jandot-bio 1.2.1
Sign up to get free protection for your applications and to get access to all the features.
- data/bin/bioruby +44 -0
- data/bin/br_biofetch.rb +47 -0
- data/bin/br_bioflat.rb +282 -0
- data/bin/br_biogetseq.rb +45 -0
- data/bin/br_pmfetch.rb +421 -0
- data/doc/Changes-0.7.rd +369 -0
- data/doc/KEGG_API.rd +1843 -0
- data/doc/KEGG_API.rd.ja +1834 -0
- data/doc/Tutorial.rd +1296 -0
- data/doc/Tutorial.rd.ja +2640 -0
- data/etc/bioinformatics/seqdatabase.ini +210 -0
- data/lib/bio.rb +279 -0
- data/lib/bio/alignment.rb +2518 -0
- data/lib/bio/appl/bl2seq/report.rb +334 -0
- data/lib/bio/appl/blast.rb +351 -0
- data/lib/bio/appl/blast/format0.rb +1438 -0
- data/lib/bio/appl/blast/format8.rb +83 -0
- data/lib/bio/appl/blast/report.rb +516 -0
- data/lib/bio/appl/blast/rexml.rb +135 -0
- data/lib/bio/appl/blast/rpsblast.rb +176 -0
- data/lib/bio/appl/blast/wublast.rb +550 -0
- data/lib/bio/appl/blast/xmlparser.rb +228 -0
- data/lib/bio/appl/blat/report.rb +489 -0
- data/lib/bio/appl/clustalw.rb +219 -0
- data/lib/bio/appl/clustalw/report.rb +152 -0
- data/lib/bio/appl/emboss.rb +203 -0
- data/lib/bio/appl/fasta.rb +237 -0
- data/lib/bio/appl/fasta/format10.rb +325 -0
- data/lib/bio/appl/gcg/msf.rb +212 -0
- data/lib/bio/appl/gcg/seq.rb +195 -0
- data/lib/bio/appl/genscan/report.rb +552 -0
- data/lib/bio/appl/hmmer.rb +126 -0
- data/lib/bio/appl/hmmer/report.rb +683 -0
- data/lib/bio/appl/iprscan/report.rb +374 -0
- data/lib/bio/appl/mafft.rb +259 -0
- data/lib/bio/appl/mafft/report.rb +226 -0
- data/lib/bio/appl/muscle.rb +52 -0
- data/lib/bio/appl/phylip/alignment.rb +129 -0
- data/lib/bio/appl/phylip/distance_matrix.rb +96 -0
- data/lib/bio/appl/probcons.rb +41 -0
- data/lib/bio/appl/psort.rb +548 -0
- data/lib/bio/appl/psort/report.rb +457 -0
- data/lib/bio/appl/pts1.rb +263 -0
- data/lib/bio/appl/sim4.rb +124 -0
- data/lib/bio/appl/sim4/report.rb +485 -0
- data/lib/bio/appl/sosui/report.rb +151 -0
- data/lib/bio/appl/spidey/report.rb +593 -0
- data/lib/bio/appl/targetp/report.rb +267 -0
- data/lib/bio/appl/tcoffee.rb +55 -0
- data/lib/bio/appl/tmhmm/report.rb +222 -0
- data/lib/bio/command.rb +337 -0
- data/lib/bio/data/aa.rb +349 -0
- data/lib/bio/data/codontable.rb +722 -0
- data/lib/bio/data/na.rb +223 -0
- data/lib/bio/db.rb +329 -0
- data/lib/bio/db/aaindex.rb +357 -0
- data/lib/bio/db/embl/common.rb +336 -0
- data/lib/bio/db/embl/embl.rb +402 -0
- data/lib/bio/db/embl/sptr.rb +1283 -0
- data/lib/bio/db/embl/swissprot.rb +42 -0
- data/lib/bio/db/embl/trembl.rb +41 -0
- data/lib/bio/db/embl/uniprot.rb +42 -0
- data/lib/bio/db/fantom.rb +599 -0
- data/lib/bio/db/fasta.rb +907 -0
- data/lib/bio/db/genbank/common.rb +290 -0
- data/lib/bio/db/genbank/ddbj.rb +22 -0
- data/lib/bio/db/genbank/genbank.rb +215 -0
- data/lib/bio/db/genbank/genpept.rb +60 -0
- data/lib/bio/db/genbank/refseq.rb +18 -0
- data/lib/bio/db/gff.rb +174 -0
- data/lib/bio/db/go.rb +481 -0
- data/lib/bio/db/kegg/brite.rb +41 -0
- data/lib/bio/db/kegg/compound.rb +131 -0
- data/lib/bio/db/kegg/drug.rb +98 -0
- data/lib/bio/db/kegg/enzyme.rb +148 -0
- data/lib/bio/db/kegg/expression.rb +155 -0
- data/lib/bio/db/kegg/genes.rb +263 -0
- data/lib/bio/db/kegg/genome.rb +241 -0
- data/lib/bio/db/kegg/glycan.rb +170 -0
- data/lib/bio/db/kegg/keggtab.rb +357 -0
- data/lib/bio/db/kegg/kgml.rb +256 -0
- data/lib/bio/db/kegg/orthology.rb +136 -0
- data/lib/bio/db/kegg/reaction.rb +82 -0
- data/lib/bio/db/kegg/taxonomy.rb +331 -0
- data/lib/bio/db/lasergene.rb +209 -0
- data/lib/bio/db/litdb.rb +107 -0
- data/lib/bio/db/medline.rb +323 -0
- data/lib/bio/db/nbrf.rb +191 -0
- data/lib/bio/db/newick.rb +658 -0
- data/lib/bio/db/nexus.rb +1854 -0
- data/lib/bio/db/pdb.rb +29 -0
- data/lib/bio/db/pdb/atom.rb +77 -0
- data/lib/bio/db/pdb/chain.rb +210 -0
- data/lib/bio/db/pdb/chemicalcomponent.rb +224 -0
- data/lib/bio/db/pdb/model.rb +148 -0
- data/lib/bio/db/pdb/pdb.rb +1911 -0
- data/lib/bio/db/pdb/residue.rb +176 -0
- data/lib/bio/db/pdb/utils.rb +399 -0
- data/lib/bio/db/prosite.rb +597 -0
- data/lib/bio/db/rebase.rb +457 -0
- data/lib/bio/db/soft.rb +404 -0
- data/lib/bio/db/transfac.rb +375 -0
- data/lib/bio/feature.rb +226 -0
- data/lib/bio/io/das.rb +461 -0
- data/lib/bio/io/dbget.rb +194 -0
- data/lib/bio/io/ddbjxml.rb +581 -0
- data/lib/bio/io/ebisoap.rb +158 -0
- data/lib/bio/io/ensembl.rb +229 -0
- data/lib/bio/io/fastacmd.rb +163 -0
- data/lib/bio/io/fetch.rb +181 -0
- data/lib/bio/io/flatfile.rb +1309 -0
- data/lib/bio/io/flatfile/bdb.rb +253 -0
- data/lib/bio/io/flatfile/index.rb +1371 -0
- data/lib/bio/io/flatfile/indexer.rb +787 -0
- data/lib/bio/io/higet.rb +73 -0
- data/lib/bio/io/hinv.rb +442 -0
- data/lib/bio/io/keggapi.rb +805 -0
- data/lib/bio/io/ncbirest.rb +256 -0
- data/lib/bio/io/ncbisoap.rb +155 -0
- data/lib/bio/io/pubmed.rb +307 -0
- data/lib/bio/io/registry.rb +292 -0
- data/lib/bio/io/soapwsdl.rb +119 -0
- data/lib/bio/io/sql.rb +365 -0
- data/lib/bio/location.rb +772 -0
- data/lib/bio/map.rb +410 -0
- data/lib/bio/pathway.rb +854 -0
- data/lib/bio/reference.rb +623 -0
- data/lib/bio/sequence.rb +475 -0
- data/lib/bio/sequence/aa.rb +125 -0
- data/lib/bio/sequence/common.rb +333 -0
- data/lib/bio/sequence/compat.rb +123 -0
- data/lib/bio/sequence/format.rb +181 -0
- data/lib/bio/sequence/generic.rb +24 -0
- data/lib/bio/sequence/na.rb +491 -0
- data/lib/bio/shell.rb +44 -0
- data/lib/bio/shell/core.rb +578 -0
- data/lib/bio/shell/demo.rb +146 -0
- data/lib/bio/shell/interface.rb +218 -0
- data/lib/bio/shell/irb.rb +95 -0
- data/lib/bio/shell/object.rb +71 -0
- data/lib/bio/shell/plugin/blast.rb +42 -0
- data/lib/bio/shell/plugin/codon.rb +218 -0
- data/lib/bio/shell/plugin/das.rb +58 -0
- data/lib/bio/shell/plugin/emboss.rb +23 -0
- data/lib/bio/shell/plugin/entry.rb +105 -0
- data/lib/bio/shell/plugin/flatfile.rb +101 -0
- data/lib/bio/shell/plugin/keggapi.rb +181 -0
- data/lib/bio/shell/plugin/midi.rb +430 -0
- data/lib/bio/shell/plugin/obda.rb +45 -0
- data/lib/bio/shell/plugin/psort.rb +56 -0
- data/lib/bio/shell/plugin/seq.rb +247 -0
- data/lib/bio/shell/plugin/soap.rb +87 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/bioruby_generator.rb +29 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/_classes.rhtml +4 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/_log.rhtml +27 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/_methods.rhtml +11 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/_modules.rhtml +4 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/_variables.rhtml +7 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/bioruby-bg.gif +0 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/bioruby-gem.png +0 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/bioruby-link.gif +0 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/bioruby.css +368 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/bioruby.rhtml +47 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/bioruby_controller.rb +144 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/bioruby_helper.rb +47 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/commands.rhtml +8 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/history.rhtml +10 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/index.rhtml +26 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/spinner.gif +0 -0
- data/lib/bio/shell/script.rb +25 -0
- data/lib/bio/shell/setup.rb +109 -0
- data/lib/bio/shell/web.rb +102 -0
- data/lib/bio/tree.rb +850 -0
- data/lib/bio/util/color_scheme.rb +191 -0
- data/lib/bio/util/color_scheme/buried.rb +59 -0
- data/lib/bio/util/color_scheme/helix.rb +59 -0
- data/lib/bio/util/color_scheme/hydropathy.rb +64 -0
- data/lib/bio/util/color_scheme/nucleotide.rb +31 -0
- data/lib/bio/util/color_scheme/strand.rb +59 -0
- data/lib/bio/util/color_scheme/taylor.rb +50 -0
- data/lib/bio/util/color_scheme/turn.rb +59 -0
- data/lib/bio/util/color_scheme/zappo.rb +50 -0
- data/lib/bio/util/contingency_table.rb +370 -0
- data/lib/bio/util/restriction_enzyme.rb +228 -0
- data/lib/bio/util/restriction_enzyme/analysis.rb +249 -0
- data/lib/bio/util/restriction_enzyme/analysis_basic.rb +217 -0
- data/lib/bio/util/restriction_enzyme/cut_symbol.rb +107 -0
- data/lib/bio/util/restriction_enzyme/double_stranded.rb +321 -0
- data/lib/bio/util/restriction_enzyme/double_stranded/aligned_strands.rb +130 -0
- data/lib/bio/util/restriction_enzyme/double_stranded/cut_location_pair.rb +103 -0
- data/lib/bio/util/restriction_enzyme/double_stranded/cut_location_pair_in_enzyme_notation.rb +38 -0
- data/lib/bio/util/restriction_enzyme/double_stranded/cut_locations.rb +76 -0
- data/lib/bio/util/restriction_enzyme/double_stranded/cut_locations_in_enzyme_notation.rb +107 -0
- data/lib/bio/util/restriction_enzyme/enzymes.yaml +7061 -0
- data/lib/bio/util/restriction_enzyme/range/cut_range.rb +24 -0
- data/lib/bio/util/restriction_enzyme/range/cut_ranges.rb +47 -0
- data/lib/bio/util/restriction_enzyme/range/horizontal_cut_range.rb +67 -0
- data/lib/bio/util/restriction_enzyme/range/sequence_range.rb +257 -0
- data/lib/bio/util/restriction_enzyme/range/sequence_range/calculated_cuts.rb +242 -0
- data/lib/bio/util/restriction_enzyme/range/sequence_range/fragment.rb +51 -0
- data/lib/bio/util/restriction_enzyme/range/sequence_range/fragments.rb +41 -0
- data/lib/bio/util/restriction_enzyme/range/vertical_cut_range.rb +77 -0
- data/lib/bio/util/restriction_enzyme/single_strand.rb +199 -0
- data/lib/bio/util/restriction_enzyme/single_strand/cut_locations_in_enzyme_notation.rb +135 -0
- data/lib/bio/util/restriction_enzyme/single_strand_complement.rb +23 -0
- data/lib/bio/util/restriction_enzyme/string_formatting.rb +111 -0
- data/lib/bio/util/sirna.rb +288 -0
- data/sample/any2fasta.rb +59 -0
- data/sample/biofetch.rb +475 -0
- data/sample/color_scheme_na.rb +91 -0
- data/sample/dbget +37 -0
- data/sample/enzymes.rb +78 -0
- data/sample/fasta2tab.rb +99 -0
- data/sample/fastagrep.rb +72 -0
- data/sample/fastasort.rb +54 -0
- data/sample/fsplit.rb +51 -0
- data/sample/gb2fasta.rb +30 -0
- data/sample/gb2tab.rb +325 -0
- data/sample/gbtab2mysql.rb +161 -0
- data/sample/genes2nuc.rb +33 -0
- data/sample/genes2pep.rb +33 -0
- data/sample/genes2tab.rb +81 -0
- data/sample/genome2rb.rb +29 -0
- data/sample/genome2tab.rb +76 -0
- data/sample/goslim.rb +303 -0
- data/sample/gt2fasta.rb +47 -0
- data/sample/na2aa.rb +34 -0
- data/sample/pmfetch.rb +42 -0
- data/sample/pmsearch.rb +42 -0
- data/sample/psortplot_html.rb +214 -0
- data/sample/ssearch2tab.rb +96 -0
- data/sample/tdiary.rb +158 -0
- data/sample/tfastx2tab.rb +100 -0
- data/sample/vs-genes.rb +212 -0
- data/test/data/HMMER/hmmpfam.out +64 -0
- data/test/data/HMMER/hmmsearch.out +88 -0
- data/test/data/SOSUI/sample.report +11 -0
- data/test/data/TMHMM/sample.report +21 -0
- data/test/data/aaindex/DAYM780301 +30 -0
- data/test/data/aaindex/PRAM900102 +20 -0
- data/test/data/bl2seq/cd8a_cd8b_blastp.bl2seq +53 -0
- data/test/data/bl2seq/cd8a_p53_e-5blastp.bl2seq +37 -0
- data/test/data/blast/2.2.15.blastp.m7 +876 -0
- data/test/data/blast/b0002.faa +15 -0
- data/test/data/blast/b0002.faa.m0 +128 -0
- data/test/data/blast/b0002.faa.m7 +65 -0
- data/test/data/blast/b0002.faa.m8 +1 -0
- data/test/data/embl/AB090716.embl +65 -0
- data/test/data/embl/AB090716.embl.rel89 +63 -0
- data/test/data/fasta/example1.txt +75 -0
- data/test/data/fasta/example2.txt +21 -0
- data/test/data/genscan/sample.report +63 -0
- data/test/data/iprscan/merged.raw +32 -0
- data/test/data/iprscan/merged.txt +74 -0
- data/test/data/prosite/prosite.dat +2233 -0
- data/test/data/refseq/nm_126355.entret +64 -0
- data/test/data/soft/GDS100_partial.soft +92 -0
- data/test/data/soft/GSE3457_family_partial.soft +874 -0
- data/test/data/uniprot/p53_human.uniprot +1456 -0
- data/test/functional/bio/io/test_ensembl.rb +186 -0
- data/test/functional/bio/io/test_soapwsdl.rb +52 -0
- data/test/runner.rb +14 -0
- data/test/unit/bio/appl/bl2seq/test_report.rb +134 -0
- data/test/unit/bio/appl/blast/test_report.rb +417 -0
- data/test/unit/bio/appl/blast/test_xmlparser.rb +388 -0
- data/test/unit/bio/appl/genscan/test_report.rb +182 -0
- data/test/unit/bio/appl/hmmer/test_report.rb +342 -0
- data/test/unit/bio/appl/iprscan/test_report.rb +338 -0
- data/test/unit/bio/appl/mafft/test_report.rb +63 -0
- data/test/unit/bio/appl/sosui/test_report.rb +81 -0
- data/test/unit/bio/appl/targetp/test_report.rb +146 -0
- data/test/unit/bio/appl/test_blast.rb +163 -0
- data/test/unit/bio/appl/test_fasta.rb +130 -0
- data/test/unit/bio/appl/test_pts1.rb +140 -0
- data/test/unit/bio/appl/tmhmm/test_report.rb +126 -0
- data/test/unit/bio/data/test_aa.rb +90 -0
- data/test/unit/bio/data/test_codontable.rb +107 -0
- data/test/unit/bio/data/test_na.rb +80 -0
- data/test/unit/bio/db/embl/test_common.rb +117 -0
- data/test/unit/bio/db/embl/test_embl.rb +214 -0
- data/test/unit/bio/db/embl/test_embl_rel89.rb +219 -0
- data/test/unit/bio/db/embl/test_sptr.rb +1775 -0
- data/test/unit/bio/db/embl/test_uniprot.rb +31 -0
- data/test/unit/bio/db/kegg/test_genes.rb +45 -0
- data/test/unit/bio/db/pdb/test_pdb.rb +152 -0
- data/test/unit/bio/db/test_aaindex.rb +197 -0
- data/test/unit/bio/db/test_fasta.rb +250 -0
- data/test/unit/bio/db/test_gff.rb +127 -0
- data/test/unit/bio/db/test_lasergene.rb +95 -0
- data/test/unit/bio/db/test_newick.rb +293 -0
- data/test/unit/bio/db/test_nexus.rb +360 -0
- data/test/unit/bio/db/test_prosite.rb +1437 -0
- data/test/unit/bio/db/test_rebase.rb +101 -0
- data/test/unit/bio/db/test_soft.rb +138 -0
- data/test/unit/bio/io/test_ddbjxml.rb +75 -0
- data/test/unit/bio/io/test_ensembl.rb +109 -0
- data/test/unit/bio/io/test_fastacmd.rb +42 -0
- data/test/unit/bio/io/test_flatfile.rb +237 -0
- data/test/unit/bio/io/test_soapwsdl.rb +32 -0
- data/test/unit/bio/sequence/test_aa.rb +103 -0
- data/test/unit/bio/sequence/test_common.rb +174 -0
- data/test/unit/bio/sequence/test_compat.rb +69 -0
- data/test/unit/bio/sequence/test_na.rb +330 -0
- data/test/unit/bio/shell/plugin/test_seq.rb +185 -0
- data/test/unit/bio/test_alignment.rb +1025 -0
- data/test/unit/bio/test_command.rb +288 -0
- data/test/unit/bio/test_db.rb +96 -0
- data/test/unit/bio/test_feature.rb +116 -0
- data/test/unit/bio/test_location.rb +39 -0
- data/test/unit/bio/test_map.rb +230 -0
- data/test/unit/bio/test_pathway.rb +473 -0
- data/test/unit/bio/test_reference.rb +224 -0
- data/test/unit/bio/test_sequence.rb +329 -0
- data/test/unit/bio/test_shell.rb +18 -0
- data/test/unit/bio/test_tree.rb +593 -0
- data/test/unit/bio/util/restriction_enzyme/analysis/test_calculated_cuts.rb +299 -0
- data/test/unit/bio/util/restriction_enzyme/analysis/test_cut_ranges.rb +103 -0
- data/test/unit/bio/util/restriction_enzyme/analysis/test_sequence_range.rb +240 -0
- data/test/unit/bio/util/restriction_enzyme/double_stranded/test_aligned_strands.rb +101 -0
- data/test/unit/bio/util/restriction_enzyme/double_stranded/test_cut_location_pair.rb +75 -0
- data/test/unit/bio/util/restriction_enzyme/double_stranded/test_cut_location_pair_in_enzyme_notation.rb +73 -0
- data/test/unit/bio/util/restriction_enzyme/double_stranded/test_cut_locations.rb +53 -0
- data/test/unit/bio/util/restriction_enzyme/double_stranded/test_cut_locations_in_enzyme_notation.rb +104 -0
- data/test/unit/bio/util/restriction_enzyme/single_strand/test_cut_locations_in_enzyme_notation.rb +83 -0
- data/test/unit/bio/util/restriction_enzyme/test_analysis.rb +246 -0
- data/test/unit/bio/util/restriction_enzyme/test_cut_symbol.rb +44 -0
- data/test/unit/bio/util/restriction_enzyme/test_double_stranded.rb +115 -0
- data/test/unit/bio/util/restriction_enzyme/test_single_strand.rb +147 -0
- data/test/unit/bio/util/restriction_enzyme/test_single_strand_complement.rb +147 -0
- data/test/unit/bio/util/restriction_enzyme/test_string_formatting.rb +60 -0
- data/test/unit/bio/util/test_color_scheme.rb +33 -0
- data/test/unit/bio/util/test_contingency_table.rb +94 -0
- data/test/unit/bio/util/test_restriction_enzyme.rb +42 -0
- data/test/unit/bio/util/test_sirna.rb +245 -0
- metadata +479 -0
data/sample/genes2nuc.rb
ADDED
@@ -0,0 +1,33 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
#
|
3
|
+
# genes2nuc.rb - convert KEGG/GENES entry into FASTA format (nuc)
|
4
|
+
#
|
5
|
+
# Copyright (C) 2001 KATAYAMA Toshiaki <k@bioruby.org>
|
6
|
+
#
|
7
|
+
# This program is free software; you can redistribute it and/or modify
|
8
|
+
# it under the terms of the GNU General Public License as published by
|
9
|
+
# the Free Software Foundation; either version 2 of the License, or
|
10
|
+
# (at your option) any later version.
|
11
|
+
#
|
12
|
+
# This program is distributed in the hope that it will be useful,
|
13
|
+
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
14
|
+
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
15
|
+
# GNU General Public License for more details.
|
16
|
+
#
|
17
|
+
# $Id: genes2nuc.rb,v 0.4 2002/06/23 20:21:56 k Exp $
|
18
|
+
#
|
19
|
+
|
20
|
+
require 'bio/db/kegg/genes'
|
21
|
+
require 'bio/extend'
|
22
|
+
|
23
|
+
include Bio
|
24
|
+
|
25
|
+
while gets(KEGG::GENES::DELIMITER)
|
26
|
+
genes = KEGG::GENES.new($_)
|
27
|
+
|
28
|
+
next if genes.nalen == 0
|
29
|
+
|
30
|
+
puts ">#{genes.entry_id} #{genes.definition}"
|
31
|
+
puts genes.naseq.fold(60+12, 12)
|
32
|
+
end
|
33
|
+
|
data/sample/genes2pep.rb
ADDED
@@ -0,0 +1,33 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
#
|
3
|
+
# genes2nuc.rb - convert KEGG/GENES entry into FASTA format (nuc)
|
4
|
+
#
|
5
|
+
# Copyright (C) 2001 KATAYAMA Toshiaki <k@bioruby.org>
|
6
|
+
#
|
7
|
+
# This program is free software; you can redistribute it and/or modify
|
8
|
+
# it under the terms of the GNU General Public License as published by
|
9
|
+
# the Free Software Foundation; either version 2 of the License, or
|
10
|
+
# (at your option) any later version.
|
11
|
+
#
|
12
|
+
# This program is distributed in the hope that it will be useful,
|
13
|
+
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
14
|
+
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
15
|
+
# GNU General Public License for more details.
|
16
|
+
#
|
17
|
+
# $Id: genes2pep.rb,v 0.4 2002/06/23 20:21:56 k Exp $
|
18
|
+
#
|
19
|
+
|
20
|
+
require 'bio/db/kegg/genes'
|
21
|
+
require 'bio/extend'
|
22
|
+
|
23
|
+
include Bio
|
24
|
+
|
25
|
+
while gets(KEGG::GENES::DELIMITER)
|
26
|
+
genes = KEGG::GENES.new($_)
|
27
|
+
|
28
|
+
next if genes.aalen == 0
|
29
|
+
|
30
|
+
puts ">#{genes.entry_id} #{genes.definition}"
|
31
|
+
puts genes.aaseq.fold(60+12, 12)
|
32
|
+
end
|
33
|
+
|
data/sample/genes2tab.rb
ADDED
@@ -0,0 +1,81 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
#
|
3
|
+
# genes2tab.rb - convert KEGG/GENES into tab delimited data for MySQL
|
4
|
+
#
|
5
|
+
# Usage:
|
6
|
+
#
|
7
|
+
# % genes2tab.rb /bio/db/kegg/genes/e.coli > genes_eco.tab
|
8
|
+
#
|
9
|
+
# Copyright (C) 2001 KATAYAMA Toshiaki <k@bioruby.org>
|
10
|
+
#
|
11
|
+
# This program is free software; you can redistribute it and/or modify
|
12
|
+
# it under the terms of the GNU General Public License as published by
|
13
|
+
# the Free Software Foundation; either version 2 of the License, or
|
14
|
+
# (at your option) any later version.
|
15
|
+
#
|
16
|
+
# This program is distributed in the hope that it will be useful,
|
17
|
+
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
18
|
+
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
19
|
+
# GNU General Public License for more details.
|
20
|
+
#
|
21
|
+
# $Id: genes2tab.rb,v 0.5 2002/06/23 20:21:56 k Exp $
|
22
|
+
#
|
23
|
+
|
24
|
+
require 'bio/db/kegg/genes'
|
25
|
+
|
26
|
+
include Bio
|
27
|
+
|
28
|
+
while entry = gets(KEGG::GENES::DELIMITER)
|
29
|
+
|
30
|
+
genes = KEGG::GENES.new(entry)
|
31
|
+
|
32
|
+
db = genes.dblinks.inspect
|
33
|
+
|
34
|
+
if genes.codon_usage.length == 64
|
35
|
+
cu = genes.codon_usage.join(' ')
|
36
|
+
else
|
37
|
+
cu = '\N'
|
38
|
+
end
|
39
|
+
|
40
|
+
ary = [
|
41
|
+
genes.entry_id,
|
42
|
+
genes.division,
|
43
|
+
genes.organism,
|
44
|
+
genes.name,
|
45
|
+
genes.definition,
|
46
|
+
genes.keggclass,
|
47
|
+
genes.position,
|
48
|
+
db,
|
49
|
+
cu,
|
50
|
+
genes.aalen,
|
51
|
+
genes.aaseq,
|
52
|
+
genes.nalen,
|
53
|
+
genes.naseq
|
54
|
+
]
|
55
|
+
|
56
|
+
puts ary.join("\t")
|
57
|
+
|
58
|
+
end
|
59
|
+
|
60
|
+
=begin
|
61
|
+
|
62
|
+
CREATE DATABASE IF NOT EXISTS db_name;
|
63
|
+
CREATE TABLE IF NOT EXISTS db_name.genes (
|
64
|
+
id varchar(30) not NULL, # ENTRY ID
|
65
|
+
division varchar(30), # CDS, tRNA etc.
|
66
|
+
organism varchar(255),
|
67
|
+
gene varchar(255),
|
68
|
+
definition varchar(255),
|
69
|
+
keggclass varchar(255),
|
70
|
+
position varchar(255),
|
71
|
+
dblinks varchar(255),
|
72
|
+
codon_usage text,
|
73
|
+
aalen integer,
|
74
|
+
aaseq text,
|
75
|
+
nalen integer,
|
76
|
+
naseq text
|
77
|
+
);
|
78
|
+
LOAD DATA LOCAL INFILE 'genes.tab' INTO TABLE db_name.genes;
|
79
|
+
|
80
|
+
=end
|
81
|
+
|
data/sample/genome2rb.rb
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
#
|
3
|
+
# genome2rb.rb - used to generate contents of the bio/data/keggorg.rb
|
4
|
+
#
|
5
|
+
# Usage:
|
6
|
+
#
|
7
|
+
# % genome2rb.rb genome | sort
|
8
|
+
#
|
9
|
+
# Copyright (C) 2002 KATAYAMA Toshiaki <k@bioruby.org>
|
10
|
+
#
|
11
|
+
# This program is free software; you can redistribute it and/or modify
|
12
|
+
# it under the terms of the GNU General Public License as published by
|
13
|
+
# the Free Software Foundation; either version 2 of the License, or
|
14
|
+
# (at your option) any later version.
|
15
|
+
#
|
16
|
+
# This program is distributed in the hope that it will be useful,
|
17
|
+
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
18
|
+
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
19
|
+
# GNU General Public License for more details.
|
20
|
+
#
|
21
|
+
# $Id: genome2rb.rb,v 1.1 2002/03/04 08:14:45 katayama Exp $
|
22
|
+
#
|
23
|
+
|
24
|
+
require 'bio'
|
25
|
+
|
26
|
+
Bio::FlatFile.new(Bio::KEGG::GENOME,ARGF).each do |x|
|
27
|
+
puts " '#{x.entry_id}' => [ '#{x.name}', '#{x.definition}' ],"
|
28
|
+
end
|
29
|
+
|
@@ -0,0 +1,76 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
#
|
3
|
+
# genome2tab.rb - convert KEGG/GENOME into tab delimited data for MySQL
|
4
|
+
#
|
5
|
+
# Usage:
|
6
|
+
#
|
7
|
+
# % genome2tab.rb /bio/db/kegg/genome/genome > genome.tab
|
8
|
+
#
|
9
|
+
# Copyright (C) 2001 KATAYAMA Toshiaki <k@bioruby.org>
|
10
|
+
#
|
11
|
+
# This program is free software; you can redistribute it and/or modify
|
12
|
+
# it under the terms of the GNU General Public License as published by
|
13
|
+
# the Free Software Foundation; either version 2 of the License, or
|
14
|
+
# (at your option) any later version.
|
15
|
+
#
|
16
|
+
# This program is distributed in the hope that it will be useful,
|
17
|
+
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
18
|
+
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
19
|
+
# GNU General Public License for more details.
|
20
|
+
#
|
21
|
+
# $Id: genome2tab.rb,v 0.5 2002/06/23 20:21:56 k Exp $
|
22
|
+
#
|
23
|
+
|
24
|
+
require 'bio/db/kegg/genome'
|
25
|
+
|
26
|
+
include Bio
|
27
|
+
|
28
|
+
while entry = gets(KEGG::GENOME::DELIMITER)
|
29
|
+
|
30
|
+
genome = KEGG::GENOME.new(entry)
|
31
|
+
|
32
|
+
ref = genome.references.inspect
|
33
|
+
chr = genome.chromosomes.inspect
|
34
|
+
|
35
|
+
ary = [
|
36
|
+
genome.entry_id,
|
37
|
+
genome.name,
|
38
|
+
genome.definition,
|
39
|
+
genome.taxid,
|
40
|
+
genome.taxonomy,
|
41
|
+
genome.comment,
|
42
|
+
ref,
|
43
|
+
chr,
|
44
|
+
genome.nalen,
|
45
|
+
genome.num_gene,
|
46
|
+
genome.num_rna,
|
47
|
+
genome.gc,
|
48
|
+
genome.genomemap,
|
49
|
+
]
|
50
|
+
|
51
|
+
puts ary.join("\t")
|
52
|
+
|
53
|
+
end
|
54
|
+
|
55
|
+
=begin
|
56
|
+
|
57
|
+
CREATE DATABASE IF NOT EXISTS db_name;
|
58
|
+
CREATE TABLE IF NOT EXISTS db_name.genome (
|
59
|
+
id varchar(30) not NULL,
|
60
|
+
name varchar(80),
|
61
|
+
definition varchar(255),
|
62
|
+
taxid varchar(30),
|
63
|
+
taxonomy varchar(255),
|
64
|
+
comment varchar(255),
|
65
|
+
reference text,
|
66
|
+
chromosome text,
|
67
|
+
nalen integer,
|
68
|
+
num_gene integer,
|
69
|
+
num_rna integer,
|
70
|
+
gc float,
|
71
|
+
genomemap varchar(30),
|
72
|
+
);
|
73
|
+
LOAD DATA LOCAL INFILE 'genome.tab' INTO TABLE db_name.genome;
|
74
|
+
|
75
|
+
=end
|
76
|
+
|
data/sample/goslim.rb
ADDED
@@ -0,0 +1,303 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
#
|
3
|
+
# goslim.rb - making a GO slim histgram
|
4
|
+
#
|
5
|
+
# Usage:
|
6
|
+
#
|
7
|
+
# % goslim.rb -p process.ontology -f function.ontology \
|
8
|
+
# -c component.ontology -s goslim_goa.2002 -g gene_association.mgi \
|
9
|
+
# -o mgi -r
|
10
|
+
# % R < mgi.R
|
11
|
+
# % gv mgi.pdf
|
12
|
+
#
|
13
|
+
# Copyright:: Copyright (C) 2003
|
14
|
+
# Mitsuteru C. Nakao <n@bioruby.org>
|
15
|
+
# License:: The Ruby License
|
16
|
+
#
|
17
|
+
# $Id: goslim.rb,v 1.5 2007/04/05 23:35:42 trevor Exp $
|
18
|
+
#
|
19
|
+
|
20
|
+
|
21
|
+
|
22
|
+
SCRIPT_VERSION = '$Id: goslim.rb,v 1.5 2007/04/05 23:35:42 trevor Exp $'
|
23
|
+
|
24
|
+
USAGE = "${__FILE__} - GO slim
|
25
|
+
Usage:
|
26
|
+
#{__FILE__} -p process.ontology -f function.ontology \
|
27
|
+
-c component.ontolgy -g gene_association.mgi -s goslim_goa.2002 \
|
28
|
+
-o goslim.uniqued.out -r
|
29
|
+
|
30
|
+
#{__FILE__} -p process.ontology -f function.ontology \
|
31
|
+
-c component.ontolgy -l gene_association.list -s goslim_goa.2002 \
|
32
|
+
-o mgi.out -r
|
33
|
+
|
34
|
+
#{__FILE__} -p process.ontology -f function.ontology \
|
35
|
+
-c component.ontolgy -g gene_association.mgi -s goslim_goa.2002 >\
|
36
|
+
go_goslit.paired.list
|
37
|
+
|
38
|
+
|
39
|
+
|
40
|
+
Options;
|
41
|
+
-p,--process <go/ontology/process.ontology>
|
42
|
+
-f,--function <go/ontology/function.ontolgoy>
|
43
|
+
-c,--component <go/ontology/component.ontology>
|
44
|
+
-g,--ga <go/gene-associations/gene_association.someone>
|
45
|
+
-l,--galist <a GO_ID list>
|
46
|
+
-s,--goslim <go/GO_slim/goslim_someone>
|
47
|
+
-o,--output <file_name> -- output file name.
|
48
|
+
-r,--r_script -- Writing a R script in <file_name>.R to plot a barplot.
|
49
|
+
-h,--help
|
50
|
+
-v,--version
|
51
|
+
|
52
|
+
Format:
|
53
|
+
GO ID list: /^GO:\d{7}/ for each line
|
54
|
+
|
55
|
+
Mitsuteru C. Nakao <n@bioruby.org>
|
56
|
+
"
|
57
|
+
|
58
|
+
|
59
|
+
|
60
|
+
require 'getoptlong'
|
61
|
+
parser = GetoptLong.new
|
62
|
+
parser.set_options(
|
63
|
+
['--process', '-p', GetoptLong::REQUIRED_ARGUMENT],
|
64
|
+
['--function', '-f', GetoptLong::REQUIRED_ARGUMENT],
|
65
|
+
['--component', '-c', GetoptLong::REQUIRED_ARGUMENT],
|
66
|
+
['--ga', '-g', GetoptLong::REQUIRED_ARGUMENT],
|
67
|
+
['--galist', '-l', GetoptLong::REQUIRED_ARGUMENT],
|
68
|
+
['--goslim', '-s', GetoptLong::REQUIRED_ARGUMENT],
|
69
|
+
['--output', '-o', GetoptLong::REQUIRED_ARGUMENT],
|
70
|
+
['--r_script', '-r', GetoptLong::NO_ARGUMENT],
|
71
|
+
['--help', '-h', GetoptLong::NO_ARGUMENT],
|
72
|
+
['--version', '-v', GetoptLong::NO_ARGUMENT])
|
73
|
+
|
74
|
+
begin
|
75
|
+
parser.each_option do |name, arg|
|
76
|
+
eval "$OPT_#{name.sub(/^--/, '').gsub(/-/, '_').upcase} = '#{arg}'"
|
77
|
+
end
|
78
|
+
rescue
|
79
|
+
exit(1)
|
80
|
+
end
|
81
|
+
|
82
|
+
if $OPT_VERSION
|
83
|
+
puts SCRIPT_VERSION
|
84
|
+
exit(0)
|
85
|
+
end
|
86
|
+
|
87
|
+
if $OPT_HELP or !($OPT_PROCESS or $OPT_FUNCTION or $OPT_COMPONENT or
|
88
|
+
($OPT_GA or $OPT_GALIST))
|
89
|
+
puts USAGE
|
90
|
+
exit(0)
|
91
|
+
end
|
92
|
+
|
93
|
+
|
94
|
+
|
95
|
+
|
96
|
+
# subroutines
|
97
|
+
|
98
|
+
def slim2r(datname)
|
99
|
+
tmp = "# usage: % R --vanilla < #{datname}.R
|
100
|
+
data <- read.delim2('#{datname}')
|
101
|
+
dat <- data$count
|
102
|
+
names(dat) <- paste(data$GO.Term, dat)
|
103
|
+
# set graphc format
|
104
|
+
pdf('#{datname}.pdf')
|
105
|
+
#postscript('#{datname}.ps')
|
106
|
+
# outside margins
|
107
|
+
par(mai = c(1,2.8,1,0.7))
|
108
|
+
barplot(dat,
|
109
|
+
cex.names = 0.6, # row names font size
|
110
|
+
las = 2, # set horizontal row names
|
111
|
+
horiz = T, # set horizontal
|
112
|
+
main = 'GO slim', # main title
|
113
|
+
# set color schema, proc, blue(3); func, red(2); comp, green(4)
|
114
|
+
col = cbind(c(data$aspect == 'process'),
|
115
|
+
c(data$aspect == 'function'),
|
116
|
+
c(data$aspect == 'component')) %*% c(4,2,3)) # color
|
117
|
+
dev.off()
|
118
|
+
"
|
119
|
+
end
|
120
|
+
|
121
|
+
|
122
|
+
# build GOslim uniqued list
|
123
|
+
def slim(ontology, slim_ids, tmp, ga, aspect)
|
124
|
+
tmp[aspect] = Hash.new(0)
|
125
|
+
slim_ids.each {|slim_id|
|
126
|
+
term = ontology.goid2term(slim_id)
|
127
|
+
if term
|
128
|
+
tmp[aspect][term] = 0
|
129
|
+
else
|
130
|
+
next
|
131
|
+
end
|
132
|
+
|
133
|
+
ga.each {|gaid|
|
134
|
+
begin
|
135
|
+
res = ontology.bfs_shortest_path(slim_id, gaid)
|
136
|
+
tmp[aspect][term] += 1 if res[0]
|
137
|
+
rescue NameError
|
138
|
+
$stderr.puts "Warnning: GO:#{slim_id} (#{term}) doesn't exist in the #{aspect}.ontology."
|
139
|
+
tmp[aspect].delete(term)
|
140
|
+
break
|
141
|
+
end
|
142
|
+
}
|
143
|
+
}
|
144
|
+
end
|
145
|
+
|
146
|
+
|
147
|
+
# build GO-GOslim uniqued list
|
148
|
+
def slim2(ontology, slim_ids, tmp, ga, aspect)
|
149
|
+
tmp[aspect] = Hash.new
|
150
|
+
slim_ids.each {|slim_id|
|
151
|
+
term = ontology.goid2term(slim_id)
|
152
|
+
if term
|
153
|
+
begin
|
154
|
+
unless tmp[aspect][term]['GOslim'].index(slim_id)
|
155
|
+
tmp[aspect][term]['GOslim'] << slim_id
|
156
|
+
end
|
157
|
+
rescue NameError
|
158
|
+
tmp[aspect][term] = {'GOslim'=>[slim_id], 'GO'=>[]}
|
159
|
+
end
|
160
|
+
else
|
161
|
+
next
|
162
|
+
end
|
163
|
+
|
164
|
+
ga.each {|gaid|
|
165
|
+
begin
|
166
|
+
res = ontology.bfs_shortest_path(slim_id, gaid)
|
167
|
+
tmp[aspect][term]['GO'] << gaid if res[0]
|
168
|
+
rescue NameError
|
169
|
+
|
170
|
+
break
|
171
|
+
end
|
172
|
+
}
|
173
|
+
}
|
174
|
+
end
|
175
|
+
|
176
|
+
|
177
|
+
|
178
|
+
#
|
179
|
+
# main
|
180
|
+
#
|
181
|
+
|
182
|
+
require 'bio/db/go'
|
183
|
+
|
184
|
+
aspects = ['process', 'function', 'component']
|
185
|
+
rootids = {
|
186
|
+
'process' => '0008150',
|
187
|
+
'function' => '0003674',
|
188
|
+
'component' => '0005575'}
|
189
|
+
|
190
|
+
# files open
|
191
|
+
|
192
|
+
ios = {}
|
193
|
+
files = {
|
194
|
+
'process' => $OPT_PROCESS,
|
195
|
+
'function' => $OPT_FUNCTION,
|
196
|
+
'component' => $OPT_COMPONENT,
|
197
|
+
'ga' => $OPT_GA, # gene-association
|
198
|
+
'list' => $OPT_GALIST, # gene-association list
|
199
|
+
'slim' => $OPT_GOSLIM} # GO slim
|
200
|
+
|
201
|
+
files.each {|k, file_name|
|
202
|
+
next if file_name == nil
|
203
|
+
ios[k] = File.open(file_name)
|
204
|
+
}
|
205
|
+
|
206
|
+
if $OPT_OUTPUT
|
207
|
+
ios['output'] = File.new($OPT_OUTPUT, "w+")
|
208
|
+
ios['r_script'] = File.new("#{$OPT_OUTPUT}.R", "w+")
|
209
|
+
else
|
210
|
+
ios['r_script'] = ios['output'] = $stdout
|
211
|
+
end
|
212
|
+
|
213
|
+
|
214
|
+
# start
|
215
|
+
|
216
|
+
# ontology
|
217
|
+
ontology = {}
|
218
|
+
aspects.each {|aspect|
|
219
|
+
ontology[aspect] = Bio::GO::Ontology.new(ios[aspect].read)
|
220
|
+
}
|
221
|
+
|
222
|
+
|
223
|
+
# GO slim
|
224
|
+
goslim = Bio::GO::Ontology.new(ios['slim'].read)
|
225
|
+
|
226
|
+
# assign a aspect to terms in the GO slim.
|
227
|
+
slim_ids = Hash.new([])
|
228
|
+
goslim.to_list.map {|ent| ent.node }.flatten.uniq.each {|goid|
|
229
|
+
rootids.each {|aspect, rootid|
|
230
|
+
begin
|
231
|
+
a,b = ontology[aspect].bfs_shortest_path(rootid, goid)
|
232
|
+
slim_ids[aspect] << goid
|
233
|
+
rescue NameError
|
234
|
+
$stderr.puts "Error: (#{rootid}, #{goid})"
|
235
|
+
end
|
236
|
+
}
|
237
|
+
}
|
238
|
+
|
239
|
+
|
240
|
+
|
241
|
+
|
242
|
+
# gene-associations
|
243
|
+
|
244
|
+
ga_ids = []
|
245
|
+
if $OPT_GA
|
246
|
+
ga = Bio::GO::GeneAssociation.parser(ios['ga'].read)
|
247
|
+
ga_ids = ga.map {|ent| ent.goid }
|
248
|
+
|
249
|
+
elsif $OPT_GALIST
|
250
|
+
while line = ios['list'].gets
|
251
|
+
if /^GO:(\d{7})/ =~ line
|
252
|
+
goid = $1
|
253
|
+
ga_ids << goid
|
254
|
+
end
|
255
|
+
end
|
256
|
+
else
|
257
|
+
puts "Error: -l or -g options"
|
258
|
+
exit
|
259
|
+
end
|
260
|
+
|
261
|
+
|
262
|
+
# count number
|
263
|
+
|
264
|
+
count = Hash.new(0)
|
265
|
+
|
266
|
+
aspects.each {|aspect|
|
267
|
+
slim2(ontology[aspect], slim_ids[aspect], count, ga_ids, aspect)
|
268
|
+
}
|
269
|
+
|
270
|
+
|
271
|
+
|
272
|
+
|
273
|
+
# output
|
274
|
+
|
275
|
+
if $OPT_R_SCRIPT and $OPT_OUTPUT
|
276
|
+
tmp = [['aspect', 'count', 'GO Term'].join("\t")]
|
277
|
+
else
|
278
|
+
tmp = [['aspect', 'GO ID', 'GOslim Term', 'GOslim ID'].join("\t")]
|
279
|
+
end
|
280
|
+
|
281
|
+
['component','function','process'].each {|aspect|
|
282
|
+
count[aspect].sort {|a, b| b[1]['GO'].size <=> a[1]['GO'].size }.each {|term, value|
|
283
|
+
next if term == ""
|
284
|
+
|
285
|
+
if $OPT_R_SCRIPT and $OPT_OUTPUT
|
286
|
+
tmp << [aspect, value['GO'].size, term].join("\t")
|
287
|
+
else
|
288
|
+
value['GO'].each {|goid|
|
289
|
+
tmp << [aspect, "GO:#{goid}", term,
|
290
|
+
value['GOslim'].map {|e| "GO:#{e}" }.join(' ')].join("\t")
|
291
|
+
}
|
292
|
+
end
|
293
|
+
}
|
294
|
+
}
|
295
|
+
ios['output'].puts tmp.join("\n")
|
296
|
+
|
297
|
+
|
298
|
+
if $OPT_R_SCRIPT and $OPT_OUTPUT
|
299
|
+
ios['r_script'].puts slim2r($OPT_OUTPUT)
|
300
|
+
end
|
301
|
+
|
302
|
+
|
303
|
+
#
|