bio 1.3.1 → 1.4.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/ChangeLog +2105 -3728
- data/KNOWN_ISSUES.rdoc +35 -3
- data/README.rdoc +8 -2
- data/RELEASE_NOTES.rdoc +166 -0
- data/bin/bioruby +4 -1
- data/bioruby.gemspec +146 -1
- data/bioruby.gemspec.erb +3 -1
- data/doc/ChangeLog-before-1.3.1 +3961 -0
- data/doc/Tutorial.rd +154 -22
- data/doc/Tutorial.rd.html +125 -68
- data/lib/bio.rb +21 -6
- data/lib/bio/appl/bl2seq/report.rb +11 -202
- data/lib/bio/appl/blast/format0.rb +0 -193
- data/lib/bio/appl/blast/report.rb +2 -147
- data/lib/bio/appl/blast/wublast.rb +0 -208
- data/lib/bio/appl/fasta.rb +4 -19
- data/lib/bio/appl/fasta/format10.rb +0 -14
- data/lib/bio/appl/genscan/report.rb +0 -176
- data/lib/bio/appl/hmmer.rb +1 -15
- data/lib/bio/appl/hmmer/report.rb +0 -100
- data/lib/bio/appl/meme/mast.rb +156 -0
- data/lib/bio/appl/meme/mast/report.rb +91 -0
- data/lib/bio/appl/meme/motif.rb +48 -0
- data/lib/bio/appl/psort.rb +0 -111
- data/lib/bio/appl/psort/report.rb +1 -45
- data/lib/bio/appl/pts1.rb +2 -4
- data/lib/bio/appl/sosui/report.rb +5 -54
- data/lib/bio/appl/targetp/report.rb +1 -104
- data/lib/bio/appl/tmhmm/report.rb +0 -36
- data/lib/bio/command.rb +94 -10
- data/lib/bio/data/aa.rb +1 -77
- data/lib/bio/data/codontable.rb +1 -95
- data/lib/bio/data/na.rb +1 -26
- data/lib/bio/db/aaindex.rb +1 -38
- data/lib/bio/db/fasta.rb +1 -134
- data/lib/bio/db/fasta/format_qual.rb +204 -0
- data/lib/bio/db/fasta/qual.rb +102 -0
- data/lib/bio/db/fastq.rb +645 -0
- data/lib/bio/db/fastq/fastq_to_biosequence.rb +40 -0
- data/lib/bio/db/fastq/format_fastq.rb +175 -0
- data/lib/bio/db/genbank/genbank.rb +1 -86
- data/lib/bio/db/gff.rb +0 -17
- data/lib/bio/db/go.rb +4 -72
- data/lib/bio/db/kegg/common.rb +112 -0
- data/lib/bio/db/kegg/compound.rb +29 -20
- data/lib/bio/db/kegg/drug.rb +74 -34
- data/lib/bio/db/kegg/enzyme.rb +26 -5
- data/lib/bio/db/kegg/genes.rb +128 -15
- data/lib/bio/db/kegg/genome.rb +3 -41
- data/lib/bio/db/kegg/glycan.rb +19 -24
- data/lib/bio/db/kegg/orthology.rb +16 -56
- data/lib/bio/db/kegg/reaction.rb +81 -28
- data/lib/bio/db/kegg/taxonomy.rb +1 -52
- data/lib/bio/db/litdb.rb +1 -16
- data/lib/bio/db/phyloxml/phyloxml.xsd +582 -0
- data/lib/bio/db/phyloxml/phyloxml_elements.rb +1174 -0
- data/lib/bio/db/phyloxml/phyloxml_parser.rb +954 -0
- data/lib/bio/db/phyloxml/phyloxml_writer.rb +228 -0
- data/lib/bio/db/prosite.rb +2 -95
- data/lib/bio/db/rebase.rb +5 -6
- data/lib/bio/db/sanger_chromatogram/abif.rb +120 -0
- data/lib/bio/db/sanger_chromatogram/chromatogram.rb +133 -0
- data/lib/bio/db/sanger_chromatogram/chromatogram_to_biosequence.rb +32 -0
- data/lib/bio/db/sanger_chromatogram/scf.rb +210 -0
- data/lib/bio/io/das.rb +0 -44
- data/lib/bio/io/ddbjxml.rb +1 -181
- data/lib/bio/io/flatfile.rb +1 -7
- data/lib/bio/io/flatfile/autodetection.rb +6 -0
- data/lib/bio/io/keggapi.rb +0 -442
- data/lib/bio/io/ncbirest.rb +130 -132
- data/lib/bio/io/ncbisoap.rb +2 -1
- data/lib/bio/io/pubmed.rb +0 -88
- data/lib/bio/location.rb +0 -73
- data/lib/bio/pathway.rb +0 -171
- data/lib/bio/sequence.rb +18 -1
- data/lib/bio/sequence/adapter.rb +3 -0
- data/lib/bio/sequence/format.rb +16 -0
- data/lib/bio/sequence/quality_score.rb +205 -0
- data/lib/bio/tree.rb +70 -5
- data/lib/bio/util/restriction_enzyme/single_strand.rb +3 -2
- data/lib/bio/util/sirna.rb +1 -23
- data/lib/bio/version.rb +1 -1
- data/sample/demo_aaindex.rb +67 -0
- data/sample/demo_aminoacid.rb +101 -0
- data/sample/demo_bl2seq_report.rb +220 -0
- data/sample/demo_blast_report.rb +285 -0
- data/sample/demo_codontable.rb +119 -0
- data/sample/demo_das.rb +105 -0
- data/sample/demo_ddbjxml.rb +212 -0
- data/sample/demo_fasta_remote.rb +51 -0
- data/sample/demo_fastaformat.rb +105 -0
- data/sample/demo_genbank.rb +132 -0
- data/sample/demo_genscan_report.rb +202 -0
- data/sample/demo_gff1.rb +49 -0
- data/sample/demo_go.rb +98 -0
- data/sample/demo_hmmer_report.rb +149 -0
- data/sample/demo_kegg_compound.rb +57 -0
- data/sample/demo_kegg_drug.rb +65 -0
- data/sample/demo_kegg_genome.rb +74 -0
- data/sample/demo_kegg_glycan.rb +72 -0
- data/sample/demo_kegg_orthology.rb +62 -0
- data/sample/demo_kegg_reaction.rb +66 -0
- data/sample/demo_kegg_taxonomy.rb +92 -0
- data/sample/demo_keggapi.rb +502 -0
- data/sample/demo_litdb.rb +42 -0
- data/sample/demo_locations.rb +99 -0
- data/sample/demo_ncbi_rest.rb +130 -0
- data/sample/demo_nucleicacid.rb +49 -0
- data/sample/demo_pathway.rb +196 -0
- data/sample/demo_prosite.rb +120 -0
- data/sample/demo_psort.rb +138 -0
- data/sample/demo_psort_report.rb +70 -0
- data/sample/demo_pubmed.rb +118 -0
- data/sample/demo_sirna.rb +63 -0
- data/sample/demo_sosui_report.rb +89 -0
- data/sample/demo_targetp_report.rb +135 -0
- data/sample/demo_tmhmm_report.rb +68 -0
- data/sample/pmfetch.rb +13 -4
- data/sample/pmsearch.rb +15 -4
- data/sample/test_phyloxml_big.rb +205 -0
- data/test/bioruby_test_helper.rb +61 -0
- data/test/data/KEGG/1.1.1.1.enzyme +935 -0
- data/test/data/KEGG/C00025.compound +102 -0
- data/test/data/KEGG/D00063.drug +104 -0
- data/test/data/KEGG/G00024.glycan +47 -0
- data/test/data/KEGG/G01366.glycan +18 -0
- data/test/data/KEGG/K02338.orthology +902 -0
- data/test/data/KEGG/R00006.reaction +14 -0
- data/test/data/fastq/README.txt +109 -0
- data/test/data/fastq/error_diff_ids.fastq +20 -0
- data/test/data/fastq/error_double_qual.fastq +22 -0
- data/test/data/fastq/error_double_seq.fastq +22 -0
- data/test/data/fastq/error_long_qual.fastq +20 -0
- data/test/data/fastq/error_no_qual.fastq +20 -0
- data/test/data/fastq/error_qual_del.fastq +20 -0
- data/test/data/fastq/error_qual_escape.fastq +20 -0
- data/test/data/fastq/error_qual_null.fastq +0 -0
- data/test/data/fastq/error_qual_space.fastq +21 -0
- data/test/data/fastq/error_qual_tab.fastq +21 -0
- data/test/data/fastq/error_qual_unit_sep.fastq +20 -0
- data/test/data/fastq/error_qual_vtab.fastq +20 -0
- data/test/data/fastq/error_short_qual.fastq +20 -0
- data/test/data/fastq/error_spaces.fastq +20 -0
- data/test/data/fastq/error_tabs.fastq +21 -0
- data/test/data/fastq/error_trunc_at_plus.fastq +19 -0
- data/test/data/fastq/error_trunc_at_qual.fastq +19 -0
- data/test/data/fastq/error_trunc_at_seq.fastq +18 -0
- data/test/data/fastq/error_trunc_in_plus.fastq +19 -0
- data/test/data/fastq/error_trunc_in_qual.fastq +20 -0
- data/test/data/fastq/error_trunc_in_seq.fastq +18 -0
- data/test/data/fastq/error_trunc_in_title.fastq +17 -0
- data/test/data/fastq/illumina_full_range_as_illumina.fastq +8 -0
- data/test/data/fastq/illumina_full_range_as_sanger.fastq +8 -0
- data/test/data/fastq/illumina_full_range_as_solexa.fastq +8 -0
- data/test/data/fastq/illumina_full_range_original_illumina.fastq +8 -0
- data/test/data/fastq/longreads_as_illumina.fastq +40 -0
- data/test/data/fastq/longreads_as_sanger.fastq +40 -0
- data/test/data/fastq/longreads_as_solexa.fastq +40 -0
- data/test/data/fastq/longreads_original_sanger.fastq +120 -0
- data/test/data/fastq/misc_dna_as_illumina.fastq +16 -0
- data/test/data/fastq/misc_dna_as_sanger.fastq +16 -0
- data/test/data/fastq/misc_dna_as_solexa.fastq +16 -0
- data/test/data/fastq/misc_dna_original_sanger.fastq +16 -0
- data/test/data/fastq/misc_rna_as_illumina.fastq +16 -0
- data/test/data/fastq/misc_rna_as_sanger.fastq +16 -0
- data/test/data/fastq/misc_rna_as_solexa.fastq +16 -0
- data/test/data/fastq/misc_rna_original_sanger.fastq +16 -0
- data/test/data/fastq/sanger_full_range_as_illumina.fastq +8 -0
- data/test/data/fastq/sanger_full_range_as_sanger.fastq +8 -0
- data/test/data/fastq/sanger_full_range_as_solexa.fastq +8 -0
- data/test/data/fastq/sanger_full_range_original_sanger.fastq +8 -0
- data/test/data/fastq/solexa_full_range_as_illumina.fastq +8 -0
- data/test/data/fastq/solexa_full_range_as_sanger.fastq +8 -0
- data/test/data/fastq/solexa_full_range_as_solexa.fastq +8 -0
- data/test/data/fastq/solexa_full_range_original_solexa.fastq +8 -0
- data/test/data/fastq/wrapping_as_illumina.fastq +12 -0
- data/test/data/fastq/wrapping_as_sanger.fastq +12 -0
- data/test/data/fastq/wrapping_as_solexa.fastq +12 -0
- data/test/data/fastq/wrapping_original_sanger.fastq +24 -0
- data/test/data/meme/db +0 -0
- data/test/data/meme/mast +0 -0
- data/test/data/meme/mast.out +13 -0
- data/test/data/meme/meme.out +3 -0
- data/test/data/phyloxml/apaf.xml +666 -0
- data/test/data/phyloxml/bcl_2.xml +2097 -0
- data/test/data/phyloxml/made_up.xml +144 -0
- data/test/data/phyloxml/ncbi_taxonomy_mollusca_short.xml +65 -0
- data/test/data/phyloxml/phyloxml_examples.xml +415 -0
- data/test/data/sanger_chromatogram/test_chromatogram_abif.ab1 +0 -0
- data/test/data/sanger_chromatogram/test_chromatogram_scf_v2.scf +0 -0
- data/test/data/sanger_chromatogram/test_chromatogram_scf_v3.scf +0 -0
- data/test/functional/bio/appl/test_pts1.rb +7 -5
- data/test/functional/bio/io/test_ensembl.rb +4 -3
- data/test/functional/bio/io/test_pubmed.rb +9 -3
- data/test/functional/bio/io/test_soapwsdl.rb +5 -4
- data/test/functional/bio/io/test_togows.rb +5 -4
- data/test/functional/bio/sequence/test_output_embl.rb +6 -4
- data/test/functional/bio/test_command.rb +54 -5
- data/test/runner.rb +5 -3
- data/test/unit/bio/appl/bl2seq/test_report.rb +5 -4
- data/test/unit/bio/appl/blast/test_ncbioptions.rb +4 -2
- data/test/unit/bio/appl/blast/test_report.rb +5 -4
- data/test/unit/bio/appl/blast/test_rpsblast.rb +5 -4
- data/test/unit/bio/appl/gcg/test_msf.rb +5 -5
- data/test/unit/bio/appl/genscan/test_report.rb +8 -9
- data/test/unit/bio/appl/hmmer/test_report.rb +5 -4
- data/test/unit/bio/appl/iprscan/test_report.rb +6 -5
- data/test/unit/bio/appl/mafft/test_report.rb +6 -5
- data/test/unit/bio/appl/meme/mast/test_report.rb +46 -0
- data/test/unit/bio/appl/meme/test_mast.rb +103 -0
- data/test/unit/bio/appl/meme/test_motif.rb +38 -0
- data/test/unit/bio/appl/paml/codeml/test_rates.rb +5 -4
- data/test/unit/bio/appl/paml/codeml/test_report.rb +5 -4
- data/test/unit/bio/appl/paml/test_codeml.rb +5 -4
- data/test/unit/bio/appl/sim4/test_report.rb +5 -4
- data/test/unit/bio/appl/sosui/test_report.rb +6 -5
- data/test/unit/bio/appl/targetp/test_report.rb +5 -3
- data/test/unit/bio/appl/test_blast.rb +5 -4
- data/test/unit/bio/appl/test_fasta.rb +4 -2
- data/test/unit/bio/appl/test_pts1.rb +4 -2
- data/test/unit/bio/appl/tmhmm/test_report.rb +6 -5
- data/test/unit/bio/data/test_aa.rb +5 -3
- data/test/unit/bio/data/test_codontable.rb +5 -4
- data/test/unit/bio/data/test_na.rb +5 -3
- data/test/unit/bio/db/biosql/tc_biosql.rb +5 -1
- data/test/unit/bio/db/embl/test_common.rb +4 -2
- data/test/unit/bio/db/embl/test_embl.rb +6 -6
- data/test/unit/bio/db/embl/test_embl_rel89.rb +6 -6
- data/test/unit/bio/db/embl/test_embl_to_bioseq.rb +7 -8
- data/test/unit/bio/db/embl/test_sptr.rb +6 -8
- data/test/unit/bio/db/embl/test_uniprot.rb +6 -5
- data/test/unit/bio/db/fasta/test_format_qual.rb +346 -0
- data/test/unit/bio/db/kegg/test_compound.rb +146 -0
- data/test/unit/bio/db/kegg/test_drug.rb +194 -0
- data/test/unit/bio/db/kegg/test_enzyme.rb +241 -0
- data/test/unit/bio/db/kegg/test_genes.rb +32 -4
- data/test/unit/bio/db/kegg/test_glycan.rb +260 -0
- data/test/unit/bio/db/kegg/test_orthology.rb +50 -0
- data/test/unit/bio/db/kegg/test_reaction.rb +96 -0
- data/test/unit/bio/db/pdb/test_pdb.rb +4 -2
- data/test/unit/bio/db/sanger_chromatogram/test_abif.rb +76 -0
- data/test/unit/bio/db/sanger_chromatogram/test_scf.rb +98 -0
- data/test/unit/bio/db/test_aaindex.rb +6 -6
- data/test/unit/bio/db/test_fasta.rb +5 -46
- data/test/unit/bio/db/test_fastq.rb +829 -0
- data/test/unit/bio/db/test_gff.rb +4 -2
- data/test/unit/bio/db/test_lasergene.rb +7 -5
- data/test/unit/bio/db/test_medline.rb +4 -2
- data/test/unit/bio/db/test_newick.rb +6 -6
- data/test/unit/bio/db/test_nexus.rb +4 -2
- data/test/unit/bio/db/test_phyloxml.rb +769 -0
- data/test/unit/bio/db/test_phyloxml_writer.rb +328 -0
- data/test/unit/bio/db/test_prosite.rb +6 -5
- data/test/unit/bio/db/test_qual.rb +63 -0
- data/test/unit/bio/db/test_rebase.rb +5 -3
- data/test/unit/bio/db/test_soft.rb +7 -6
- data/test/unit/bio/io/flatfile/test_autodetection.rb +6 -7
- data/test/unit/bio/io/flatfile/test_buffer.rb +6 -5
- data/test/unit/bio/io/flatfile/test_splitter.rb +4 -4
- data/test/unit/bio/io/test_ddbjxml.rb +4 -3
- data/test/unit/bio/io/test_ensembl.rb +5 -3
- data/test/unit/bio/io/test_fastacmd.rb +4 -3
- data/test/unit/bio/io/test_flatfile.rb +6 -5
- data/test/unit/bio/io/test_soapwsdl.rb +4 -3
- data/test/unit/bio/io/test_togows.rb +4 -2
- data/test/unit/bio/sequence/test_aa.rb +5 -3
- data/test/unit/bio/sequence/test_common.rb +4 -2
- data/test/unit/bio/sequence/test_compat.rb +4 -2
- data/test/unit/bio/sequence/test_dblink.rb +5 -3
- data/test/unit/bio/sequence/test_na.rb +4 -2
- data/test/unit/bio/sequence/test_quality_score.rb +330 -0
- data/test/unit/bio/shell/plugin/test_seq.rb +5 -3
- data/test/unit/bio/test_alignment.rb +5 -3
- data/test/unit/bio/test_command.rb +4 -3
- data/test/unit/bio/test_db.rb +5 -3
- data/test/unit/bio/test_feature.rb +4 -2
- data/test/unit/bio/test_location.rb +4 -2
- data/test/unit/bio/test_map.rb +5 -3
- data/test/unit/bio/test_pathway.rb +4 -2
- data/test/unit/bio/test_reference.rb +4 -2
- data/test/unit/bio/test_sequence.rb +5 -3
- data/test/unit/bio/test_shell.rb +5 -3
- data/test/unit/bio/test_tree.rb +6 -6
- data/test/unit/bio/util/restriction_enzyme/analysis/test_calculated_cuts.rb +4 -2
- data/test/unit/bio/util/restriction_enzyme/analysis/test_cut_ranges.rb +4 -2
- data/test/unit/bio/util/restriction_enzyme/analysis/test_sequence_range.rb +4 -2
- data/test/unit/bio/util/restriction_enzyme/double_stranded/test_aligned_strands.rb +4 -2
- data/test/unit/bio/util/restriction_enzyme/double_stranded/test_cut_location_pair.rb +4 -2
- data/test/unit/bio/util/restriction_enzyme/double_stranded/test_cut_location_pair_in_enzyme_notation.rb +4 -2
- data/test/unit/bio/util/restriction_enzyme/double_stranded/test_cut_locations.rb +4 -2
- data/test/unit/bio/util/restriction_enzyme/double_stranded/test_cut_locations_in_enzyme_notation.rb +4 -2
- data/test/unit/bio/util/restriction_enzyme/single_strand/test_cut_locations_in_enzyme_notation.rb +4 -2
- data/test/unit/bio/util/restriction_enzyme/test_analysis.rb +4 -2
- data/test/unit/bio/util/restriction_enzyme/test_cut_symbol.rb +4 -2
- data/test/unit/bio/util/restriction_enzyme/test_double_stranded.rb +4 -2
- data/test/unit/bio/util/restriction_enzyme/test_single_strand.rb +17 -13
- data/test/unit/bio/util/restriction_enzyme/test_single_strand_complement.rb +17 -13
- data/test/unit/bio/util/restriction_enzyme/test_string_formatting.rb +4 -2
- data/test/unit/bio/util/test_color_scheme.rb +5 -3
- data/test/unit/bio/util/test_contingency_table.rb +5 -3
- data/test/unit/bio/util/test_restriction_enzyme.rb +4 -2
- data/test/unit/bio/util/test_sirna.rb +6 -4
- metadata +147 -2
|
@@ -0,0 +1,57 @@
|
|
|
1
|
+
#
|
|
2
|
+
# = sample/demo_kegg_compound.rb - demonstration of Bio::KEGG::COMPOUND
|
|
3
|
+
#
|
|
4
|
+
# Copyright:: Copyright (C) 2001, 2002, 2004, 2007 Toshiaki Katayama <k@bioruby.org>
|
|
5
|
+
# Copyright:: Copyright (C) 2009 Kozo Nishida <kozo-ni@is.naist.jp>
|
|
6
|
+
# License:: The Ruby License
|
|
7
|
+
#
|
|
8
|
+
#
|
|
9
|
+
# == Description
|
|
10
|
+
#
|
|
11
|
+
# Demonstration of Bio::KEGG::COMPOUND, a parser class for the KEGG COMPOUND
|
|
12
|
+
# chemical structure database.
|
|
13
|
+
#
|
|
14
|
+
# == Usage
|
|
15
|
+
#
|
|
16
|
+
# Specify files containing KEGG COMPOUND data.
|
|
17
|
+
#
|
|
18
|
+
# $ ruby demo_kegg_compound.rb files...
|
|
19
|
+
#
|
|
20
|
+
# Example usage using test data:
|
|
21
|
+
#
|
|
22
|
+
# $ ruby -Ilib sample/demo_kegg_compound.rb test/data/KEGG/C00025.compound
|
|
23
|
+
#
|
|
24
|
+
# == Development information
|
|
25
|
+
#
|
|
26
|
+
# The code was moved from lib/bio/db/kegg/compound.rb and modified.
|
|
27
|
+
#
|
|
28
|
+
|
|
29
|
+
require 'bio'
|
|
30
|
+
|
|
31
|
+
Bio::FlatFile.foreach(Bio::KEGG::COMPOUND, ARGF) do |cpd|
|
|
32
|
+
puts "### cpd = Bio::KEGG::COMPOUND.new(str)"
|
|
33
|
+
puts "# cpd.entry_id"
|
|
34
|
+
p cpd.entry_id
|
|
35
|
+
puts "# cpd.names"
|
|
36
|
+
p cpd.names
|
|
37
|
+
puts "# cpd.name"
|
|
38
|
+
p cpd.name
|
|
39
|
+
puts "# cpd.formula"
|
|
40
|
+
p cpd.formula
|
|
41
|
+
puts "# cpd.mass"
|
|
42
|
+
p cpd.mass
|
|
43
|
+
puts "# cpd.reactions"
|
|
44
|
+
p cpd.reactions
|
|
45
|
+
puts "# cpd.rpairs"
|
|
46
|
+
p cpd.rpairs
|
|
47
|
+
puts "# cpd.pathways"
|
|
48
|
+
p cpd.pathways
|
|
49
|
+
puts "# cpd.enzymes"
|
|
50
|
+
p cpd.enzymes
|
|
51
|
+
puts "# cpd.dblinks"
|
|
52
|
+
p cpd.dblinks
|
|
53
|
+
puts "# cpd.kcf"
|
|
54
|
+
p cpd.kcf
|
|
55
|
+
puts "=" * 78
|
|
56
|
+
end
|
|
57
|
+
|
|
@@ -0,0 +1,65 @@
|
|
|
1
|
+
#
|
|
2
|
+
# = sample/demo_kegg_drug.rb - demonstration of Bio::KEGG::DRUG
|
|
3
|
+
#
|
|
4
|
+
# Copyright:: Copyright (C) 2007 Toshiaki Katayama <k@bioruby.org>
|
|
5
|
+
# License:: The Ruby License
|
|
6
|
+
#
|
|
7
|
+
#
|
|
8
|
+
# == Description
|
|
9
|
+
#
|
|
10
|
+
# Demonstration of Bio::KEGG::DRUG, a parser class for the KEGG DRUG
|
|
11
|
+
# drug database entry.
|
|
12
|
+
#
|
|
13
|
+
# == Usage
|
|
14
|
+
#
|
|
15
|
+
# Specify files containing KEGG DRUG data.
|
|
16
|
+
#
|
|
17
|
+
# $ ruby demo_kegg_drug.rb files...
|
|
18
|
+
#
|
|
19
|
+
# == Example of running this script
|
|
20
|
+
#
|
|
21
|
+
# Download test data.
|
|
22
|
+
#
|
|
23
|
+
# $ ruby -Ilib bin/br_biofetch.rb dr D00001 > D00001.drug
|
|
24
|
+
# $ ruby -Ilib bin/br_biofetch.rb dr D00002 > D00002.drug
|
|
25
|
+
#
|
|
26
|
+
# Run this script.
|
|
27
|
+
#
|
|
28
|
+
# $ ruby -Ilib sample/demo_kegg_drug.rb D00001.drug D00002.drug
|
|
29
|
+
#
|
|
30
|
+
# == Development information
|
|
31
|
+
#
|
|
32
|
+
# The code was moved from lib/bio/db/kegg/drug.rb and modified.
|
|
33
|
+
#
|
|
34
|
+
|
|
35
|
+
require 'bio'
|
|
36
|
+
|
|
37
|
+
Bio::FlatFile.foreach(Bio::KEGG::DRUG, ARGF) do |dr|
|
|
38
|
+
#entry = ARGF.read # dr:D00001
|
|
39
|
+
#dr = Bio::KEGG::DRUG.new(entry)
|
|
40
|
+
|
|
41
|
+
puts "### dr = Bio::KEGG::DRUG.new(str)"
|
|
42
|
+
puts "# dr.entry_id"
|
|
43
|
+
p dr.entry_id
|
|
44
|
+
puts "# dr.names"
|
|
45
|
+
p dr.names
|
|
46
|
+
puts "# dr.name"
|
|
47
|
+
p dr.name
|
|
48
|
+
puts "# dr.formula"
|
|
49
|
+
p dr.formula
|
|
50
|
+
puts "# dr.mass"
|
|
51
|
+
p dr.mass
|
|
52
|
+
puts "# dr.activity"
|
|
53
|
+
p dr.activity
|
|
54
|
+
puts "# dr.remark"
|
|
55
|
+
p dr.remark
|
|
56
|
+
puts "# dr.comment"
|
|
57
|
+
p dr.comment
|
|
58
|
+
puts "# dr.dblinks"
|
|
59
|
+
p dr.dblinks
|
|
60
|
+
puts "# dr.kcf"
|
|
61
|
+
p dr.kcf
|
|
62
|
+
|
|
63
|
+
puts "=" * 78
|
|
64
|
+
end
|
|
65
|
+
|
|
@@ -0,0 +1,74 @@
|
|
|
1
|
+
#
|
|
2
|
+
# = sample/demo_kegg_genome.rb - demonstration of Bio::KEGG::GENOME
|
|
3
|
+
#
|
|
4
|
+
# Copyright:: Copyright (C) 2001, 2002, 2007 Toshiaki Katayama <k@bioruby.org>
|
|
5
|
+
# License:: The Ruby License
|
|
6
|
+
#
|
|
7
|
+
#
|
|
8
|
+
# == Description
|
|
9
|
+
#
|
|
10
|
+
# Demonstration of Bio::KEGG::GENOME, a parser class for the KEGG/GENOME
|
|
11
|
+
# genome database.
|
|
12
|
+
#
|
|
13
|
+
# == Usage
|
|
14
|
+
#
|
|
15
|
+
# Specify files containing KEGG GENOME data.
|
|
16
|
+
#
|
|
17
|
+
# $ ruby demo_kegg_genome.rb files...
|
|
18
|
+
#
|
|
19
|
+
# == Example of running this script
|
|
20
|
+
#
|
|
21
|
+
# Download test data.
|
|
22
|
+
#
|
|
23
|
+
# $ ruby -Ilib bin/br_biofetch.rb genome eco > eco.genome
|
|
24
|
+
# $ ruby -Ilib bin/br_biofetch.rb genome hsa > hsa.genome
|
|
25
|
+
#
|
|
26
|
+
# Run this script.
|
|
27
|
+
#
|
|
28
|
+
# $ ruby -Ilib sample/demo_kegg_genome.rb eco.genome hsa.genome
|
|
29
|
+
#
|
|
30
|
+
# == Development information
|
|
31
|
+
#
|
|
32
|
+
# The code was moved from lib/bio/db/kegg/genome.rb and modified.
|
|
33
|
+
#
|
|
34
|
+
|
|
35
|
+
require 'bio'
|
|
36
|
+
|
|
37
|
+
#if __FILE__ == $0
|
|
38
|
+
|
|
39
|
+
begin
|
|
40
|
+
require 'pp'
|
|
41
|
+
def p(arg); pp(arg); end
|
|
42
|
+
rescue LoadError
|
|
43
|
+
end
|
|
44
|
+
|
|
45
|
+
#require 'bio/io/flatfile'
|
|
46
|
+
|
|
47
|
+
ff = Bio::FlatFile.new(Bio::KEGG::GENOME, ARGF)
|
|
48
|
+
|
|
49
|
+
ff.each do |genome|
|
|
50
|
+
|
|
51
|
+
puts "### Tags"
|
|
52
|
+
p genome.tags
|
|
53
|
+
|
|
54
|
+
[
|
|
55
|
+
%w( ENTRY entry_id ),
|
|
56
|
+
%w( NAME name ),
|
|
57
|
+
%w( DEFINITION definition ),
|
|
58
|
+
%w( TAXONOMY taxonomy taxid lineage ),
|
|
59
|
+
%w( REFERENCE references ),
|
|
60
|
+
%w( CHROMOSOME chromosomes ),
|
|
61
|
+
%w( PLASMID plasmids ),
|
|
62
|
+
%w( STATISTICS statistics nalen num_gene num_rna ),
|
|
63
|
+
].each do |x|
|
|
64
|
+
puts "### " + x.shift
|
|
65
|
+
x.each do |m|
|
|
66
|
+
p genome.__send__(m)
|
|
67
|
+
end
|
|
68
|
+
end
|
|
69
|
+
|
|
70
|
+
puts "=" * 78
|
|
71
|
+
end
|
|
72
|
+
|
|
73
|
+
#end
|
|
74
|
+
|
|
@@ -0,0 +1,72 @@
|
|
|
1
|
+
#
|
|
2
|
+
# = sample/demo_kegg_glycan.rb - demonstration of Bio::KEGG::GLYCAN
|
|
3
|
+
#
|
|
4
|
+
# Copyright:: Copyright (C) 2004 Toshiaki Katayama <k@bioruby.org>
|
|
5
|
+
# License:: The Ruby License
|
|
6
|
+
#
|
|
7
|
+
#
|
|
8
|
+
# == Description
|
|
9
|
+
#
|
|
10
|
+
# Demonstration of Bio::KEGG::GLYCAN, a parser class for the KEGG GLYCAN
|
|
11
|
+
# glycome informatics database.
|
|
12
|
+
#
|
|
13
|
+
# == Usage
|
|
14
|
+
#
|
|
15
|
+
# Specify files containing KEGG GLYCAN data.
|
|
16
|
+
#
|
|
17
|
+
# $ ruby demo_kegg_glycan.rb files...
|
|
18
|
+
#
|
|
19
|
+
# == Example of running this script
|
|
20
|
+
#
|
|
21
|
+
# Download test data.
|
|
22
|
+
#
|
|
23
|
+
# $ ruby -Ilib bin/br_biofetch.rb glycan G00001 > G00001.glycan
|
|
24
|
+
# $ ruby -Ilib bin/br_biofetch.rb glycan G00024 > G00024.glycan
|
|
25
|
+
#
|
|
26
|
+
# Run this script.
|
|
27
|
+
#
|
|
28
|
+
# $ ruby -Ilib sample/demo_kegg_glycan.rb G00001.glycan G00024.glycan
|
|
29
|
+
#
|
|
30
|
+
# == Development information
|
|
31
|
+
#
|
|
32
|
+
# The code was moved from lib/bio/db/kegg/glycan.rb and modified.
|
|
33
|
+
#
|
|
34
|
+
|
|
35
|
+
require 'bio'
|
|
36
|
+
|
|
37
|
+
Bio::FlatFile.foreach(Bio::KEGG::GLYCAN, ARGF) do |gl|
|
|
38
|
+
#entry = ARGF.read # gl:G00024
|
|
39
|
+
#gl = Bio::KEGG::GLYCAN.new(entry)
|
|
40
|
+
|
|
41
|
+
puts "### gl = Bio::KEGG::GLYCAN.new(str)"
|
|
42
|
+
puts "# gl.entry_id"
|
|
43
|
+
p gl.entry_id
|
|
44
|
+
puts "# gl.name"
|
|
45
|
+
p gl.name
|
|
46
|
+
puts "# gl.composition"
|
|
47
|
+
p gl.composition
|
|
48
|
+
puts "# gl.mass"
|
|
49
|
+
p gl.mass
|
|
50
|
+
puts "# gl.keggclass"
|
|
51
|
+
p gl.keggclass
|
|
52
|
+
#puts "# gl.bindings"
|
|
53
|
+
#p gl.bindings
|
|
54
|
+
puts "# gl.compounds"
|
|
55
|
+
p gl.compounds
|
|
56
|
+
puts "# gl.reactions"
|
|
57
|
+
p gl.reactions
|
|
58
|
+
puts "# gl.pathways"
|
|
59
|
+
p gl.pathways
|
|
60
|
+
puts "# gl.enzymes"
|
|
61
|
+
p gl.enzymes
|
|
62
|
+
puts "# gl.orthologs"
|
|
63
|
+
p gl.orthologs
|
|
64
|
+
puts "# gl.references"
|
|
65
|
+
p gl.references
|
|
66
|
+
puts "# gl.dblinks"
|
|
67
|
+
p gl.dblinks
|
|
68
|
+
puts "# gl.kcf"
|
|
69
|
+
p gl.kcf
|
|
70
|
+
|
|
71
|
+
puts "=" * 78
|
|
72
|
+
end
|
|
@@ -0,0 +1,62 @@
|
|
|
1
|
+
#
|
|
2
|
+
# = sample/demo_kegg_orthology.rb - demonstration of Bio::KEGG::ORTHOLOGY
|
|
3
|
+
#
|
|
4
|
+
# Copyright:: Copyright (C) 2003-2007 Toshiaki Katayama <k@bioruby.org>
|
|
5
|
+
# Copyright:: Copyright (C) 2003 Masumi Itoh <m@bioruby.org>
|
|
6
|
+
# License:: The Ruby License
|
|
7
|
+
#
|
|
8
|
+
#
|
|
9
|
+
# == Description
|
|
10
|
+
#
|
|
11
|
+
# Demonstration of Bio::KEGG::ORTHOLOGY, the parser class for the KEGG
|
|
12
|
+
# ORTHOLOGY database entry.
|
|
13
|
+
#
|
|
14
|
+
# == Usage
|
|
15
|
+
#
|
|
16
|
+
# Specify files containing KEGG ORTHOLOGY data.
|
|
17
|
+
#
|
|
18
|
+
# $ ruby demo_kegg_orthology.rb files...
|
|
19
|
+
#
|
|
20
|
+
# == Example of running this script
|
|
21
|
+
#
|
|
22
|
+
# Download test data.
|
|
23
|
+
#
|
|
24
|
+
# $ ruby -Ilib bin/br_biofetch.rb ko K00001 > K00001.ko
|
|
25
|
+
# $ ruby -Ilib bin/br_biofetch.rb ko K00161 > K00161.ko
|
|
26
|
+
#
|
|
27
|
+
# Run this script.
|
|
28
|
+
#
|
|
29
|
+
# $ ruby -Ilib sample/demo_kegg_orthology.rb K00001.ko K00161.ko
|
|
30
|
+
#
|
|
31
|
+
# == Development information
|
|
32
|
+
#
|
|
33
|
+
# The code was moved from lib/bio/db/kegg/orthology.rb and modified.
|
|
34
|
+
#
|
|
35
|
+
|
|
36
|
+
require 'bio'
|
|
37
|
+
|
|
38
|
+
Bio::FlatFile.foreach(Bio::KEGG::ORTHOLOGY, ARGF) do |ko|
|
|
39
|
+
puts "### ko = Bio::KEGG::ORTHOLOGY.new(str)"
|
|
40
|
+
|
|
41
|
+
puts "# ko.ko_id"
|
|
42
|
+
p ko.entry_id
|
|
43
|
+
puts "# ko.name"
|
|
44
|
+
p ko.name
|
|
45
|
+
puts "# ko.names"
|
|
46
|
+
p ko.names
|
|
47
|
+
puts "# ko.definition"
|
|
48
|
+
p ko.definition
|
|
49
|
+
puts "# ko.keggclass"
|
|
50
|
+
p ko.keggclass
|
|
51
|
+
puts "# ko.keggclasses"
|
|
52
|
+
p ko.keggclasses
|
|
53
|
+
puts "# ko.pathways"
|
|
54
|
+
p ko.pathways
|
|
55
|
+
puts "# ko.dblinks"
|
|
56
|
+
p ko.dblinks
|
|
57
|
+
puts "# ko.genes"
|
|
58
|
+
p ko.genes
|
|
59
|
+
|
|
60
|
+
puts "=" * 78
|
|
61
|
+
end
|
|
62
|
+
|
|
@@ -0,0 +1,66 @@
|
|
|
1
|
+
#
|
|
2
|
+
# = sample/demo_kegg_reaction.rb - demonstration of Bio::KEGG::REACTION
|
|
3
|
+
#
|
|
4
|
+
# Copyright:: Copyright (C) 2004 Toshiaki Katayama <k@bioruby.org>
|
|
5
|
+
# Copyright:: Copyright (C) 2009 Kozo Nishida <kozo-ni@is.naist.jp>
|
|
6
|
+
# License:: The Ruby License
|
|
7
|
+
#
|
|
8
|
+
#
|
|
9
|
+
# == Description
|
|
10
|
+
#
|
|
11
|
+
# Demonstration of Bio::KEGG::REACTION, the parser class for the KEGG
|
|
12
|
+
# REACTION biochemical reaction database.
|
|
13
|
+
#
|
|
14
|
+
# == Usage
|
|
15
|
+
#
|
|
16
|
+
# Specify files containing KEGG REACTION data.
|
|
17
|
+
#
|
|
18
|
+
# $ ruby demo_kegg_reaction.rb files...
|
|
19
|
+
#
|
|
20
|
+
# Example usage using test data:
|
|
21
|
+
#
|
|
22
|
+
# $ ruby -Ilib sample/demo_kegg_reaction.rb test/data/KEGG/R00006.reaction
|
|
23
|
+
#
|
|
24
|
+
# == Example of running this script
|
|
25
|
+
#
|
|
26
|
+
# Download test data.
|
|
27
|
+
#
|
|
28
|
+
# $ ruby -Ilib bin/br_biofetch.rb reaction R00259 > R00259.reaction
|
|
29
|
+
# $ ruby -Ilib bin/br_biofetch.rb reaction R02282 > R02282.reaction
|
|
30
|
+
#
|
|
31
|
+
# Run this script.
|
|
32
|
+
#
|
|
33
|
+
# $ ruby -Ilib sample/demo_kegg_reaction.rb R00259.reaction R02282.reaction
|
|
34
|
+
#
|
|
35
|
+
# == Development information
|
|
36
|
+
#
|
|
37
|
+
# The code was moved from lib/bio/db/kegg/reaction.rb and modified.
|
|
38
|
+
#
|
|
39
|
+
|
|
40
|
+
require 'bio'
|
|
41
|
+
|
|
42
|
+
Bio::FlatFile.foreach(Bio::KEGG::REACTION, ARGF) do |rn|
|
|
43
|
+
puts "### rn = Bio::KEGG::REACTION.new(str)"
|
|
44
|
+
|
|
45
|
+
puts "# rn.entry_id"
|
|
46
|
+
p rn.entry_id
|
|
47
|
+
puts "# rn.name"
|
|
48
|
+
p rn.name
|
|
49
|
+
puts "# rn.definition"
|
|
50
|
+
p rn.definition
|
|
51
|
+
puts "# rn.equation"
|
|
52
|
+
p rn.equation
|
|
53
|
+
puts "# rn.rpairs"
|
|
54
|
+
p rn.rpairs
|
|
55
|
+
puts "# rn.pathways"
|
|
56
|
+
p rn.pathways
|
|
57
|
+
puts "# rn.enzymes"
|
|
58
|
+
p rn.enzymes
|
|
59
|
+
puts "# rn.orthologs"
|
|
60
|
+
p rn.orthologs
|
|
61
|
+
puts "# rn.orthologs_as_hash"
|
|
62
|
+
p rn.orthologs_as_hash
|
|
63
|
+
|
|
64
|
+
puts "=" * 78
|
|
65
|
+
end
|
|
66
|
+
|
|
@@ -0,0 +1,92 @@
|
|
|
1
|
+
#
|
|
2
|
+
# = sample/demo_kegg_taxonomy.rb - demonstration of Bio::KEGG::Taxonomy
|
|
3
|
+
#
|
|
4
|
+
# Copyright:: Copyright (C) 2007 Toshiaki Katayama <k@bioruby.org>
|
|
5
|
+
# License:: The Ruby License
|
|
6
|
+
#
|
|
7
|
+
#
|
|
8
|
+
# == Description
|
|
9
|
+
#
|
|
10
|
+
# IMPORTANT NOTE: currently, this sample does not work!
|
|
11
|
+
#
|
|
12
|
+
# Demonstration of Bio::KEGG::Taxonomy.
|
|
13
|
+
#
|
|
14
|
+
# == Usage
|
|
15
|
+
#
|
|
16
|
+
# Specify a file containing KEGG Taxonomy data.
|
|
17
|
+
#
|
|
18
|
+
# $ ruby demo_kegg_taxonomy.rb file
|
|
19
|
+
#
|
|
20
|
+
# Optionally, when a file containing organisms list (1 line per 1 organism)
|
|
21
|
+
# is specified after the file, only the specified organisms are shown.
|
|
22
|
+
#
|
|
23
|
+
# $ ruby demo_kegg_taxonomy.rb kegg_taxonomy_file org_list_file
|
|
24
|
+
#
|
|
25
|
+
# == Example of running this script
|
|
26
|
+
#
|
|
27
|
+
# Download test data.
|
|
28
|
+
#
|
|
29
|
+
# $ wget ftp://ftp.genome.jp/pub/kegg/genes/taxonomy
|
|
30
|
+
#
|
|
31
|
+
# The downloaded filename is "taxonomy".
|
|
32
|
+
#
|
|
33
|
+
# Run this script.
|
|
34
|
+
#
|
|
35
|
+
# $ ruby -Ilib sample/demo_kegg_taxonomy.rb taxonomy
|
|
36
|
+
#
|
|
37
|
+
# == Development information
|
|
38
|
+
#
|
|
39
|
+
# The code was moved from lib/bio/db/kegg/taxonomy.rb.
|
|
40
|
+
#
|
|
41
|
+
|
|
42
|
+
require 'bio'
|
|
43
|
+
|
|
44
|
+
#if __FILE__ == $0
|
|
45
|
+
|
|
46
|
+
# Usage:
|
|
47
|
+
# % wget ftp://ftp.genome.jp/pub/kegg/genes/taxonomy
|
|
48
|
+
# % ruby taxonomy.rb taxonomy | less -S
|
|
49
|
+
|
|
50
|
+
taxonomy = ARGV.shift
|
|
51
|
+
org_list = ARGV.shift || nil
|
|
52
|
+
|
|
53
|
+
if org_list
|
|
54
|
+
orgs = File.readlines(org_list).map{|x| x.strip}
|
|
55
|
+
else
|
|
56
|
+
orgs = nil
|
|
57
|
+
end
|
|
58
|
+
|
|
59
|
+
tree = Bio::KEGG::Taxonomy.new(taxonomy, orgs)
|
|
60
|
+
|
|
61
|
+
puts ">>> tree - original"
|
|
62
|
+
puts tree
|
|
63
|
+
|
|
64
|
+
puts ">>> tree - after compact"
|
|
65
|
+
tree.compact
|
|
66
|
+
puts tree
|
|
67
|
+
|
|
68
|
+
puts ">>> tree - after reduce"
|
|
69
|
+
tree.reduce
|
|
70
|
+
puts tree
|
|
71
|
+
|
|
72
|
+
puts ">>> path - sorted"
|
|
73
|
+
tree.path.sort.each do |path|
|
|
74
|
+
puts path.join("/")
|
|
75
|
+
end
|
|
76
|
+
|
|
77
|
+
puts ">>> group : orgs"
|
|
78
|
+
tree.dfs(tree.root) do |parent, children|
|
|
79
|
+
if orgs = tree.organisms(parent)
|
|
80
|
+
puts "#{parent.ljust(30)} (#{orgs.size})\t#{orgs.join(', ')}"
|
|
81
|
+
end
|
|
82
|
+
end
|
|
83
|
+
|
|
84
|
+
puts ">>> group : subgroups"
|
|
85
|
+
tree.dfs_with_level(tree.root) do |parent, children, level|
|
|
86
|
+
subgroups = children.keys.sort
|
|
87
|
+
indent = " " * level
|
|
88
|
+
label = "#{indent} #{level} #{parent}"
|
|
89
|
+
puts "#{label.ljust(35)}\t#{subgroups.join(', ')}"
|
|
90
|
+
end
|
|
91
|
+
|
|
92
|
+
#end
|