wwood-bioruby 1.2.11
Sign up to get free protection for your applications and to get access to all the features.
- data/README.rdoc +205 -0
- data/README_DEV.rdoc +285 -0
- data/VERSION.yml +4 -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/lib/bio.rb +306 -0
- data/lib/bio/alignment.rb +2518 -0
- data/lib/bio/appl/bl2seq/report.rb +334 -0
- data/lib/bio/appl/blast.rb +505 -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 +635 -0
- data/lib/bio/appl/blast/xmlparser.rb +236 -0
- data/lib/bio/appl/blat/report.rb +530 -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 +235 -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/paml/baseml.rb +95 -0
- data/lib/bio/appl/paml/baseml/report.rb +32 -0
- data/lib/bio/appl/paml/codeml.rb +242 -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/common.rb +348 -0
- data/lib/bio/appl/paml/common_report.rb +38 -0
- data/lib/bio/appl/paml/yn00.rb +103 -0
- data/lib/bio/appl/paml/yn00/report.rb +32 -0
- data/lib/bio/appl/phylip/alignment.rb +133 -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 +542 -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 +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 +353 -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/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.rb +410 -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/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.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 +456 -0
- data/lib/bio/db/soft.rb +404 -0
- data/lib/bio/db/transfac.rb +375 -0
- data/lib/bio/db/url.rb +42 -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.rb +482 -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/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.rb +456 -0
- data/lib/bio/sequence/aa.rb +152 -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/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 +852 -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 +200 -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/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 +14 -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_psort.rb +57 -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/db/test_url.rb +36 -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 +505 -0
- data/test/unit/bio/io/test_soapwsdl.rb +32 -0
- data/test/unit/bio/sequence/test_aa.rb +115 -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 +543 -0
@@ -0,0 +1,85 @@
|
|
1
|
+
#
|
2
|
+
# = bio/db/embl/embl_to_biosequence.rb - Bio::EMBL to Bio::Sequence adapter module
|
3
|
+
#
|
4
|
+
# Copyright:: Copyright (C) 2008
|
5
|
+
# Naohisa Goto <ng@bioruby.org>,
|
6
|
+
# License:: The Ruby License
|
7
|
+
#
|
8
|
+
# $Id:$
|
9
|
+
#
|
10
|
+
|
11
|
+
require 'bio/sequence'
|
12
|
+
require 'bio/sequence/adapter'
|
13
|
+
|
14
|
+
# Internal use only. Normal users should not use this module.
|
15
|
+
#
|
16
|
+
# Bio::EMBL to Bio::Sequence adapter module.
|
17
|
+
# It is internally used in Bio::EMBL#to_biosequence.
|
18
|
+
#
|
19
|
+
module Bio::Sequence::Adapter::EMBL
|
20
|
+
|
21
|
+
extend Bio::Sequence::Adapter
|
22
|
+
|
23
|
+
private
|
24
|
+
|
25
|
+
def_biosequence_adapter :seq
|
26
|
+
|
27
|
+
def_biosequence_adapter :id_namespace do |orig|
|
28
|
+
'EMBL'
|
29
|
+
end
|
30
|
+
|
31
|
+
def_biosequence_adapter :entry_id
|
32
|
+
|
33
|
+
def_biosequence_adapter :primary_accession do |orig|
|
34
|
+
orig.accessions[0]
|
35
|
+
end
|
36
|
+
|
37
|
+
def_biosequence_adapter :secondary_accessions do |orig|
|
38
|
+
orig.accessions[1..-1] || []
|
39
|
+
end
|
40
|
+
|
41
|
+
def_biosequence_adapter :molecule_type
|
42
|
+
|
43
|
+
def_biosequence_adapter :data_class
|
44
|
+
|
45
|
+
def_biosequence_adapter :definition, :description
|
46
|
+
|
47
|
+
def_biosequence_adapter :topology
|
48
|
+
|
49
|
+
def_biosequence_adapter :date_created
|
50
|
+
|
51
|
+
def_biosequence_adapter :date_modified
|
52
|
+
|
53
|
+
def_biosequence_adapter :release_created
|
54
|
+
|
55
|
+
def_biosequence_adapter :release_modified
|
56
|
+
|
57
|
+
def_biosequence_adapter :entry_version
|
58
|
+
|
59
|
+
def_biosequence_adapter :division
|
60
|
+
|
61
|
+
def_biosequence_adapter :sequence_version, :version
|
62
|
+
|
63
|
+
def_biosequence_adapter :keywords
|
64
|
+
|
65
|
+
def_biosequence_adapter :species
|
66
|
+
|
67
|
+
def_biosequence_adapter :classification
|
68
|
+
|
69
|
+
#--
|
70
|
+
# unsupported yet
|
71
|
+
# def_biosequence_adapter :organelle do |orig|
|
72
|
+
# orig.fetch('OG')
|
73
|
+
# end
|
74
|
+
#++
|
75
|
+
|
76
|
+
def_biosequence_adapter :references
|
77
|
+
|
78
|
+
def_biosequence_adapter :features
|
79
|
+
|
80
|
+
def_biosequence_adapter :comments, :cc
|
81
|
+
|
82
|
+
def_biosequence_adapter :dblinks
|
83
|
+
|
84
|
+
end #module Bio::Sequence::Adapter::EMBL
|
85
|
+
|
@@ -0,0 +1,190 @@
|
|
1
|
+
#
|
2
|
+
# = bio/db/embl/format_embl.rb - EMBL format generater
|
3
|
+
#
|
4
|
+
# Copyright:: Copyright (C) 2008
|
5
|
+
# Jan Aerts <jandot@bioruby.org>,
|
6
|
+
# Naohisa Goto <ng@bioruby.org>
|
7
|
+
# License:: The Ruby License
|
8
|
+
#
|
9
|
+
# $Id: format_embl.rb,v 1.1.2.7 2008/06/19 12:45:15 ngoto Exp $
|
10
|
+
#
|
11
|
+
|
12
|
+
require 'bio/sequence/format'
|
13
|
+
|
14
|
+
module Bio::Sequence::Format::NucFormatter
|
15
|
+
|
16
|
+
# INTERNAL USE ONLY, YOU SHOULD NOT USE THIS CLASS.
|
17
|
+
# Embl format output class for Bio::Sequence.
|
18
|
+
class Embl < Bio::Sequence::Format::FormatterBase
|
19
|
+
|
20
|
+
# helper methods
|
21
|
+
include Bio::Sequence::Format::INSDFeatureHelper
|
22
|
+
|
23
|
+
private
|
24
|
+
|
25
|
+
# wrapping with EMBL style
|
26
|
+
def embl_wrap(prefix, str)
|
27
|
+
wrap(str.to_s, 80, prefix)
|
28
|
+
end
|
29
|
+
|
30
|
+
# Given words (an Array of String) are wrapping with EMBL style.
|
31
|
+
# Each word is never splitted inside the word.
|
32
|
+
def embl_wrap_words(prefix, array)
|
33
|
+
width = 80
|
34
|
+
result = []
|
35
|
+
str = nil
|
36
|
+
array.each do |x|
|
37
|
+
if str then
|
38
|
+
if str.length + 1 + x.length > width then
|
39
|
+
str = nil
|
40
|
+
else
|
41
|
+
str.concat ' '
|
42
|
+
str.concat x
|
43
|
+
end
|
44
|
+
end
|
45
|
+
unless str then
|
46
|
+
str = prefix + x
|
47
|
+
result.push str
|
48
|
+
end
|
49
|
+
end
|
50
|
+
result.join("\n")
|
51
|
+
end
|
52
|
+
|
53
|
+
# format reference
|
54
|
+
# ref:: Bio::Reference object
|
55
|
+
# hash:: (optional) a hash for RN (reference number) administration
|
56
|
+
def reference_format_embl(ref, hash = nil)
|
57
|
+
lines = Array.new
|
58
|
+
if ref.embl_gb_record_number or hash then
|
59
|
+
refno = ref.embl_gb_record_number.to_i
|
60
|
+
hash ||= {}
|
61
|
+
if refno <= 0 or hash[refno] then
|
62
|
+
refno = hash.keys.sort[-1].to_i + 1
|
63
|
+
hash[refno] = true
|
64
|
+
end
|
65
|
+
lines << embl_wrap("RN ", "[#{refno}]")
|
66
|
+
end
|
67
|
+
if ref.comments then
|
68
|
+
ref.comments.each do |cmnt|
|
69
|
+
lines << embl_wrap("RC ", cmnt)
|
70
|
+
end
|
71
|
+
end
|
72
|
+
unless ref.sequence_position.to_s.empty? then
|
73
|
+
lines << embl_wrap("RP ", "#{ref.sequence_position}")
|
74
|
+
end
|
75
|
+
unless ref.doi.to_s.empty? then
|
76
|
+
lines << embl_wrap("RX ", "DOI; #{ref.doi}.")
|
77
|
+
end
|
78
|
+
unless ref.pubmed.to_s.empty? then
|
79
|
+
lines << embl_wrap("RX ", "PUBMED; #{ref.pubmed}.")
|
80
|
+
end
|
81
|
+
unless ref.authors.empty? then
|
82
|
+
auth = ref.authors.collect do |x|
|
83
|
+
y = x.to_s.strip.split(/\, *([^\,]+)\z/)
|
84
|
+
y[1].gsub!(/\. +/, '.') if y[1]
|
85
|
+
y.join(' ')
|
86
|
+
end
|
87
|
+
lastauth = auth.pop
|
88
|
+
auth.each { |x| x.concat ',' }
|
89
|
+
auth.push(lastauth.to_s + ';')
|
90
|
+
lines << embl_wrap_words('RA ', auth)
|
91
|
+
end
|
92
|
+
lines << embl_wrap('RT ',
|
93
|
+
(ref.title.to_s.empty? ? '' :
|
94
|
+
"\"#{ref.title}\"") + ';')
|
95
|
+
unless ref.journal.to_s.empty? then
|
96
|
+
volissue = "#{ref.volume.to_s}"
|
97
|
+
volissue = "#{volissue}(#{ref.issue})" unless ref.issue.to_s.empty?
|
98
|
+
rl = "#{ref.journal}"
|
99
|
+
rl += " #{volissue}" unless volissue.empty?
|
100
|
+
rl += ":#{ref.pages}" unless ref.pages.to_s.empty?
|
101
|
+
rl += "(#{ref.year})" unless ref.year.to_s.empty?
|
102
|
+
rl += '.'
|
103
|
+
lines << embl_wrap('RL ', rl)
|
104
|
+
end
|
105
|
+
lines << "XX"
|
106
|
+
return lines.join("\n")
|
107
|
+
end
|
108
|
+
|
109
|
+
def seq_format_embl(seq)
|
110
|
+
counter = 0
|
111
|
+
result = seq.gsub(/.{1,60}/) do |x|
|
112
|
+
counter += x.length
|
113
|
+
x = x.gsub(/.{10}/, '\0 ')
|
114
|
+
sprintf(" %-66s%9d\n", x, counter)
|
115
|
+
end
|
116
|
+
result.chomp!
|
117
|
+
result
|
118
|
+
end
|
119
|
+
|
120
|
+
def seq_composition(seq)
|
121
|
+
{ :a => seq.count('aA'),
|
122
|
+
:c => seq.count('cC'),
|
123
|
+
:g => seq.count('gG'),
|
124
|
+
:t => seq.count('tTuU'),
|
125
|
+
:other => seq.count('^aAcCgGtTuU')
|
126
|
+
}
|
127
|
+
end
|
128
|
+
|
129
|
+
# moleculue type
|
130
|
+
def mol_type_embl
|
131
|
+
if mt = molecule_type then
|
132
|
+
mt
|
133
|
+
elsif f = (features or []).find { |f| f.feature == 'source' } and
|
134
|
+
q = f.qualifiers.find { |q| q.qualifier == 'mol_type' } then
|
135
|
+
q.value
|
136
|
+
else
|
137
|
+
'NA'
|
138
|
+
end
|
139
|
+
end
|
140
|
+
|
141
|
+
# CC line. Comments.
|
142
|
+
def comments_format_embl(cmnts)
|
143
|
+
return '' if !cmnts or cmnts.empty?
|
144
|
+
cmnts = [ cmnts ] unless cmnts.kind_of?(Array)
|
145
|
+
a = []
|
146
|
+
cmnts.each do |str|
|
147
|
+
a.push embl_wrap('CC ', str)
|
148
|
+
end
|
149
|
+
unless a.empty? then
|
150
|
+
a.push "XX "
|
151
|
+
a.push '' # dummy to put "\n" at the end of the string
|
152
|
+
end
|
153
|
+
a.join("\n")
|
154
|
+
end
|
155
|
+
|
156
|
+
|
157
|
+
# Erb template of EMBL format for Bio::Sequence
|
158
|
+
erb_template <<'__END_OF_TEMPLATE__'
|
159
|
+
ID <%= primary_accession || entry_id %>; SV <%= sequence_version %>; <%= topology %>; <%= mol_type_embl %>; <%= data_class %>; <%= division %>; <%= seq.length %> BP.
|
160
|
+
XX
|
161
|
+
<%= embl_wrap('AC ', accessions.reject{|a| a.nil?}.join('; ') + ';') %>
|
162
|
+
XX
|
163
|
+
DT <%= format_date(date_created || null_date) %> (Rel. <%= release_created || 0 %>, Created)
|
164
|
+
DT <%= format_date(date_modified || null_date) %> (Rel. <%= release_modified || 0 %>, Last updated, Version <%= entry_version || 0 %>)
|
165
|
+
XX
|
166
|
+
<%= embl_wrap('DE ', definition) %>
|
167
|
+
XX
|
168
|
+
<%= embl_wrap('KW ', (keywords || []).join('; ') + '.') %>
|
169
|
+
XX
|
170
|
+
OS <%= species %>
|
171
|
+
<%= embl_wrap('OC ', (classification || []).join('; ') + '.') %>
|
172
|
+
XX
|
173
|
+
<% hash = {}; (references || []).each do |ref| %><%= reference_format_embl(ref, hash) %>
|
174
|
+
<% end %><% (dblinks || []).each do |r|
|
175
|
+
%>DR <%= r.database %>; <%= r.id %><% unless r.secondary_ids.empty? %>; <%= r.secondary_ids[0] %><% end %>.
|
176
|
+
<% end %><% if dblinks and !dblinks.empty? then
|
177
|
+
%>XX
|
178
|
+
<% end %><%= comments_format_embl(comments)
|
179
|
+
%>FH Key Location/Qualifiers
|
180
|
+
FH
|
181
|
+
<%= format_features_embl(features || []) %>XX
|
182
|
+
SQ Sequence <%= seq.length %> BP; <% c = seq_composition(seq) %><%= c[:a] %> A; <%= c[:c] %> C; <%= c[:g] %> G; <%= c[:t] %> T; <%= c[:other] %> other;
|
183
|
+
<%= seq_format_embl(seq) %>
|
184
|
+
//
|
185
|
+
__END_OF_TEMPLATE__
|
186
|
+
|
187
|
+
end #class Embl
|
188
|
+
|
189
|
+
end #module Bio::Sequence::Format::NucFormatter
|
190
|
+
|
@@ -0,0 +1,1283 @@
|
|
1
|
+
#
|
2
|
+
# = bio/db/embl/sptr.rb - UniProt/SwissProt and TrEMBL database class
|
3
|
+
#
|
4
|
+
# Copyright:: Copyright (C) 2001-2006 Mitsuteru C. Nakao <n@bioruby.org>
|
5
|
+
# License:: The Ruby License
|
6
|
+
#
|
7
|
+
# $Id:$
|
8
|
+
#
|
9
|
+
# == Description
|
10
|
+
#
|
11
|
+
# Shared methods for UniProtKB/SwissProt and TrEMBL classes.
|
12
|
+
#
|
13
|
+
# See the SWISS-PROT document file SPECLIST.TXT or UniProtKB/SwissProt
|
14
|
+
# user manual.
|
15
|
+
#
|
16
|
+
# == Examples
|
17
|
+
#
|
18
|
+
# str = File.read("p53_human.swiss")
|
19
|
+
# obj = Bio::SPTR.new(str)
|
20
|
+
# obj.entry_id #=> "P53_HUMAN"
|
21
|
+
#
|
22
|
+
# == References
|
23
|
+
#
|
24
|
+
# * Swiss-Prot Protein knowledgebase. TrEMBL Computer-annotated supplement
|
25
|
+
# to Swiss-Prot
|
26
|
+
# http://au.expasy.org/sprot/
|
27
|
+
#
|
28
|
+
# * UniProt
|
29
|
+
# http://uniprot.org/
|
30
|
+
#
|
31
|
+
# * The UniProtKB/SwissProt/TrEMBL User Manual
|
32
|
+
# http://www.expasy.org/sprot/userman.html
|
33
|
+
#
|
34
|
+
|
35
|
+
|
36
|
+
require 'bio/db'
|
37
|
+
require 'bio/db/embl/common'
|
38
|
+
|
39
|
+
module Bio
|
40
|
+
|
41
|
+
# Parser class for UniProtKB/SwissProt and TrEMBL database entry.
|
42
|
+
class SPTR < EMBLDB
|
43
|
+
include Bio::EMBLDB::Common
|
44
|
+
|
45
|
+
@@entry_regrexp = /[A-Z0-9]{1,4}_[A-Z0-9]{1,5}/
|
46
|
+
@@data_class = ["STANDARD", "PRELIMINARY"]
|
47
|
+
|
48
|
+
# returns a Hash of the ID line.
|
49
|
+
#
|
50
|
+
# returns a content (Int or String) of the ID line by a given key.
|
51
|
+
# Hash keys: ['ENTRY_NAME', 'DATA_CLASS', 'MODECULE_TYPE', 'SEQUENCE_LENGTH']
|
52
|
+
#
|
53
|
+
# === ID Line
|
54
|
+
# ID P53_HUMAN STANDARD; PRT; 393 AA.
|
55
|
+
# #"ID #{ENTRY_NAME} #{DATA_CLASS}; #{MOLECULE_TYPE}; #{SEQUENCE_LENGTH}."
|
56
|
+
#
|
57
|
+
# === Examples
|
58
|
+
# obj.id_line #=> {"ENTRY_NAME"=>"P53_HUMAN", "DATA_CLASS"=>"STANDARD",
|
59
|
+
# "SEQUENCE_LENGTH"=>393, "MOLECULE_TYPE"=>"PRT"}
|
60
|
+
#
|
61
|
+
# obj.id_line('ENTRY_NAME') #=> "P53_HUMAN"
|
62
|
+
#
|
63
|
+
def id_line(key = nil)
|
64
|
+
return id_line[key] if key
|
65
|
+
return @data['ID'] if @data['ID']
|
66
|
+
|
67
|
+
part = @orig['ID'].split(/ +/)
|
68
|
+
@data['ID'] = {
|
69
|
+
'ENTRY_NAME' => part[1],
|
70
|
+
'DATA_CLASS' => part[2].sub(/;/,''),
|
71
|
+
'MOLECULE_TYPE' => part[3].sub(/;/,''),
|
72
|
+
'SEQUENCE_LENGTH' => part[4].to_i
|
73
|
+
}
|
74
|
+
end
|
75
|
+
|
76
|
+
|
77
|
+
# returns a ENTRY_NAME in the ID line.
|
78
|
+
#
|
79
|
+
def entry_id
|
80
|
+
id_line('ENTRY_NAME')
|
81
|
+
end
|
82
|
+
alias entry_name entry_id
|
83
|
+
alias entry entry_id
|
84
|
+
|
85
|
+
|
86
|
+
# returns a MOLECULE_TYPE in the ID line.
|
87
|
+
#
|
88
|
+
# A short-cut for Bio::SPTR#id_line('MOLECULE_TYPE').
|
89
|
+
def molecule
|
90
|
+
id_line('MOLECULE_TYPE')
|
91
|
+
end
|
92
|
+
alias molecule_type molecule
|
93
|
+
|
94
|
+
|
95
|
+
# returns a SEQUENCE_LENGTH in the ID line.
|
96
|
+
#
|
97
|
+
# A short-cut for Bio::SPTR#id_line('SEQUENCE_LENGHT').
|
98
|
+
def sequence_length
|
99
|
+
id_line('SEQUENCE_LENGTH')
|
100
|
+
end
|
101
|
+
alias aalen sequence_length
|
102
|
+
|
103
|
+
|
104
|
+
# Bio::EMBLDB::Common#ac -> ary
|
105
|
+
# #accessions -> ary
|
106
|
+
# #accession -> String (accessions.first)
|
107
|
+
@@ac_regrexp = /[OPQ][0-9][A-Z0-9]{3}[0-9]/
|
108
|
+
|
109
|
+
|
110
|
+
|
111
|
+
# returns a Hash of information in the DT lines.
|
112
|
+
# hash keys:
|
113
|
+
# ['created', 'sequence', 'annotation']
|
114
|
+
# also Symbols acceptable (ASAP):
|
115
|
+
# [:created, :sequence, :annotation]
|
116
|
+
#
|
117
|
+
# returns a String of information in the DT lines by a given key..
|
118
|
+
#
|
119
|
+
# === DT Line; date (3/entry)
|
120
|
+
# DT DD-MMM-YYY (rel. NN, Created)
|
121
|
+
# DT DD-MMM-YYY (rel. NN, Last sequence update)
|
122
|
+
# DT DD-MMM-YYY (rel. NN, Last annotation update)
|
123
|
+
def dt(key = nil)
|
124
|
+
return dt[key] if key
|
125
|
+
return @data['DT'] if @data['DT']
|
126
|
+
|
127
|
+
part = self.get('DT').split(/\n/)
|
128
|
+
@data['DT'] = {
|
129
|
+
'created' => part[0].sub(/\w{2} /,'').strip,
|
130
|
+
'sequence' => part[1].sub(/\w{2} /,'').strip,
|
131
|
+
'annotation' => part[2].sub(/\w{2} /,'').strip
|
132
|
+
}
|
133
|
+
end
|
134
|
+
|
135
|
+
|
136
|
+
# returns the proposed official name of the protein.
|
137
|
+
#
|
138
|
+
# === DE Line; description (>=1)
|
139
|
+
# "DE #{OFFICIAL_NAME} (#{SYNONYM})"
|
140
|
+
# "DE #{OFFICIAL_NAME} (#{SYNONYM}) [CONTEINS: #1; #2]."
|
141
|
+
# OFFICIAL_NAME 1/entry
|
142
|
+
# SYNONYM >=0
|
143
|
+
# CONTEINS >=0
|
144
|
+
def protein_name
|
145
|
+
name = ""
|
146
|
+
if de_line = fetch('DE') then
|
147
|
+
str = de_line[/^[^\[]*/] # everything preceding the first [ (the "contains" part)
|
148
|
+
name = str[/^[^(]*/].strip
|
149
|
+
name << ' (Fragment)' if str =~ /fragment/i
|
150
|
+
end
|
151
|
+
return name
|
152
|
+
end
|
153
|
+
|
154
|
+
|
155
|
+
# returns an array of synonyms (unofficial names).
|
156
|
+
#
|
157
|
+
# synonyms are each placed in () following the official name on the DE line.
|
158
|
+
def synonyms
|
159
|
+
ary = Array.new
|
160
|
+
if de_line = fetch('DE') then
|
161
|
+
line = de_line.sub(/\[.*\]/,'') # ignore stuff between [ and ]. That's the "contains" part
|
162
|
+
line.scan(/\([^)]+/) do |synonym|
|
163
|
+
unless synonym =~ /fragment/i then
|
164
|
+
ary << synonym[1..-1].strip # index to remove the leading (
|
165
|
+
end
|
166
|
+
end
|
167
|
+
end
|
168
|
+
return ary
|
169
|
+
end
|
170
|
+
|
171
|
+
|
172
|
+
# returns gene names in the GN line.
|
173
|
+
#
|
174
|
+
# New UniProt/SwissProt format:
|
175
|
+
# * Bio::SPTR#gn -> [ <gene record>* ]
|
176
|
+
# where <gene record> is:
|
177
|
+
# { :name => '...',
|
178
|
+
# :synonyms => [ 's1', 's2', ... ],
|
179
|
+
# :loci => [ 'l1', 'l2', ... ],
|
180
|
+
# :orfs => [ 'o1', 'o2', ... ]
|
181
|
+
# }
|
182
|
+
#
|
183
|
+
# Old format:
|
184
|
+
# * Bio::SPTR#gn -> Array # AND
|
185
|
+
# * Bio::SPTR#gn[0] -> Array # OR
|
186
|
+
#
|
187
|
+
# === GN Line: Gene name(s) (>=0, optional)
|
188
|
+
def gn
|
189
|
+
unless @data['GN']
|
190
|
+
case fetch('GN')
|
191
|
+
when /Name=/,/ORFNames=/
|
192
|
+
@data['GN'] = gn_uniprot_parser
|
193
|
+
else
|
194
|
+
@data['GN'] = gn_old_parser
|
195
|
+
end
|
196
|
+
end
|
197
|
+
@data['GN']
|
198
|
+
end
|
199
|
+
|
200
|
+
|
201
|
+
# returns contents in the old style GN line.
|
202
|
+
# === GN Line: Gene name(s) (>=0, optional)
|
203
|
+
# GN HNS OR DRDX OR OSMZ OR BGLY.
|
204
|
+
# GN CECA1 AND CECA2.
|
205
|
+
# GN CECA1 AND (HOGE OR FUGA).
|
206
|
+
#
|
207
|
+
# GN NAME1 [(AND|OR) NAME]+.
|
208
|
+
#
|
209
|
+
# Bio::SPTR#gn -> Array # AND
|
210
|
+
# #gn[0] -> Array # OR
|
211
|
+
# #gene_names -> Array
|
212
|
+
def gn_old_parser
|
213
|
+
names = Array.new
|
214
|
+
if get('GN').size > 0
|
215
|
+
names = fetch('GN').sub(/\.$/,'').split(/ AND /)
|
216
|
+
names.map! { |synonyms|
|
217
|
+
synonyms = synonyms.gsub(/\(|\)/,'').split(/ OR /).map { |e|
|
218
|
+
e.strip
|
219
|
+
}
|
220
|
+
}
|
221
|
+
end
|
222
|
+
@data['GN'] = names
|
223
|
+
end
|
224
|
+
private :gn_old_parser
|
225
|
+
|
226
|
+
# returns contents in the structured GN line.
|
227
|
+
# The new format of the GN line is:
|
228
|
+
# GN Name=; Synonyms=[, ...]; OrderedLocusNames=[, ...];
|
229
|
+
# GN ORFNames=[, ...];
|
230
|
+
#
|
231
|
+
# * Bio::SPTR#gn -> [ <gene record>* ]
|
232
|
+
# where <gene record> is:
|
233
|
+
# { :name => '...',
|
234
|
+
# :synonyms => [ 's1', 's2', ... ],
|
235
|
+
# :loci => [ 'l1', 'l2', ... ],
|
236
|
+
# :orfs => [ 'o1', 'o2', ... ]
|
237
|
+
# }
|
238
|
+
def gn_uniprot_parser
|
239
|
+
@data['GN'] = Array.new
|
240
|
+
gn_line = fetch('GN').strip
|
241
|
+
records = gn_line.split(/\s*and\s*/)
|
242
|
+
records.each do |record|
|
243
|
+
gene_hash = {:name => '', :synonyms => [], :loci => [], :orfs => []}
|
244
|
+
record.each_line(';') do |element|
|
245
|
+
case element
|
246
|
+
when /Name=/ then
|
247
|
+
gene_hash[:name] = $'[0..-2]
|
248
|
+
when /Synonyms=/ then
|
249
|
+
gene_hash[:synonyms] = $'[0..-2].split(/\s*,\s*/)
|
250
|
+
when /OrderedLocusNames=/ then
|
251
|
+
gene_hash[:loci] = $'[0..-2].split(/\s*,\s*/)
|
252
|
+
when /ORFNames=/ then
|
253
|
+
gene_hash[:orfs] = $'[0..-2].split(/\s*,\s*/)
|
254
|
+
end
|
255
|
+
end
|
256
|
+
@data['GN'] << gene_hash
|
257
|
+
end
|
258
|
+
return @data['GN']
|
259
|
+
end
|
260
|
+
private :gn_uniprot_parser
|
261
|
+
|
262
|
+
|
263
|
+
# returns a Array of gene names in the GN line.
|
264
|
+
def gene_names
|
265
|
+
gn # set @data['GN'] if it hasn't been already done
|
266
|
+
if @data['GN'].first.class == Hash then
|
267
|
+
@data['GN'].collect { |element| element[:name] }
|
268
|
+
else
|
269
|
+
@data['GN'].first
|
270
|
+
end
|
271
|
+
end
|
272
|
+
|
273
|
+
|
274
|
+
# returns a String of the first gene name in the GN line.
|
275
|
+
def gene_name
|
276
|
+
gene_names.first
|
277
|
+
end
|
278
|
+
|
279
|
+
|
280
|
+
# returns a Array of Hashs or a String of the OS line when a key given.
|
281
|
+
# * Bio::EMBLDB#os -> Array
|
282
|
+
# [{'name' => '(Human)', 'os' => 'Homo sapiens'},
|
283
|
+
# {'name' => '(Rat)', 'os' => 'Rattus norveticus'}]
|
284
|
+
# * Bio::EPTR#os[0] -> Hash
|
285
|
+
# {'name' => "(Human)", 'os' => 'Homo sapiens'}
|
286
|
+
# * Bio::SPTR#os[0]['name'] -> "(Human)"
|
287
|
+
# * Bio::EPTR#os(0) -> "Homo sapiens (Human)"
|
288
|
+
#
|
289
|
+
# === OS Line; organism species (>=1)
|
290
|
+
# OS Genus species (name).
|
291
|
+
# OS Genus species (name0) (name1).
|
292
|
+
# OS Genus species (name0) (name1).
|
293
|
+
# OS Genus species (name0), G s0 (name0), and G s (name0) (name1).
|
294
|
+
# OS Homo sapiens (Human), and Rarrus norveticus (Rat)
|
295
|
+
# OS Hippotis sp. Clark and Watts 825.
|
296
|
+
# OS unknown cyperaceous sp.
|
297
|
+
def os(num = nil)
|
298
|
+
unless @data['OS']
|
299
|
+
os = Array.new
|
300
|
+
fetch('OS').split(/, and|, /).each do |tmp|
|
301
|
+
if tmp =~ /(\w+ *[\w\d \:\'\+\-\.]+[\w\d\.])/
|
302
|
+
org = $1
|
303
|
+
tmp =~ /(\(.+\))/
|
304
|
+
os.push({'name' => $1, 'os' => org})
|
305
|
+
else
|
306
|
+
raise "Error: OS Line. #{$!}\n#{fetch('OS')}\n"
|
307
|
+
end
|
308
|
+
end
|
309
|
+
@data['OS'] = os
|
310
|
+
end
|
311
|
+
|
312
|
+
if num
|
313
|
+
# EX. "Trifolium repens (white clover)"
|
314
|
+
return "#{@data['OS'][num]['os']} #{@data['OS'][num]['name']}"
|
315
|
+
else
|
316
|
+
return @data['OS']
|
317
|
+
end
|
318
|
+
end
|
319
|
+
|
320
|
+
|
321
|
+
# Bio::EMBLDB::Common#og -> Array
|
322
|
+
# OG Line; organella (0 or 1/entry)
|
323
|
+
# ["MITOCHONDRION", "CHLOROPLAST", "Cyanelle", "Plasmid"]
|
324
|
+
# or a plasmid name (e.g. "Plasmid pBR322").
|
325
|
+
|
326
|
+
|
327
|
+
# Bio::EMBLDB::Common#oc -> Array
|
328
|
+
# OC Line; organism classification (>=1)
|
329
|
+
# "OC Eukaryota; Alveolata; Apicomplexa; Piroplasmida; Theileriidae;"
|
330
|
+
# "OC Theileria."
|
331
|
+
|
332
|
+
|
333
|
+
|
334
|
+
# returns a Hash of oraganism taxonomy cross-references.
|
335
|
+
# * Bio::SPTR#ox -> Hash
|
336
|
+
# {'NCBI_TaxID' => ['1234','2345','3456','4567'], ...}
|
337
|
+
#
|
338
|
+
# === OX Line; organism taxonomy cross-reference (>=1 per entry)
|
339
|
+
# OX NCBI_TaxID=1234;
|
340
|
+
# OX NCBI_TaxID=1234, 2345, 3456, 4567;
|
341
|
+
def ox
|
342
|
+
unless @data['OX']
|
343
|
+
tmp = fetch('OX').sub(/\.$/,'').split(/;/).map { |e| e.strip }
|
344
|
+
hsh = Hash.new
|
345
|
+
tmp.each do |e|
|
346
|
+
db,refs = e.split(/=/)
|
347
|
+
hsh[db] = refs.split(/, */)
|
348
|
+
end
|
349
|
+
@data['OX'] = hsh
|
350
|
+
end
|
351
|
+
return @data['OX']
|
352
|
+
end
|
353
|
+
|
354
|
+
# === The OH Line;
|
355
|
+
#
|
356
|
+
# OH NCBI_TaxID=TaxID; HostName.
|
357
|
+
# http://br.expasy.org/sprot/userman.html#OH_line
|
358
|
+
def oh
|
359
|
+
unless @data['OH']
|
360
|
+
@data['OH'] = fetch('OH').split("\. ").map {|x|
|
361
|
+
if x =~ /NCBI_TaxID=(\d+);/
|
362
|
+
taxid = $1
|
363
|
+
else
|
364
|
+
raise ArgumentError, ["Error: Invalid OH line format (#{self.entry_id}):",
|
365
|
+
$!, "\n", get('OH'), "\n"].join
|
366
|
+
|
367
|
+
end
|
368
|
+
if x =~ /NCBI_TaxID=\d+; (.+)/
|
369
|
+
host_name = $1
|
370
|
+
host_name.sub!(/\.$/, '')
|
371
|
+
else
|
372
|
+
host_name = nil
|
373
|
+
end
|
374
|
+
{'NCBI_TaxID' => taxid, 'HostName' => host_name}
|
375
|
+
}
|
376
|
+
end
|
377
|
+
@data['OH']
|
378
|
+
end
|
379
|
+
|
380
|
+
|
381
|
+
|
382
|
+
# Bio::EMBLDB::Common#ref -> Array
|
383
|
+
# R Lines
|
384
|
+
# RN RC RP RX RA RT RL
|
385
|
+
|
386
|
+
# returns contents in the R lines.
|
387
|
+
# * Bio::EMBLDB::Common#ref -> [ <refernece information Hash>* ]
|
388
|
+
# where <reference information Hash> is:
|
389
|
+
# {'RN' => '', 'RC' => '', 'RP' => '', 'RX' => '',
|
390
|
+
# 'RA' => '', 'RT' => '', 'RL' => '', 'RG' => ''}
|
391
|
+
#
|
392
|
+
# R Lines
|
393
|
+
# * RN RC RP RX RA RT RL RG
|
394
|
+
def ref
|
395
|
+
unless @data['R']
|
396
|
+
@data['R'] = [get('R').split(/\nRN /)].flatten.map { |str|
|
397
|
+
hash = {'RN' => '', 'RC' => '', 'RP' => '', 'RX' => '',
|
398
|
+
'RA' => '', 'RT' => '', 'RL' => '', 'RG' => ''}
|
399
|
+
str = 'RN ' + str unless /^RN / =~ str
|
400
|
+
|
401
|
+
str.split("\n").each do |line|
|
402
|
+
if /^(R[NPXARLCTG]) (.+)/ =~ line
|
403
|
+
hash[$1] += $2 + ' '
|
404
|
+
else
|
405
|
+
raise "Invalid format in R lines, \n[#{line}]\n"
|
406
|
+
end
|
407
|
+
end
|
408
|
+
|
409
|
+
hash['RN'] = set_RN(hash['RN'])
|
410
|
+
hash['RC'] = set_RC(hash['RC'])
|
411
|
+
hash['RP'] = set_RP(hash['RP'])
|
412
|
+
hash['RX'] = set_RX(hash['RX'])
|
413
|
+
hash['RA'] = set_RA(hash['RA'])
|
414
|
+
hash['RT'] = set_RT(hash['RT'])
|
415
|
+
hash['RL'] = set_RL(hash['RL'])
|
416
|
+
hash['RG'] = set_RG(hash['RG'])
|
417
|
+
|
418
|
+
hash
|
419
|
+
}
|
420
|
+
|
421
|
+
end
|
422
|
+
@data['R']
|
423
|
+
end
|
424
|
+
|
425
|
+
def set_RN(data)
|
426
|
+
data.strip
|
427
|
+
end
|
428
|
+
|
429
|
+
def set_RC(data)
|
430
|
+
data.scan(/([STP]\w+)=(.+);/).map { |comment|
|
431
|
+
[comment[1].split(/, and |, /)].flatten.map { |text|
|
432
|
+
{'Token' => comment[0], 'Text' => text}
|
433
|
+
}
|
434
|
+
}.flatten
|
435
|
+
end
|
436
|
+
private :set_RC
|
437
|
+
|
438
|
+
def set_RP(data)
|
439
|
+
data = data.strip
|
440
|
+
data = data.sub(/\.$/, '')
|
441
|
+
data.split(/, AND |, /i).map {|x|
|
442
|
+
x = x.strip
|
443
|
+
x = x.gsub(' ', ' ')
|
444
|
+
}
|
445
|
+
end
|
446
|
+
private :set_RP
|
447
|
+
|
448
|
+
def set_RX(data)
|
449
|
+
rx = {'MEDLINE' => nil, 'PubMed' => nil, 'DOI' => nil}
|
450
|
+
if data =~ /MEDLINE=(.+?);/
|
451
|
+
rx['MEDLINE'] = $1
|
452
|
+
end
|
453
|
+
if data =~ /PubMed=(.+?);/
|
454
|
+
rx['PubMed'] = $1
|
455
|
+
end
|
456
|
+
if data =~ /DOI=(.+?);/
|
457
|
+
rx['DOI'] = $1
|
458
|
+
end
|
459
|
+
rx
|
460
|
+
end
|
461
|
+
private :set_RX
|
462
|
+
|
463
|
+
def set_RA(data)
|
464
|
+
data = data.sub(/; *$/, '')
|
465
|
+
end
|
466
|
+
private :set_RA
|
467
|
+
|
468
|
+
def set_RT(data)
|
469
|
+
data = data.sub(/; *$/, '')
|
470
|
+
data = data.gsub(/(^"|"$)/, '')
|
471
|
+
end
|
472
|
+
private :set_RT
|
473
|
+
|
474
|
+
def set_RL(data)
|
475
|
+
data = data.strip
|
476
|
+
end
|
477
|
+
private :set_RL
|
478
|
+
|
479
|
+
def set_RG(data)
|
480
|
+
data = data.split('; ')
|
481
|
+
end
|
482
|
+
private :set_RG
|
483
|
+
|
484
|
+
|
485
|
+
|
486
|
+
# returns Bio::Reference object from Bio::EMBLDB::Common#ref.
|
487
|
+
# * Bio::EMBLDB::Common#ref -> Bio::References
|
488
|
+
def references
|
489
|
+
unless @data['references']
|
490
|
+
ary = self.ref.map {|ent|
|
491
|
+
hash = Hash.new('')
|
492
|
+
ent.each {|key, value|
|
493
|
+
case key
|
494
|
+
when 'RA'
|
495
|
+
hash['authors'] = value.split(/, /)
|
496
|
+
when 'RT'
|
497
|
+
hash['title'] = value
|
498
|
+
when 'RL'
|
499
|
+
if value =~ /(.*) (\d+) \((\d+)\), (\d+-\d+) \((\d+)\)$/
|
500
|
+
hash['journal'] = $1
|
501
|
+
hash['volume'] = $2
|
502
|
+
hash['issue'] = $3
|
503
|
+
hash['pages'] = $4
|
504
|
+
hash['year'] = $5
|
505
|
+
else
|
506
|
+
hash['journal'] = value
|
507
|
+
end
|
508
|
+
when 'RX' # PUBMED, MEDLINE, DOI
|
509
|
+
value.each do |tag, xref|
|
510
|
+
hash[ tag.downcase ] = xref
|
511
|
+
end
|
512
|
+
end
|
513
|
+
}
|
514
|
+
Reference.new(hash)
|
515
|
+
}
|
516
|
+
@data['references'] = References.new(ary)
|
517
|
+
end
|
518
|
+
@data['references']
|
519
|
+
end
|
520
|
+
|
521
|
+
|
522
|
+
|
523
|
+
|
524
|
+
|
525
|
+
|
526
|
+
# === The HI line
|
527
|
+
# Bio::SPTR#hi #=> hash
|
528
|
+
def hi
|
529
|
+
unless @data['HI']
|
530
|
+
@data['HI'] = []
|
531
|
+
fetch('HI').split(/\. /).each do |hlist|
|
532
|
+
hash = {'Category' => '', 'Keywords' => [], 'Keyword' => ''}
|
533
|
+
hash['Category'], hash['Keywords'] = hlist.split(': ')
|
534
|
+
hash['Keywords'] = hash['Keywords'].split('; ')
|
535
|
+
hash['Keyword'] = hash['Keywords'].pop
|
536
|
+
hash['Keyword'].sub!(/\.$/, '')
|
537
|
+
@data['HI'] << hash
|
538
|
+
end
|
539
|
+
end
|
540
|
+
@data['HI']
|
541
|
+
end
|
542
|
+
|
543
|
+
|
544
|
+
@@cc_topics = ['PHARMACEUTICAL',
|
545
|
+
'BIOTECHNOLOGY',
|
546
|
+
'TOXIC DOSE',
|
547
|
+
'ALLERGEN',
|
548
|
+
'RNA EDITING',
|
549
|
+
'POLYMORPHISM',
|
550
|
+
'BIOPHYSICOCHEMICAL PROPERTIES',
|
551
|
+
'MASS SPECTROMETRY',
|
552
|
+
'WEB RESOURCE',
|
553
|
+
'ENZYME REGULATION',
|
554
|
+
'DISEASE',
|
555
|
+
'INTERACTION',
|
556
|
+
'DEVELOPMENTAL STAGE',
|
557
|
+
'INDUCTION',
|
558
|
+
'CAUTION',
|
559
|
+
'ALTERNATIVE PRODUCTS',
|
560
|
+
'DOMAIN',
|
561
|
+
'PTM',
|
562
|
+
'MISCELLANEOUS',
|
563
|
+
'TISSUE SPECIFICITY',
|
564
|
+
'COFACTOR',
|
565
|
+
'PATHWAY',
|
566
|
+
'SUBUNIT',
|
567
|
+
'CATALYTIC ACTIVITY',
|
568
|
+
'SUBCELLULAR LOCATION',
|
569
|
+
'FUNCTION',
|
570
|
+
'SIMILARITY']
|
571
|
+
# returns contents in the CC lines.
|
572
|
+
# * Bio::SPTR#cc -> Hash
|
573
|
+
#
|
574
|
+
# returns an object of contents in the TOPIC.
|
575
|
+
# * Bio::SPTR#cc(TOPIC) -> Array w/in Hash, Hash
|
576
|
+
#
|
577
|
+
# returns contents of the "ALTERNATIVE PRODUCTS".
|
578
|
+
# * Bio::SPTR#cc('ALTERNATIVE PRODUCTS') -> Hash
|
579
|
+
# {'Event' => str,
|
580
|
+
# 'Named isoforms' => int,
|
581
|
+
# 'Comment' => str,
|
582
|
+
# 'Variants'=>[{'Name' => str, 'Synonyms' => str, 'IsoId' => str, 'Sequence' => []}]}
|
583
|
+
#
|
584
|
+
# CC -!- ALTERNATIVE PRODUCTS:
|
585
|
+
# CC Event=Alternative splicing; Named isoforms=15;
|
586
|
+
# ...
|
587
|
+
# CC placentae isoforms. All tissues differentially splice exon 13;
|
588
|
+
# CC Name=A; Synonyms=no del;
|
589
|
+
# CC IsoId=P15529-1; Sequence=Displayed;
|
590
|
+
#
|
591
|
+
# returns contents of the "DATABASE".
|
592
|
+
# * Bio::SPTR#cc('DATABASE') -> Array
|
593
|
+
# [{'NAME'=>str,'NOTE'=>str, 'WWW'=>URI,'FTP'=>URI}, ...]
|
594
|
+
#
|
595
|
+
# CC -!- DATABASE: NAME=Text[; NOTE=Text][; WWW="Address"][; FTP="Address"].
|
596
|
+
#
|
597
|
+
# returns contents of the "MASS SPECTROMETRY".
|
598
|
+
# * Bio::SPTR#cc('MASS SPECTROMETRY') -> Array
|
599
|
+
# [{'MW"=>float,'MW_ERR'=>float, 'METHOD'=>str,'RANGE'=>str}, ...]
|
600
|
+
#
|
601
|
+
# CC -!- MASS SPECTROMETRY: MW=XXX[; MW_ERR=XX][; METHOD=XX][;RANGE=XX-XX].
|
602
|
+
#
|
603
|
+
# === CC lines (>=0, optional)
|
604
|
+
# CC -!- TISSUE SPECIFICITY: HIGHEST LEVELS FOUND IN TESTIS. ALSO PRESENT
|
605
|
+
# CC IN LIVER, KIDNEY, LUNG AND BRAIN.
|
606
|
+
#
|
607
|
+
# CC -!- TOPIC: FIRST LINE OF A COMMENT BLOCK;
|
608
|
+
# CC SECOND AND SUBSEQUENT LINES OF A COMMENT BLOCK.
|
609
|
+
#
|
610
|
+
# See also http://www.expasy.org/sprot/userman.html#CC_line
|
611
|
+
#
|
612
|
+
def cc(topic = nil)
|
613
|
+
unless @data['CC']
|
614
|
+
cc = Hash.new
|
615
|
+
comment_border= '-' * (77 - 4 + 1)
|
616
|
+
dlm = /-!- /
|
617
|
+
|
618
|
+
# 12KD_MYCSM has no CC lines.
|
619
|
+
return cc if get('CC').size == 0
|
620
|
+
|
621
|
+
cc_raw = fetch('CC')
|
622
|
+
|
623
|
+
# Removing the copyright statement.
|
624
|
+
cc_raw.sub!(/ *---.+---/m, '')
|
625
|
+
|
626
|
+
# Not any CC Lines without the copyright statement.
|
627
|
+
return cc if cc_raw == ''
|
628
|
+
|
629
|
+
begin
|
630
|
+
cc_raw, copyright = cc_raw.split(/#{comment_border}/)[0]
|
631
|
+
cc_raw = cc_raw.sub(dlm,'')
|
632
|
+
cc_raw.split(dlm).each do |tmp|
|
633
|
+
tmp = tmp.strip
|
634
|
+
|
635
|
+
if /(^[A-Z ]+[A-Z]): (.+)/ =~ tmp
|
636
|
+
key = $1
|
637
|
+
body = $2
|
638
|
+
body.gsub!(/- (?!AND)/,'-')
|
639
|
+
body.strip!
|
640
|
+
unless cc[key]
|
641
|
+
cc[key] = [body]
|
642
|
+
else
|
643
|
+
cc[key].push(body)
|
644
|
+
end
|
645
|
+
else
|
646
|
+
raise ["Error: [#{entry_id}]: CC Lines", '"', tmp, '"',
|
647
|
+
'', get('CC'),''].join("\n")
|
648
|
+
end
|
649
|
+
end
|
650
|
+
rescue NameError
|
651
|
+
if fetch('CC') == ''
|
652
|
+
return {}
|
653
|
+
else
|
654
|
+
raise ["Error: Invalid CC Lines: [#{entry_id}]: ",
|
655
|
+
"\n'#{self.get('CC')}'\n", "(#{$!})"].join
|
656
|
+
end
|
657
|
+
rescue NoMethodError
|
658
|
+
end
|
659
|
+
|
660
|
+
@data['CC'] = cc
|
661
|
+
end
|
662
|
+
|
663
|
+
|
664
|
+
case topic
|
665
|
+
when 'ALLERGEN'
|
666
|
+
return @data['CC'][topic]
|
667
|
+
when 'ALTERNATIVE PRODUCTS'
|
668
|
+
return cc_alternative_products(@data['CC'][topic])
|
669
|
+
when 'BIOPHYSICOCHEMICAL PROPERTIES'
|
670
|
+
return cc_biophysiochemical_properties(@data['CC'][topic])
|
671
|
+
when 'BIOTECHNOLOGY'
|
672
|
+
return @data['CC'][topic]
|
673
|
+
when 'CATALITIC ACTIVITY'
|
674
|
+
return cc_catalytic_activity(@data['CC'][topic])
|
675
|
+
when 'CAUTION'
|
676
|
+
return cc_caution(@data['CC'][topic])
|
677
|
+
when 'COFACTOR'
|
678
|
+
return @data['CC'][topic]
|
679
|
+
when 'DEVELOPMENTAL STAGE'
|
680
|
+
return @data['CC'][topic].join('')
|
681
|
+
when 'DISEASE'
|
682
|
+
return @data['CC'][topic].join('')
|
683
|
+
when 'DOMAIN'
|
684
|
+
return @data['CC'][topic]
|
685
|
+
when 'ENZYME REGULATION'
|
686
|
+
return @data['CC'][topic].join('')
|
687
|
+
when 'FUNCTION'
|
688
|
+
return @data['CC'][topic].join('')
|
689
|
+
when 'INDUCTION'
|
690
|
+
return @data['CC'][topic].join('')
|
691
|
+
when 'INTERACTION'
|
692
|
+
return cc_interaction(@data['CC'][topic])
|
693
|
+
when 'MASS SPECTROMETRY'
|
694
|
+
return cc_mass_spectrometry(@data['CC'][topic])
|
695
|
+
when 'MISCELLANEOUS'
|
696
|
+
return @data['CC'][topic]
|
697
|
+
when 'PATHWAY'
|
698
|
+
return cc_pathway(@data['CC'][topic])
|
699
|
+
when 'PHARMACEUTICAL'
|
700
|
+
return @data['CC'][topic]
|
701
|
+
when 'POLYMORPHISM'
|
702
|
+
return @data['CC'][topic]
|
703
|
+
when 'PTM'
|
704
|
+
return @data['CC'][topic]
|
705
|
+
when 'RNA EDITING'
|
706
|
+
return cc_rna_editing(@data['CC'][topic])
|
707
|
+
when 'SIMILARITY'
|
708
|
+
return @data['CC'][topic]
|
709
|
+
when 'SUBCELLULAR LOCATION'
|
710
|
+
return cc_subcellular_location(@data['CC'][topic])
|
711
|
+
when 'SUBUNIT'
|
712
|
+
return @data['CC'][topic]
|
713
|
+
when 'TISSUE SPECIFICITY'
|
714
|
+
return @data['CC'][topic]
|
715
|
+
when 'TOXIC DOSE'
|
716
|
+
return @data['CC'][topic]
|
717
|
+
when 'WEB RESOURCE'
|
718
|
+
return cc_web_resource(@data['CC'][topic])
|
719
|
+
when 'DATABASE'
|
720
|
+
# DATABASE: NAME=Text[; NOTE=Text][; WWW="Address"][; FTP="Address"].
|
721
|
+
tmp = Array.new
|
722
|
+
db = @data['CC']['DATABASE']
|
723
|
+
return db unless db
|
724
|
+
|
725
|
+
db.each do |e|
|
726
|
+
db = {'NAME' => nil, 'NOTE' => nil, 'WWW' => nil, 'FTP' => nil}
|
727
|
+
e.sub(/.$/,'').split(/;/).each do |line|
|
728
|
+
case line
|
729
|
+
when /NAME=(.+)/
|
730
|
+
db['NAME'] = $1
|
731
|
+
when /NOTE=(.+)/
|
732
|
+
db['NOTE'] = $1
|
733
|
+
when /WWW="(.+)"/
|
734
|
+
db['WWW'] = $1
|
735
|
+
when /FTP="(.+)"/
|
736
|
+
db['FTP'] = $1
|
737
|
+
end
|
738
|
+
end
|
739
|
+
tmp.push(db)
|
740
|
+
end
|
741
|
+
return tmp
|
742
|
+
when nil
|
743
|
+
return @data['CC']
|
744
|
+
else
|
745
|
+
return @data['CC'][topic]
|
746
|
+
end
|
747
|
+
end
|
748
|
+
|
749
|
+
|
750
|
+
def cc_alternative_products(data)
|
751
|
+
ap = data.join('')
|
752
|
+
return ap unless ap
|
753
|
+
|
754
|
+
# Event, Named isoforms, Comment, [Name, Synonyms, IsoId, Sequnce]+
|
755
|
+
tmp = {'Event' => "", 'Named isoforms' => "", 'Comment' => "",
|
756
|
+
'Variants' => []}
|
757
|
+
if /Event=(.+?);/ =~ ap
|
758
|
+
tmp['Event'] = $1
|
759
|
+
tmp['Event'] = tmp['Event'].sub(/;/,'').split(/, /)
|
760
|
+
end
|
761
|
+
if /Named isoforms=(\S+?);/ =~ ap
|
762
|
+
tmp['Named isoforms'] = $1
|
763
|
+
end
|
764
|
+
if /Comment=(.+?);/m =~ ap
|
765
|
+
tmp['Comment'] = $1
|
766
|
+
end
|
767
|
+
ap.scan(/Name=.+?Sequence=.+?;/).each do |ent|
|
768
|
+
tmp['Variants'] << cc_alternative_products_variants(ent)
|
769
|
+
end
|
770
|
+
return tmp
|
771
|
+
end
|
772
|
+
private :cc_alternative_products
|
773
|
+
|
774
|
+
def cc_alternative_products_variants(data)
|
775
|
+
variant = {'Name' => '', 'Synonyms' => [], 'IsoId' => [], 'Sequence' => []}
|
776
|
+
data.split(/; /).map {|x| x.split(/=/) }.each do |e|
|
777
|
+
case e[0]
|
778
|
+
when 'Sequence', 'Synonyms', 'IsoId'
|
779
|
+
e[1] = e[1].sub(/;/,'').split(/, /)
|
780
|
+
end
|
781
|
+
variant[e[0]] = e[1]
|
782
|
+
end
|
783
|
+
variant
|
784
|
+
end
|
785
|
+
private :cc_alternative_products_variants
|
786
|
+
|
787
|
+
|
788
|
+
def cc_biophysiochemical_properties(data)
|
789
|
+
data = data[0]
|
790
|
+
|
791
|
+
hash = {'Absorption' => {},
|
792
|
+
'Kinetic parameters' => {},
|
793
|
+
'pH dependence' => "",
|
794
|
+
'Redox potential' => "",
|
795
|
+
'Temperature dependence' => ""}
|
796
|
+
if data =~ /Absorption: Abs\(max\)=(.+?);/
|
797
|
+
hash['Absorption']['Abs(max)'] = $1
|
798
|
+
end
|
799
|
+
if data =~ /Absorption: Abs\(max\)=.+; Note=(.+?);/
|
800
|
+
hash['Absorption']['Note'] = $1
|
801
|
+
end
|
802
|
+
if data =~ /Kinetic parameters: KM=(.+?); Vmax=(.+?);/
|
803
|
+
hash['Kinetic parameters']['KM'] = $1
|
804
|
+
hash['Kinetic parameters']['Vmax'] = $2
|
805
|
+
end
|
806
|
+
if data =~ /Kinetic parameters: KM=.+; Vmax=.+; Note=(.+?);/
|
807
|
+
hash['Kinetic parameters']['Note'] = $1
|
808
|
+
end
|
809
|
+
if data =~ /pH dependence: (.+?);/
|
810
|
+
hash['pH dependence'] = $1
|
811
|
+
end
|
812
|
+
if data =~ /Redox potential: (.+?);/
|
813
|
+
hash['Redox potential'] = $1
|
814
|
+
end
|
815
|
+
if data =~ /Temperature dependence: (.+?);/
|
816
|
+
hash['Temperature dependence'] = $1
|
817
|
+
end
|
818
|
+
hash
|
819
|
+
end
|
820
|
+
private :cc_biophysiochemical_properties
|
821
|
+
|
822
|
+
|
823
|
+
def cc_caution(data)
|
824
|
+
data.join('')
|
825
|
+
end
|
826
|
+
private :cc_caution
|
827
|
+
|
828
|
+
|
829
|
+
# returns conteins in a line of the CC INTERACTION section.
|
830
|
+
#
|
831
|
+
# CC P46527:CDKN1B; NbExp=1; IntAct=EBI-359815, EBI-519280;
|
832
|
+
def cc_interaction(data)
|
833
|
+
str = data.join('')
|
834
|
+
it = str.scan(/(.+?); NbExp=(.+?); IntAct=(.+?);/)
|
835
|
+
it.map {|ent|
|
836
|
+
ent.map! {|x| x.strip }
|
837
|
+
if ent[0] =~ /^(.+):(.+)/
|
838
|
+
spac = $1
|
839
|
+
spid = $2.split(' ')[0]
|
840
|
+
optid = nil
|
841
|
+
elsif ent[0] =~ /Self/
|
842
|
+
spac = self.entry_id
|
843
|
+
spid = self.entry_id
|
844
|
+
optid = nil
|
845
|
+
end
|
846
|
+
if ent[0] =~ /^.+:.+ (.+)/
|
847
|
+
optid = $1
|
848
|
+
end
|
849
|
+
|
850
|
+
{'SP_Ac' => spac,
|
851
|
+
'identifier' => spid,
|
852
|
+
'NbExp' => ent[1],
|
853
|
+
'IntAct' => ent[2].split(', '),
|
854
|
+
'optional_identifier' => optid}
|
855
|
+
}
|
856
|
+
end
|
857
|
+
private :cc_interaction
|
858
|
+
|
859
|
+
|
860
|
+
def cc_mass_spectrometry(data)
|
861
|
+
# MASS SPECTROMETRY: MW=XXX[; MW_ERR=XX][; METHOD=XX][;RANGE=XX-XX].
|
862
|
+
return data unless data
|
863
|
+
|
864
|
+
data.map { |m|
|
865
|
+
mass = {'MW' => nil, 'MW_ERR' => nil, 'METHOD' => nil, 'RANGE' => nil,
|
866
|
+
'NOTE' => nil}
|
867
|
+
m.sub(/.$/,'').split(/;/).each do |line|
|
868
|
+
case line
|
869
|
+
when /MW=(.+)/
|
870
|
+
mass['MW'] = $1
|
871
|
+
when /MW_ERR=(.+)/
|
872
|
+
mass['MW_ERR'] = $1
|
873
|
+
when /METHOD=(.+)/
|
874
|
+
mass['METHOD'] = $1
|
875
|
+
when /RANGE=(\d+-\d+)/
|
876
|
+
mass['RANGE'] = $1 # RANGE class ?
|
877
|
+
when /NOTE=(.+)/
|
878
|
+
mass['NOTE'] = $1
|
879
|
+
end
|
880
|
+
end
|
881
|
+
mass
|
882
|
+
}
|
883
|
+
end
|
884
|
+
private :cc_mass_spectrometry
|
885
|
+
|
886
|
+
|
887
|
+
def cc_pathway(data)
|
888
|
+
data.map {|x| x.sub(/\.$/, '') }.map {|x|
|
889
|
+
x.split(/; | and |: /)
|
890
|
+
}[0]
|
891
|
+
end
|
892
|
+
private :cc_pathway
|
893
|
+
|
894
|
+
|
895
|
+
def cc_rna_editing(data)
|
896
|
+
data = data.join('')
|
897
|
+
entry = {'Modified_positions' => [], 'Note' => ""}
|
898
|
+
if data =~ /Modified_positions=(.+?)(\.|;)/
|
899
|
+
entry['Modified_positions'] = $1.sub(/\.$/, '').split(', ')
|
900
|
+
else
|
901
|
+
raise ArgumentError, "Invarid CC RNA Editing lines (#{self.entry_id}):#{$!}\n#{get('CC')}"
|
902
|
+
end
|
903
|
+
if data =~ /Note=(.+)/
|
904
|
+
entry['Note'] = $1
|
905
|
+
end
|
906
|
+
entry
|
907
|
+
end
|
908
|
+
private :cc_rna_editing
|
909
|
+
|
910
|
+
|
911
|
+
def cc_subcellular_location(data)
|
912
|
+
data.map {|x|
|
913
|
+
x.split('. ').map {|y|
|
914
|
+
y.split('; ').map {|z|
|
915
|
+
z.sub(/\.$/, '')
|
916
|
+
}
|
917
|
+
}
|
918
|
+
}[0]
|
919
|
+
end
|
920
|
+
private :cc_subcellular_location
|
921
|
+
|
922
|
+
|
923
|
+
# CC -!- WEB RESOURCE: NAME=ResourceName[; NOTE=FreeText][; URL=WWWAddress].
|
924
|
+
def cc_web_resource(data)
|
925
|
+
data.map {|x|
|
926
|
+
entry = {'NAME' => nil, 'NOTE' => nil, 'URL' => nil}
|
927
|
+
x.split(';').each do |y|
|
928
|
+
case y
|
929
|
+
when /NAME=(.+)/
|
930
|
+
entry['NAME'] = $1.strip
|
931
|
+
when /NOTE=(.+)/
|
932
|
+
entry['NOTE'] = $1.strip
|
933
|
+
when /URL="(.+)"/
|
934
|
+
entry['URL'] = $1.strip
|
935
|
+
end
|
936
|
+
end
|
937
|
+
entry
|
938
|
+
}
|
939
|
+
end
|
940
|
+
|
941
|
+
|
942
|
+
# returns databases cross-references in the DR lines.
|
943
|
+
# * Bio::SPTR#dr -> Hash w/in Array
|
944
|
+
#
|
945
|
+
# === DR Line; defabases cross-reference (>=0)
|
946
|
+
# DR database_identifier; primary_identifier; secondary_identifier.
|
947
|
+
# a cross_ref pre one line
|
948
|
+
@@dr_database_identifier = ['EMBL','CARBBANK','DICTYDB','ECO2DBASE',
|
949
|
+
'ECOGENE',
|
950
|
+
'FLYBASE','GCRDB','HIV','HSC-2DPAGE','HSSP','INTERPRO','MAIZEDB',
|
951
|
+
'MAIZE-2DPAGE','MENDEL','MGD''MIM','PDB','PFAM','PIR','PRINTS',
|
952
|
+
'PROSITE','REBASE','AARHUS/GHENT-2DPAGE','SGD','STYGENE','SUBTILIST',
|
953
|
+
'SWISS-2DPAGE','TIGR','TRANSFAC','TUBERCULIST','WORMPEP','YEPD','ZFIN']
|
954
|
+
|
955
|
+
# Backup Bio::EMBLDB#dr as embl_dr
|
956
|
+
alias :embl_dr :dr
|
957
|
+
|
958
|
+
# Bio::SPTR#dr
|
959
|
+
def dr(key = nil)
|
960
|
+
unless key
|
961
|
+
embl_dr
|
962
|
+
else
|
963
|
+
(embl_dr[key] or []).map {|x|
|
964
|
+
{'Accession' => x[0],
|
965
|
+
'Version' => x[1],
|
966
|
+
' ' => x[2],
|
967
|
+
'Molecular Type' => x[3]}
|
968
|
+
}
|
969
|
+
end
|
970
|
+
end
|
971
|
+
|
972
|
+
|
973
|
+
# Bio::EMBLDB::Common#kw - Array
|
974
|
+
# #keywords -> Array
|
975
|
+
#
|
976
|
+
# KW Line; keyword (>=1)
|
977
|
+
# KW [Keyword;]+
|
978
|
+
|
979
|
+
|
980
|
+
# returns contents in the feature table.
|
981
|
+
#
|
982
|
+
# == Examples
|
983
|
+
#
|
984
|
+
# sp = Bio::SPTR.new(entry)
|
985
|
+
# ft = sp.ft
|
986
|
+
# ft.class #=> Hash
|
987
|
+
# ft.keys.each do |feature_key|
|
988
|
+
# ft[feature_key].each do |feature|
|
989
|
+
# feature['From'] #=> '1'
|
990
|
+
# feature['To'] #=> '21'
|
991
|
+
# feature['Description'] #=> ''
|
992
|
+
# feature['FTId'] #=> ''
|
993
|
+
# feature['diff'] #=> []
|
994
|
+
# feature['original'] #=> [feature_key, '1', '21', '', '']
|
995
|
+
# end
|
996
|
+
# end
|
997
|
+
#
|
998
|
+
# * Bio::SPTR#ft -> Hash
|
999
|
+
# {FEATURE_KEY => [{'From' => int, 'To' => int,
|
1000
|
+
# 'Description' => aStr, 'FTId' => aStr,
|
1001
|
+
# 'diff' => [original_residues, changed_residues],
|
1002
|
+
# 'original' => aAry }],...}
|
1003
|
+
#
|
1004
|
+
# returns an Array of the information about the feature_name in the feature table.
|
1005
|
+
# * Bio::SPTR#ft(feature_name) -> Array of Hash
|
1006
|
+
# [{'From' => str, 'To' => str, 'Description' => str, 'FTId' => str},...]
|
1007
|
+
#
|
1008
|
+
# == FT Line; feature table data (>=0, optional)
|
1009
|
+
#
|
1010
|
+
# Col Data item
|
1011
|
+
# ----- -----------------
|
1012
|
+
# 1- 2 FT
|
1013
|
+
# 6-13 Feature name
|
1014
|
+
# 15-20 `FROM' endpoint
|
1015
|
+
# 22-27 `TO' endpoint
|
1016
|
+
# 35-75 Description (>=0 per key)
|
1017
|
+
# ----- -----------------
|
1018
|
+
#
|
1019
|
+
# Note: 'FROM' and 'TO' endopoints are allowed to use non-numerial charactors
|
1020
|
+
# including '<', '>' or '?'. (c.f. '<1', '?42')
|
1021
|
+
#
|
1022
|
+
# See also http://www.expasy.org/sprot/userman.html#FT_line
|
1023
|
+
#
|
1024
|
+
def ft(feature_key = nil)
|
1025
|
+
return ft[feature_key] if feature_key
|
1026
|
+
return @data['FT'] if @data['FT']
|
1027
|
+
|
1028
|
+
table = []
|
1029
|
+
begin
|
1030
|
+
get('FT').split("\n").each do |line|
|
1031
|
+
if line =~ /^FT \w/
|
1032
|
+
feature = line.chomp.ljust(74)
|
1033
|
+
table << [feature[ 5..12].strip, # Feature Name
|
1034
|
+
feature[14..19].strip, # From
|
1035
|
+
feature[21..26].strip, # To
|
1036
|
+
feature[34..74].strip ] # Description
|
1037
|
+
else
|
1038
|
+
table.last << line.chomp.sub!(/^FT +/, '')
|
1039
|
+
end
|
1040
|
+
end
|
1041
|
+
|
1042
|
+
# Joining Description lines
|
1043
|
+
table = table.map { |feature|
|
1044
|
+
ftid = feature.pop if feature.last =~ /FTId=/
|
1045
|
+
if feature.size > 4
|
1046
|
+
feature = [feature[0],
|
1047
|
+
feature[1],
|
1048
|
+
feature[2],
|
1049
|
+
feature[3, feature.size - 3].join(" ")]
|
1050
|
+
end
|
1051
|
+
feature << if ftid then ftid else '' end
|
1052
|
+
}
|
1053
|
+
|
1054
|
+
hash = {}
|
1055
|
+
table.each do |feature|
|
1056
|
+
hash[feature[0]] = [] unless hash[feature[0]]
|
1057
|
+
hash[feature[0]] << {
|
1058
|
+
# Removing '<', '>' or '?' in FROM/TO endopoint.
|
1059
|
+
'From' => feature[1].sub(/\D/, '').to_i,
|
1060
|
+
'To' => feature[2].sub(/\D/, '').to_i,
|
1061
|
+
'Description' => feature[3],
|
1062
|
+
'FTId' => feature[4].to_s.sub(/\/FTId=/, '').sub(/\.$/, ''),
|
1063
|
+
'diff' => [],
|
1064
|
+
'original' => feature
|
1065
|
+
}
|
1066
|
+
|
1067
|
+
case feature[0]
|
1068
|
+
when 'VARSPLIC', 'VARIANT', 'VAR_SEQ', 'CONFLICT'
|
1069
|
+
case hash[feature[0]].last['Description']
|
1070
|
+
when /(\w[\w ]*\w*) - ?> (\w[\w ]*\w*)/
|
1071
|
+
original_res = $1
|
1072
|
+
changed_res = $2
|
1073
|
+
original_res = original_res.gsub(/ /,'').strip
|
1074
|
+
chenged_res = changed_res.gsub(/ /,'').strip
|
1075
|
+
when /Missing/i
|
1076
|
+
original_res = seq.subseq(hash[feature[0]].last['From'],
|
1077
|
+
hash[feature[0]].last['To'])
|
1078
|
+
changed_res = ''
|
1079
|
+
end
|
1080
|
+
hash[feature[0]].last['diff'] = [original_res, chenged_res]
|
1081
|
+
end
|
1082
|
+
end
|
1083
|
+
rescue
|
1084
|
+
raise "Invalid FT Lines(#{$!}) in #{entry_id}:, \n'#{self.get('FT')}'\n"
|
1085
|
+
end
|
1086
|
+
|
1087
|
+
@data['FT'] = hash
|
1088
|
+
end
|
1089
|
+
|
1090
|
+
|
1091
|
+
|
1092
|
+
# returns a Hash of conteins in the SQ lines.
|
1093
|
+
# * Bio::SPTRL#sq -> hsh
|
1094
|
+
#
|
1095
|
+
# returns a value of a key given in the SQ lines.
|
1096
|
+
# * Bio::SPTRL#sq(key) -> int or str
|
1097
|
+
# * Keys: ['MW', 'mw', 'molecular', 'weight', 'aalen', 'len', 'length',
|
1098
|
+
# 'CRC64']
|
1099
|
+
#
|
1100
|
+
# === SQ Line; sequence header (1/entry)
|
1101
|
+
# SQ SEQUENCE 233 AA; 25630 MW; 146A1B48A1475C86 CRC64;
|
1102
|
+
# SQ SEQUENCE \d+ AA; \d+ MW; [0-9A-Z]+ CRC64;
|
1103
|
+
#
|
1104
|
+
# MW, Dalton unit.
|
1105
|
+
# CRC64 (64-bit Cyclic Redundancy Check, ISO 3309).
|
1106
|
+
def sq(key = nil)
|
1107
|
+
unless @data['SQ']
|
1108
|
+
if fetch('SQ') =~ /(\d+) AA\; (\d+) MW; (.+) CRC64;/
|
1109
|
+
@data['SQ'] = { 'aalen' => $1.to_i, 'MW' => $2.to_i, 'CRC64' => $3 }
|
1110
|
+
else
|
1111
|
+
raise "Invalid SQ Line: \n'#{fetch('SQ')}'"
|
1112
|
+
end
|
1113
|
+
end
|
1114
|
+
|
1115
|
+
if key
|
1116
|
+
case key
|
1117
|
+
when /mw/, /molecular/, /weight/
|
1118
|
+
@data['SQ']['MW']
|
1119
|
+
when /len/, /length/, /AA/
|
1120
|
+
@data['SQ']['aalen']
|
1121
|
+
else
|
1122
|
+
@data['SQ'][key]
|
1123
|
+
end
|
1124
|
+
else
|
1125
|
+
@data['SQ']
|
1126
|
+
end
|
1127
|
+
end
|
1128
|
+
|
1129
|
+
|
1130
|
+
# returns a Bio::Sequence::AA of the amino acid sequence.
|
1131
|
+
# * Bio::SPTR#seq -> Bio::Sequence::AA
|
1132
|
+
#
|
1133
|
+
# blank Line; sequence data (>=1)
|
1134
|
+
def seq
|
1135
|
+
unless @data['']
|
1136
|
+
@data[''] = Sequence::AA.new( fetch('').gsub(/ |\d+/,'') )
|
1137
|
+
end
|
1138
|
+
return @data['']
|
1139
|
+
end
|
1140
|
+
alias aaseq seq
|
1141
|
+
|
1142
|
+
end # class SPTR
|
1143
|
+
|
1144
|
+
end # module Bio
|
1145
|
+
|
1146
|
+
|
1147
|
+
|
1148
|
+
=begin
|
1149
|
+
|
1150
|
+
= Bio::SPTR < Bio::DB
|
1151
|
+
|
1152
|
+
Class for a entry in the SWISS-PROT/TrEMBL database.
|
1153
|
+
|
1154
|
+
* ((<URL:http://www.ebi.ac.uk/swissprot/>))
|
1155
|
+
* ((<URL:http://www.ebi.ac.uk/trembl/>))
|
1156
|
+
* ((<URL:http://www.ebi.ac.uk/sprot/userman.html>))
|
1157
|
+
|
1158
|
+
|
1159
|
+
--- Bio::SPTR.new(a_sp_entry)
|
1160
|
+
|
1161
|
+
=== ID line (Identification)
|
1162
|
+
|
1163
|
+
--- Bio::SPTR#id_line -> {'ENTRY_NAME' => str, 'DATA_CLASS' => str,
|
1164
|
+
'MOLECULE_TYPE' => str, 'SEQUENCE_LENGTH' => int }
|
1165
|
+
--- Bio::SPTR#id_line(key) -> str
|
1166
|
+
|
1167
|
+
key = (ENTRY_NAME|MOLECULE_TYPE|DATA_CLASS|SEQUENCE_LENGTH)
|
1168
|
+
|
1169
|
+
--- Bio::SPTR#entry_id -> str
|
1170
|
+
--- Bio::SPTR#molecule -> str
|
1171
|
+
--- Bio::SPTR#sequence_length -> int
|
1172
|
+
|
1173
|
+
|
1174
|
+
=== AC lines (Accession number)
|
1175
|
+
|
1176
|
+
--- Bio::SPTR#ac -> ary
|
1177
|
+
--- Bio::SPTR#accessions -> ary
|
1178
|
+
--- Bio::SPTR#accession -> accessions.first
|
1179
|
+
|
1180
|
+
|
1181
|
+
=== GN line (Gene name(s))
|
1182
|
+
|
1183
|
+
--- Bio::SPTR#gn -> [ary, ...] or [{:name => str, :synonyms => [], :loci => [], :orfs => []}]
|
1184
|
+
--- Bio::SPTR#gene_name -> str
|
1185
|
+
--- Bio::SPTR#gene_names -> [str] or [str]
|
1186
|
+
|
1187
|
+
|
1188
|
+
=== DT lines (Date)
|
1189
|
+
|
1190
|
+
--- Bio::SPTR#dt -> {'created' => str, 'sequence' => str, 'annotation' => str}
|
1191
|
+
--- Bio::SPTR#dt(key) -> str
|
1192
|
+
|
1193
|
+
key := (created|annotation|sequence)
|
1194
|
+
|
1195
|
+
|
1196
|
+
=== DE lines (Description)
|
1197
|
+
|
1198
|
+
--- Bio::SPTR#de -> str
|
1199
|
+
#definition -> str
|
1200
|
+
|
1201
|
+
--- Bio::SPTR#protein_name
|
1202
|
+
|
1203
|
+
Returns the proposed official name of the protein
|
1204
|
+
|
1205
|
+
|
1206
|
+
--- Bio::SPTR#synonyms
|
1207
|
+
|
1208
|
+
Returns an array of synonyms (unofficial names)
|
1209
|
+
|
1210
|
+
=== KW lines (Keyword)
|
1211
|
+
|
1212
|
+
--- Bio::SPTR#kw -> ary
|
1213
|
+
|
1214
|
+
=== OS lines (Organism species)
|
1215
|
+
|
1216
|
+
--- Bio::SPTR#os -> [{'name' => str, 'os' => str}, ...]
|
1217
|
+
|
1218
|
+
=== OC lines (organism classification)
|
1219
|
+
|
1220
|
+
--- Bio::SPTR#oc -> ary
|
1221
|
+
|
1222
|
+
=== OG line (Organella)
|
1223
|
+
|
1224
|
+
--- Bio::SPTR#og -> ary
|
1225
|
+
|
1226
|
+
=== OX line (Organism taxonomy cross-reference)
|
1227
|
+
|
1228
|
+
--- Bio::SPTR#ox -> {'NCBI_TaxID' => [], ...}
|
1229
|
+
|
1230
|
+
=== RN RC RP RX RA RT RL RG lines (Reference)
|
1231
|
+
|
1232
|
+
--- Bio::SPTR#ref -> [{'RN' => int, 'RP' => str, 'RC' => str, 'RX' => str, ''RT' => str, 'RL' => str, 'RA' => str, 'RC' => str, 'RG' => str},...]
|
1233
|
+
|
1234
|
+
=== DR lines (Database cross-reference)
|
1235
|
+
|
1236
|
+
--- Bio::SPTR#dr -> {'EMBL' => ary, ...}
|
1237
|
+
|
1238
|
+
=== FT lines (Feature table data)
|
1239
|
+
|
1240
|
+
--- Bio::SPTR#ft -> hsh
|
1241
|
+
|
1242
|
+
=== SQ lines (Sequence header and data)
|
1243
|
+
|
1244
|
+
--- Bio::SPTR#sq -> {'CRC64' => str, 'MW' => int, 'aalen' => int}
|
1245
|
+
--- Bio::SPTR#sq(key) -> int or str
|
1246
|
+
|
1247
|
+
key := (aalen|MW|CRC64)
|
1248
|
+
|
1249
|
+
--- Bio::EMBL#seq -> Bio::Sequece::AA
|
1250
|
+
#aaseq -> Bio::Sequece::AA
|
1251
|
+
|
1252
|
+
=end
|
1253
|
+
|
1254
|
+
# Content Occurrence in an entry
|
1255
|
+
# ---- --------------------------- --------------------------------
|
1256
|
+
# ID - identification (begins each entry; 1 per entry)
|
1257
|
+
# AC - accession number(s) (>=1 per entry)
|
1258
|
+
# DT - date (3 per entry)
|
1259
|
+
# DE - description (>=1 per entry)
|
1260
|
+
# GN - gene name(s) (>=0 per entry; optional)
|
1261
|
+
# OS - organism species (>=1 per entry)
|
1262
|
+
# OG - organelle (0 or 1 per entry; optional)
|
1263
|
+
# OC - organism classification (>=1 per entry)
|
1264
|
+
# OX - organism taxonomy x-ref (>=1 per entry)
|
1265
|
+
# OH - Organism Host
|
1266
|
+
# RN - reference number (>=1 per entry)
|
1267
|
+
# RP - reference positions (>=1 per entry)
|
1268
|
+
# RC - reference comment(s) (>=0 per entry; optional)
|
1269
|
+
# RX - reference cross-reference(s) (>=0 per entry; optional)
|
1270
|
+
# RA - reference author(s) (>=1 per entry)
|
1271
|
+
# RT - reference title (>=0 per entry; optional)
|
1272
|
+
# RL - reference location (>=1 per entry)
|
1273
|
+
# RG - reference group(s)
|
1274
|
+
# CC - comments or notes (>=0 per entry; optional)
|
1275
|
+
# DR - database cross-references (>=0 per entry; optional)
|
1276
|
+
# KW - keywords (>=1 per entry)
|
1277
|
+
# FT - feature table data (>=0 per entry; optional)
|
1278
|
+
# SQ - sequence header (1 per entry)
|
1279
|
+
# - (blanks) The sequence data (>=1 per entry)
|
1280
|
+
# // - termination line (ends each entry; 1 per entry)
|
1281
|
+
# ---- --------------------------- --------------------------------
|
1282
|
+
|
1283
|
+
|