ngoto-bio 1.2.9.9001
Sign up to get free protection for your applications and to get access to all the features.
- data/ChangeLog +2046 -0
- data/README.rdoc +223 -0
- data/README_DEV.rdoc +285 -0
- data/Rakefile +70 -0
- data/bin/bioruby +44 -0
- data/bin/br_biofetch.rb +47 -0
- data/bin/br_bioflat.rb +293 -0
- data/bin/br_biogetseq.rb +45 -0
- data/bin/br_pmfetch.rb +421 -0
- data/bioruby.gemspec +463 -0
- data/bioruby.gemspec.erb +79 -0
- data/doc/Changes-0.7.rd +369 -0
- data/doc/Changes-1.3.rdoc +195 -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/extconf.rb +2 -0
- data/lib/bio/alignment.rb +2518 -0
- data/lib/bio/appl/bl2seq/report.rb +334 -0
- data/lib/bio/appl/blast/ddbj.rb +142 -0
- data/lib/bio/appl/blast/format0.rb +1438 -0
- data/lib/bio/appl/blast/format8.rb +83 -0
- data/lib/bio/appl/blast/genomenet.rb +263 -0
- data/lib/bio/appl/blast/ncbioptions.rb +220 -0
- data/lib/bio/appl/blast/remote.rb +105 -0
- data/lib/bio/appl/blast/report.rb +767 -0
- data/lib/bio/appl/blast/rexml.rb +144 -0
- data/lib/bio/appl/blast/rpsblast.rb +277 -0
- data/lib/bio/appl/blast/wublast.rb +671 -0
- data/lib/bio/appl/blast/xmlparser.rb +236 -0
- data/lib/bio/appl/blast.rb +505 -0
- data/lib/bio/appl/blat/report.rb +530 -0
- data/lib/bio/appl/clustalw/report.rb +152 -0
- data/lib/bio/appl/clustalw.rb +219 -0
- data/lib/bio/appl/emboss.rb +203 -0
- data/lib/bio/appl/fasta/format10.rb +325 -0
- data/lib/bio/appl/fasta.rb +235 -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/report.rb +683 -0
- data/lib/bio/appl/hmmer.rb +126 -0
- data/lib/bio/appl/iprscan/report.rb +374 -0
- data/lib/bio/appl/mafft/report.rb +226 -0
- data/lib/bio/appl/mafft.rb +259 -0
- data/lib/bio/appl/muscle.rb +52 -0
- data/lib/bio/appl/paml/baseml/report.rb +32 -0
- data/lib/bio/appl/paml/baseml.rb +95 -0
- data/lib/bio/appl/paml/codeml/rates.rb +67 -0
- data/lib/bio/appl/paml/codeml/report.rb +67 -0
- data/lib/bio/appl/paml/codeml.rb +242 -0
- data/lib/bio/appl/paml/common.rb +348 -0
- data/lib/bio/appl/paml/common_report.rb +38 -0
- data/lib/bio/appl/paml/yn00/report.rb +32 -0
- data/lib/bio/appl/paml/yn00.rb +103 -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/report.rb +457 -0
- data/lib/bio/appl/psort.rb +548 -0
- data/lib/bio/appl/pts1.rb +263 -0
- data/lib/bio/appl/sim4/report.rb +485 -0
- data/lib/bio/appl/sim4.rb +124 -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 +231 -0
- data/lib/bio/command.rb +593 -0
- data/lib/bio/compat/features.rb +157 -0
- data/lib/bio/compat/references.rb +128 -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/aaindex.rb +357 -0
- data/lib/bio/db/biosql/biosql_to_biosequence.rb +67 -0
- data/lib/bio/db/biosql/sequence.rb +508 -0
- data/lib/bio/db/embl/common.rb +352 -0
- data/lib/bio/db/embl/embl.rb +500 -0
- data/lib/bio/db/embl/embl_to_biosequence.rb +85 -0
- data/lib/bio/db/embl/format_embl.rb +190 -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 +597 -0
- data/lib/bio/db/fasta/defline.rb +532 -0
- data/lib/bio/db/fasta/fasta_to_biosequence.rb +63 -0
- data/lib/bio/db/fasta/format_fasta.rb +97 -0
- data/lib/bio/db/fasta.rb +410 -0
- data/lib/bio/db/genbank/common.rb +307 -0
- data/lib/bio/db/genbank/ddbj.rb +22 -0
- data/lib/bio/db/genbank/format_genbank.rb +187 -0
- data/lib/bio/db/genbank/genbank.rb +250 -0
- data/lib/bio/db/genbank/genbank_to_biosequence.rb +86 -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 +1846 -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 +166 -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 +326 -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/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/pdb.rb +29 -0
- data/lib/bio/db/prosite.rb +597 -0
- data/lib/bio/db/rebase.rb +456 -0
- data/lib/bio/db/soft.rb +404 -0
- data/lib/bio/db/transfac.rb +375 -0
- data/lib/bio/db.rb +329 -0
- data/lib/bio/feature.rb +139 -0
- data/lib/bio/io/biosql/biodatabase.rb +64 -0
- data/lib/bio/io/biosql/bioentry.rb +29 -0
- data/lib/bio/io/biosql/bioentry_dbxref.rb +11 -0
- data/lib/bio/io/biosql/bioentry_path.rb +12 -0
- data/lib/bio/io/biosql/bioentry_qualifier_value.rb +10 -0
- data/lib/bio/io/biosql/bioentry_reference.rb +10 -0
- data/lib/bio/io/biosql/bioentry_relationship.rb +10 -0
- data/lib/bio/io/biosql/biosequence.rb +11 -0
- data/lib/bio/io/biosql/comment.rb +7 -0
- data/lib/bio/io/biosql/config/database.yml +20 -0
- data/lib/bio/io/biosql/dbxref.rb +13 -0
- data/lib/bio/io/biosql/dbxref_qualifier_value.rb +12 -0
- data/lib/bio/io/biosql/location.rb +32 -0
- data/lib/bio/io/biosql/location_qualifier_value.rb +11 -0
- data/lib/bio/io/biosql/ontology.rb +10 -0
- data/lib/bio/io/biosql/reference.rb +9 -0
- data/lib/bio/io/biosql/seqfeature.rb +32 -0
- data/lib/bio/io/biosql/seqfeature_dbxref.rb +11 -0
- data/lib/bio/io/biosql/seqfeature_path.rb +11 -0
- data/lib/bio/io/biosql/seqfeature_qualifier_value.rb +20 -0
- data/lib/bio/io/biosql/seqfeature_relationship.rb +11 -0
- data/lib/bio/io/biosql/taxon.rb +12 -0
- data/lib/bio/io/biosql/taxon_name.rb +9 -0
- data/lib/bio/io/biosql/term.rb +27 -0
- data/lib/bio/io/biosql/term_dbxref.rb +11 -0
- data/lib/bio/io/biosql/term_path.rb +12 -0
- data/lib/bio/io/biosql/term_relationship.rb +13 -0
- data/lib/bio/io/biosql/term_relationship_term.rb +11 -0
- data/lib/bio/io/biosql/term_synonym.rb +10 -0
- data/lib/bio/io/das.rb +461 -0
- data/lib/bio/io/dbget.rb +194 -0
- data/lib/bio/io/ddbjxml.rb +638 -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 +195 -0
- data/lib/bio/io/flatfile/autodetection.rb +545 -0
- data/lib/bio/io/flatfile/bdb.rb +253 -0
- data/lib/bio/io/flatfile/buffer.rb +237 -0
- data/lib/bio/io/flatfile/index.rb +1381 -0
- data/lib/bio/io/flatfile/indexer.rb +805 -0
- data/lib/bio/io/flatfile/splitter.rb +297 -0
- data/lib/bio/io/flatfile.rb +473 -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 +733 -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 +186 -0
- data/lib/bio/location.rb +867 -0
- data/lib/bio/map.rb +410 -0
- data/lib/bio/pathway.rb +960 -0
- data/lib/bio/reference.rb +602 -0
- data/lib/bio/sequence/aa.rb +125 -0
- data/lib/bio/sequence/adapter.rb +108 -0
- data/lib/bio/sequence/common.rb +310 -0
- data/lib/bio/sequence/compat.rb +123 -0
- data/lib/bio/sequence/dblink.rb +54 -0
- data/lib/bio/sequence/format.rb +358 -0
- data/lib/bio/sequence/format_raw.rb +23 -0
- data/lib/bio/sequence/generic.rb +24 -0
- data/lib/bio/sequence/na.rb +491 -0
- data/lib/bio/sequence.rb +456 -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/shell.rb +44 -0
- data/lib/bio/tree.rb +852 -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/color_scheme.rb +191 -0
- data/lib/bio/util/contingency_table.rb +370 -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/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/double_stranded.rb +321 -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/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/sequence_range.rb +257 -0
- data/lib/bio/util/restriction_enzyme/range/vertical_cut_range.rb +77 -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.rb +200 -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/restriction_enzyme.rb +228 -0
- data/lib/bio/util/sirna.rb +288 -0
- data/lib/bio.rb +300 -0
- data/rdoc.zsh +8 -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/demo_sequence.rb +158 -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/setup.rb +1596 -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/blast/blastp-multi.m7 +188 -0
- data/test/data/command/echoarg2.bat +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/paml/codeml/control_file.txt +30 -0
- data/test/data/paml/codeml/output.txt +78 -0
- data/test/data/paml/codeml/rates +217 -0
- data/test/data/prosite/prosite.dat +2233 -0
- data/test/data/refseq/nm_126355.entret +64 -0
- data/test/data/rpsblast/misc.rpsblast +193 -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/appl/test_pts1.rb +115 -0
- data/test/functional/bio/io/test_ensembl.rb +229 -0
- data/test/functional/bio/io/test_soapwsdl.rb +52 -0
- data/test/functional/bio/sequence/test_output_embl.rb +51 -0
- data/test/functional/bio/test_command.rb +301 -0
- data/test/runner.rb +23 -0
- data/test/unit/bio/appl/bl2seq/test_report.rb +134 -0
- data/test/unit/bio/appl/blast/test_ncbioptions.rb +112 -0
- data/test/unit/bio/appl/blast/test_report.rb +1135 -0
- data/test/unit/bio/appl/blast/test_rpsblast.rb +398 -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/paml/codeml/test_rates.rb +45 -0
- data/test/unit/bio/appl/paml/codeml/test_report.rb +45 -0
- data/test/unit/bio/appl/paml/test_codeml.rb +174 -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 +277 -0
- data/test/unit/bio/appl/test_fasta.rb +130 -0
- data/test/unit/bio/appl/test_pts1.rb +77 -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_embl_to_bioseq.rb +203 -0
- data/test/unit/bio/db/embl/test_sptr.rb +1812 -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 +1190 -0
- data/test/unit/bio/db/test_lasergene.rb +95 -0
- data/test/unit/bio/db/test_medline.rb +127 -0
- data/test/unit/bio/db/test_newick.rb +293 -0
- data/test/unit/bio/db/test_nexus.rb +364 -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/flatfile/test_autodetection.rb +375 -0
- data/test/unit/bio/io/flatfile/test_buffer.rb +251 -0
- data/test/unit/bio/io/flatfile/test_splitter.rb +369 -0
- data/test/unit/bio/io/test_ddbjxml.rb +80 -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 +488 -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 +373 -0
- data/test/unit/bio/sequence/test_compat.rb +69 -0
- data/test/unit/bio/sequence/test_dblink.rb +58 -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 +349 -0
- data/test/unit/bio/test_db.rb +96 -0
- data/test/unit/bio/test_feature.rb +144 -0
- data/test/unit/bio/test_location.rb +599 -0
- data/test/unit/bio/test_map.rb +230 -0
- data/test/unit/bio/test_pathway.rb +499 -0
- data/test/unit/bio/test_reference.rb +252 -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 +484 -0
data/sample/gb2tab.rb
ADDED
@@ -0,0 +1,325 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
#
|
3
|
+
# gb2tab.rb - convert GenBank into tab delimited data for MySQL
|
4
|
+
#
|
5
|
+
# Usage:
|
6
|
+
#
|
7
|
+
# % gb2tab.rb gb*.seq
|
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: gb2tab.rb,v 0.11 2002/04/22 09:10:10 k Exp $
|
22
|
+
#
|
23
|
+
|
24
|
+
require 'bio'
|
25
|
+
|
26
|
+
$stderr.puts Time.now
|
27
|
+
|
28
|
+
ARGV.each do |gbkfile|
|
29
|
+
|
30
|
+
gbk = open("#{gbkfile}")
|
31
|
+
ent = open("#{gbkfile}.ent.tab", "w")
|
32
|
+
ft = open("#{gbkfile}.ft.tab", "w")
|
33
|
+
ref = open("#{gbkfile}.ref.tab", "w")
|
34
|
+
seq = open("#{gbkfile}.seq.tab", "w")
|
35
|
+
|
36
|
+
while entry = gbk.gets(Bio::GenBank::DELIMITER)
|
37
|
+
|
38
|
+
gb = Bio::GenBank.new(entry)
|
39
|
+
|
40
|
+
### MAIN BODY
|
41
|
+
|
42
|
+
ary = [
|
43
|
+
gb.entry_id,
|
44
|
+
gb.nalen,
|
45
|
+
gb.strand,
|
46
|
+
gb.natype,
|
47
|
+
gb.circular,
|
48
|
+
gb.division,
|
49
|
+
gb.date,
|
50
|
+
gb.definition,
|
51
|
+
gb.accession,
|
52
|
+
gb.versions.inspect,
|
53
|
+
gb.keywords.inspect,
|
54
|
+
gb.segment.inspect,
|
55
|
+
gb.common_name,
|
56
|
+
gb.organism,
|
57
|
+
gb.taxonomy,
|
58
|
+
gb.comment,
|
59
|
+
gb.basecount.inspect,
|
60
|
+
gb.origin,
|
61
|
+
]
|
62
|
+
|
63
|
+
ent.puts ary.join("\t")
|
64
|
+
|
65
|
+
### FEATURES
|
66
|
+
|
67
|
+
num = 0
|
68
|
+
|
69
|
+
gb.features.each do |f|
|
70
|
+
num += 1
|
71
|
+
|
72
|
+
span_min, span_max = f.locations.span
|
73
|
+
|
74
|
+
if f.qualifiers.empty?
|
75
|
+
ary = [
|
76
|
+
gb.entry_id,
|
77
|
+
num,
|
78
|
+
f.feature,
|
79
|
+
f.position,
|
80
|
+
span_min,
|
81
|
+
span_max,
|
82
|
+
'',
|
83
|
+
'',
|
84
|
+
]
|
85
|
+
ft.puts ary.join("\t")
|
86
|
+
else
|
87
|
+
f.each do |q|
|
88
|
+
ary = [
|
89
|
+
gb.entry_id,
|
90
|
+
num,
|
91
|
+
f.feature,
|
92
|
+
f.position,
|
93
|
+
span_min,
|
94
|
+
span_max,
|
95
|
+
q.qualifier,
|
96
|
+
q.value,
|
97
|
+
]
|
98
|
+
ft.puts ary.join("\t")
|
99
|
+
end
|
100
|
+
end
|
101
|
+
|
102
|
+
end
|
103
|
+
|
104
|
+
### REFERENCE
|
105
|
+
|
106
|
+
num = 0
|
107
|
+
|
108
|
+
gb.references.each do |r|
|
109
|
+
num += 1
|
110
|
+
|
111
|
+
ary = [
|
112
|
+
gb.entry_id,
|
113
|
+
num,
|
114
|
+
r.authors.inspect,
|
115
|
+
r.title,
|
116
|
+
r.journal,
|
117
|
+
r.medline,
|
118
|
+
r.pubmed,
|
119
|
+
]
|
120
|
+
|
121
|
+
ref.puts ary.join("\t")
|
122
|
+
end
|
123
|
+
|
124
|
+
### SEQUENCE
|
125
|
+
|
126
|
+
maxlen = 16 * 10 ** 6
|
127
|
+
|
128
|
+
num = 0
|
129
|
+
|
130
|
+
0.step(gb.nalen, maxlen) do |i|
|
131
|
+
num += 1
|
132
|
+
|
133
|
+
ary = [
|
134
|
+
gb.entry_id,
|
135
|
+
num,
|
136
|
+
gb.naseq[i, maxlen]
|
137
|
+
]
|
138
|
+
|
139
|
+
seq.puts ary.join("\t")
|
140
|
+
|
141
|
+
end
|
142
|
+
|
143
|
+
end
|
144
|
+
|
145
|
+
gbk.close
|
146
|
+
ent.close
|
147
|
+
ft.close
|
148
|
+
ref.close
|
149
|
+
seq.close
|
150
|
+
|
151
|
+
end
|
152
|
+
|
153
|
+
$stderr.puts Time.now
|
154
|
+
|
155
|
+
=begin
|
156
|
+
|
157
|
+
Example usage in zsh:
|
158
|
+
|
159
|
+
% gb2tab.rb *.seq
|
160
|
+
% for i in *.seq
|
161
|
+
> do
|
162
|
+
> base=`basename $i .seq`
|
163
|
+
> ruby -pe "gsub(/%HOGE%/,'$base')" gb2tab.sql | mysql
|
164
|
+
> done
|
165
|
+
|
166
|
+
gb2tab.sql:
|
167
|
+
|
168
|
+
CREATE DATABASE IF NOT EXISTS genbank;
|
169
|
+
USE genbank;
|
170
|
+
|
171
|
+
CREATE TABLE IF NOT EXISTS %HOGE% (
|
172
|
+
id varchar(16) NOT NULL PRIMARY KEY,
|
173
|
+
nalen integer,
|
174
|
+
strand varchar(5),
|
175
|
+
natype varchar(5),
|
176
|
+
circular varchar(10),
|
177
|
+
division varchar(5),
|
178
|
+
date varchar(12),
|
179
|
+
definition varchar(255),
|
180
|
+
accession varchar(30),
|
181
|
+
versions varchar(30),
|
182
|
+
keywords varchar(255),
|
183
|
+
segment varchar(255),
|
184
|
+
source varchar(255),
|
185
|
+
organism varchar(255),
|
186
|
+
taxonomy varchar(255),
|
187
|
+
comment text,
|
188
|
+
basecount varchar(255),
|
189
|
+
origin varchar(255),
|
190
|
+
KEY (nalen),
|
191
|
+
KEY (division),
|
192
|
+
KEY (accession),
|
193
|
+
KEY (organism),
|
194
|
+
KEY (taxonomy)
|
195
|
+
);
|
196
|
+
LOAD DATA LOCAL INFILE '%HOGE%.seq.ent.tab' INTO TABLE %HOGE%;
|
197
|
+
|
198
|
+
CREATE TABLE IF NOT EXISTS %HOGE%ft (
|
199
|
+
id varchar(16) NOT NULL,
|
200
|
+
num integer,
|
201
|
+
feature varchar(30),
|
202
|
+
position text,
|
203
|
+
span_min integer,
|
204
|
+
span_max integer,
|
205
|
+
qualifier varchar(30),
|
206
|
+
value text,
|
207
|
+
KEY (id),
|
208
|
+
KEY (num),
|
209
|
+
KEY (feature),
|
210
|
+
KEY (span_min),
|
211
|
+
KEY (span_max),
|
212
|
+
KEY (qualifier)
|
213
|
+
);
|
214
|
+
LOAD DATA LOCAL INFILE '%HOGE%.seq.ft.tab' INTO TABLE %HOGE%ft;
|
215
|
+
|
216
|
+
CREATE TABLE IF NOT EXISTS %HOGE%ref (
|
217
|
+
id varchar(16) NOT NULL,
|
218
|
+
num integer,
|
219
|
+
authors text,
|
220
|
+
title text,
|
221
|
+
journal text,
|
222
|
+
medline varchar(255),
|
223
|
+
pubmed varchar(255),
|
224
|
+
KEY (id),
|
225
|
+
KEY (medline),
|
226
|
+
KEY (pubmed)
|
227
|
+
);
|
228
|
+
LOAD DATA LOCAL INFILE '%HOGE%.seq.ref.tab' INTO TABLE %HOGE%ref;
|
229
|
+
|
230
|
+
CREATE TABLE IF NOT EXISTS %HOGE%seq (
|
231
|
+
id varchar(16) NOT NULL,
|
232
|
+
num integer,
|
233
|
+
naseq mediumtext,
|
234
|
+
KEY (id)
|
235
|
+
);
|
236
|
+
LOAD DATA LOCAL INFILE '%HOGE%.seq.seq.tab' INTO TABLE %HOGE%seq;
|
237
|
+
|
238
|
+
|
239
|
+
gbmerge.sql sample:
|
240
|
+
|
241
|
+
CREATE TABLE IF NOT EXISTS ent (
|
242
|
+
id varchar(16) NOT NULL PRIMARY KEY,
|
243
|
+
nalen integer,
|
244
|
+
strand varchar(5),
|
245
|
+
natype varchar(5),
|
246
|
+
circular varchar(10),
|
247
|
+
division varchar(5),
|
248
|
+
date varchar(12),
|
249
|
+
definition varchar(255),
|
250
|
+
accession varchar(30),
|
251
|
+
versions varchar(30),
|
252
|
+
keywords varchar(255),
|
253
|
+
segment varchar(255),
|
254
|
+
source varchar(255),
|
255
|
+
organism varchar(255),
|
256
|
+
taxonomy varchar(255),
|
257
|
+
comment text,
|
258
|
+
basecount varchar(255),
|
259
|
+
origin varchar(255),
|
260
|
+
KEY (nalen),
|
261
|
+
KEY (division),
|
262
|
+
KEY (accession),
|
263
|
+
KEY (organism),
|
264
|
+
KEY (taxonomy)
|
265
|
+
) TYPE=MERGE UNION=(
|
266
|
+
gbbct1,
|
267
|
+
gbbct2,
|
268
|
+
..., # list up all tables by yourself
|
269
|
+
gbvrt
|
270
|
+
);
|
271
|
+
|
272
|
+
CREATE TABLE IF NOT EXISTS ft (
|
273
|
+
id varchar(16) NOT NULL,
|
274
|
+
num integer,
|
275
|
+
feature varchar(30),
|
276
|
+
position text,
|
277
|
+
span_min integer,
|
278
|
+
span_max integer,
|
279
|
+
qualifier varchar(30),
|
280
|
+
value text,
|
281
|
+
KEY (id),
|
282
|
+
KEY (num),
|
283
|
+
KEY (feature),
|
284
|
+
KEY (span_min),
|
285
|
+
KEY (span_max),
|
286
|
+
KEY (qualifier)
|
287
|
+
) TYPE=MERGE UNION=(
|
288
|
+
gbbct1ft,
|
289
|
+
gbbct2ft,
|
290
|
+
..., # list up all ft tables by yourself
|
291
|
+
gbvrtft
|
292
|
+
);
|
293
|
+
|
294
|
+
CREATE TABLE IF NOT EXISTS ref (
|
295
|
+
id varchar(16) NOT NULL,
|
296
|
+
num integer,
|
297
|
+
authors text,
|
298
|
+
title text,
|
299
|
+
journal text,
|
300
|
+
medline varchar(255),
|
301
|
+
pubmed varchar(255),
|
302
|
+
KEY (id),
|
303
|
+
KEY (medline),
|
304
|
+
KEY (pubmed)
|
305
|
+
) TYPE=MERGE UNION=(
|
306
|
+
gbbct1ref,
|
307
|
+
gbbct2ref,
|
308
|
+
..., # list up all ref tables by yourself
|
309
|
+
gbvrtref
|
310
|
+
);
|
311
|
+
|
312
|
+
CREATE TABLE IF NOT EXISTS seq (
|
313
|
+
id varchar(16) NOT NULL,
|
314
|
+
num integer,
|
315
|
+
naseq mediumtext,
|
316
|
+
KEY (id)
|
317
|
+
) TYPE=MERGE UNION=(
|
318
|
+
gbbct1seq,
|
319
|
+
gbbct2seq,
|
320
|
+
..., # list up all seq tables by yourself
|
321
|
+
gbvrtseq
|
322
|
+
);
|
323
|
+
|
324
|
+
=end
|
325
|
+
|
@@ -0,0 +1,161 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
#
|
3
|
+
# gbtab2mysql.rb - load tab delimited GenBank data files into MySQL
|
4
|
+
#
|
5
|
+
# Copyright (C) 2002 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
|
+
# You should have received a copy of the GNU General Public License
|
18
|
+
# along with this program; if not, write to the Free Software
|
19
|
+
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
|
20
|
+
#
|
21
|
+
# $Id: gbtab2mysql.rb,v 1.3 2002/06/25 19:30:26 k Exp $
|
22
|
+
#
|
23
|
+
|
24
|
+
require 'dbi'
|
25
|
+
|
26
|
+
$schema_ent = <<END
|
27
|
+
id varchar(16) NOT NULL PRIMARY KEY,
|
28
|
+
nalen integer,
|
29
|
+
strand varchar(5),
|
30
|
+
natype varchar(5),
|
31
|
+
circular varchar(10),
|
32
|
+
division varchar(5),
|
33
|
+
date varchar(12),
|
34
|
+
definition varchar(255),
|
35
|
+
accession varchar(30),
|
36
|
+
versions varchar(30),
|
37
|
+
keywords varchar(255),
|
38
|
+
segment varchar(255),
|
39
|
+
source varchar(255),
|
40
|
+
organism varchar(255),
|
41
|
+
taxonomy varchar(255),
|
42
|
+
comment text,
|
43
|
+
basecount varchar(255),
|
44
|
+
origin varchar(255),
|
45
|
+
KEY (nalen),
|
46
|
+
KEY (division),
|
47
|
+
KEY (accession),
|
48
|
+
KEY (organism),
|
49
|
+
KEY (taxonomy)
|
50
|
+
END
|
51
|
+
|
52
|
+
$schema_ft = <<END
|
53
|
+
id varchar(16) NOT NULL,
|
54
|
+
num integer,
|
55
|
+
feature varchar(30),
|
56
|
+
position text,
|
57
|
+
span_min integer,
|
58
|
+
span_max integer,
|
59
|
+
qualifier varchar(30),
|
60
|
+
value text,
|
61
|
+
KEY (id),
|
62
|
+
KEY (num),
|
63
|
+
KEY (feature),
|
64
|
+
KEY (span_min),
|
65
|
+
KEY (span_max),
|
66
|
+
KEY (qualifier)
|
67
|
+
END
|
68
|
+
|
69
|
+
$schema_ref = <<END
|
70
|
+
id varchar(16) NOT NULL,
|
71
|
+
num integer,
|
72
|
+
authors text,
|
73
|
+
title text,
|
74
|
+
journal text,
|
75
|
+
medline varchar(255),
|
76
|
+
pubmed varchar(255),
|
77
|
+
KEY (id),
|
78
|
+
KEY (medline),
|
79
|
+
KEY (pubmed)
|
80
|
+
END
|
81
|
+
|
82
|
+
$schema_seq = <<END
|
83
|
+
id varchar(16) NOT NULL,
|
84
|
+
num integer,
|
85
|
+
naseq mediumtext,
|
86
|
+
KEY (id)
|
87
|
+
END
|
88
|
+
|
89
|
+
|
90
|
+
def create_table(dbh, table)
|
91
|
+
$stderr.puts("create tables on #{table}") if $DEBUG
|
92
|
+
|
93
|
+
query = "CREATE TABLE IF NOT EXISTS #{table} ( #{$schema_ent} )"
|
94
|
+
dbh.execute(query)
|
95
|
+
query = "CREATE TABLE IF NOT EXISTS #{table}ft ( #{$schema_ft} )"
|
96
|
+
dbh.execute(query)
|
97
|
+
query = "CREATE TABLE IF NOT EXISTS #{table}ref ( #{$schema_ref} )"
|
98
|
+
dbh.execute(query)
|
99
|
+
query = "CREATE TABLE IF NOT EXISTS #{table}seq ( #{$schema_seq} )"
|
100
|
+
dbh.execute(query)
|
101
|
+
end
|
102
|
+
|
103
|
+
|
104
|
+
def load_tab(dbh, base, table)
|
105
|
+
$stderr.puts("load #{base} into #{table}") if $DEBUG
|
106
|
+
|
107
|
+
query = "LOAD DATA LOCAL INFILE '#{base}.seq.ent.tab' INTO TABLE #{table}"
|
108
|
+
dbh.execute(query)
|
109
|
+
query = "LOAD DATA LOCAL INFILE '#{base}.seq.ft.tab' INTO TABLE #{table}ft"
|
110
|
+
dbh.execute(query)
|
111
|
+
query = "LOAD DATA LOCAL INFILE '#{base}.seq.ref.tab' INTO TABLE #{table}ref"
|
112
|
+
dbh.execute(query)
|
113
|
+
query = "LOAD DATA LOCAL INFILE '#{base}.seq.seq.tab' INTO TABLE #{table}seq"
|
114
|
+
dbh.execute(query)
|
115
|
+
end
|
116
|
+
|
117
|
+
|
118
|
+
def merge_table(dbh, tables)
|
119
|
+
query = "CREATE TABLE IF NOT EXISTS ent ( #{$schema_ent} )" +
|
120
|
+
" TYPE=MERGE UNION=( #{tables.join(', ')} )"
|
121
|
+
dbh.execute(query)
|
122
|
+
query = "CREATE TABLE IF NOT EXISTS ft ( #{$schema_ft} )" +
|
123
|
+
" TYPE=MERGE UNION=( #{tables.join('ft, ') + 'ft' } )"
|
124
|
+
dbh.execute(query)
|
125
|
+
query = "CREATE TABLE IF NOT EXISTS ref ( #{$schema_ref} )" +
|
126
|
+
" TYPE=MERGE UNION=( #{tables.join('ref, ') + 'ref' } )"
|
127
|
+
dbh.execute(query)
|
128
|
+
query = "CREATE TABLE IF NOT EXISTS seq ( #{$schema_seq} )" +
|
129
|
+
" TYPE=MERGE UNION=( #{tables.join('seq, ') + 'seq' } )"
|
130
|
+
dbh.execute(query)
|
131
|
+
end
|
132
|
+
|
133
|
+
|
134
|
+
$stderr.puts Time.now
|
135
|
+
|
136
|
+
DBI.connect('dbi:Mysql:genbank:localhost', 'root') do |dbh|
|
137
|
+
tables = Array.new
|
138
|
+
|
139
|
+
Dir.glob("*.seq").sort.each do |gbk|
|
140
|
+
base = File.basename(gbk, '.seq')
|
141
|
+
|
142
|
+
div = base[/gb.../]
|
143
|
+
num = base[/\d+/].to_i
|
144
|
+
|
145
|
+
table = div
|
146
|
+
table = "%s%d" % [ div, (num - 1) / 20 + 1 ] if num > 20
|
147
|
+
|
148
|
+
unless dbh.tables.include?(table)
|
149
|
+
create_table(dbh, table)
|
150
|
+
tables.push(table)
|
151
|
+
end
|
152
|
+
|
153
|
+
load_tab(dbh, base, table)
|
154
|
+
end
|
155
|
+
|
156
|
+
merge_table(dbh, tables)
|
157
|
+
end
|
158
|
+
|
159
|
+
$stderr.puts Time.now
|
160
|
+
|
161
|
+
|
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
|
+
|