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 +1,152 @@
|
|
1
|
+
#
|
2
|
+
# = bio/sequence/aa.rb - amino acid sequence class
|
3
|
+
#
|
4
|
+
# Copyright:: Copyright (C) 2006
|
5
|
+
# Toshiaki Katayama <k@bioruby.org>,
|
6
|
+
# Ryan Raaum <ryan@raaum.org>
|
7
|
+
# License:: The Ruby License
|
8
|
+
#
|
9
|
+
# $Id: aa.rb,v 1.4 2007/04/05 23:35:41 trevor Exp $
|
10
|
+
#
|
11
|
+
|
12
|
+
require 'bio/sequence/common'
|
13
|
+
|
14
|
+
module Bio
|
15
|
+
|
16
|
+
autoload :AminoAcid, 'bio/data/aa'
|
17
|
+
|
18
|
+
class Sequence
|
19
|
+
|
20
|
+
# = DESCRIPTION
|
21
|
+
# Bio::Sequence::AA represents a bare Amino Acid sequence in bioruby.
|
22
|
+
#
|
23
|
+
# = USAGE
|
24
|
+
# # Create an Amino Acid sequence.
|
25
|
+
# aa = Bio::Sequence::AA.new('ACDEFGHIKLMNPQRSTVWYU')
|
26
|
+
#
|
27
|
+
# # What are the three-letter codes for all the residues?
|
28
|
+
# puts aa.codes
|
29
|
+
#
|
30
|
+
# # What are the names of all the residues?
|
31
|
+
# puts aa.names
|
32
|
+
#
|
33
|
+
# # What is the molecular weight of this peptide?
|
34
|
+
# puts aa.molecular_weight
|
35
|
+
class AA < String
|
36
|
+
|
37
|
+
include Bio::Sequence::Common
|
38
|
+
|
39
|
+
# Generate an amino acid sequence object from a string.
|
40
|
+
#
|
41
|
+
# s = Bio::Sequence::AA.new("RRLEHTFVFLRNFSLMLLRY")
|
42
|
+
#
|
43
|
+
# or maybe (if you have an amino acid sequence in a file)
|
44
|
+
#
|
45
|
+
# s = Bio::Sequence:AA.new(File.open('aa.txt').read)
|
46
|
+
#
|
47
|
+
# Amino Acid sequences are *always* all uppercase in bioruby
|
48
|
+
#
|
49
|
+
# s = Bio::Sequence::AA.new("rrLeHtfV")
|
50
|
+
# puts s #=> "RRLEHTFVF"
|
51
|
+
#
|
52
|
+
# Whitespace is stripped from the sequence
|
53
|
+
#
|
54
|
+
# s = Bio::Sequence::AA.new("RRL\nELA\tRG\r RL")
|
55
|
+
# puts s #=> "RRLELARGRL"
|
56
|
+
# ---
|
57
|
+
# *Arguments*:
|
58
|
+
# * (required) _str_: String
|
59
|
+
# *Returns*:: Bio::Sequence::AA object
|
60
|
+
def initialize(str)
|
61
|
+
super
|
62
|
+
self.upcase!
|
63
|
+
self.tr!(" \t\n\r",'')
|
64
|
+
end
|
65
|
+
|
66
|
+
|
67
|
+
# Estimate molecular weight based on
|
68
|
+
# Fasman1976[http://www.genome.ad.jp/dbget-bin/www_bget?aaindex+FASG760101]
|
69
|
+
#
|
70
|
+
# s = Bio::Sequence::AA.new("RRLE")
|
71
|
+
# puts s.molecular_weight #=> 572.655
|
72
|
+
# ---
|
73
|
+
# *Returns*:: Float object
|
74
|
+
def molecular_weight
|
75
|
+
Bio::AminoAcid.weight(self)
|
76
|
+
end
|
77
|
+
|
78
|
+
# Create a ruby regular expression instance
|
79
|
+
# (Regexp)[http://corelib.rubyonrails.org/classes/Regexp.html]
|
80
|
+
#
|
81
|
+
# s = Bio::Sequence::AA.new("RRLE")
|
82
|
+
# puts s.to_re #=> /RRLE/
|
83
|
+
# ---
|
84
|
+
# *Returns*:: Regexp object
|
85
|
+
def to_re
|
86
|
+
Bio::AminoAcid.to_re(self)
|
87
|
+
end
|
88
|
+
|
89
|
+
# Generate the list of the names of each residue along with the
|
90
|
+
# sequence (3 letters code). Codes used in bioruby are found in the
|
91
|
+
# Bio::AminoAcid::NAMES hash.
|
92
|
+
#
|
93
|
+
# s = Bio::Sequence::AA.new("RRLE")
|
94
|
+
# puts s.codes #=> ["Arg", "Arg", "Leu", "Glu"]
|
95
|
+
# ---
|
96
|
+
# *Returns*:: Array object
|
97
|
+
def codes
|
98
|
+
array = []
|
99
|
+
self.each_byte do |x|
|
100
|
+
array.push(Bio::AminoAcid.names[x.chr])
|
101
|
+
end
|
102
|
+
return array
|
103
|
+
end
|
104
|
+
|
105
|
+
# Generate the list of the names of each residue along with the
|
106
|
+
# sequence (full name). Names used in bioruby are found in the
|
107
|
+
# Bio::AminoAcid::NAMES hash.
|
108
|
+
#
|
109
|
+
# s = Bio::Sequence::AA.new("RRLE")
|
110
|
+
# puts s.names
|
111
|
+
# #=> ["arginine", "arginine", "leucine", "glutamic acid"]
|
112
|
+
# ---
|
113
|
+
# *Returns*:: Array object
|
114
|
+
def names
|
115
|
+
self.codes.map do |x|
|
116
|
+
Bio::AminoAcid.names[x]
|
117
|
+
end
|
118
|
+
end
|
119
|
+
|
120
|
+
|
121
|
+
# Return the number of bases considered acidic in this amino acid sequence in neutral conditions.
|
122
|
+
# Amino acids considered acidic are D and E.
|
123
|
+
def acidic_count
|
124
|
+
count = 0
|
125
|
+
comp = self.composition
|
126
|
+
Bio::AminoAcid::ACIDIC_AMINO_ACIDS.each do |acidic|
|
127
|
+
if comp[acidic]
|
128
|
+
count += comp[acidic]
|
129
|
+
end
|
130
|
+
end
|
131
|
+
return count
|
132
|
+
end
|
133
|
+
|
134
|
+
# Return the number of bases considered basic in this amino acid sequence in neutral conditions.
|
135
|
+
# Amino acids considered acidic are H, K and R.
|
136
|
+
def basic_count
|
137
|
+
count = 0
|
138
|
+
comp = self.composition
|
139
|
+
Bio::AminoAcid::BASIC_AMINO_ACIDS.each do |basic|
|
140
|
+
if comp[basic]
|
141
|
+
count += comp[basic]
|
142
|
+
end
|
143
|
+
end
|
144
|
+
return count
|
145
|
+
end
|
146
|
+
|
147
|
+
end # AA
|
148
|
+
|
149
|
+
end # Sequence
|
150
|
+
|
151
|
+
end # Bio
|
152
|
+
|
@@ -0,0 +1,108 @@
|
|
1
|
+
#
|
2
|
+
# = bio/sequence/adapter.rb - Bio::Sequence adapter helper 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
|
+
|
13
|
+
# Internal use only. Normal users should not use this module.
|
14
|
+
#
|
15
|
+
# Helper methods for defining adapters used when converting data classes to
|
16
|
+
# Bio::Sequence class, with pseudo lazy evaluation and pseudo memoization.
|
17
|
+
#
|
18
|
+
# This module is used by using "extend", not "include".
|
19
|
+
#
|
20
|
+
module Bio::Sequence::Adapter
|
21
|
+
|
22
|
+
autoload :GenBank, 'bio/db/genbank/genbank_to_biosequence'
|
23
|
+
autoload :EMBL, 'bio/db/embl/embl_to_biosequence'
|
24
|
+
autoload :FastaFormat, 'bio/db/fasta/fasta_to_biosequence'
|
25
|
+
autoload :BioSQL, 'bio/db/biosql/biosql_to_biosequence'
|
26
|
+
|
27
|
+
private
|
28
|
+
|
29
|
+
# Defines a reader attribute method with psudo lazy evaluation/memoization.
|
30
|
+
#
|
31
|
+
# It defines a method <i>name</i> like attr_reader, but at the first time
|
32
|
+
# when the method <i>name</i> is called, it acts as follows:
|
33
|
+
# When instance variable @<i>name</i> is not defined,
|
34
|
+
# calls <tt>__get__<i>name</i>(@source_data)</tt> and stores the returned
|
35
|
+
# value to @<i>name</i>, and changes its behavior to the same as
|
36
|
+
# <tt>attr_reader </tt><i>:name</i>.
|
37
|
+
# When instance variable @name is already defined,
|
38
|
+
# its behavior is changed to the same as
|
39
|
+
# <tt>attr_reader </tt><i>:name</i>.
|
40
|
+
# When the object is frozen, storing to the instance variable and
|
41
|
+
# changing methods behavior do not occur, and the value of
|
42
|
+
# <tt>__get__<i>name</i>(@source_data)</tt> is returned.
|
43
|
+
#
|
44
|
+
# Note that it assumes that the source data object is stored in
|
45
|
+
# @source_data instance variable.
|
46
|
+
def attr_reader_lazy(name)
|
47
|
+
#$stderr.puts "attr_reader_lazy :#{name}"
|
48
|
+
varname = "@#{name}".intern
|
49
|
+
methodname = "__get__#{name}".intern
|
50
|
+
|
51
|
+
# module to reset method's behavior to normal attr_reader
|
52
|
+
reset = "Attr_#{name}".intern
|
53
|
+
const_set(reset, Module.new { attr_reader name })
|
54
|
+
reset_module_name = "#{self}::#{reset}"
|
55
|
+
|
56
|
+
# define attr method
|
57
|
+
module_eval <<__END_OF_DEF__
|
58
|
+
def #{name}
|
59
|
+
unless defined? #{varname} then
|
60
|
+
#$stderr.puts "LAZY #{name}: calling #{methodname}"
|
61
|
+
val = #{methodname}(@source_data)
|
62
|
+
#{varname} = val unless frozen?
|
63
|
+
else
|
64
|
+
val = #{varname}
|
65
|
+
end
|
66
|
+
unless frozen? then
|
67
|
+
#$stderr.puts "LAZY #{name}: finalize: attr_reader :#{name}"
|
68
|
+
self.extend(#{reset_module_name})
|
69
|
+
end
|
70
|
+
val
|
71
|
+
end
|
72
|
+
__END_OF_DEF__
|
73
|
+
end
|
74
|
+
|
75
|
+
# Defines a Bio::Sequence to Bio::* adapter method with
|
76
|
+
# psudo lazy evaluation and psudo memoization.
|
77
|
+
#
|
78
|
+
# Without block, defines a private method <tt>__get__<i>name</i>(orig)</tt>
|
79
|
+
# which calls <i>source_method</i> for @source_data.
|
80
|
+
#
|
81
|
+
# def__get__(name, source_method) is the same as:
|
82
|
+
# def __get__name(orig); orig.source_method; end
|
83
|
+
# attr_reader_lazy name
|
84
|
+
#
|
85
|
+
# If block is given, <tt>__get__<i>name</i>(orig)</tt> is defined
|
86
|
+
# with the block. The @source_data is given as an argument of the block,
|
87
|
+
# i.e. the block must get an argument.
|
88
|
+
#
|
89
|
+
def def_biosequence_adapter(name, source_method = name, &block)
|
90
|
+
methodname = "__get__#{name}".intern
|
91
|
+
|
92
|
+
if block then
|
93
|
+
define_method(methodname, block)
|
94
|
+
else
|
95
|
+
module_eval <<__END_OF_DEF__
|
96
|
+
def #{methodname}(orig)
|
97
|
+
orig.#{source_method}
|
98
|
+
end
|
99
|
+
__END_OF_DEF__
|
100
|
+
end
|
101
|
+
private methodname
|
102
|
+
attr_reader_lazy name
|
103
|
+
true
|
104
|
+
end
|
105
|
+
|
106
|
+
end #module Bio::Sequence::Adapter
|
107
|
+
|
108
|
+
|
@@ -0,0 +1,310 @@
|
|
1
|
+
#
|
2
|
+
# = bio/sequence/common.rb - common methods for biological sequence
|
3
|
+
#
|
4
|
+
# Copyright:: Copyright (C) 2006
|
5
|
+
# Toshiaki Katayama <k@bioruby.org>,
|
6
|
+
# Ryan Raaum <ryan@raaum.org>
|
7
|
+
# License:: The Ruby License
|
8
|
+
#
|
9
|
+
# $Id:$
|
10
|
+
#
|
11
|
+
|
12
|
+
module Bio
|
13
|
+
|
14
|
+
autoload :Locations, 'bio/location'
|
15
|
+
|
16
|
+
class Sequence
|
17
|
+
|
18
|
+
# = DESCRIPTION
|
19
|
+
# Bio::Sequence::Common is a
|
20
|
+
# Mixin[http://www.rubycentral.com/book/tut_modules.html]
|
21
|
+
# implementing methods common to
|
22
|
+
# Bio::Sequence::AA and Bio::Sequence::NA. All of these methods
|
23
|
+
# are available to either Amino Acid or Nucleic Acid sequences, and
|
24
|
+
# by encapsulation are also available to Bio::Sequence objects.
|
25
|
+
#
|
26
|
+
# = USAGE
|
27
|
+
#
|
28
|
+
# # Create a sequence
|
29
|
+
# dna = Bio::Sequence.auto('atgcatgcatgc')
|
30
|
+
#
|
31
|
+
# # Splice out a subsequence using a Genbank-style location string
|
32
|
+
# puts dna.splice('complement(1..4)')
|
33
|
+
#
|
34
|
+
# # What is the base composition?
|
35
|
+
# puts dna.composition
|
36
|
+
#
|
37
|
+
# # Create a random sequence with the composition of a current sequence
|
38
|
+
# puts dna.randomize
|
39
|
+
module Common
|
40
|
+
|
41
|
+
# Return sequence as
|
42
|
+
# String[http://corelib.rubyonrails.org/classes/String.html].
|
43
|
+
# The original sequence is unchanged.
|
44
|
+
#
|
45
|
+
# seq = Bio::Sequence::NA.new('atgc')
|
46
|
+
# puts s.to_s #=> 'atgc'
|
47
|
+
# puts s.to_s.class #=> String
|
48
|
+
# puts s #=> 'atgc'
|
49
|
+
# puts s.class #=> Bio::Sequence::NA
|
50
|
+
# ---
|
51
|
+
# *Returns*:: String object
|
52
|
+
def to_s
|
53
|
+
String.new(self)
|
54
|
+
end
|
55
|
+
alias to_str to_s
|
56
|
+
|
57
|
+
# Create a new sequence based on the current sequence.
|
58
|
+
# The original sequence is unchanged.
|
59
|
+
#
|
60
|
+
# s = Bio::Sequence::NA.new('atgc')
|
61
|
+
# s2 = s.seq
|
62
|
+
# puts s2 #=> 'atgc'
|
63
|
+
# ---
|
64
|
+
# *Returns*:: new Bio::Sequence::NA/AA object
|
65
|
+
def seq
|
66
|
+
self.class.new(self)
|
67
|
+
end
|
68
|
+
|
69
|
+
# Normalize the current sequence, removing all whitespace and
|
70
|
+
# transforming all positions to uppercase if the sequence is AA or
|
71
|
+
# transforming all positions to lowercase if the sequence is NA.
|
72
|
+
# The original sequence is modified.
|
73
|
+
#
|
74
|
+
# s = Bio::Sequence::NA.new('atgc')
|
75
|
+
# s.normalize!
|
76
|
+
# ---
|
77
|
+
# *Returns*:: current Bio::Sequence::NA/AA object (modified)
|
78
|
+
def normalize!
|
79
|
+
initialize(self)
|
80
|
+
self
|
81
|
+
end
|
82
|
+
alias seq! normalize!
|
83
|
+
|
84
|
+
# Add new data to the end of the current sequence.
|
85
|
+
# The original sequence is modified.
|
86
|
+
#
|
87
|
+
# s = Bio::Sequence::NA.new('atgc')
|
88
|
+
# s << 'atgc'
|
89
|
+
# puts s #=> "atgcatgc"
|
90
|
+
# s << s
|
91
|
+
# puts s #=> "atgcatgcatgcatgc"
|
92
|
+
# ---
|
93
|
+
# *Returns*:: current Bio::Sequence::NA/AA object (modified)
|
94
|
+
def concat(*arg)
|
95
|
+
super(self.class.new(*arg))
|
96
|
+
end
|
97
|
+
|
98
|
+
def <<(*arg)
|
99
|
+
concat(*arg)
|
100
|
+
end
|
101
|
+
|
102
|
+
# Create a new sequence by adding to an existing sequence.
|
103
|
+
# The existing sequence is not modified.
|
104
|
+
#
|
105
|
+
# s = Bio::Sequence::NA.new('atgc')
|
106
|
+
# s2 = s + 'atgc'
|
107
|
+
# puts s2 #=> "atgcatgc"
|
108
|
+
# puts s #=> "atgc"
|
109
|
+
#
|
110
|
+
# The new sequence is of the same class as the existing sequence if
|
111
|
+
# the new data was added to an existing sequence,
|
112
|
+
#
|
113
|
+
# puts s2.class == s.class #=> true
|
114
|
+
#
|
115
|
+
# but if an existing sequence is added to a String, the result is a String
|
116
|
+
#
|
117
|
+
# s3 = 'atgc' + s
|
118
|
+
# puts s3.class #=> String
|
119
|
+
# ---
|
120
|
+
# *Returns*:: new Bio::Sequence::NA/AA *or* String object
|
121
|
+
def +(*arg)
|
122
|
+
self.class.new(super(*arg))
|
123
|
+
end
|
124
|
+
|
125
|
+
# Returns a new sequence containing the subsequence identified by the
|
126
|
+
# start and end numbers given as parameters. *Important:* Biological
|
127
|
+
# sequence numbering conventions (one-based) rather than ruby's
|
128
|
+
# (zero-based) numbering conventions are used.
|
129
|
+
#
|
130
|
+
# s = Bio::Sequence::NA.new('atggaatga')
|
131
|
+
# puts s.subseq(1,3) #=> "atg"
|
132
|
+
#
|
133
|
+
# Start defaults to 1 and end defaults to the entire existing string, so
|
134
|
+
# subseq called without any parameters simply returns a new sequence
|
135
|
+
# identical to the existing sequence.
|
136
|
+
#
|
137
|
+
# puts s.subseq #=> "atggaatga"
|
138
|
+
# ---
|
139
|
+
# *Arguments*:
|
140
|
+
# * (optional) _s_(start): Integer (default 1)
|
141
|
+
# * (optional) _e_(end): Integer (default current sequence length)
|
142
|
+
# *Returns*:: new Bio::Sequence::NA/AA object
|
143
|
+
def subseq(s = 1, e = self.length)
|
144
|
+
raise "Error: start/end position must be a positive integer" unless s > 0 and e > 0
|
145
|
+
s -= 1
|
146
|
+
e -= 1
|
147
|
+
self[s..e]
|
148
|
+
end
|
149
|
+
|
150
|
+
# This method steps through a sequences in steps of 'step_size' by
|
151
|
+
# subsequences of 'window_size'. Typically used with a block.
|
152
|
+
# Any remaining sequence at the terminal end will be returned.
|
153
|
+
#
|
154
|
+
# Prints average GC% on each 100bp
|
155
|
+
#
|
156
|
+
# s.window_search(100) do |subseq|
|
157
|
+
# puts subseq.gc
|
158
|
+
# end
|
159
|
+
#
|
160
|
+
# Prints every translated peptide (length 5aa) in the same frame
|
161
|
+
#
|
162
|
+
# s.window_search(15, 3) do |subseq|
|
163
|
+
# puts subseq.translate
|
164
|
+
# end
|
165
|
+
#
|
166
|
+
# Split genome sequence by 10000bp with 1000bp overlap in fasta format
|
167
|
+
#
|
168
|
+
# i = 1
|
169
|
+
# remainder = s.window_search(10000, 9000) do |subseq|
|
170
|
+
# puts subseq.to_fasta("segment #{i}", 60)
|
171
|
+
# i += 1
|
172
|
+
# end
|
173
|
+
# puts remainder.to_fasta("segment #{i}", 60)
|
174
|
+
# ---
|
175
|
+
# *Arguments*:
|
176
|
+
# * (required) _window_size_: Fixnum
|
177
|
+
# * (optional) _step_size_: Fixnum (default 1)
|
178
|
+
# *Returns*:: new Bio::Sequence::NA/AA object
|
179
|
+
def window_search(window_size, step_size = 1)
|
180
|
+
last_step = 0
|
181
|
+
0.step(self.length - window_size, step_size) do |i|
|
182
|
+
yield self[i, window_size]
|
183
|
+
last_step = i
|
184
|
+
end
|
185
|
+
return self[last_step + window_size .. -1]
|
186
|
+
end
|
187
|
+
|
188
|
+
# Returns a float total value for the sequence given a hash of
|
189
|
+
# base or residue values,
|
190
|
+
#
|
191
|
+
# values = {'a' => 0.1, 't' => 0.2, 'g' => 0.3, 'c' => 0.4}
|
192
|
+
# s = Bio::Sequence::NA.new('atgc')
|
193
|
+
# puts s.total(values) #=> 1.0
|
194
|
+
# ---
|
195
|
+
# *Arguments*:
|
196
|
+
# * (required) _hash_: Hash object
|
197
|
+
# *Returns*:: Float object
|
198
|
+
def total(hash)
|
199
|
+
hash.default = 0.0 unless hash.default
|
200
|
+
sum = 0.0
|
201
|
+
self.each_byte do |x|
|
202
|
+
begin
|
203
|
+
sum += hash[x.chr]
|
204
|
+
end
|
205
|
+
end
|
206
|
+
return sum
|
207
|
+
end
|
208
|
+
|
209
|
+
# Returns a hash of the occurrence counts for each residue or base.
|
210
|
+
#
|
211
|
+
# s = Bio::Sequence::NA.new('atgc')
|
212
|
+
# puts s.composition #=> {"a"=>1, "c"=>1, "g"=>1, "t"=>1}
|
213
|
+
# ---
|
214
|
+
# *Returns*:: Hash object
|
215
|
+
def composition
|
216
|
+
count = Hash.new(0)
|
217
|
+
self.scan(/./) do |x|
|
218
|
+
count[x] += 1
|
219
|
+
end
|
220
|
+
return count
|
221
|
+
end
|
222
|
+
|
223
|
+
# Returns a randomized sequence. The default is to retain the same
|
224
|
+
# base/residue composition as the original. If a hash of base/residue
|
225
|
+
# counts is given, the new sequence will be based on that hash
|
226
|
+
# composition. If a block is given, each new randomly selected
|
227
|
+
# position will be passed into the block. In all cases, the
|
228
|
+
# original sequence is not modified.
|
229
|
+
#
|
230
|
+
# s = Bio::Sequence::NA.new('atgc')
|
231
|
+
# puts s.randomize #=> "tcag" (for example)
|
232
|
+
#
|
233
|
+
# new_composition = {'a' => 2, 't' => 2}
|
234
|
+
# puts s.randomize(new_composition) #=> "ttaa" (for example)
|
235
|
+
#
|
236
|
+
# count = 0
|
237
|
+
# s.randomize { |x| count += 1 }
|
238
|
+
# puts count #=> 4
|
239
|
+
# ---
|
240
|
+
# *Arguments*:
|
241
|
+
# * (optional) _hash_: Hash object
|
242
|
+
# *Returns*:: new Bio::Sequence::NA/AA object
|
243
|
+
def randomize(hash = nil)
|
244
|
+
if hash
|
245
|
+
tmp = ''
|
246
|
+
hash.each {|k, v|
|
247
|
+
tmp += k * v.to_i
|
248
|
+
}
|
249
|
+
else
|
250
|
+
tmp = self
|
251
|
+
end
|
252
|
+
seq = self.class.new(tmp)
|
253
|
+
# Reference: http://en.wikipedia.org/wiki/Fisher-Yates_shuffle
|
254
|
+
seq.length.downto(2) do |n|
|
255
|
+
k = rand(n)
|
256
|
+
c = seq[n - 1]
|
257
|
+
seq[n - 1] = seq[k]
|
258
|
+
seq[k] = c
|
259
|
+
end
|
260
|
+
if block_given? then
|
261
|
+
(0...seq.length).each do |i|
|
262
|
+
yield seq[i, 1]
|
263
|
+
end
|
264
|
+
return self.class.new('')
|
265
|
+
else
|
266
|
+
return seq
|
267
|
+
end
|
268
|
+
end
|
269
|
+
|
270
|
+
# Return a new sequence extracted from the original using a GenBank style
|
271
|
+
# position string. See also documentation for the Bio::Location class.
|
272
|
+
#
|
273
|
+
# s = Bio::Sequence::NA.new('atgcatgcatgcatgc')
|
274
|
+
# puts s.splice('1..3') #=> "atg"
|
275
|
+
# puts s.splice('join(1..3,8..10)') #=> "atgcat"
|
276
|
+
# puts s.splice('complement(1..3)') #=> "cat"
|
277
|
+
# puts s.splice('complement(join(1..3,8..10))') #=> "atgcat"
|
278
|
+
#
|
279
|
+
# Note that 'complement'ed Genbank position strings will have no
|
280
|
+
# effect on Bio::Sequence::AA objects.
|
281
|
+
# ---
|
282
|
+
# *Arguments*:
|
283
|
+
# * (required) _position_: String *or* Bio::Location object
|
284
|
+
# *Returns*:: Bio::Sequence::NA/AA object
|
285
|
+
def splice(position)
|
286
|
+
unless position.is_a?(Locations) then
|
287
|
+
position = Locations.new(position)
|
288
|
+
end
|
289
|
+
s = ''
|
290
|
+
position.each do |location|
|
291
|
+
if location.sequence
|
292
|
+
s << location.sequence
|
293
|
+
else
|
294
|
+
exon = self.subseq(location.from, location.to)
|
295
|
+
begin
|
296
|
+
exon.complement! if location.strand < 0
|
297
|
+
rescue NameError
|
298
|
+
end
|
299
|
+
s << exon
|
300
|
+
end
|
301
|
+
end
|
302
|
+
return self.class.new(s)
|
303
|
+
end
|
304
|
+
alias splicing splice
|
305
|
+
|
306
|
+
end # Common
|
307
|
+
|
308
|
+
end # Sequence
|
309
|
+
|
310
|
+
end # Bio
|