jandot-ruby-ensembl-api 0.9.2

data/lib/ensembl.rb

@@ -0,0 +1,23 @@
+module Ensembl
+  ENSEMBL_RELEASE = 50
+end
+
+begin
+  require 'rubygems'
+  require 'bio'
+  rescue LoadError
+    raise LoadError, "You must have bioruby installed"
+end
+
+# Database connection
+require File.dirname(__FILE__) + '/ensembl/db_connection.rb'
+
+# Core modules
+require File.dirname(__FILE__) + '/ensembl/core/activerecord.rb'
+require File.dirname(__FILE__) + '/ensembl/core/transcript.rb'
+require File.dirname(__FILE__) + '/ensembl/core/slice.rb'
+require File.dirname(__FILE__) + '/ensembl/core/project.rb'
+require File.dirname(__FILE__) + '/ensembl/core/transform.rb'
+
+# Variation modules
+require File.dirname(__FILE__) + '/ensembl/variation/activerecord.rb'

data/samples/examples_perl_tutorial.rb

@@ -0,0 +1,120 @@
+#!/usr/local/bin/ruby
+
+require File.dirname(__FILE__) + '/../lib/ensembl.rb'
+require 'yaml'
+require 'progressbar'
+
+include Ensembl::Core
+
+## Connecting to the Database
+DBConnection.connect('homo_sapiens')
+
+## Object adaptors
+# not necessary, ruby uses class methods instead
+
+## Slices
+puts "== Some slices: =="
+puts Slice.fetch_by_region('chromosome','X').to_yaml
+puts Slice.fetch_by_region('clone','AL359765.6').to_yaml
+puts Slice.fetch_by_region('supercontig','NT_011333').to_yaml
+puts Slice.fetch_by_region('chromosome', '20', 1000000, 2000000).to_yaml
+puts Slice.fetch_by_gene_stable_id('ENSG00000099889', 5000).to_yaml
+
+puts "== All chromosomes: =="
+Slice.fetch_all('chromosome', 'NCBI36').each do |chr|
+  puts chr.display_name
+end
+
+puts "== Number of clone slices: " + Slice.fetch_all('clone').length.to_s
+
+puts "== Subslices of chromosome 19 (length = 10000000; overlap = 250): =="
+Slice.fetch_by_region('chromosome','19').split(10000000, 250).each do |sub_slice|
+  puts sub_slice.display_name
+end
+
+puts "== Sequence of a very small slice: Chr19:112200..112250 =="
+slice = Slice.fetch_by_region('chromosome','19',112200,112250)
+puts slice.seq
+
+puts "== Query a slice about itself =="
+puts slice.to_yaml
+
+puts "== Get genes for a slice =="
+slice = Slice.fetch_by_region('chromosome','19',112200,1122000)
+slice.genes.each do |gene|
+  puts gene.stable_id
+end
+
+puts "== Get DNA alignment features for 20:80000..88000 =="
+slice = Slice.fetch_by_region('chromosome','20',80000,88000)
+slice.dna_align_features[0..2].each do |daf|
+  puts daf.to_yaml
+end
+
+puts "== Get sequence for transcript ENST00000383673 =="
+transcript = Transcript.find_by_stable_id('ENST00000383673')
+puts transcript.seq
+
+puts "== Get synonyms for marker D9S1038E =="
+marker = Ensembl::Core::Marker.find_by_name('D9S1038E')
+marker.marker_synonyms[0..5].each do |ms|
+  puts ms.to_yaml
+end
+
+puts "== Get 5 features for this marker =="
+marker = Ensembl::Core::Marker.find_by_name('D9S1038E')
+marker.marker_features[0..5].each do |mf|
+  puts 'name: ' + marker.name
+  puts 'seq_region name: ' + mf.seq_region.name
+  puts 'start: ' + mf.seq_region_start.to_s
+  puts 'stop: ' + mf.seq_region_end.to_s
+end
+
+puts "== Get 5 features for chromosome 22 =="
+slice = Ensembl::Core::Slice.fetch_by_region('chromosome', '22')
+slice.marker_features.slice(0,5).each do |mf|
+  puts mf.marker.name + "\t" + mf.slice.display_name
+end
+
+puts "== Transcript: from cDNA to genomic positions =="
+transcript = Ensembl::Core::Transcript.find(276333)
+puts "Transcript is ENST00000215574"
+puts "Genomic position 488053 is cDNA position: " + transcript.genomic2cdna(488053).to_s
+puts "cDNA position 601 is genomic position: " + transcript.cdna2genomic(601).to_s
+puts "Genomic position 488053 is CDS position: " + transcript.genomic2cds(488053).to_s
+puts "CDS position 401 is genomic position: " + transcript.cds2genomic(401).to_s
+
+puts "== Transcript: get pieces of DNA for a transcript =="
+transcript = Ensembl::Core::Transcript.find_by_stable_id('ENST00000380593')
+puts transcript.stable_id
+puts "5'UTR: " + transcript.five_prime_utr_seq
+puts "3'UTR: " + transcript.three_prime_utr_seq
+puts "CDS: " + transcript.cds_seq
+puts "protein: " + transcript.protein_seq
+
+#### And now we'll do some stuff with cows.
+CoreDBConnection.connection.disconnect!
+CoreDBConnection.connect('bos_taurus')
+
+puts "== Projecting a slice from component to assembly: =="
+puts "==   scaffold Chr4.003.105:42..2007 to chromosome level =="
+source_slice = Slice.fetch_by_region('scaffold','Chr4.003.105', 42, 2007)
+target_slices = source_slice.project('chromosome')
+puts target_slices.collect{|s| s.display_name}.join("\n")
+
+puts "== Projecting a slice from assembly to components: =="
+puts "==   chromosome slice chr4:329500..380000 to contig level =="
+source_slice = Slice.fetch_by_region('chromosome', '4', 329500, 380000)
+target_slices = source_slice.project('contig')
+puts target_slices.collect{|s| s.display_name}.join("\n")
+
+puts "== Transforming a gene from chromosome level to scaffold level =="
+gene = Gene.find(2408)
+cloned_gene = gene.transform('scaffold')
+puts gene.slice.display_name
+puts cloned_gene.slice.display_name
+
+puts "== Relationships for Gene class =="
+puts 'belongs to: ' + Gene.reflect_on_all_associations(:belongs_to).collect{|a| a.name.to_s}.join(',')
+puts 'has many: ' + Gene.reflect_on_all_associations(:has_many).collect{|a| a.name.to_s}.join(',')
+

data/samples/small_example_ruby_api.rb

@@ -0,0 +1,34 @@
+#!/usr/bin/ruby
+require '../lib/ensembl'
+
+include Ensembl::Core
+
+DBConnection.connect('homo_sapiens')
+
+puts "== Get a slice =="
+slice = Slice.fetch_by_region('chromosome','4',10000,99999,-1)
+puts slice.display_name
+
+puts "== Print all gene for that slice (regardless of what coord_system genes are annotated on) =="
+slice.genes.each do |gene|
+  puts gene.stable_id + "\t" + gene.status + "\t" + gene.slice.display_name
+end
+
+puts "== Get a transcript and print its 5'UTR, CDS and protein sequence =="
+transcript = Transcript.find_by_stable_id('ENST00000380593')
+puts "5'UTR: " + transcript.five_prime_utr_seq
+puts "CDS: " + transcript.cds_seq
+puts "peptide: " + transcript.protein_seq
+
+DBConnection.connection.disconnect!
+DBConnection.connect('bos_taurus',45)
+
+puts "== Transforming a cow gene from chromosome level to scaffold level =="
+gene = Gene.find(2408)
+cloned_gene = gene.transform('scaffold')
+puts "Original: " + gene.slice.display_name
+puts "Now: " + cloned_gene.slice.display_name
+
+puts "== What things are related to a 'gene' object? =="
+puts 'Genes belong to: ' + Gene.reflect_on_all_associations(:belongs_to).collect{|a| a.name.to_s}.join(',')
+puts 'Genes have many: ' + Gene.reflect_on_all_associations(:has_many).collect{|a| a.name.to_s}.join(',')

data/test/unit/release_45/core/run_tests.rb

@@ -0,0 +1,12 @@
+require 'test/unit'
+
+# Either run the tests that use Bos taurus
+#require 'test_project'
+#require 'test_transform'
+#require 'test_slice'
+
+# Or the ones using Homo sapiens
+require 'test_relationships'
+require 'test_project_human'
+require 'test_sequence'
+require 'test_transcript'

data/test/unit/release_45/core/test_project.rb

@@ -0,0 +1,235 @@
+#
+# = test/unit/test_project.rb - Unit test for Ensembl::Core
+#
+# Copyright::   Copyright (C) 2007
+#               Jan Aerts <http://jandot.myopenid.com>
+# License::     Ruby's
+#
+# $Id:
+require 'pathname'
+libpath = Pathname.new(File.join(File.dirname(__FILE__), ['..'] * 4, 'lib')).cleanpath.to_s
+$:.unshift(libpath) unless $:.include?(libpath)
+
+require 'test/unit'
+require 'ensembl'
+
+include Ensembl::Core
+
+DBConnection.connect('bos_taurus')
+
+class CoordinateMappingsTestSimple < Test::Unit::TestCase
+  # First see if the relationships work
+  def test_assemblies
+    # Scaffold Chr4.003.105 should only be a component of chromosome 4
+    scaffold_coord_system = CoordSystem.find_by_name('scaffold')
+    chr4_105 = SeqRegion.find_by_name_and_coord_system_id('Chr4.003.105', scaffold_coord_system.id)
+    assert_equal(1, chr4_105.assembled_seq_regions.length)
+
+    # Chromosome 4 has 4118 components (127 scaffolds and 3991 contigs)
+    chr_coord_system = CoordSystem.find_by_name('chromosome')
+    chr4 = SeqRegion.find_by_name_and_coord_system_id('4', chr_coord_system.id)
+    assert_equal(4118, chr4.component_seq_regions.length)
+
+    # Chromosome 4 has 127 scaffolds
+    assert_equal(127, chr4.component_seq_regions('scaffold').length)
+
+    # Positions of the link between Chr4 and Chr4.003.105
+    # * Scaffold Chr4.003.105 starts at position 96652111 on chromosome Chr4
+    # * Scaffold Chr4.003.105 does not have links as assembly with coord_system 'chromosome'
+    assert_equal(96652111, chr4_105.assembly_links_as_component('chromosome')[0].asm_start)
+    assert_equal(nil, chr4_105.assembly_links_as_assembly('chromosome')[0])
+    end
+end
+
+class Sequences < Test::Unit::TestCase
+  def setup
+    @seq_region = SeqRegion.find(92594)
+  end
+
+  def test_simple
+    assert_equal('AGCTATTTTATGACTT', @seq_region.seq.slice(4,16))
+  end
+
+  def test_subseq
+    assert_equal('AGCTATTTTATGACTT', @seq_region.subseq(5,20))
+  end
+end
+
+class SliceProjectFromComponentToAssembly < Test::Unit::TestCase
+  # |------------------------------------------> chromosome
+  #     ^                 ^
+  #     |                 |
+  #     |-----------------> scaffold
+  def test_project_from_whole_component_to_assembly
+    source_slice = Slice.fetch_by_region('scaffold','Chr4.003.105')
+    target_slices = source_slice.project('chromosome')
+
+    # Start and stop of chr4_105 on Chr4
+    assert_equal(96652111, target_slices[0].start)
+    assert_equal(97251689, target_slices[0].stop)
+  end
+
+  # |------------------------------------------> chromosome
+  #         ^        ^
+  #         |        |
+  #     |-----------------> scaffold
+  def test_project_from_component_to_assembly_with_positions
+    source_slice = Slice.fetch_by_region('scaffold','Chr4.003.105', 42, 2007)
+    target_slices = source_slice.project('chromosome')
+
+    # Position 42 on chr4_105 is position 96652152, position 2007 is 96654117
+    assert_equal(96652152, target_slices[0].start)
+    assert_equal(96654117, target_slices[0].stop)
+  end
+
+  # |------------------------------------------> scaffold
+  #         ^        ^
+  #         |        |
+  #       ----------------> contig
+  #      /
+  #   |--
+  def test_project_from_component_to_assembly_with_positions_and_cmp_start_not_1
+    source_slice = Slice.fetch_by_region('contig', 'AAFC03020247', 42, 2007)
+    target_slices = source_slice.project('scaffold')
+
+    # Position 42 on AAFC03020247 is position 6570 on ChrUn.003.3522, position 2007 is 8565
+    assert_equal(6570, target_slices[0].start)
+    assert_equal(8535, target_slices[0].stop)
+  end
+
+  # |------------------------------------------> scaffold
+  #         ^        ^
+  #         |        |
+  #     <-----------------| contig
+  def test_project_from_component_to_assembly_with_strand
+    source_slice_fw = Slice.fetch_by_region('contig', 'AAFC03020247')
+    target_slices_fw = source_slice_fw.project('scaffold')
+
+    assert_equal(1, target_slices_fw[0].strand)
+
+    source_slice_rev = Slice.fetch_by_region('contig', 'AAFC03061502')
+    target_slices_rev = source_slice_rev.project('scaffold')
+
+    assert_equal(-1, target_slices_rev[0].strand)
+  end
+end
+
+class SliceProjectFromComponentToAssemblyUsingTopLevel < Test::Unit::TestCase
+  # |------------------------------------------> chromosome
+  #     ^                 ^
+  #     |                 |
+  #     |-----------------> scaffold
+  def test_project_from_whole_component_to_assembly
+    source_slice = Slice.fetch_by_region('scaffold','Chr4.003.105')
+    target_slices = source_slice.project('toplevel')
+
+    # Start and stop of chr4_105 on Chr4
+    assert_equal(96652111, target_slices[0].start)
+    assert_equal(97251689, target_slices[0].stop)
+  end
+
+  # |------------------------------------------> chromosome
+  #         ^        ^
+  #         |        |
+  #     |-----------------> scaffold
+  def test_project_from_component_to_assembly_with_positions
+    source_slice = Slice.fetch_by_region('scaffold','Chr4.003.105', 42, 2007)
+    target_slices = source_slice.project('toplevel')
+
+    # Position 42 on chr4_105 is position 96652152, position 2007 is 96654117
+    assert_equal(96652152, target_slices[0].start)
+    assert_equal(96654117, target_slices[0].stop)
+  end
+end
+
+class SliceProjectFromAssemblyToComponentForwardStrands < Test::Unit::TestCase
+  def setup
+    @source_slice_single_scaffold = Slice.fetch_by_region('chromosome', '4', 96652152, 96654117)
+    @target_slices_single_scaffold = @source_slice_single_scaffold.project('scaffold')
+
+    @source_slice_two_scaffolds = Slice.fetch_by_region('chromosome','4', 96652152, 98000000)
+    @target_slices_two_scaffolds = @source_slice_two_scaffolds.project('scaffold')
+
+    @source_slice_four_scaffolds = Slice.fetch_by_region('chromosome', '4', 96652152, 99000000)
+    @target_slices_four_scaffolds = @source_slice_four_scaffolds.project('scaffold')
+
+    @source_slice_contigs_with_strand = Slice.fetch_by_region('chromosome', '4', 329500, 380000)
+    @target_slices_contigs_with_strand = @source_slice_contigs_with_strand.project('contig')
+
+    @source_slice_contigs_with_strand_ends_in_gaps = Slice.fetch_by_region('chromosome', '4', 345032, 388626)
+    @target_slices_contigs_with_strand_ends_in_gaps = @source_slice_contigs_with_strand_ends_in_gaps.project('contig')
+  end
+
+  #     |-----------------> scaffold
+  #         ^          ^
+  #         |          |
+  # |------------------------------------------> chromosome
+  def test_project_from_assembly_to_single_component
+    # Position 96652152 on chr4 is position 42 on scaffold, position 96654117 is 2007
+    assert_equal('Chr4.003.105', @target_slices_single_scaffold[0].seq_region.name)
+    assert_equal(42, @target_slices_single_scaffold[0].start)
+    assert_equal(2007, @target_slices_single_scaffold[0].stop)
+  end
+
+  #     |----->   |--------> scaffold
+  #         ^          ^
+  #         |          |
+  # |------------------------------------------> chromosome
+  def test_project_from_assembly_to_two_components
+    # This chromosomal region is covered by scaffolds Chr4.003.105, a gap and Chr5.003.106
+    #  * Position 96652152 on chr 4 is position 42 on scaffold Chr4.105
+    #  * Position 98000000 on chr 4 is position 738311 on scaffold Chr4.106
+    assert_equal(3, @target_slices_two_scaffolds.length)
+    assert_equal('scaffold:Btau_3.1:Chr4.003.105:42:599579:1', @target_slices_two_scaffolds[0].display_name)
+    assert_equal(Gap, @target_slices_two_scaffolds[1].class)
+    assert_equal('scaffold:Btau_3.1:Chr4.003.106:1:738311:1', @target_slices_two_scaffolds[2].display_name)
+  end
+
+  #     |----->   |-------->   |--->    |------->  scaffold
+  #         ^                                ^
+  #         |                                |
+  # |--------------------------------------------------> chromosome
+  def test_project_from_assembly_to_four_components
+    # This chromosomal region is covered by scaffolds Chr4.003.105 and Chr5.003.106
+    assert_equal(7, @target_slices_four_scaffolds.length)
+    assert_equal('scaffold:Btau_3.1:Chr4.003.105:42:599579:1', @target_slices_four_scaffolds[0].display_name)
+    assert_equal(Gap, @target_slices_four_scaffolds[1].class)
+    assert_equal('scaffold:Btau_3.1:Chr4.003.106:1:1009889:1', @target_slices_four_scaffolds[2].display_name)
+    assert_equal(Gap, @target_slices_four_scaffolds[3].class)
+    assert_equal('scaffold:Btau_3.1:Chr4.003.107:1:608924:1', @target_slices_four_scaffolds[4].display_name)
+    assert_equal(Gap, @target_slices_four_scaffolds[5].class)
+    assert_equal('scaffold:Btau_3.1:Chr4.003.108:1:99498:1', @target_slices_four_scaffolds[6].display_name)
+  end
+
+  #     |----->   |-------->   <---|  <--|  |----->  contig
+  #         ^                                 ^
+  #         |                                 |
+  # |--------------------------------------------------> chromosome
+  def test_project_from_assembly_to_contigs_with_strand
+    # This chromosomal region is covered by 5 contigs and 1 gap: CoCoCoGaCoCo
+    # Two of the contigs are on the reverse strand.
+    assert_equal(6, @target_slices_contigs_with_strand.length)
+    assert_equal('contig::AAFC03092598:60948:61145:1', @target_slices_contigs_with_strand[0].display_name)
+    assert_equal('contig::AAFC03118261:25411:37082:1', @target_slices_contigs_with_strand[1].display_name)
+    assert_equal('contig::AAFC03092594:1:3622:-1', @target_slices_contigs_with_strand[2].display_name)
+    assert_equal(Gap, @target_slices_contigs_with_strand[3].class)
+    assert_equal('contig::AAFC03092597:820:35709:-1', @target_slices_contigs_with_strand[4].display_name)
+    assert_equal('contig::AAFC03032210:13347:13415:1', @target_slices_contigs_with_strand[5].display_name)
+  end
+
+  #      <--|  |----->        contig
+  #   ^                 ^
+  #   |                 |
+  # |--------------------------------------------------> chromosome
+  def test_project_from_assembly_to_contigs_with_strand_and_ending_in_gaps
+    # This chromosomal region is covered by 2 contigs and 2 gaps at the end: GaCoCoGa
+    # Two of the contigs are on the reverse strand.
+    assert_equal(4, @target_slices_contigs_with_strand_ends_in_gaps.length)
+    assert_equal(Gap, @target_slices_contigs_with_strand_ends_in_gaps[0].class)
+    assert_equal('contig::AAFC03092597:820:35709:-1', @target_slices_contigs_with_strand_ends_in_gaps[1].display_name)
+    assert_equal('contig::AAFC03032210:13347:22036:1', @target_slices_contigs_with_strand_ends_in_gaps[2].display_name)
+    assert_equal(Gap, @target_slices_contigs_with_strand_ends_in_gaps[3].class)
+  end
+
+
+end

data/test/unit/release_45/core/test_project_human.rb

@@ -0,0 +1,58 @@
+#
+# = test/unit/test_project.rb - Unit test for Ensembl::Core
+#
+# Copyright::   Copyright (C) 2007
+#               Jan Aerts <http://jandot.myopenid.com>
+# License::     Ruby's
+#
+# $Id:
+require 'pathname'
+libpath = Pathname.new(File.join(File.dirname(__FILE__), ['..'] * 4, 'lib')).cleanpath.to_s
+$:.unshift(libpath) unless $:.include?(libpath)
+
+require 'test/unit'
+require 'ensembl'
+
+include Ensembl::Core
+
+DBConnection.connect('homo_sapiens')
+
+class AssemblyExceptions < Test::Unit::TestCase
+  def test_chr_x
+    source_slice = Slice.fetch_by_region('chromosome','X', 2709497, 2709520)
+    assert_equal('tagttatagattaaaagaagttaa', source_slice.seq)
+  end
+
+  def test_slice_overlapping_PAR_and_allosome
+    source_slice = Slice.fetch_by_region('chromosome','Y',2709500,2709540)
+    target_slices = source_slice.project('contig')
+    assert_equal('contig::AC006209.25.1.141759:23323:23343:-1', target_slices[0].display_name)
+    assert_equal('contig::AC006040.3.1.186504:57272:57291:1', target_slices[1].display_name)
+  end
+
+  def test_seq_slice_overlapping_PAR
+    seq = ''
+    File.open('../../data/seq_y.fa').reject{|l| l=~/^>/}.each do |line|
+      line.chomp!
+      seq += line
+    end
+    seq.downcase!
+
+    source_slice = Slice.fetch_by_region('chromosome', 'Y', 2709497, 2709542)
+    assert_equal(seq.downcase, source_slice.seq)
+  end
+
+  # The MHC haplotypes for human are not implemented yet, so we raise an error
+  # in the code.
+  def test_seq_slice_overlapping_HAP
+    seq = ''
+    File.open('../../data/seq_c6qbl.fa').reject{|l| l=~/^>/}.each do |line|
+      line.chomp!
+      seq += line
+    end
+    seq.downcase!
+
+    source_slice = Slice.fetch_by_region('chromosome', 'c6_QBL', 33451191, 33451690)
+    assert_raise(NotImplementedError) {source_slice.seq}
+  end
+end