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 +1,357 @@
|
|
1
|
+
#
|
2
|
+
# = bio/db/aaindex.rb - AAindex database class
|
3
|
+
#
|
4
|
+
# Copyright:: Copyright (C) 2001
|
5
|
+
# KAWASHIMA Shuichi <s@bioruby.org>
|
6
|
+
# Copyright:: Copyright (C) 2006
|
7
|
+
# Mitsuteru C. Nakao <n@bioruby.org>
|
8
|
+
# License:: The Ruby License
|
9
|
+
#
|
10
|
+
# $Id: aaindex.rb,v 1.20 2007/04/05 23:35:40 trevor Exp $
|
11
|
+
#
|
12
|
+
# == Description
|
13
|
+
#
|
14
|
+
# Classes for Amino Acid Index Database (AAindex and AAindex2).
|
15
|
+
# * AAindex Manual: http://www.genome.jp/dbget-bin/show_man?aaindex
|
16
|
+
#
|
17
|
+
# == Examples
|
18
|
+
#
|
19
|
+
# aax1 = Bio::AAindex.auto("PRAM900102.aaindex1")
|
20
|
+
# aax2 = Bio::AAindex.auto("DAYM780301.aaindex2")
|
21
|
+
#
|
22
|
+
# aax1 = Bio::AAindex1.new("PRAM900102.aaindex1")
|
23
|
+
# aax1.entry_id
|
24
|
+
# aax1.index
|
25
|
+
#
|
26
|
+
# aax2 = Bio::AAindex2.new("DAYM780301.aaindex2")
|
27
|
+
# aax2.entry_id
|
28
|
+
# aax2.matrix
|
29
|
+
# aax2.matrix[2,2]
|
30
|
+
# aax2.matrix('R', 'A')
|
31
|
+
# aax2['R', 'A']
|
32
|
+
#
|
33
|
+
# == References
|
34
|
+
#
|
35
|
+
# * http://www.genome.jp/aaindex/
|
36
|
+
#
|
37
|
+
|
38
|
+
require "bio/db"
|
39
|
+
require "matrix"
|
40
|
+
|
41
|
+
module Bio
|
42
|
+
|
43
|
+
# Super class for AAindex1 and AAindex2
|
44
|
+
class AAindex < KEGGDB
|
45
|
+
|
46
|
+
# Delimiter
|
47
|
+
DELIMITER ="\n//\n"
|
48
|
+
|
49
|
+
# Delimiter
|
50
|
+
RS = DELIMITER
|
51
|
+
|
52
|
+
# Bio::DB API
|
53
|
+
TAGSIZE = 2
|
54
|
+
|
55
|
+
# Auto detecter for two AAindex formats.
|
56
|
+
# returns a Bio::AAindex1 object or a Bio::AAindex2 object.
|
57
|
+
def self.auto(str)
|
58
|
+
case str
|
59
|
+
when /^I /m
|
60
|
+
Bio::AAindex1.new(str)
|
61
|
+
when /^M /m
|
62
|
+
Bio::AAindex2.new(str)
|
63
|
+
else
|
64
|
+
raise
|
65
|
+
end
|
66
|
+
end
|
67
|
+
|
68
|
+
#
|
69
|
+
def initialize(entry)
|
70
|
+
super(entry, TAGSIZE)
|
71
|
+
end
|
72
|
+
|
73
|
+
# Returns entry_id in the H line.
|
74
|
+
def entry_id
|
75
|
+
if @data['entry_id']
|
76
|
+
@data['entry_id']
|
77
|
+
else
|
78
|
+
@data['entry_id'] = field_fetch('H')
|
79
|
+
end
|
80
|
+
end
|
81
|
+
|
82
|
+
# Returns definition in the D line.
|
83
|
+
def definition
|
84
|
+
if @data['definition']
|
85
|
+
@data['definition']
|
86
|
+
else
|
87
|
+
@data['definition'] = field_fetch('D')
|
88
|
+
end
|
89
|
+
end
|
90
|
+
|
91
|
+
# Returns database links in the R line.
|
92
|
+
# cf.) ['LIT:123456', 'PMID:12345678']
|
93
|
+
def dblinks
|
94
|
+
if @data['ref']
|
95
|
+
@data['ref']
|
96
|
+
else
|
97
|
+
@data['ref'] = field_fetch('R').split(' ')
|
98
|
+
end
|
99
|
+
end
|
100
|
+
|
101
|
+
# Returns authors in the A line.
|
102
|
+
def author
|
103
|
+
if @data['author']
|
104
|
+
@data['author']
|
105
|
+
else
|
106
|
+
@data['author'] = field_fetch('A')
|
107
|
+
end
|
108
|
+
end
|
109
|
+
|
110
|
+
# Returns title in the T line.
|
111
|
+
def title
|
112
|
+
if @data['title']
|
113
|
+
@data['title']
|
114
|
+
else
|
115
|
+
@data['title'] = field_fetch('T')
|
116
|
+
end
|
117
|
+
end
|
118
|
+
|
119
|
+
# Returns journal name in the J line.
|
120
|
+
def journal
|
121
|
+
if @data['journal']
|
122
|
+
@data['journal']
|
123
|
+
else
|
124
|
+
@data['journal'] = field_fetch('J')
|
125
|
+
end
|
126
|
+
end
|
127
|
+
|
128
|
+
# Returns comment (if any).
|
129
|
+
def comment
|
130
|
+
if @data['comment']
|
131
|
+
@data['comment']
|
132
|
+
else
|
133
|
+
@data['comment'] = field_fetch('*')
|
134
|
+
end
|
135
|
+
end
|
136
|
+
end
|
137
|
+
|
138
|
+
|
139
|
+
# Class for AAindex1 format.
|
140
|
+
class AAindex1 < AAindex
|
141
|
+
|
142
|
+
def initialize(entry)
|
143
|
+
super(entry)
|
144
|
+
end
|
145
|
+
|
146
|
+
# Returns correlation_coefficient (Hash) in the C line.
|
147
|
+
#
|
148
|
+
# cf.) {'ABCD12010203' => 0.999, 'CDEF123456' => 0.543, ...}
|
149
|
+
def correlation_coefficient
|
150
|
+
if @data['correlation_coefficient']
|
151
|
+
@data['correlation_coefficient']
|
152
|
+
else
|
153
|
+
hash = {}
|
154
|
+
ary = field_fetch('C').split(' ')
|
155
|
+
ary.each do |x|
|
156
|
+
next unless x =~ /^[A-Z]/
|
157
|
+
hash[x] = ary[ary.index(x) + 1].to_f
|
158
|
+
end
|
159
|
+
@data['correlation_coefficient'] = hash
|
160
|
+
end
|
161
|
+
end
|
162
|
+
|
163
|
+
# Returns the index (Array) in the I line.
|
164
|
+
#
|
165
|
+
# an argument: :string, :float, :zscore or :integer
|
166
|
+
def index(type = :float)
|
167
|
+
aa = %w( A R N D C Q E G H I L K M F P S T W Y V )
|
168
|
+
values = field_fetch('I', 1).split(' ')
|
169
|
+
|
170
|
+
if values.size != 20
|
171
|
+
raise "Invalid format in #{entry_id} : #{values.inspect}"
|
172
|
+
end
|
173
|
+
|
174
|
+
if type == :zscore and values.size > 0
|
175
|
+
sum = 0.0
|
176
|
+
values.each do |a|
|
177
|
+
sum += a.to_f
|
178
|
+
end
|
179
|
+
mean = sum / values.size # / 20
|
180
|
+
var = 0.0
|
181
|
+
values.each do |a|
|
182
|
+
var += (a.to_f - mean) ** 2
|
183
|
+
end
|
184
|
+
sd = Math.sqrt(var)
|
185
|
+
end
|
186
|
+
|
187
|
+
if type == :integer
|
188
|
+
figure = 0
|
189
|
+
values.each do |a|
|
190
|
+
figure = [ figure, a[/\..*/].length - 1 ].max
|
191
|
+
end
|
192
|
+
end
|
193
|
+
|
194
|
+
hash = {}
|
195
|
+
|
196
|
+
aa.each_with_index do |a, i|
|
197
|
+
case type
|
198
|
+
when :string
|
199
|
+
hash[a] = values[i]
|
200
|
+
when :float
|
201
|
+
hash[a] = values[i].to_f
|
202
|
+
when :zscore
|
203
|
+
hash[a] = (values[i].to_f - mean) / sd
|
204
|
+
when :integer
|
205
|
+
hash[a] = (values[i].to_f * 10 ** figure).to_i
|
206
|
+
end
|
207
|
+
end
|
208
|
+
return hash
|
209
|
+
end
|
210
|
+
|
211
|
+
end
|
212
|
+
|
213
|
+
|
214
|
+
# Class for AAindex2 format.
|
215
|
+
class AAindex2 < AAindex
|
216
|
+
|
217
|
+
def initialize(entry)
|
218
|
+
super(entry)
|
219
|
+
end
|
220
|
+
|
221
|
+
# Returns row labels.
|
222
|
+
def rows
|
223
|
+
if @data['rows']
|
224
|
+
@data['rows']
|
225
|
+
else
|
226
|
+
label_data
|
227
|
+
@rows
|
228
|
+
end
|
229
|
+
end
|
230
|
+
|
231
|
+
# Returns col labels.
|
232
|
+
def cols
|
233
|
+
if @data['cols']
|
234
|
+
@data['cols']
|
235
|
+
else
|
236
|
+
label_data
|
237
|
+
@cols
|
238
|
+
end
|
239
|
+
end
|
240
|
+
|
241
|
+
# Returns the value of amino acids substitution (aa1 -> aa2).
|
242
|
+
def [](aa1 = nil, aa2 = nil)
|
243
|
+
matrix[cols.index(aa1), rows.index(aa2)]
|
244
|
+
end
|
245
|
+
|
246
|
+
# Returns amino acids matrix in Matrix.
|
247
|
+
def matrix(aa1 = nil, aa2 = nil)
|
248
|
+
return self[aa1, aa2] if aa1 and aa2
|
249
|
+
|
250
|
+
if @data['matrix']
|
251
|
+
@data['matrix']
|
252
|
+
else
|
253
|
+
ma = []
|
254
|
+
label_data.each_line do |line|
|
255
|
+
ma << line.strip.split(/\s+/).map {|x| x.to_f }
|
256
|
+
end
|
257
|
+
@data['matrix'] = Matrix[*ma]
|
258
|
+
end
|
259
|
+
end
|
260
|
+
|
261
|
+
# Returns amino acids matrix in Matrix for the old format (<= ver 5.0).
|
262
|
+
def old_matrix # for AAindex <= ver 5.0
|
263
|
+
return @data['matrix'] if @data['matrix']
|
264
|
+
|
265
|
+
@aa = {}
|
266
|
+
# used to determine row/column of the aa
|
267
|
+
attr_reader :aa
|
268
|
+
alias_method :aa, :rows
|
269
|
+
alias_method :aa, :cols
|
270
|
+
|
271
|
+
field = field_fetch('I')
|
272
|
+
|
273
|
+
case field
|
274
|
+
when / (ARNDCQEGHILKMFPSTWYV)\s+(.*)/ # 20x19/2 matrix
|
275
|
+
aalist = $1
|
276
|
+
values = $2.split(/\s+/)
|
277
|
+
|
278
|
+
0.upto(aalist.length - 1) do |i|
|
279
|
+
@aa[aalist[i].chr] = i
|
280
|
+
end
|
281
|
+
|
282
|
+
ma = Array.new
|
283
|
+
20.times do
|
284
|
+
ma.push(Array.new(20)) # 2D array of 20x(20)
|
285
|
+
end
|
286
|
+
|
287
|
+
for i in 0 .. 19 do
|
288
|
+
for j in i .. 19 do
|
289
|
+
ma[i][j] = values[i + j*(j+1)/2].to_f
|
290
|
+
ma[j][i] = ma[i][j]
|
291
|
+
end
|
292
|
+
end
|
293
|
+
@data['matrix'] = Matrix[*ma]
|
294
|
+
when / -ARNDCQEGHILKMFPSTWYV / # 21x20/2 matrix (with gap)
|
295
|
+
raise NotImplementedError
|
296
|
+
when / ACDEFGHIKLMNPQRSTVWYJ- / # 21x21 matrix (with gap)
|
297
|
+
raise NotImplementedError
|
298
|
+
end
|
299
|
+
end
|
300
|
+
|
301
|
+
private
|
302
|
+
|
303
|
+
def label_data
|
304
|
+
if @data['data']
|
305
|
+
@data['data']
|
306
|
+
else
|
307
|
+
label, data = get('M').split("\n", 2)
|
308
|
+
if /M rows = (\S+), cols = (\S+)/.match(label)
|
309
|
+
rows, cols = $1, $2
|
310
|
+
@rows = rows.split('')
|
311
|
+
@cols = cols.split('')
|
312
|
+
end
|
313
|
+
@data['data'] = data
|
314
|
+
end
|
315
|
+
end
|
316
|
+
|
317
|
+
end # class AAindex2
|
318
|
+
|
319
|
+
end # module Bio
|
320
|
+
|
321
|
+
|
322
|
+
if __FILE__ == $0
|
323
|
+
require 'bio/io/fetch'
|
324
|
+
|
325
|
+
puts "### AAindex1 (PRAM900102)"
|
326
|
+
aax1 = Bio::AAindex1.new(Bio::Fetch.query('aaindex', 'PRAM900102', 'raw'))
|
327
|
+
p aax1.entry_id
|
328
|
+
p aax1.definition
|
329
|
+
p aax1.dblinks
|
330
|
+
p aax1.author
|
331
|
+
p aax1.title
|
332
|
+
p aax1.journal
|
333
|
+
p aax1.comment
|
334
|
+
p aax1.correlation_coefficient
|
335
|
+
p aax1.index
|
336
|
+
p aax1
|
337
|
+
puts "### AAindex2 (DAYM780301)"
|
338
|
+
aax2 = Bio::AAindex2.new(Bio::Fetch.query('aaindex', 'DAYM780301', 'raw'))
|
339
|
+
p aax2.entry_id
|
340
|
+
p aax2.definition
|
341
|
+
p aax2.dblinks
|
342
|
+
p aax2.author
|
343
|
+
p aax2.title
|
344
|
+
p aax2.journal
|
345
|
+
p aax1.comment
|
346
|
+
p aax2.rows
|
347
|
+
p aax2.cols
|
348
|
+
p aax2.matrix
|
349
|
+
p aax2.matrix[2,2]
|
350
|
+
p aax2.matrix[2,3]
|
351
|
+
p aax2.matrix[4,3]
|
352
|
+
p aax2.matrix.determinant
|
353
|
+
p aax2.matrix.rank
|
354
|
+
p aax2.matrix.transpose
|
355
|
+
p aax2
|
356
|
+
end
|
357
|
+
|
@@ -0,0 +1,67 @@
|
|
1
|
+
#
|
2
|
+
# = bio/db/biosql/biosql_to_biosequence.rb - Bio::SQL::Sequence to Bio::Sequence adapter module
|
3
|
+
#
|
4
|
+
# Copyright:: Copyright (C) 2008
|
5
|
+
# Naohisa Goto <ng@bioruby.org>,
|
6
|
+
# Raoul Jean Pierre Bonnal
|
7
|
+
# License:: The Ruby License
|
8
|
+
#
|
9
|
+
# $Id:$
|
10
|
+
#
|
11
|
+
|
12
|
+
require 'bio/sequence'
|
13
|
+
require 'bio/sequence/adapter'
|
14
|
+
|
15
|
+
# Internal use only. Normal users should not use this module.
|
16
|
+
#
|
17
|
+
# Bio::SQL::Sequence to Bio::Sequence adapter module.
|
18
|
+
# It is internally used in Bio::SQL::Sequence#to_biosequence.
|
19
|
+
#
|
20
|
+
module Bio::Sequence::Adapter::BioSQL
|
21
|
+
|
22
|
+
extend Bio::Sequence::Adapter
|
23
|
+
|
24
|
+
private
|
25
|
+
|
26
|
+
def_biosequence_adapter :seq
|
27
|
+
|
28
|
+
def_biosequence_adapter :entry_id
|
29
|
+
|
30
|
+
def_biosequence_adapter :primary_accession
|
31
|
+
|
32
|
+
def_biosequence_adapter :secondary_accessions
|
33
|
+
|
34
|
+
def_biosequence_adapter :molecule_type
|
35
|
+
|
36
|
+
#--
|
37
|
+
#TODO: identify where is stored data_class in biosql
|
38
|
+
#++
|
39
|
+
|
40
|
+
def_biosequence_adapter :data_class
|
41
|
+
|
42
|
+
def_biosequence_adapter :definition, :description
|
43
|
+
|
44
|
+
def_biosequence_adapter :topology
|
45
|
+
|
46
|
+
def_biosequence_adapter :date_created
|
47
|
+
|
48
|
+
def_biosequence_adapter :date_modified
|
49
|
+
|
50
|
+
def_biosequence_adapter :division
|
51
|
+
|
52
|
+
def_biosequence_adapter :sequence_version
|
53
|
+
|
54
|
+
def_biosequence_adapter :keywords
|
55
|
+
|
56
|
+
def_biosequence_adapter :species
|
57
|
+
|
58
|
+
def_biosequence_adapter :classification, :taxonomy
|
59
|
+
|
60
|
+
def_biosequence_adapter :references
|
61
|
+
|
62
|
+
def_biosequence_adapter :features
|
63
|
+
|
64
|
+
def_biosequence_adapter :comments
|
65
|
+
|
66
|
+
end #module Bio::Sequence::Adapter::BioSQL
|
67
|
+
|
@@ -0,0 +1,508 @@
|
|
1
|
+
|
2
|
+
#TODO save on db reading from a genbank or embl object
|
3
|
+
module Bio
|
4
|
+
class SQL
|
5
|
+
|
6
|
+
class Sequence
|
7
|
+
private
|
8
|
+
# example
|
9
|
+
# bioentry_qualifier_anchor :molecule_type, :synonym=>'mol_type'
|
10
|
+
# this function creates other 3 functions, molecule_type, molecule_type=, molecule_type_update
|
11
|
+
#molecule_type => return an array of strings, where each string is the value associated with the qualifier, ordered by rank.
|
12
|
+
#molecule_type=value add a bioentry_qualifier value to the table
|
13
|
+
#molecule_type_update(value, rank) update an entry of the table with an existing rank
|
14
|
+
#the method inferr the qualifier term from the name of the first symbol, or you can specify a synonym to use
|
15
|
+
|
16
|
+
#creating an object with to_biosql is transaction safe.
|
17
|
+
|
18
|
+
#TODO: implement setting for more than a qualifier-vale.
|
19
|
+
def self.bioentry_qualifier_anchor(sym, *args)
|
20
|
+
options = args.first || Hash.new
|
21
|
+
#options.assert_valid_keys(:rank,:synonym,:multi)
|
22
|
+
method_reader = sym.to_s.to_sym
|
23
|
+
method_writer_operator = (sym.to_s+"=").to_sym
|
24
|
+
method_writer_modder = (sym.to_s+"_update").to_sym
|
25
|
+
synonym = options[:synonym].nil? ? sym.to_s : options[:synonym]
|
26
|
+
|
27
|
+
#Bio::SQL::Term.create(:name=>synonym, :ontology=> Bio::SQL::Ontology.find_by_name('Annotation Tags')) unless Bio::SQL::Term.exists?(:name =>synonym)
|
28
|
+
send :define_method, method_reader do
|
29
|
+
#return an array of bioentry_qualifier_values
|
30
|
+
begin
|
31
|
+
ontology_annotation_tags = Ontology.find_or_create_by_name('Annotation Tags')
|
32
|
+
term = Term.find_or_create_by_name(:name => synonym, :ontology=> ontology_annotation_tags)
|
33
|
+
bioentry_qualifier_values = @entry.bioentry_qualifier_values.find_all_by_term_id(term)
|
34
|
+
bioentry_qualifier_values.map{|row| row.value} unless bioentry_qualifier_values.nil?
|
35
|
+
rescue Exception => e
|
36
|
+
puts "Reader Error: #{synonym} #{e.message}"
|
37
|
+
end
|
38
|
+
end
|
39
|
+
|
40
|
+
send :define_method, method_writer_operator do |value|
|
41
|
+
begin
|
42
|
+
ontology_annotation_tags = Ontology.find_or_create_by_name('Annotation Tags')
|
43
|
+
term = Term.find_or_create_by_name(:name => synonym, :ontology=> ontology_annotation_tags)
|
44
|
+
datas = @entry.bioentry_qualifier_values.find_all_by_term_id(term.term_id)
|
45
|
+
#add an element incrementing the rank or setting the first to 1
|
46
|
+
@entry.bioentry_qualifier_values.create(:term_id=>term.term_id, :rank=>datas.empty? ? 1 : datas.last.rank.succ, :value=>value)
|
47
|
+
rescue Exception => e
|
48
|
+
puts "WriterOperator= Error: #{synonym} #{e.message}"
|
49
|
+
end
|
50
|
+
end
|
51
|
+
|
52
|
+
send :define_method, method_writer_modder do |value, rank|
|
53
|
+
begin
|
54
|
+
ontology_annotation_tags = Ontology.find_or_create_by_name('Annotation Tags')
|
55
|
+
term = Term.find_or_create_by_name(:name => synonym, :ontology=> ontology_annotation_tags)
|
56
|
+
data = @entry.bioentry_qualifier_values.find_by_term_id_and_rank(term.term_id, rank)
|
57
|
+
if data.nil?
|
58
|
+
send method_writer_operator, value
|
59
|
+
else
|
60
|
+
data.value=value
|
61
|
+
data.save!
|
62
|
+
end
|
63
|
+
rescue Exception => e
|
64
|
+
puts "WriterModder Error: #{synonym} #{e.message}"
|
65
|
+
end
|
66
|
+
end
|
67
|
+
|
68
|
+
end
|
69
|
+
public
|
70
|
+
attr_reader :entry
|
71
|
+
|
72
|
+
def delete
|
73
|
+
@entry.destroy
|
74
|
+
end
|
75
|
+
|
76
|
+
def get_seqfeature(sf)
|
77
|
+
|
78
|
+
#in seqfeature BioSQL class
|
79
|
+
locations_str = sf.locations.map{|loc| loc.to_s}.join(',')
|
80
|
+
#pp sf.locations.inspect
|
81
|
+
locations_str = "join(#{locations_str})" if sf.locations.count>1
|
82
|
+
Bio::Feature.new(sf.type_term.name, locations_str,sf.seqfeature_qualifier_values.collect{|sfqv| Bio::Feature::Qualifier.new(sfqv.term.name,sfqv.value)})
|
83
|
+
end
|
84
|
+
|
85
|
+
def length=(len)
|
86
|
+
@entry.biosequence.length=len
|
87
|
+
end
|
88
|
+
|
89
|
+
def initialize(options={})
|
90
|
+
options.assert_valid_keys(:entry, :biodatabase_id,:biosequence)
|
91
|
+
return @entry = options[:entry] unless options[:entry].nil?
|
92
|
+
|
93
|
+
return to_biosql(options[:biosequence], options[:biodatabase_id]) unless options[:biosequence].nil? or options[:biodatabase_id].nil?
|
94
|
+
|
95
|
+
end
|
96
|
+
|
97
|
+
def to_biosql(bs,biodatabase_id)
|
98
|
+
#Transcaction works greatly!!!
|
99
|
+
|
100
|
+
#
|
101
|
+
begin
|
102
|
+
Bioentry.transaction do
|
103
|
+
|
104
|
+
@entry = Bioentry.new(:biodatabase_id=>biodatabase_id, :name=>bs.entry_id)
|
105
|
+
|
106
|
+
puts "primary" if $DEBUG
|
107
|
+
self.primary_accession = bs.primary_accession
|
108
|
+
|
109
|
+
puts "def" if $DEBUG
|
110
|
+
self.definition = bs.definition unless bs.definition.nil?
|
111
|
+
|
112
|
+
puts "seqver" if $DEBUG
|
113
|
+
self.sequence_version = bs.sequence_version || 0
|
114
|
+
|
115
|
+
puts "divi" if $DEBUG
|
116
|
+
self.division = bs.division unless bs.division.nil?
|
117
|
+
|
118
|
+
@entry.save!
|
119
|
+
puts "secacc" if $DEBUG
|
120
|
+
|
121
|
+
bs.secondary_accessions.each do |sa|
|
122
|
+
#write as qualifier every secondary accession into the array
|
123
|
+
self.secondary_accessions = sa
|
124
|
+
end unless bs.secondary_accessions.nil?
|
125
|
+
|
126
|
+
|
127
|
+
#to create the sequence entry needs to exists
|
128
|
+
puts "seq" if $DEBUG
|
129
|
+
puts bs.seq if $DEBUG
|
130
|
+
self.seq = bs.seq unless bs.seq.nil?
|
131
|
+
puts "mol" if $DEBUG
|
132
|
+
|
133
|
+
self.molecule_type = bs.molecule_type unless bs.molecule_type.nil?
|
134
|
+
puts "dc" if $DEBUG
|
135
|
+
|
136
|
+
self.data_class = bs.data_class unless bs.data_class.nil?
|
137
|
+
puts "top" if $DEBUG
|
138
|
+
self.topology = bs.topology unless bs.topology.nil?
|
139
|
+
puts "datec" if $DEBUG
|
140
|
+
self.date_created = bs.date_created unless bs.date_created.nil?
|
141
|
+
puts "datemod" if $DEBUG
|
142
|
+
self.date_modified = bs.date_modified unless bs.date_modified.nil?
|
143
|
+
puts "key" if $DEBUG
|
144
|
+
|
145
|
+
bs.keywords.each do |kw|
|
146
|
+
#write as qualifier every secondary accessions into the array
|
147
|
+
self.keywords = kw
|
148
|
+
end unless bs.keywords.nil?
|
149
|
+
#FIX: problem settinf taxon_name: embl has "Arabidopsis thaliana (thale cress)" but in taxon_name table there isn't this name. I must check if there is a new version of the table
|
150
|
+
puts "spec" if $DEBUG
|
151
|
+
self.species = bs.species unless bs.species.nil?
|
152
|
+
puts "Debug: #{bs.species}" if $DEBUG
|
153
|
+
puts "Debug: feat..start" if $DEBUG
|
154
|
+
|
155
|
+
bs.features.each do |feat|
|
156
|
+
self.feature=feat
|
157
|
+
end unless bs.features.nil?
|
158
|
+
puts "Debug: feat...end" if $DEBUG
|
159
|
+
|
160
|
+
#TODO: add comments and references
|
161
|
+
bs.references.each do |reference|
|
162
|
+
# puts reference.inspect
|
163
|
+
self.reference=reference
|
164
|
+
end unless bs.references.nil?
|
165
|
+
|
166
|
+
bs.comments.each do |comment|
|
167
|
+
self.comment=comment
|
168
|
+
end unless bs.comments.nil?
|
169
|
+
|
170
|
+
end #transaction
|
171
|
+
return self
|
172
|
+
rescue Exception => e
|
173
|
+
puts "to_biosql exception: #{e}"
|
174
|
+
puts $!
|
175
|
+
end #rescue
|
176
|
+
end #to_biosql
|
177
|
+
|
178
|
+
|
179
|
+
def name
|
180
|
+
@entry.name
|
181
|
+
end
|
182
|
+
alias entry_id name
|
183
|
+
|
184
|
+
def name=(value)
|
185
|
+
@entry.name=value
|
186
|
+
end
|
187
|
+
alias entry_id= name=
|
188
|
+
|
189
|
+
def primary_accession
|
190
|
+
@entry.accession
|
191
|
+
end
|
192
|
+
|
193
|
+
def primary_accession=(value)
|
194
|
+
@entry.accession=value
|
195
|
+
end
|
196
|
+
|
197
|
+
#TODO def secondary_accession
|
198
|
+
# @entry.bioentry_qualifier_values
|
199
|
+
# end
|
200
|
+
|
201
|
+
def organism
|
202
|
+
@entry.taxon.nil? ? "" : "#{@entry.taxon.taxon_scientific_name.name}"+ (@entry.taxon.taxon_genbank_common_name ? "(#{@entry.taxon.taxon_genbank_common_name.name})" : '')
|
203
|
+
end
|
204
|
+
alias species organism
|
205
|
+
|
206
|
+
def organism=(value)
|
207
|
+
taxon_name=TaxonName.find_by_name_and_name_class(value.gsub(/\s+\(.+\)/,''),'scientific name')
|
208
|
+
if taxon_name.nil?
|
209
|
+
puts "Error value doesn't exists in taxon_name table with scientific name constraint."
|
210
|
+
else
|
211
|
+
@entry.taxon_id=taxon_name.taxon_id
|
212
|
+
@entry.save!
|
213
|
+
end
|
214
|
+
end
|
215
|
+
alias species= organism=
|
216
|
+
|
217
|
+
def database
|
218
|
+
@entry.biodatabase.name
|
219
|
+
end
|
220
|
+
|
221
|
+
def database_desc
|
222
|
+
@entry.biodatabase.description
|
223
|
+
end
|
224
|
+
|
225
|
+
def version
|
226
|
+
@entry.version
|
227
|
+
end
|
228
|
+
alias sequence_version version
|
229
|
+
|
230
|
+
def version=(value)
|
231
|
+
@entry.version=value
|
232
|
+
end
|
233
|
+
alias sequence_version= version=
|
234
|
+
|
235
|
+
def division
|
236
|
+
@entry.division
|
237
|
+
end
|
238
|
+
def division=(value)
|
239
|
+
@entry.division=value
|
240
|
+
end
|
241
|
+
|
242
|
+
def description
|
243
|
+
@entry.description
|
244
|
+
end
|
245
|
+
alias definition description
|
246
|
+
|
247
|
+
def description=(value)
|
248
|
+
@entry.description=value
|
249
|
+
end
|
250
|
+
alias definition= description=
|
251
|
+
|
252
|
+
def identifier
|
253
|
+
@entry.identifier
|
254
|
+
end
|
255
|
+
|
256
|
+
def identifier=(value)
|
257
|
+
@entry.identifier=value
|
258
|
+
end
|
259
|
+
|
260
|
+
bioentry_qualifier_anchor :data_class
|
261
|
+
bioentry_qualifier_anchor :molecule_type, :synonym=>'mol_type'
|
262
|
+
bioentry_qualifier_anchor :topology
|
263
|
+
bioentry_qualifier_anchor :date_created
|
264
|
+
bioentry_qualifier_anchor :date_modified, :synonym=>'date_changed'
|
265
|
+
bioentry_qualifier_anchor :keywords, :synonym=>'keyword'
|
266
|
+
bioentry_qualifier_anchor :secondary_accessions, :synonym=>'secondary_accession'
|
267
|
+
|
268
|
+
def features
|
269
|
+
@entry.seqfeatures.collect {|sf|
|
270
|
+
self.get_seqfeature(sf)}
|
271
|
+
end
|
272
|
+
|
273
|
+
def feature=(feat)
|
274
|
+
#ToDo: avoid Ontology find here, probably more efficient create class variables
|
275
|
+
type_term_ontology = Ontology.find_or_create_by_name('SeqFeature Keys')
|
276
|
+
type_term = Term.find_or_create_by_name(:name=>feat.feature, :ontology=>type_term_ontology)
|
277
|
+
source_term_ontology = Ontology.find_or_create_by_name('SeqFeature Sources')
|
278
|
+
source_term = Term.find_or_create_by_name(:name=>'EMBLGenBankSwit',:ontology=>source_term_ontology)
|
279
|
+
seqfeature = Seqfeature.create(:bioentry=>@entry, :source_term=>source_term, :type_term=>type_term, :rank=>@entry.seqfeatures.count.succ, :display_name=>'')
|
280
|
+
#seqfeature.save!
|
281
|
+
feat.locations.each do |loc|
|
282
|
+
location = Location.new(:seqfeature=>seqfeature, :start_pos=>loc.from, :end_pos=>loc.to, :strand=>loc.strand, :rank=>seqfeature.locations.count.succ)
|
283
|
+
location.save!
|
284
|
+
end
|
285
|
+
qual_term_ontology = Ontology.find_or_create_by_name('Annotation Tags')
|
286
|
+
feat.each do |qualifier|
|
287
|
+
qual_term = Term.find_or_create_by_name(:name=>qualifier.qualifier, :ontology=>qual_term_ontology)
|
288
|
+
qual = SeqfeatureQualifierValue.new(:seqfeature=>seqfeature, :term=>qual_term, :value=>qualifier.value.to_s, :rank=>seqfeature.seqfeature_qualifier_values.count.succ)
|
289
|
+
qual.save!
|
290
|
+
end
|
291
|
+
end
|
292
|
+
|
293
|
+
#return the seqfeature mapped from BioSQL with a type_term like 'CDS'
|
294
|
+
def cdsfeatures
|
295
|
+
@entry.cdsfeatures
|
296
|
+
end
|
297
|
+
|
298
|
+
# Returns the sequence.
|
299
|
+
# Returns a Bio::Sequence::Generic object.
|
300
|
+
|
301
|
+
def seq
|
302
|
+
s = @entry.biosequence
|
303
|
+
Bio::Sequence::Generic.new(s ? s.seq : '')
|
304
|
+
end
|
305
|
+
|
306
|
+
def seq=(value)
|
307
|
+
|
308
|
+
#chk which type of alphabet is, NU/NA/nil
|
309
|
+
if @entry.biosequence.nil?
|
310
|
+
# puts "intoseq1"
|
311
|
+
@entry.biosequence = Biosequence.new(:seq=>value)
|
312
|
+
@entry.biosequence.save!
|
313
|
+
|
314
|
+
else
|
315
|
+
@entry.biosequence.seq=value
|
316
|
+
end
|
317
|
+
self.length=value.length
|
318
|
+
#@entry.biosequence.length=value.length
|
319
|
+
#break
|
320
|
+
@entry.save!
|
321
|
+
end
|
322
|
+
|
323
|
+
def taxonomy
|
324
|
+
tax = []
|
325
|
+
taxon = @entry.taxon
|
326
|
+
while taxon and taxon.taxon_id != taxon.parent_taxon_id
|
327
|
+
tax << taxon.taxon_scientific_name.name
|
328
|
+
#Note: I don't like this call very much, correct with a relationship in the ref class.
|
329
|
+
taxon = Taxon.find(taxon.parent_taxon_id)
|
330
|
+
end
|
331
|
+
tax.reverse
|
332
|
+
end
|
333
|
+
|
334
|
+
def length
|
335
|
+
@entry.biosequence.length
|
336
|
+
end
|
337
|
+
|
338
|
+
def references
|
339
|
+
#return and array of hash, hash has these keys ["title", "dbxref_id", "reference_id", "authors", "crc", "location"]
|
340
|
+
#probably would be better to d a class refrence to collect these informations
|
341
|
+
@entry.bioentry_references.collect do |bio_ref|
|
342
|
+
hash = Hash.new
|
343
|
+
hash['authors'] = bio_ref.reference.authors.gsub(/\.\s/, "\.\s\|").split(/\|/)
|
344
|
+
|
345
|
+
hash['sequence_position'] = "#{bio_ref.start_pos}-#{bio_ref.end_pos}" if (bio_ref.start_pos and bio_ref.end_pos)
|
346
|
+
hash['title'] = bio_ref.reference.title
|
347
|
+
hash['embl_gb_record_number'] = bio_ref.rank
|
348
|
+
#TODO: solve the problem with specific comment per reference.
|
349
|
+
#TODO: get dbxref
|
350
|
+
#take a look when location is build up in def reference=(value)
|
351
|
+
|
352
|
+
bio_ref.reference.location.split('|').each do |element|
|
353
|
+
key,value=element.split('=')
|
354
|
+
hash[key]=value
|
355
|
+
end unless bio_ref.reference.location.nil?
|
356
|
+
|
357
|
+
hash['xrefs'] = bio_ref.reference.dbxref ? "#{bio_ref.reference.dbxref.dbname}; #{bio_ref.reference.dbxref.accession}." : ''
|
358
|
+
Bio::Reference.new(hash)
|
359
|
+
end
|
360
|
+
end
|
361
|
+
|
362
|
+
def comments
|
363
|
+
@entry.comments.map do |comment|
|
364
|
+
comment.comment_text
|
365
|
+
end
|
366
|
+
end
|
367
|
+
|
368
|
+
|
369
|
+
def reference=(value)
|
370
|
+
|
371
|
+
locations=Array.new
|
372
|
+
locations << "journal=#{value.journal}" unless value.journal.empty?
|
373
|
+
locations << "volume=#{value.volume}" unless value.volume.empty?
|
374
|
+
locations << "issue=#{value.issue}" unless value.issue.empty?
|
375
|
+
locations << "pages=#{value.pages}" unless value.pages.empty?
|
376
|
+
locations << "year=#{value.year}" unless value.year.empty?
|
377
|
+
locations << "pubmed=#{value.pubmed}" unless value.pubmed.empty?
|
378
|
+
locations << "medline=#{value.medline}" unless value.medline.empty?
|
379
|
+
locations << "doi=#{value.doi}" unless value.doi.nil?
|
380
|
+
locations << "abstract=#{value.abstract}" unless value.abstract.empty?
|
381
|
+
locations << "url=#{value.url}" unless value.url.nil?
|
382
|
+
locations << "mesh=#{value.mesh}" unless value.mesh.empty?
|
383
|
+
locations << "affiliations=#{value.affiliations}" unless value.affiliations.empty?
|
384
|
+
locations << "comments=#{value.comments.join('~')}"unless value.comments.nil?
|
385
|
+
start_pos, end_pos = value.sequence_position ? value.sequence_position.gsub(/\s*/,'').split('-') : [nil,nil]
|
386
|
+
reference=Reference.find_or_create_by_title(:title=>value.title, :authors=>value.authors.join(' '), :location=>locations.join('|'))
|
387
|
+
|
388
|
+
bio_reference=BioentryReference.new(:bioentry=>@entry,:reference=>reference,:rank=>value.embl_gb_record_number, :start_pos=>start_pos, :end_pos=>end_pos)
|
389
|
+
bio_reference.save!
|
390
|
+
end
|
391
|
+
|
392
|
+
def comment=(value)
|
393
|
+
comment=Comment.new(:bioentry=>@entry, :comment_text=>value, :rank=>@entry.comments.count.succ)
|
394
|
+
comment.save!
|
395
|
+
end
|
396
|
+
|
397
|
+
def save
|
398
|
+
#I should add chks for SQL errors
|
399
|
+
@entry.biosequence.save!
|
400
|
+
@entry.save!
|
401
|
+
end
|
402
|
+
def to_fasta
|
403
|
+
#prima erano 2 print in stdout, meglio ritornare una stringa in modo che poi ci si possa fare quello che si vuole
|
404
|
+
#print ">" + accession + "\n"
|
405
|
+
#print seq.gsub(Regexp.new(".{1,#{60}}"), "\\0\n")
|
406
|
+
">" + accession + "\n" + seq.gsub(Regexp.new(".{1,#{60}}"), "\\0\n")
|
407
|
+
end
|
408
|
+
|
409
|
+
def to_fasta_reverse_complememt
|
410
|
+
">" + accession + "\n" + seq.reverse_complement.gsub(Regexp.new(".{1,#{60}}"), "\\0\n")
|
411
|
+
end
|
412
|
+
|
413
|
+
|
414
|
+
|
415
|
+
def to_biosequence
|
416
|
+
Bio::Sequence.adapter(self,Bio::Sequence::Adapter::BioSQL)
|
417
|
+
end
|
418
|
+
end #Sequence
|
419
|
+
|
420
|
+
|
421
|
+
end #SQL
|
422
|
+
end #Bio
|
423
|
+
|
424
|
+
#TODO create tests for sequence object, roundtrip of informations
|
425
|
+
|
426
|
+
if __FILE__ == $0
|
427
|
+
|
428
|
+
require 'bio'
|
429
|
+
require 'bio/io/sql'
|
430
|
+
require 'pp'
|
431
|
+
|
432
|
+
# connection = Bio::SQL.establish_connection('bio/io/biosql/config/database.yml','development')
|
433
|
+
connection = Bio::SQL.establish_connection({'development'=>{'database'=>"biorails_development", 'adapter'=>"postgresql", 'username'=>"rails", 'password'=>nil}},'development')
|
434
|
+
databases = Bio::SQL.list_databases
|
435
|
+
|
436
|
+
# parser = Bio::FlatFile.auto('/home/febo/Desktop/aj224122.embl')
|
437
|
+
parser = Bio::FlatFile.auto('/home/febo/Desktop/aj224122.gb')
|
438
|
+
#parser = Bio::FlatFile.auto('/home/febo/Desktop/aj224122.fasta')
|
439
|
+
|
440
|
+
parser.each do |entry|
|
441
|
+
biosequence = entry.to_biosequence
|
442
|
+
result = Bio::SQL::Sequence.new(:biosequence=>biosequence,:biodatabase_id=>databases.first[:id]) unless Bio::SQL.exists_accession(biosequence.primary_accession)
|
443
|
+
|
444
|
+
if result.nil?
|
445
|
+
pp "The sequence is already present into the biosql database"
|
446
|
+
else
|
447
|
+
# pp "Sequence"
|
448
|
+
puts result.to_biosequence.output(:genbank) #:embl
|
449
|
+
result.delete
|
450
|
+
end
|
451
|
+
end
|
452
|
+
|
453
|
+
if false
|
454
|
+
sqlseq = Bio::SQL.fetch_accession('AJ224122')
|
455
|
+
#only output tests.
|
456
|
+
pp "Connection"
|
457
|
+
pp connection
|
458
|
+
pp "Seq in dbs"
|
459
|
+
pp Bio::SQL.list_entries
|
460
|
+
#; NC_003098
|
461
|
+
|
462
|
+
|
463
|
+
#pp sqlseq
|
464
|
+
pp sqlseq.entry.inspect
|
465
|
+
pp "sequence"
|
466
|
+
#pp Bio::Sequence.auto(sqlseq.seq)
|
467
|
+
pp "entry_id"
|
468
|
+
pp sqlseq.entry_id
|
469
|
+
|
470
|
+
pp "primary"
|
471
|
+
pp sqlseq.accession
|
472
|
+
pp "secondary_accessions"
|
473
|
+
pp sqlseq.secondary_accessions
|
474
|
+
pp "molecule type"
|
475
|
+
pp sqlseq.molecule_type
|
476
|
+
pp "data_class"
|
477
|
+
pp sqlseq.data_class
|
478
|
+
pp "division"
|
479
|
+
pp sqlseq.division
|
480
|
+
# NOTE : Topology is not represented in biosql?
|
481
|
+
pp "topology"
|
482
|
+
#TODO: CIRCULAR this at present maps to bioentry_qualifier_value, though there are plans to make it a column in table biosequence.
|
483
|
+
pp sqlseq.topology
|
484
|
+
pp "version"
|
485
|
+
pp sqlseq.version
|
486
|
+
#sequence.date_created = nil #????
|
487
|
+
pp "date modified"
|
488
|
+
pp sqlseq.date_modified
|
489
|
+
pp "definition"
|
490
|
+
pp sqlseq.definition
|
491
|
+
pp "keywords"
|
492
|
+
pp sqlseq.keywords
|
493
|
+
pp "species"
|
494
|
+
pp sqlseq.organism
|
495
|
+
#sequence.classification = self.taxonomy.to_s.sub(/\.\z/, '').split(/\s*\;\s*/)"
|
496
|
+
pp "classification"
|
497
|
+
pp sqlseq.taxonomy
|
498
|
+
#sequence.organnella = nil # not used
|
499
|
+
pp "comments"
|
500
|
+
pp sqlseq.comments
|
501
|
+
pp "references"
|
502
|
+
pp sqlseq.references
|
503
|
+
pp "features"
|
504
|
+
pp sqlseq.features
|
505
|
+
puts sqlseq.to_biosequence.output(:embl)
|
506
|
+
end
|
507
|
+
##
|
508
|
+
end
|