false
+  version_requirements: *id001
+- !ruby/object:Gem::Dependency 
+  name: shoulda
+  requirement: &id002 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
     - - ">="
@@ -29,10 +44,10 @@ dependencies:
         version: "0"
   type: :development
   prerelease: false
-  version_requirements: *id001
+  version_requirements: *id002
 - !ruby/object:Gem::Dependency 
   name: bundler
-  requirement: &id002 !ruby/object:Gem::Requirement 
+  requirement: &id003 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
     - - ~>
@@ -44,10 +59,10 @@ dependencies:
         version: 1.0.0
   type: :development
   prerelease: false
-  version_requirements: *id002
+  version_requirements: *id003
 - !ruby/object:Gem::Dependency 
   name: jeweler
-  requirement: &id003 !ruby/object:Gem::Requirement 
+  requirement: &id004 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
     - - ~>
@@ -59,10 +74,10 @@ dependencies:
         version: 1.5.2
   type: :development
   prerelease: false
-  version_requirements: *id003
+  version_requirements: *id004
 - !ruby/object:Gem::Dependency 
   name: rcov
-  requirement: &id004 !ruby/object:Gem::Requirement 
+  requirement: &id005 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
     - - ">="
@@ -72,35 +87,37 @@ dependencies:
         version: "0"
   type: :development
   prerelease: false
-  version_requirements: *id004
+  version_requirements: *id005
 - !ruby/object:Gem::Dependency 
   name: bio
-  requirement: &id005 !ruby/object:Gem::Requirement 
+  requirement: &id006 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
         segments: 
         - 1
-        - 4
+        - 3
         - 1
-        version: 1.4.1
+        version: 1.3.1
   type: :development
   prerelease: false
-  version_requirements: *id005
+  version_requirements: *id006
 - !ruby/object:Gem::Dependency 
   name: rspec
-  requirement: &id006 !ruby/object:Gem::Requirement 
+  requirement: &id007 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
         segments: 
+        - 2
         - 0
-        version: "0"
+        - 0
+        version: 2.0.0
   type: :development
   prerelease: false
-  version_requirements: *id006
+  version_requirements: *id007
 description: |
   GFF3 (genome browser) information and digest mRNA and CDS sequences.
   Options for low memory use and caching of records.
@@ -131,6 +148,7 @@ files:
 - lib/bio/db/gff/gffinmemory.rb
 - lib/bio/db/gff/gffnocache.rb
 - lib/bio/db/gff/gffparser.rb
+- lib/bio/output/gfffastawriter.rb
 - lib/bio/system/lruhash.rb
 - spec/gff3_assemble2_spec.rb
 - spec/gff3_assemble3_spec.rb
@@ -162,7 +180,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
-      hash: -1033924243
+      hash: -876270257
       segments: 
       - 0
       version: "0"