ngoto-bio 1.2.9.9001
Sign up to get free protection for your applications and to get access to all the features.
- data/ChangeLog +2046 -0
- data/README.rdoc +223 -0
- data/README_DEV.rdoc +285 -0
- data/Rakefile +70 -0
- data/bin/bioruby +44 -0
- data/bin/br_biofetch.rb +47 -0
- data/bin/br_bioflat.rb +293 -0
- data/bin/br_biogetseq.rb +45 -0
- data/bin/br_pmfetch.rb +421 -0
- data/bioruby.gemspec +463 -0
- data/bioruby.gemspec.erb +79 -0
- data/doc/Changes-0.7.rd +369 -0
- data/doc/Changes-1.3.rdoc +195 -0
- data/doc/KEGG_API.rd +1843 -0
- data/doc/KEGG_API.rd.ja +1834 -0
- data/doc/Tutorial.rd +1296 -0
- data/doc/Tutorial.rd.ja +2640 -0
- data/etc/bioinformatics/seqdatabase.ini +210 -0
- data/extconf.rb +2 -0
- data/lib/bio/alignment.rb +2518 -0
- data/lib/bio/appl/bl2seq/report.rb +334 -0
- data/lib/bio/appl/blast/ddbj.rb +142 -0
- data/lib/bio/appl/blast/format0.rb +1438 -0
- data/lib/bio/appl/blast/format8.rb +83 -0
- data/lib/bio/appl/blast/genomenet.rb +263 -0
- data/lib/bio/appl/blast/ncbioptions.rb +220 -0
- data/lib/bio/appl/blast/remote.rb +105 -0
- data/lib/bio/appl/blast/report.rb +767 -0
- data/lib/bio/appl/blast/rexml.rb +144 -0
- data/lib/bio/appl/blast/rpsblast.rb +277 -0
- data/lib/bio/appl/blast/wublast.rb +671 -0
- data/lib/bio/appl/blast/xmlparser.rb +236 -0
- data/lib/bio/appl/blast.rb +505 -0
- data/lib/bio/appl/blat/report.rb +530 -0
- data/lib/bio/appl/clustalw/report.rb +152 -0
- data/lib/bio/appl/clustalw.rb +219 -0
- data/lib/bio/appl/emboss.rb +203 -0
- data/lib/bio/appl/fasta/format10.rb +325 -0
- data/lib/bio/appl/fasta.rb +235 -0
- data/lib/bio/appl/gcg/msf.rb +212 -0
- data/lib/bio/appl/gcg/seq.rb +195 -0
- data/lib/bio/appl/genscan/report.rb +552 -0
- data/lib/bio/appl/hmmer/report.rb +683 -0
- data/lib/bio/appl/hmmer.rb +126 -0
- data/lib/bio/appl/iprscan/report.rb +374 -0
- data/lib/bio/appl/mafft/report.rb +226 -0
- data/lib/bio/appl/mafft.rb +259 -0
- data/lib/bio/appl/muscle.rb +52 -0
- data/lib/bio/appl/paml/baseml/report.rb +32 -0
- data/lib/bio/appl/paml/baseml.rb +95 -0
- data/lib/bio/appl/paml/codeml/rates.rb +67 -0
- data/lib/bio/appl/paml/codeml/report.rb +67 -0
- data/lib/bio/appl/paml/codeml.rb +242 -0
- data/lib/bio/appl/paml/common.rb +348 -0
- data/lib/bio/appl/paml/common_report.rb +38 -0
- data/lib/bio/appl/paml/yn00/report.rb +32 -0
- data/lib/bio/appl/paml/yn00.rb +103 -0
- data/lib/bio/appl/phylip/alignment.rb +129 -0
- data/lib/bio/appl/phylip/distance_matrix.rb +96 -0
- data/lib/bio/appl/probcons.rb +41 -0
- data/lib/bio/appl/psort/report.rb +457 -0
- data/lib/bio/appl/psort.rb +548 -0
- data/lib/bio/appl/pts1.rb +263 -0
- data/lib/bio/appl/sim4/report.rb +485 -0
- data/lib/bio/appl/sim4.rb +124 -0
- data/lib/bio/appl/sosui/report.rb +151 -0
- data/lib/bio/appl/spidey/report.rb +593 -0
- data/lib/bio/appl/targetp/report.rb +267 -0
- data/lib/bio/appl/tcoffee.rb +55 -0
- data/lib/bio/appl/tmhmm/report.rb +231 -0
- data/lib/bio/command.rb +593 -0
- data/lib/bio/compat/features.rb +157 -0
- data/lib/bio/compat/references.rb +128 -0
- data/lib/bio/data/aa.rb +349 -0
- data/lib/bio/data/codontable.rb +722 -0
- data/lib/bio/data/na.rb +223 -0
- data/lib/bio/db/aaindex.rb +357 -0
- data/lib/bio/db/biosql/biosql_to_biosequence.rb +67 -0
- data/lib/bio/db/biosql/sequence.rb +508 -0
- data/lib/bio/db/embl/common.rb +352 -0
- data/lib/bio/db/embl/embl.rb +500 -0
- data/lib/bio/db/embl/embl_to_biosequence.rb +85 -0
- data/lib/bio/db/embl/format_embl.rb +190 -0
- data/lib/bio/db/embl/sptr.rb +1283 -0
- data/lib/bio/db/embl/swissprot.rb +42 -0
- data/lib/bio/db/embl/trembl.rb +41 -0
- data/lib/bio/db/embl/uniprot.rb +42 -0
- data/lib/bio/db/fantom.rb +597 -0
- data/lib/bio/db/fasta/defline.rb +532 -0
- data/lib/bio/db/fasta/fasta_to_biosequence.rb +63 -0
- data/lib/bio/db/fasta/format_fasta.rb +97 -0
- data/lib/bio/db/fasta.rb +410 -0
- data/lib/bio/db/genbank/common.rb +307 -0
- data/lib/bio/db/genbank/ddbj.rb +22 -0
- data/lib/bio/db/genbank/format_genbank.rb +187 -0
- data/lib/bio/db/genbank/genbank.rb +250 -0
- data/lib/bio/db/genbank/genbank_to_biosequence.rb +86 -0
- data/lib/bio/db/genbank/genpept.rb +60 -0
- data/lib/bio/db/genbank/refseq.rb +18 -0
- data/lib/bio/db/gff.rb +1846 -0
- data/lib/bio/db/go.rb +481 -0
- data/lib/bio/db/kegg/brite.rb +41 -0
- data/lib/bio/db/kegg/compound.rb +131 -0
- data/lib/bio/db/kegg/drug.rb +98 -0
- data/lib/bio/db/kegg/enzyme.rb +148 -0
- data/lib/bio/db/kegg/expression.rb +155 -0
- data/lib/bio/db/kegg/genes.rb +263 -0
- data/lib/bio/db/kegg/genome.rb +241 -0
- data/lib/bio/db/kegg/glycan.rb +166 -0
- data/lib/bio/db/kegg/keggtab.rb +357 -0
- data/lib/bio/db/kegg/kgml.rb +256 -0
- data/lib/bio/db/kegg/orthology.rb +136 -0
- data/lib/bio/db/kegg/reaction.rb +82 -0
- data/lib/bio/db/kegg/taxonomy.rb +331 -0
- data/lib/bio/db/lasergene.rb +209 -0
- data/lib/bio/db/litdb.rb +107 -0
- data/lib/bio/db/medline.rb +326 -0
- data/lib/bio/db/nbrf.rb +191 -0
- data/lib/bio/db/newick.rb +658 -0
- data/lib/bio/db/nexus.rb +1854 -0
- data/lib/bio/db/pdb/atom.rb +77 -0
- data/lib/bio/db/pdb/chain.rb +210 -0
- data/lib/bio/db/pdb/chemicalcomponent.rb +224 -0
- data/lib/bio/db/pdb/model.rb +148 -0
- data/lib/bio/db/pdb/pdb.rb +1911 -0
- data/lib/bio/db/pdb/residue.rb +176 -0
- data/lib/bio/db/pdb/utils.rb +399 -0
- data/lib/bio/db/pdb.rb +29 -0
- data/lib/bio/db/prosite.rb +597 -0
- data/lib/bio/db/rebase.rb +456 -0
- data/lib/bio/db/soft.rb +404 -0
- data/lib/bio/db/transfac.rb +375 -0
- data/lib/bio/db.rb +329 -0
- data/lib/bio/feature.rb +139 -0
- data/lib/bio/io/biosql/biodatabase.rb +64 -0
- data/lib/bio/io/biosql/bioentry.rb +29 -0
- data/lib/bio/io/biosql/bioentry_dbxref.rb +11 -0
- data/lib/bio/io/biosql/bioentry_path.rb +12 -0
- data/lib/bio/io/biosql/bioentry_qualifier_value.rb +10 -0
- data/lib/bio/io/biosql/bioentry_reference.rb +10 -0
- data/lib/bio/io/biosql/bioentry_relationship.rb +10 -0
- data/lib/bio/io/biosql/biosequence.rb +11 -0
- data/lib/bio/io/biosql/comment.rb +7 -0
- data/lib/bio/io/biosql/config/database.yml +20 -0
- data/lib/bio/io/biosql/dbxref.rb +13 -0
- data/lib/bio/io/biosql/dbxref_qualifier_value.rb +12 -0
- data/lib/bio/io/biosql/location.rb +32 -0
- data/lib/bio/io/biosql/location_qualifier_value.rb +11 -0
- data/lib/bio/io/biosql/ontology.rb +10 -0
- data/lib/bio/io/biosql/reference.rb +9 -0
- data/lib/bio/io/biosql/seqfeature.rb +32 -0
- data/lib/bio/io/biosql/seqfeature_dbxref.rb +11 -0
- data/lib/bio/io/biosql/seqfeature_path.rb +11 -0
- data/lib/bio/io/biosql/seqfeature_qualifier_value.rb +20 -0
- data/lib/bio/io/biosql/seqfeature_relationship.rb +11 -0
- data/lib/bio/io/biosql/taxon.rb +12 -0
- data/lib/bio/io/biosql/taxon_name.rb +9 -0
- data/lib/bio/io/biosql/term.rb +27 -0
- data/lib/bio/io/biosql/term_dbxref.rb +11 -0
- data/lib/bio/io/biosql/term_path.rb +12 -0
- data/lib/bio/io/biosql/term_relationship.rb +13 -0
- data/lib/bio/io/biosql/term_relationship_term.rb +11 -0
- data/lib/bio/io/biosql/term_synonym.rb +10 -0
- data/lib/bio/io/das.rb +461 -0
- data/lib/bio/io/dbget.rb +194 -0
- data/lib/bio/io/ddbjxml.rb +638 -0
- data/lib/bio/io/ebisoap.rb +158 -0
- data/lib/bio/io/ensembl.rb +229 -0
- data/lib/bio/io/fastacmd.rb +163 -0
- data/lib/bio/io/fetch.rb +195 -0
- data/lib/bio/io/flatfile/autodetection.rb +545 -0
- data/lib/bio/io/flatfile/bdb.rb +253 -0
- data/lib/bio/io/flatfile/buffer.rb +237 -0
- data/lib/bio/io/flatfile/index.rb +1381 -0
- data/lib/bio/io/flatfile/indexer.rb +805 -0
- data/lib/bio/io/flatfile/splitter.rb +297 -0
- data/lib/bio/io/flatfile.rb +473 -0
- data/lib/bio/io/higet.rb +73 -0
- data/lib/bio/io/hinv.rb +442 -0
- data/lib/bio/io/keggapi.rb +805 -0
- data/lib/bio/io/ncbirest.rb +733 -0
- data/lib/bio/io/ncbisoap.rb +155 -0
- data/lib/bio/io/pubmed.rb +307 -0
- data/lib/bio/io/registry.rb +292 -0
- data/lib/bio/io/soapwsdl.rb +119 -0
- data/lib/bio/io/sql.rb +186 -0
- data/lib/bio/location.rb +867 -0
- data/lib/bio/map.rb +410 -0
- data/lib/bio/pathway.rb +960 -0
- data/lib/bio/reference.rb +602 -0
- data/lib/bio/sequence/aa.rb +125 -0
- data/lib/bio/sequence/adapter.rb +108 -0
- data/lib/bio/sequence/common.rb +310 -0
- data/lib/bio/sequence/compat.rb +123 -0
- data/lib/bio/sequence/dblink.rb +54 -0
- data/lib/bio/sequence/format.rb +358 -0
- data/lib/bio/sequence/format_raw.rb +23 -0
- data/lib/bio/sequence/generic.rb +24 -0
- data/lib/bio/sequence/na.rb +491 -0
- data/lib/bio/sequence.rb +456 -0
- data/lib/bio/shell/core.rb +578 -0
- data/lib/bio/shell/demo.rb +146 -0
- data/lib/bio/shell/interface.rb +218 -0
- data/lib/bio/shell/irb.rb +95 -0
- data/lib/bio/shell/object.rb +71 -0
- data/lib/bio/shell/plugin/blast.rb +42 -0
- data/lib/bio/shell/plugin/codon.rb +218 -0
- data/lib/bio/shell/plugin/das.rb +58 -0
- data/lib/bio/shell/plugin/emboss.rb +23 -0
- data/lib/bio/shell/plugin/entry.rb +105 -0
- data/lib/bio/shell/plugin/flatfile.rb +101 -0
- data/lib/bio/shell/plugin/keggapi.rb +181 -0
- data/lib/bio/shell/plugin/midi.rb +430 -0
- data/lib/bio/shell/plugin/obda.rb +45 -0
- data/lib/bio/shell/plugin/psort.rb +56 -0
- data/lib/bio/shell/plugin/seq.rb +247 -0
- data/lib/bio/shell/plugin/soap.rb +87 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/bioruby_generator.rb +29 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/_classes.rhtml +4 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/_log.rhtml +27 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/_methods.rhtml +11 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/_modules.rhtml +4 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/_variables.rhtml +7 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/bioruby-bg.gif +0 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/bioruby-gem.png +0 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/bioruby-link.gif +0 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/bioruby.css +368 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/bioruby.rhtml +47 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/bioruby_controller.rb +144 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/bioruby_helper.rb +47 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/commands.rhtml +8 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/history.rhtml +10 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/index.rhtml +26 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/spinner.gif +0 -0
- data/lib/bio/shell/script.rb +25 -0
- data/lib/bio/shell/setup.rb +109 -0
- data/lib/bio/shell/web.rb +102 -0
- data/lib/bio/shell.rb +44 -0
- data/lib/bio/tree.rb +852 -0
- data/lib/bio/util/color_scheme/buried.rb +59 -0
- data/lib/bio/util/color_scheme/helix.rb +59 -0
- data/lib/bio/util/color_scheme/hydropathy.rb +64 -0
- data/lib/bio/util/color_scheme/nucleotide.rb +31 -0
- data/lib/bio/util/color_scheme/strand.rb +59 -0
- data/lib/bio/util/color_scheme/taylor.rb +50 -0
- data/lib/bio/util/color_scheme/turn.rb +59 -0
- data/lib/bio/util/color_scheme/zappo.rb +50 -0
- data/lib/bio/util/color_scheme.rb +191 -0
- data/lib/bio/util/contingency_table.rb +370 -0
- data/lib/bio/util/restriction_enzyme/analysis.rb +249 -0
- data/lib/bio/util/restriction_enzyme/analysis_basic.rb +217 -0
- data/lib/bio/util/restriction_enzyme/cut_symbol.rb +107 -0
- data/lib/bio/util/restriction_enzyme/double_stranded/aligned_strands.rb +130 -0
- data/lib/bio/util/restriction_enzyme/double_stranded/cut_location_pair.rb +103 -0
- data/lib/bio/util/restriction_enzyme/double_stranded/cut_location_pair_in_enzyme_notation.rb +38 -0
- data/lib/bio/util/restriction_enzyme/double_stranded/cut_locations.rb +76 -0
- data/lib/bio/util/restriction_enzyme/double_stranded/cut_locations_in_enzyme_notation.rb +107 -0
- data/lib/bio/util/restriction_enzyme/double_stranded.rb +321 -0
- data/lib/bio/util/restriction_enzyme/enzymes.yaml +7061 -0
- data/lib/bio/util/restriction_enzyme/range/cut_range.rb +24 -0
- data/lib/bio/util/restriction_enzyme/range/cut_ranges.rb +47 -0
- data/lib/bio/util/restriction_enzyme/range/horizontal_cut_range.rb +67 -0
- data/lib/bio/util/restriction_enzyme/range/sequence_range/calculated_cuts.rb +242 -0
- data/lib/bio/util/restriction_enzyme/range/sequence_range/fragment.rb +51 -0
- data/lib/bio/util/restriction_enzyme/range/sequence_range/fragments.rb +41 -0
- data/lib/bio/util/restriction_enzyme/range/sequence_range.rb +257 -0
- data/lib/bio/util/restriction_enzyme/range/vertical_cut_range.rb +77 -0
- data/lib/bio/util/restriction_enzyme/single_strand/cut_locations_in_enzyme_notation.rb +135 -0
- data/lib/bio/util/restriction_enzyme/single_strand.rb +200 -0
- data/lib/bio/util/restriction_enzyme/single_strand_complement.rb +23 -0
- data/lib/bio/util/restriction_enzyme/string_formatting.rb +111 -0
- data/lib/bio/util/restriction_enzyme.rb +228 -0
- data/lib/bio/util/sirna.rb +288 -0
- data/lib/bio.rb +300 -0
- data/rdoc.zsh +8 -0
- data/sample/any2fasta.rb +59 -0
- data/sample/biofetch.rb +475 -0
- data/sample/color_scheme_na.rb +91 -0
- data/sample/dbget +37 -0
- data/sample/demo_sequence.rb +158 -0
- data/sample/enzymes.rb +78 -0
- data/sample/fasta2tab.rb +99 -0
- data/sample/fastagrep.rb +72 -0
- data/sample/fastasort.rb +54 -0
- data/sample/fsplit.rb +51 -0
- data/sample/gb2fasta.rb +30 -0
- data/sample/gb2tab.rb +325 -0
- data/sample/gbtab2mysql.rb +161 -0
- data/sample/genes2nuc.rb +33 -0
- data/sample/genes2pep.rb +33 -0
- data/sample/genes2tab.rb +81 -0
- data/sample/genome2rb.rb +29 -0
- data/sample/genome2tab.rb +76 -0
- data/sample/goslim.rb +303 -0
- data/sample/gt2fasta.rb +47 -0
- data/sample/na2aa.rb +34 -0
- data/sample/pmfetch.rb +42 -0
- data/sample/pmsearch.rb +42 -0
- data/sample/psortplot_html.rb +214 -0
- data/sample/ssearch2tab.rb +96 -0
- data/sample/tdiary.rb +158 -0
- data/sample/tfastx2tab.rb +100 -0
- data/sample/vs-genes.rb +212 -0
- data/setup.rb +1596 -0
- data/test/data/HMMER/hmmpfam.out +64 -0
- data/test/data/HMMER/hmmsearch.out +88 -0
- data/test/data/SOSUI/sample.report +11 -0
- data/test/data/TMHMM/sample.report +21 -0
- data/test/data/aaindex/DAYM780301 +30 -0
- data/test/data/aaindex/PRAM900102 +20 -0
- data/test/data/bl2seq/cd8a_cd8b_blastp.bl2seq +53 -0
- data/test/data/bl2seq/cd8a_p53_e-5blastp.bl2seq +37 -0
- data/test/data/blast/2.2.15.blastp.m7 +876 -0
- data/test/data/blast/b0002.faa +15 -0
- data/test/data/blast/b0002.faa.m0 +128 -0
- data/test/data/blast/b0002.faa.m7 +65 -0
- data/test/data/blast/b0002.faa.m8 +1 -0
- data/test/data/blast/blastp-multi.m7 +188 -0
- data/test/data/command/echoarg2.bat +1 -0
- data/test/data/embl/AB090716.embl +65 -0
- data/test/data/embl/AB090716.embl.rel89 +63 -0
- data/test/data/fasta/example1.txt +75 -0
- data/test/data/fasta/example2.txt +21 -0
- data/test/data/genscan/sample.report +63 -0
- data/test/data/iprscan/merged.raw +32 -0
- data/test/data/iprscan/merged.txt +74 -0
- data/test/data/paml/codeml/control_file.txt +30 -0
- data/test/data/paml/codeml/output.txt +78 -0
- data/test/data/paml/codeml/rates +217 -0
- data/test/data/prosite/prosite.dat +2233 -0
- data/test/data/refseq/nm_126355.entret +64 -0
- data/test/data/rpsblast/misc.rpsblast +193 -0
- data/test/data/soft/GDS100_partial.soft +92 -0
- data/test/data/soft/GSE3457_family_partial.soft +874 -0
- data/test/data/uniprot/p53_human.uniprot +1456 -0
- data/test/functional/bio/appl/test_pts1.rb +115 -0
- data/test/functional/bio/io/test_ensembl.rb +229 -0
- data/test/functional/bio/io/test_soapwsdl.rb +52 -0
- data/test/functional/bio/sequence/test_output_embl.rb +51 -0
- data/test/functional/bio/test_command.rb +301 -0
- data/test/runner.rb +23 -0
- data/test/unit/bio/appl/bl2seq/test_report.rb +134 -0
- data/test/unit/bio/appl/blast/test_ncbioptions.rb +112 -0
- data/test/unit/bio/appl/blast/test_report.rb +1135 -0
- data/test/unit/bio/appl/blast/test_rpsblast.rb +398 -0
- data/test/unit/bio/appl/genscan/test_report.rb +182 -0
- data/test/unit/bio/appl/hmmer/test_report.rb +342 -0
- data/test/unit/bio/appl/iprscan/test_report.rb +338 -0
- data/test/unit/bio/appl/mafft/test_report.rb +63 -0
- data/test/unit/bio/appl/paml/codeml/test_rates.rb +45 -0
- data/test/unit/bio/appl/paml/codeml/test_report.rb +45 -0
- data/test/unit/bio/appl/paml/test_codeml.rb +174 -0
- data/test/unit/bio/appl/sosui/test_report.rb +81 -0
- data/test/unit/bio/appl/targetp/test_report.rb +146 -0
- data/test/unit/bio/appl/test_blast.rb +277 -0
- data/test/unit/bio/appl/test_fasta.rb +130 -0
- data/test/unit/bio/appl/test_pts1.rb +77 -0
- data/test/unit/bio/appl/tmhmm/test_report.rb +126 -0
- data/test/unit/bio/data/test_aa.rb +90 -0
- data/test/unit/bio/data/test_codontable.rb +107 -0
- data/test/unit/bio/data/test_na.rb +80 -0
- data/test/unit/bio/db/embl/test_common.rb +117 -0
- data/test/unit/bio/db/embl/test_embl.rb +214 -0
- data/test/unit/bio/db/embl/test_embl_rel89.rb +219 -0
- data/test/unit/bio/db/embl/test_embl_to_bioseq.rb +203 -0
- data/test/unit/bio/db/embl/test_sptr.rb +1812 -0
- data/test/unit/bio/db/embl/test_uniprot.rb +31 -0
- data/test/unit/bio/db/kegg/test_genes.rb +45 -0
- data/test/unit/bio/db/pdb/test_pdb.rb +152 -0
- data/test/unit/bio/db/test_aaindex.rb +197 -0
- data/test/unit/bio/db/test_fasta.rb +250 -0
- data/test/unit/bio/db/test_gff.rb +1190 -0
- data/test/unit/bio/db/test_lasergene.rb +95 -0
- data/test/unit/bio/db/test_medline.rb +127 -0
- data/test/unit/bio/db/test_newick.rb +293 -0
- data/test/unit/bio/db/test_nexus.rb +364 -0
- data/test/unit/bio/db/test_prosite.rb +1437 -0
- data/test/unit/bio/db/test_rebase.rb +101 -0
- data/test/unit/bio/db/test_soft.rb +138 -0
- data/test/unit/bio/io/flatfile/test_autodetection.rb +375 -0
- data/test/unit/bio/io/flatfile/test_buffer.rb +251 -0
- data/test/unit/bio/io/flatfile/test_splitter.rb +369 -0
- data/test/unit/bio/io/test_ddbjxml.rb +80 -0
- data/test/unit/bio/io/test_ensembl.rb +109 -0
- data/test/unit/bio/io/test_fastacmd.rb +42 -0
- data/test/unit/bio/io/test_flatfile.rb +488 -0
- data/test/unit/bio/io/test_soapwsdl.rb +32 -0
- data/test/unit/bio/sequence/test_aa.rb +103 -0
- data/test/unit/bio/sequence/test_common.rb +373 -0
- data/test/unit/bio/sequence/test_compat.rb +69 -0
- data/test/unit/bio/sequence/test_dblink.rb +58 -0
- data/test/unit/bio/sequence/test_na.rb +330 -0
- data/test/unit/bio/shell/plugin/test_seq.rb +185 -0
- data/test/unit/bio/test_alignment.rb +1025 -0
- data/test/unit/bio/test_command.rb +349 -0
- data/test/unit/bio/test_db.rb +96 -0
- data/test/unit/bio/test_feature.rb +144 -0
- data/test/unit/bio/test_location.rb +599 -0
- data/test/unit/bio/test_map.rb +230 -0
- data/test/unit/bio/test_pathway.rb +499 -0
- data/test/unit/bio/test_reference.rb +252 -0
- data/test/unit/bio/test_sequence.rb +329 -0
- data/test/unit/bio/test_shell.rb +18 -0
- data/test/unit/bio/test_tree.rb +593 -0
- data/test/unit/bio/util/restriction_enzyme/analysis/test_calculated_cuts.rb +299 -0
- data/test/unit/bio/util/restriction_enzyme/analysis/test_cut_ranges.rb +103 -0
- data/test/unit/bio/util/restriction_enzyme/analysis/test_sequence_range.rb +240 -0
- data/test/unit/bio/util/restriction_enzyme/double_stranded/test_aligned_strands.rb +101 -0
- data/test/unit/bio/util/restriction_enzyme/double_stranded/test_cut_location_pair.rb +75 -0
- data/test/unit/bio/util/restriction_enzyme/double_stranded/test_cut_location_pair_in_enzyme_notation.rb +73 -0
- data/test/unit/bio/util/restriction_enzyme/double_stranded/test_cut_locations.rb +53 -0
- data/test/unit/bio/util/restriction_enzyme/double_stranded/test_cut_locations_in_enzyme_notation.rb +104 -0
- data/test/unit/bio/util/restriction_enzyme/single_strand/test_cut_locations_in_enzyme_notation.rb +83 -0
- data/test/unit/bio/util/restriction_enzyme/test_analysis.rb +246 -0
- data/test/unit/bio/util/restriction_enzyme/test_cut_symbol.rb +44 -0
- data/test/unit/bio/util/restriction_enzyme/test_double_stranded.rb +115 -0
- data/test/unit/bio/util/restriction_enzyme/test_single_strand.rb +147 -0
- data/test/unit/bio/util/restriction_enzyme/test_single_strand_complement.rb +147 -0
- data/test/unit/bio/util/restriction_enzyme/test_string_formatting.rb +60 -0
- data/test/unit/bio/util/test_color_scheme.rb +33 -0
- data/test/unit/bio/util/test_contingency_table.rb +94 -0
- data/test/unit/bio/util/test_restriction_enzyme.rb +42 -0
- data/test/unit/bio/util/test_sirna.rb +245 -0
- metadata +484 -0
@@ -0,0 +1,370 @@
|
|
1
|
+
#
|
2
|
+
# bio/util/contingency_table.rb - Statistical contingency table analysis for aligned sequences
|
3
|
+
#
|
4
|
+
# Author:: Trevor Wennblom <mailto:trevor@corevx.com>
|
5
|
+
# Copyright:: Copyright (c) 2005-2007 Midwinter Laboratories, LLC (http://midwinterlabs.com)
|
6
|
+
# License:: The Ruby License
|
7
|
+
#
|
8
|
+
# $Id: contingency_table.rb,v 1.7 2007/04/05 23:35:41 trevor Exp $
|
9
|
+
#
|
10
|
+
|
11
|
+
module Bio #:nodoc:
|
12
|
+
|
13
|
+
#
|
14
|
+
# bio/util/contingency_table.rb - Statistical contingency table analysis for aligned sequences
|
15
|
+
#
|
16
|
+
# Author:: Trevor Wennblom <mailto:trevor@corevx.com>
|
17
|
+
# Copyright:: Copyright (c) 2005-2007 Midwinter Laboratories, LLC (http://midwinterlabs.com)
|
18
|
+
# License:: The Ruby License
|
19
|
+
#
|
20
|
+
# = Description
|
21
|
+
#
|
22
|
+
# The Bio::ContingencyTable class provides basic statistical contingency table
|
23
|
+
# analysis for two positions within aligned sequences.
|
24
|
+
#
|
25
|
+
# When ContingencyTable is instantiated the set of characters in the
|
26
|
+
# aligned sequences may be passed to it as an array. This is
|
27
|
+
# important since it uses these characters to create the table's rows
|
28
|
+
# and columns. If this array is not passed it will use it's default
|
29
|
+
# of an amino acid and nucleotide alphabet in lowercase along with the
|
30
|
+
# clustal spacer '-'.
|
31
|
+
#
|
32
|
+
# To get data from the table the most used functions will be
|
33
|
+
# chi_square and contingency_coefficient:
|
34
|
+
#
|
35
|
+
# ctable = Bio::ContingencyTable.new()
|
36
|
+
# ctable['a']['t'] += 1
|
37
|
+
# # .. put more values into the table
|
38
|
+
# puts ctable.chi_square
|
39
|
+
# puts ctable.contingency_coefficient # between 0.0 and 1.0
|
40
|
+
#
|
41
|
+
# The contingency_coefficient represents the degree of correlation of
|
42
|
+
# change between two sequence positions in a multiple-sequence
|
43
|
+
# alignment. 0.0 indicates no correlation, 1.0 is the maximum
|
44
|
+
# correlation.
|
45
|
+
#
|
46
|
+
#
|
47
|
+
# = Further Reading
|
48
|
+
#
|
49
|
+
# * http://en.wikipedia.org/wiki/Contingency_table
|
50
|
+
# * http://www.physics.csbsju.edu/stats/exact.details.html
|
51
|
+
# * Numerical Recipes in C by Press, Flannery, Teukolsky, and Vetterling
|
52
|
+
#
|
53
|
+
# = Usage
|
54
|
+
#
|
55
|
+
# What follows is an example of ContingencyTable in typical usage
|
56
|
+
# analyzing results from a clustal alignment.
|
57
|
+
#
|
58
|
+
# require 'bio'
|
59
|
+
#
|
60
|
+
# seqs = {}
|
61
|
+
# max_length = 0
|
62
|
+
# Bio::ClustalW::Report.new( IO.read('sample.aln') ).to_a.each do |entry|
|
63
|
+
# data = entry.data.strip
|
64
|
+
# seqs[entry.definition] = data.downcase
|
65
|
+
# max_length = data.size if max_length == 0
|
66
|
+
# raise "Aligned sequences must be the same length!" unless data.size == max_length
|
67
|
+
# end
|
68
|
+
#
|
69
|
+
# VERBOSE = true
|
70
|
+
# puts "i\tj\tchi_square\tcontingency_coefficient" if VERBOSE
|
71
|
+
# correlations = {}
|
72
|
+
#
|
73
|
+
# 0.upto(max_length - 1) do |i|
|
74
|
+
# (i+1).upto(max_length - 1) do |j|
|
75
|
+
# ctable = Bio::ContingencyTable.new()
|
76
|
+
# seqs.each_value { |seq| ctable.table[ seq[i].chr ][ seq[j].chr ] += 1 }
|
77
|
+
#
|
78
|
+
# chi_square = ctable.chi_square
|
79
|
+
# contingency_coefficient = ctable.contingency_coefficient
|
80
|
+
# puts [(i+1), (j+1), chi_square, contingency_coefficient].join("\t") if VERBOSE
|
81
|
+
#
|
82
|
+
# correlations["#{i+1},#{j+1}"] = contingency_coefficient
|
83
|
+
# correlations["#{j+1},#{i+1}"] = contingency_coefficient # Both ways are accurate
|
84
|
+
# end
|
85
|
+
# end
|
86
|
+
#
|
87
|
+
# require 'yaml'
|
88
|
+
# File.new('results.yml', 'a+') { |f| f.puts correlations.to_yaml }
|
89
|
+
#
|
90
|
+
#
|
91
|
+
# = Tutorial
|
92
|
+
#
|
93
|
+
# ContingencyTable returns the statistical significance of change
|
94
|
+
# between two positions in an alignment. If you would like to see how
|
95
|
+
# every possible combination of positions in your alignment compares
|
96
|
+
# to one another you must set this up yourself. Hopefully the
|
97
|
+
# provided examples will help you get started without too much
|
98
|
+
# trouble.
|
99
|
+
#
|
100
|
+
# def lite_example(sequences, max_length, characters)
|
101
|
+
#
|
102
|
+
# %w{i j chi_square contingency_coefficient}.each { |x| print x.ljust(12) }
|
103
|
+
# puts
|
104
|
+
#
|
105
|
+
# 0.upto(max_length - 1) do |i|
|
106
|
+
# (i+1).upto(max_length - 1) do |j|
|
107
|
+
# ctable = Bio::ContingencyTable.new( characters )
|
108
|
+
# sequences.each do |seq|
|
109
|
+
# i_char = seq[i].chr
|
110
|
+
# j_char = seq[j].chr
|
111
|
+
# ctable.table[i_char][j_char] += 1
|
112
|
+
# end
|
113
|
+
# chi_square = ctable.chi_square
|
114
|
+
# contingency_coefficient = ctable.contingency_coefficient
|
115
|
+
# [(i+1), (j+1), chi_square, contingency_coefficient].each { |x| print x.to_s.ljust(12) }
|
116
|
+
# puts
|
117
|
+
# end
|
118
|
+
# end
|
119
|
+
#
|
120
|
+
# end
|
121
|
+
#
|
122
|
+
# allowed_letters = Array.new
|
123
|
+
# allowed_letters = 'abcdefghijk'.split('')
|
124
|
+
#
|
125
|
+
# seqs = Array.new
|
126
|
+
# seqs << 'abcde'
|
127
|
+
# seqs << 'abcde'
|
128
|
+
# seqs << 'aacje'
|
129
|
+
# seqs << 'aacae'
|
130
|
+
#
|
131
|
+
# length_of_every_sequence = seqs[0].size # 5 letters long
|
132
|
+
#
|
133
|
+
# lite_example(seqs, length_of_every_sequence, allowed_letters)
|
134
|
+
#
|
135
|
+
#
|
136
|
+
# Producing the following results:
|
137
|
+
#
|
138
|
+
# i j chi_square contingency_coefficient
|
139
|
+
# 1 2 0.0 0.0
|
140
|
+
# 1 3 0.0 0.0
|
141
|
+
# 1 4 0.0 0.0
|
142
|
+
# 1 5 0.0 0.0
|
143
|
+
# 2 3 0.0 0.0
|
144
|
+
# 2 4 4.0 0.707106781186548
|
145
|
+
# 2 5 0.0 0.0
|
146
|
+
# 3 4 0.0 0.0
|
147
|
+
# 3 5 0.0 0.0
|
148
|
+
# 4 5 0.0 0.0
|
149
|
+
#
|
150
|
+
# The position i=2 and j=4 has a high contingency coefficient
|
151
|
+
# indicating that the changes at these positions are related. Note
|
152
|
+
# that i and j are arbitrary, this could be represented as i=4 and j=2
|
153
|
+
# since they both refer to position two and position four in the
|
154
|
+
# alignment. Here are some more examples:
|
155
|
+
#
|
156
|
+
# seqs = Array.new
|
157
|
+
# seqs << 'abcde'
|
158
|
+
# seqs << 'abcde'
|
159
|
+
# seqs << 'aacje'
|
160
|
+
# seqs << 'aacae'
|
161
|
+
# seqs << 'akcfe'
|
162
|
+
# seqs << 'akcfe'
|
163
|
+
#
|
164
|
+
# length_of_every_sequence = seqs[0].size # 5 letters long
|
165
|
+
#
|
166
|
+
# lite_example(seqs, length_of_every_sequence, allowed_letters)
|
167
|
+
#
|
168
|
+
#
|
169
|
+
# Results:
|
170
|
+
#
|
171
|
+
# i j chi_square contingency_coefficient
|
172
|
+
# 1 2 0.0 0.0
|
173
|
+
# 1 3 0.0 0.0
|
174
|
+
# 1 4 0.0 0.0
|
175
|
+
# 1 5 0.0 0.0
|
176
|
+
# 2 3 0.0 0.0
|
177
|
+
# 2 4 12.0 0.816496580927726
|
178
|
+
# 2 5 0.0 0.0
|
179
|
+
# 3 4 0.0 0.0
|
180
|
+
# 3 5 0.0 0.0
|
181
|
+
# 4 5 0.0 0.0
|
182
|
+
#
|
183
|
+
# Here we can see that the strength of the correlation of change has
|
184
|
+
# increased when more data is added with correlated changes at the
|
185
|
+
# same positions.
|
186
|
+
#
|
187
|
+
# seqs = Array.new
|
188
|
+
# seqs << 'abcde'
|
189
|
+
# seqs << 'abcde'
|
190
|
+
# seqs << 'kacje' # changed first letter
|
191
|
+
# seqs << 'aacae'
|
192
|
+
# seqs << 'akcfa' # changed last letter
|
193
|
+
# seqs << 'akcfe'
|
194
|
+
#
|
195
|
+
# length_of_every_sequence = seqs[0].size # 5 letters long
|
196
|
+
#
|
197
|
+
# lite_example(seqs, length_of_every_sequence, allowed_letters)
|
198
|
+
#
|
199
|
+
#
|
200
|
+
# Results:
|
201
|
+
#
|
202
|
+
# i j chi_square contingency_coefficient
|
203
|
+
# 1 2 2.4 0.534522483824849
|
204
|
+
# 1 3 0.0 0.0
|
205
|
+
# 1 4 6.0 0.707106781186548
|
206
|
+
# 1 5 0.24 0.196116135138184
|
207
|
+
# 2 3 0.0 0.0
|
208
|
+
# 2 4 12.0 0.816496580927726
|
209
|
+
# 2 5 2.4 0.534522483824849
|
210
|
+
# 3 4 0.0 0.0
|
211
|
+
# 3 5 0.0 0.0
|
212
|
+
# 4 5 2.4 0.534522483824849
|
213
|
+
#
|
214
|
+
# With random changes it becomes more difficult to identify correlated
|
215
|
+
# changes, yet positions two and four still have the highest
|
216
|
+
# correlation as indicated by the contingency coefficient. The best
|
217
|
+
# way to improve the accuracy of your results, as is often the case
|
218
|
+
# with statistics, is to increase the sample size.
|
219
|
+
#
|
220
|
+
#
|
221
|
+
# = A Note on Efficiency
|
222
|
+
#
|
223
|
+
# ContingencyTable is slow. It involves many calculations for even a
|
224
|
+
# seemingly small five-string data set. Even worse, it's very
|
225
|
+
# dependent on matrix traversal, and this is done with two dimensional
|
226
|
+
# hashes which dashes any hope of decent speed.
|
227
|
+
#
|
228
|
+
# Finally, half of the matrix is redundant and positions could be
|
229
|
+
# summed with their companion position to reduce calculations. For
|
230
|
+
# example the positions (5,2) and (2,5) could both have their values
|
231
|
+
# added together and just stored in (2,5) while (5,2) could be an
|
232
|
+
# illegal position. Also, positions (1,1), (2,2), (3,3), etc. will
|
233
|
+
# never be used.
|
234
|
+
#
|
235
|
+
# The purpose of this package is flexibility and education. The code
|
236
|
+
# is short and to the point in aims of achieving that purpose. If the
|
237
|
+
# BioRuby project moves towards C extensions in the future a
|
238
|
+
# professional caliber version will likely be created.
|
239
|
+
#
|
240
|
+
|
241
|
+
class ContingencyTable
|
242
|
+
# Since we're making this math-notation friendly here is the layout of @table:
|
243
|
+
# * @table[row][column]
|
244
|
+
# * @table[i][j]
|
245
|
+
# * @table[y][x]
|
246
|
+
attr_accessor :table
|
247
|
+
attr_reader :characters
|
248
|
+
|
249
|
+
# Create a ContingencyTable that has characters_in_sequence.size rows and
|
250
|
+
# characters_in_sequence.size columns for each row
|
251
|
+
#
|
252
|
+
# ---
|
253
|
+
# *Arguments*
|
254
|
+
# * +characters_in_sequences+: (_optional_) The allowable characters that will be present in the aligned sequences.
|
255
|
+
# *Returns*:: +ContingencyTable+ object to be filled with values and calculated upon
|
256
|
+
def initialize(characters_in_sequences = nil)
|
257
|
+
@characters = ( characters_in_sequences or %w{a c d e f g h i k l m n p q r s t v w y - x u} )
|
258
|
+
tmp = Hash[*@characters.collect { |v| [v, 0] }.flatten]
|
259
|
+
@table = Hash[*@characters.collect { |v| [v, tmp.dup] }.flatten]
|
260
|
+
end
|
261
|
+
|
262
|
+
# Report the sum of all values in a given row
|
263
|
+
#
|
264
|
+
# ---
|
265
|
+
# *Arguments*
|
266
|
+
# * +i+: Row to sum
|
267
|
+
# *Returns*:: +Integer+ sum of row
|
268
|
+
def row_sum(i)
|
269
|
+
total = 0
|
270
|
+
@table[i].each { |k, v| total += v }
|
271
|
+
total
|
272
|
+
end
|
273
|
+
|
274
|
+
# Report the sum of all values in a given column
|
275
|
+
#
|
276
|
+
# ---
|
277
|
+
# *Arguments*
|
278
|
+
# * +j+: Column to sum
|
279
|
+
# *Returns*:: +Integer+ sum of column
|
280
|
+
def column_sum(j)
|
281
|
+
total = 0
|
282
|
+
@table.each { |row_key, column| total += column[j] }
|
283
|
+
total
|
284
|
+
end
|
285
|
+
|
286
|
+
# Report the sum of all values in all columns.
|
287
|
+
#
|
288
|
+
# * This is the same thing as asking for the sum of all values in the table.
|
289
|
+
#
|
290
|
+
# ---
|
291
|
+
# *Arguments*
|
292
|
+
# * _none_
|
293
|
+
# *Returns*:: +Integer+ sum of all columns
|
294
|
+
def column_sum_all
|
295
|
+
total = 0
|
296
|
+
@characters.each { |j| total += column_sum(j) }
|
297
|
+
total
|
298
|
+
end
|
299
|
+
|
300
|
+
# Report the sum of all values in all rows.
|
301
|
+
#
|
302
|
+
# * This is the same thing as asking for the sum of all values in the table.
|
303
|
+
#
|
304
|
+
# ---
|
305
|
+
# *Arguments*
|
306
|
+
# * _none_
|
307
|
+
# *Returns*:: +Integer+ sum of all rows
|
308
|
+
def row_sum_all
|
309
|
+
total = 0
|
310
|
+
@characters.each { |i| total += row_sum(i) }
|
311
|
+
total
|
312
|
+
end
|
313
|
+
alias table_sum_all row_sum_all
|
314
|
+
|
315
|
+
# Calculate _e_, the _expected_ value.
|
316
|
+
#
|
317
|
+
# ---
|
318
|
+
# *Arguments*
|
319
|
+
# * +i+: row
|
320
|
+
# * +j+: column
|
321
|
+
# *Returns*:: +Float+ e(sub:ij) = (r(sub:i)/N) * (c(sub:j))
|
322
|
+
def expected(i, j)
|
323
|
+
(row_sum(i).to_f / table_sum_all) * column_sum(j)
|
324
|
+
end
|
325
|
+
|
326
|
+
# Report the chi square of the entire table
|
327
|
+
#
|
328
|
+
# ---
|
329
|
+
# *Arguments*
|
330
|
+
# * _none_
|
331
|
+
# *Returns*:: +Float+ chi square value
|
332
|
+
def chi_square
|
333
|
+
total = 0
|
334
|
+
c = @characters
|
335
|
+
max = c.size - 1
|
336
|
+
@characters.each do |i| # Loop through every row in the ContingencyTable
|
337
|
+
@characters.each do |j| # Loop through every column in the ContingencyTable
|
338
|
+
total += chi_square_element(i, j)
|
339
|
+
end
|
340
|
+
end
|
341
|
+
total
|
342
|
+
end
|
343
|
+
|
344
|
+
# Report the chi-square relation of two elements in the table
|
345
|
+
#
|
346
|
+
# ---
|
347
|
+
# *Arguments*
|
348
|
+
# * +i+: row
|
349
|
+
# * +j+: column
|
350
|
+
# *Returns*:: +Float+ chi-square of an intersection
|
351
|
+
def chi_square_element(i, j)
|
352
|
+
eij = expected(i, j)
|
353
|
+
return 0 if eij == 0
|
354
|
+
( @table[i][j] - eij )**2 / eij
|
355
|
+
end
|
356
|
+
|
357
|
+
# Report the contingency coefficient of the table
|
358
|
+
#
|
359
|
+
# ---
|
360
|
+
# *Arguments*
|
361
|
+
# * _none_
|
362
|
+
# *Returns*:: +Float+ contingency_coefficient of the table
|
363
|
+
def contingency_coefficient
|
364
|
+
c_s = chi_square
|
365
|
+
Math.sqrt(c_s / (table_sum_all + c_s) )
|
366
|
+
end
|
367
|
+
|
368
|
+
end # ContingencyTable
|
369
|
+
end # Bio
|
370
|
+
|
@@ -0,0 +1,249 @@
|
|
1
|
+
#
|
2
|
+
# bio/util/restriction_enzyme/analysis.rb - Does the work of fragmenting the DNA from the enzymes
|
3
|
+
#
|
4
|
+
# Author:: Trevor Wennblom <mailto:trevor@corevx.com>
|
5
|
+
# Copyright:: Copyright (c) 2005-2007 Midwinter Laboratories, LLC (http://midwinterlabs.com)
|
6
|
+
# License:: The Ruby License
|
7
|
+
#
|
8
|
+
# $Id: analysis.rb,v 1.20 2007/07/16 19:28:48 k Exp $
|
9
|
+
#
|
10
|
+
|
11
|
+
require 'bio/util/restriction_enzyme'
|
12
|
+
require 'bio/util/restriction_enzyme/analysis_basic'
|
13
|
+
|
14
|
+
module Bio
|
15
|
+
class RestrictionEnzyme
|
16
|
+
|
17
|
+
class Analysis
|
18
|
+
|
19
|
+
# See cut instance method
|
20
|
+
def self.cut( sequence, *args )
|
21
|
+
self.new.cut( sequence, *args )
|
22
|
+
end
|
23
|
+
|
24
|
+
# See main documentation for Bio::RestrictionEnzyme
|
25
|
+
#
|
26
|
+
#
|
27
|
+
# +cut+ takes into account
|
28
|
+
# permutations of cut variations based on competitiveness of enzymes for an
|
29
|
+
# enzyme cutsite or enzyme bindsite on a sequence.
|
30
|
+
#
|
31
|
+
# Example:
|
32
|
+
#
|
33
|
+
# FIXME add output
|
34
|
+
#
|
35
|
+
# Bio::RestrictionEnzyme::Analysis.cut('gaattc', 'EcoRI')
|
36
|
+
#
|
37
|
+
# _same as:_
|
38
|
+
#
|
39
|
+
# Bio::RestrictionEnzyme::Analysis.cut('gaattc', 'g^aattc')
|
40
|
+
# ---
|
41
|
+
# *Arguments*
|
42
|
+
# * +sequence+: +String+ kind of object that will be used as a nucleic acid sequence.
|
43
|
+
# * +args+: Series of enzyme names, enzymes sequences with cut marks, or RestrictionEnzyme objects.
|
44
|
+
# *Returns*:: Bio::RestrictionEnzyme::Fragments object populated with Bio::RestrictionEnzyme::Fragment objects. (Note: unrelated to Bio::RestrictionEnzyme::Range::SequenceRange::Fragments) or a +Symbol+ containing an error code
|
45
|
+
def cut( sequence, *args )
|
46
|
+
view_ranges = false
|
47
|
+
|
48
|
+
args.select { |i| i.class == Hash }.each do |hsh|
|
49
|
+
hsh.each do |key, value|
|
50
|
+
if key == :view_ranges
|
51
|
+
unless ( value.kind_of?(TrueClass) or value.kind_of?(FalseClass) )
|
52
|
+
raise ArgumentError, "view_ranges must be set to true or false, currently #{value.inspect}."
|
53
|
+
end
|
54
|
+
view_ranges = value
|
55
|
+
end
|
56
|
+
end
|
57
|
+
end
|
58
|
+
|
59
|
+
res = cut_and_return_by_permutations( sequence, *args )
|
60
|
+
return res if res.class == Symbol
|
61
|
+
# Format the fragments for the user
|
62
|
+
fragments_for_display( res, view_ranges )
|
63
|
+
end
|
64
|
+
|
65
|
+
#########
|
66
|
+
protected
|
67
|
+
#########
|
68
|
+
|
69
|
+
# See cut instance method
|
70
|
+
#
|
71
|
+
# ---
|
72
|
+
# *Arguments*
|
73
|
+
# * +sequence+: +String+ kind of object that will be used as a nucleic acid sequence.
|
74
|
+
# * +args+: Series of enzyme names, enzymes sequences with cut marks, or RestrictionEnzyme objects.
|
75
|
+
# May also supply a +Hash+ with the key ":max_permutations" to specificy how many permutations are allowed - a value of 0 indicates no permutations are allowed.
|
76
|
+
# *Returns*:: +Hash+ Keys are a permutation ID, values are SequenceRange objects that have cuts applied.
|
77
|
+
# _also_ may return the +Symbol+ ':sequence_empty', ':no_cuts_found', or ':too_many_permutations'
|
78
|
+
def cut_and_return_by_permutations( sequence, *args )
|
79
|
+
my_hash = {}
|
80
|
+
maximum_permutations = nil
|
81
|
+
|
82
|
+
hashes_in_args = args.select { |i| i.class == Hash }
|
83
|
+
args.delete_if { |i| i.class == Hash }
|
84
|
+
hashes_in_args.each do |hsh|
|
85
|
+
hsh.each do |key, value|
|
86
|
+
case key
|
87
|
+
when :max_permutations, 'max_permutations', :maximum_permutations, 'maximum_permutations'
|
88
|
+
maximum_permutations = value.to_i unless value == nil
|
89
|
+
when :view_ranges
|
90
|
+
else
|
91
|
+
raise ArgumentError, "Received key #{key.inspect} in argument - I only know the key ':max_permutations' and ':view_ranges' currently. Hash passed: #{hsh.inspect}"
|
92
|
+
end
|
93
|
+
end
|
94
|
+
end
|
95
|
+
|
96
|
+
if !sequence.kind_of?(String) or sequence.empty?
|
97
|
+
logger.warn "The supplied sequence is empty." if defined?(logger)
|
98
|
+
return :sequence_empty
|
99
|
+
end
|
100
|
+
sequence = Bio::Sequence::NA.new( sequence )
|
101
|
+
|
102
|
+
enzyme_actions, initial_cuts = create_enzyme_actions( sequence, *args )
|
103
|
+
|
104
|
+
if enzyme_actions.empty? and initial_cuts.empty?
|
105
|
+
logger.warn "This enzyme does not make any cuts on this sequence." if defined?(logger)
|
106
|
+
return :no_cuts_found
|
107
|
+
end
|
108
|
+
|
109
|
+
# * When enzyme_actions.size is equal to '1' that means there are no permutations.
|
110
|
+
# * If enzyme_actions.size is equal to '2' there is one
|
111
|
+
# permutation ("[0, 1]")
|
112
|
+
# * If enzyme_actions.size is equal to '3' there are two
|
113
|
+
# permutations ("[0, 1, 2]")
|
114
|
+
# * and so on..
|
115
|
+
if maximum_permutations and enzyme_actions.size > 1
|
116
|
+
if (enzyme_actions.size - 1) > maximum_permutations.to_i
|
117
|
+
logger.warn "More permutations than maximum, skipping. Found: #{enzyme_actions.size-1} Max: #{maximum_permutations.to_i}" if defined?(logger)
|
118
|
+
return :too_many_permutations
|
119
|
+
end
|
120
|
+
end
|
121
|
+
|
122
|
+
if enzyme_actions.size > 1
|
123
|
+
permutations = permute(enzyme_actions.size)
|
124
|
+
|
125
|
+
permutations.each do |permutation|
|
126
|
+
previous_cut_ranges = []
|
127
|
+
# Primary and complement strands are both measured from '0' to 'sequence.size-1' here
|
128
|
+
sequence_range = Bio::RestrictionEnzyme::Range::SequenceRange.new( 0, 0, sequence.size-1, sequence.size-1 )
|
129
|
+
|
130
|
+
# Add the cuts to the sequence_range from each enzyme_action contained
|
131
|
+
# in initial_cuts. These are the cuts that have no competition so are
|
132
|
+
# not subject to permutations.
|
133
|
+
initial_cuts.each do |enzyme_action|
|
134
|
+
enzyme_action.cut_ranges.each do |cut_range|
|
135
|
+
sequence_range.add_cut_range(cut_range)
|
136
|
+
end
|
137
|
+
end
|
138
|
+
|
139
|
+
permutation.each do |id|
|
140
|
+
enzyme_action = enzyme_actions[id]
|
141
|
+
|
142
|
+
# conflict is false if the current enzyme action may cut in it's range.
|
143
|
+
# conflict is true if it cannot due to a previous enzyme action making
|
144
|
+
# a cut where this enzyme action needs a whole recognition site.
|
145
|
+
conflict = false
|
146
|
+
|
147
|
+
# If current size of enzyme_action overlaps with previous cut_range, don't cut
|
148
|
+
# note that the enzyme action may fall in the middle of a previous enzyme action
|
149
|
+
# so all cut locations must be checked that would fall underneath.
|
150
|
+
previous_cut_ranges.each do |cut_range|
|
151
|
+
next unless cut_range.class == Bio::RestrictionEnzyme::Range::VerticalCutRange # we aren't concerned with horizontal cuts
|
152
|
+
previous_cut_left = cut_range.range.first
|
153
|
+
previous_cut_right = cut_range.range.last
|
154
|
+
|
155
|
+
# Keep in mind:
|
156
|
+
# * The cut location is to the immediate right of the base located at the index.
|
157
|
+
# ex: at^gc -- the cut location is at index 1
|
158
|
+
# * The enzyme action location is located at the base of the index.
|
159
|
+
# ex: atgc -- 0 => 'a', 1 => 't', 2 => 'g', 3 => 'c'
|
160
|
+
# method create_enzyme_actions has similar commentary if interested
|
161
|
+
if (enzyme_action.right <= previous_cut_left) or
|
162
|
+
(enzyme_action.left > previous_cut_right) or
|
163
|
+
(enzyme_action.left > previous_cut_left and enzyme_action.right <= previous_cut_right) # in between cuts
|
164
|
+
# no conflict
|
165
|
+
else
|
166
|
+
conflict = true
|
167
|
+
end
|
168
|
+
end
|
169
|
+
|
170
|
+
next if conflict == true
|
171
|
+
enzyme_action.cut_ranges.each { |cut_range| sequence_range.add_cut_range(cut_range) }
|
172
|
+
previous_cut_ranges += enzyme_action.cut_ranges
|
173
|
+
end # permutation.each
|
174
|
+
|
175
|
+
# Fill in the source sequence for sequence_range so it knows what bases
|
176
|
+
# to use
|
177
|
+
sequence_range.fragments.primary = sequence
|
178
|
+
sequence_range.fragments.complement = sequence.forward_complement
|
179
|
+
my_hash[permutation] = sequence_range
|
180
|
+
end # permutations.each
|
181
|
+
|
182
|
+
else # if enzyme_actions.size == 1
|
183
|
+
# no permutations, just do it
|
184
|
+
sequence_range = Bio::RestrictionEnzyme::Range::SequenceRange.new( 0, 0, sequence.size-1, sequence.size-1 )
|
185
|
+
initial_cuts.each { |enzyme_action| enzyme_action.cut_ranges.each { |cut_range| sequence_range.add_cut_range(cut_range) } }
|
186
|
+
sequence_range.fragments.primary = sequence
|
187
|
+
sequence_range.fragments.complement = sequence.forward_complement
|
188
|
+
my_hash[0] = sequence_range
|
189
|
+
end
|
190
|
+
|
191
|
+
my_hash
|
192
|
+
end
|
193
|
+
|
194
|
+
|
195
|
+
# Returns permutation orders for a given number of elements.
|
196
|
+
#
|
197
|
+
# Examples:
|
198
|
+
# permute(0) # => [[0]]
|
199
|
+
# permute(1) # => [[0]]
|
200
|
+
# permute(2) # => [[1, 0], [0, 1]]
|
201
|
+
# permute(3) # => [[2, 1, 0], [2, 0, 1], [1, 2, 0], [0, 2, 1], [1, 0, 2], [0, 1, 2]]
|
202
|
+
# permute(4) # => [[3, 2, 1, 0],
|
203
|
+
# [3, 2, 0, 1],
|
204
|
+
# [3, 1, 2, 0],
|
205
|
+
# [3, 0, 2, 1],
|
206
|
+
# [3, 1, 0, 2],
|
207
|
+
# [3, 0, 1, 2],
|
208
|
+
# [2, 3, 1, 0],
|
209
|
+
# [2, 3, 0, 1],
|
210
|
+
# [1, 3, 2, 0],
|
211
|
+
# [0, 3, 2, 1],
|
212
|
+
# [1, 3, 0, 2],
|
213
|
+
# [0, 3, 1, 2],
|
214
|
+
# [2, 1, 3, 0],
|
215
|
+
# [2, 0, 3, 1],
|
216
|
+
# [1, 2, 3, 0],
|
217
|
+
# [0, 2, 3, 1],
|
218
|
+
# [1, 0, 3, 2],
|
219
|
+
# [0, 1, 3, 2],
|
220
|
+
# [2, 1, 0, 3],
|
221
|
+
# [2, 0, 1, 3],
|
222
|
+
# [1, 2, 0, 3],
|
223
|
+
# [0, 2, 1, 3],
|
224
|
+
# [1, 0, 2, 3],
|
225
|
+
# [0, 1, 2, 3]]
|
226
|
+
#
|
227
|
+
# ---
|
228
|
+
# *Arguments*
|
229
|
+
# * +count+: +Number+ of different elements to be permuted
|
230
|
+
# * +permutations+: ignore - for the recursive algorithm
|
231
|
+
# *Returns*:: +Array+ of +Array+ objects with different possible permutation orders. See examples.
|
232
|
+
def permute(count, permutations = [[0]])
|
233
|
+
return permutations if count <= 1
|
234
|
+
new_arrays = []
|
235
|
+
new_array = []
|
236
|
+
|
237
|
+
(permutations[0].size + 1).times do |n|
|
238
|
+
new_array.clear
|
239
|
+
permutations.each { |a| new_array << a.dup }
|
240
|
+
new_array.each { |e| e.insert(n, permutations[0].size) }
|
241
|
+
new_arrays += new_array
|
242
|
+
end
|
243
|
+
|
244
|
+
permute(count-1, new_arrays)
|
245
|
+
end
|
246
|
+
|
247
|
+
end # Analysis
|
248
|
+
end # RestrictionEnzyme
|
249
|
+
end # Bio
|