jandot-bio 1.2.1
Sign up to get free protection for your applications and to get access to all the features.
- data/bin/bioruby +44 -0
- data/bin/br_biofetch.rb +47 -0
- data/bin/br_bioflat.rb +282 -0
- data/bin/br_biogetseq.rb +45 -0
- data/bin/br_pmfetch.rb +421 -0
- data/doc/Changes-0.7.rd +369 -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/lib/bio.rb +279 -0
- data/lib/bio/alignment.rb +2518 -0
- data/lib/bio/appl/bl2seq/report.rb +334 -0
- data/lib/bio/appl/blast.rb +351 -0
- data/lib/bio/appl/blast/format0.rb +1438 -0
- data/lib/bio/appl/blast/format8.rb +83 -0
- data/lib/bio/appl/blast/report.rb +516 -0
- data/lib/bio/appl/blast/rexml.rb +135 -0
- data/lib/bio/appl/blast/rpsblast.rb +176 -0
- data/lib/bio/appl/blast/wublast.rb +550 -0
- data/lib/bio/appl/blast/xmlparser.rb +228 -0
- data/lib/bio/appl/blat/report.rb +489 -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 +237 -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/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.rb +548 -0
- data/lib/bio/appl/psort/report.rb +457 -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 +222 -0
- data/lib/bio/command.rb +337 -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.rb +329 -0
- data/lib/bio/db/aaindex.rb +357 -0
- data/lib/bio/db/embl/common.rb +336 -0
- data/lib/bio/db/embl/embl.rb +402 -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 +599 -0
- data/lib/bio/db/fasta.rb +907 -0
- data/lib/bio/db/genbank/common.rb +290 -0
- data/lib/bio/db/genbank/ddbj.rb +22 -0
- data/lib/bio/db/genbank/genbank.rb +215 -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 +174 -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 +170 -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 +323 -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 +457 -0
- data/lib/bio/db/soft.rb +404 -0
- data/lib/bio/db/transfac.rb +375 -0
- data/lib/bio/feature.rb +226 -0
- data/lib/bio/io/das.rb +461 -0
- data/lib/bio/io/dbget.rb +194 -0
- data/lib/bio/io/ddbjxml.rb +581 -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 +181 -0
- data/lib/bio/io/flatfile.rb +1309 -0
- data/lib/bio/io/flatfile/bdb.rb +253 -0
- data/lib/bio/io/flatfile/index.rb +1371 -0
- data/lib/bio/io/flatfile/indexer.rb +787 -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 +256 -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 +365 -0
- data/lib/bio/location.rb +772 -0
- data/lib/bio/map.rb +410 -0
- data/lib/bio/pathway.rb +854 -0
- data/lib/bio/reference.rb +623 -0
- data/lib/bio/sequence.rb +475 -0
- data/lib/bio/sequence/aa.rb +125 -0
- data/lib/bio/sequence/common.rb +333 -0
- data/lib/bio/sequence/compat.rb +123 -0
- data/lib/bio/sequence/format.rb +181 -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 +850 -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 +199 -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/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/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/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/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/prosite/prosite.dat +2233 -0
- data/test/data/refseq/nm_126355.entret +64 -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/io/test_ensembl.rb +186 -0
- data/test/functional/bio/io/test_soapwsdl.rb +52 -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_report.rb +417 -0
- data/test/unit/bio/appl/blast/test_xmlparser.rb +388 -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/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 +163 -0
- data/test/unit/bio/appl/test_fasta.rb +130 -0
- data/test/unit/bio/appl/test_pts1.rb +140 -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_sptr.rb +1775 -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 +127 -0
- data/test/unit/bio/db/test_lasergene.rb +95 -0
- data/test/unit/bio/db/test_newick.rb +293 -0
- data/test/unit/bio/db/test_nexus.rb +360 -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/test_ddbjxml.rb +75 -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 +237 -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 +174 -0
- data/test/unit/bio/sequence/test_compat.rb +69 -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 +288 -0
- data/test/unit/bio/test_db.rb +96 -0
- data/test/unit/bio/test_feature.rb +116 -0
- data/test/unit/bio/test_location.rb +39 -0
- data/test/unit/bio/test_map.rb +230 -0
- data/test/unit/bio/test_pathway.rb +473 -0
- data/test/unit/bio/test_reference.rb +224 -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 +479 -0
@@ -0,0 +1,256 @@
|
|
1
|
+
#
|
2
|
+
# = bio/io/ncbirest.rb - NCBI Entrez client module
|
3
|
+
#
|
4
|
+
# Copyright:: Copyright (C) 2008 Toshiaki Katayama <k@bioruby.org>
|
5
|
+
# License:: The Ruby License
|
6
|
+
#
|
7
|
+
# $Id: ncbirest.rb,v 1.2 2008/02/19 04:49:35 k Exp $
|
8
|
+
#
|
9
|
+
|
10
|
+
require 'bio/command'
|
11
|
+
|
12
|
+
module Bio
|
13
|
+
|
14
|
+
# == Description
|
15
|
+
#
|
16
|
+
# The Bio::NCBI::REST class provides REST client for the NCBI E-Utilities
|
17
|
+
#
|
18
|
+
# Entrez utilities index:
|
19
|
+
#
|
20
|
+
# * http://www.ncbi.nlm.nih.gov/entrez/utils/utils_index.html
|
21
|
+
#
|
22
|
+
# == Usage
|
23
|
+
#
|
24
|
+
# Bio::NCBI::REST.esearch("tardigrada", {"db"=>"nuccore", "rettype"=>"count"})
|
25
|
+
# Bio::NCBI::REST.esearch("tardigrada", {"db"=>"nuccore", "rettype"=>"gb"})
|
26
|
+
# Bio::NCBI::REST.esearch("yeast kinase", {"db"=>"nuccore", "rettype"=>"gb", "retmode"=>"xml", "retmax"=>5})
|
27
|
+
# Bio::NCBI::REST.efetch("185041", {"db"=>"nuccore", "rettype"=>"gb"})
|
28
|
+
# Bio::NCBI::REST.efetch("J00231", {"db"=>"nuccore", "rettype"=>"gb", "retmode"=>"xml"})
|
29
|
+
#
|
30
|
+
class NCBI
|
31
|
+
class REST
|
32
|
+
|
33
|
+
# Run retrieval scripts on weekends or between 9 pm and 5 am Eastern Time
|
34
|
+
# weekdays for any series of more than 100 requests.
|
35
|
+
# -> Not implemented yet in BioRuby
|
36
|
+
|
37
|
+
# Make no more than one request every 3 seconds.
|
38
|
+
NCBI_INTERVAL = 3
|
39
|
+
@@last_access = nil
|
40
|
+
|
41
|
+
private
|
42
|
+
|
43
|
+
def ncbi_access_wait(wait = NCBI_INTERVAL)
|
44
|
+
if @@last_access
|
45
|
+
duration = Time.now - @@last_access
|
46
|
+
if wait > duration
|
47
|
+
sleep wait - duration
|
48
|
+
end
|
49
|
+
end
|
50
|
+
@@last_access = Time.now
|
51
|
+
end
|
52
|
+
|
53
|
+
public
|
54
|
+
|
55
|
+
# Search the NCBI database by given keywords using E-Utils and returns
|
56
|
+
# an array of entry IDs.
|
57
|
+
#
|
58
|
+
# For information on the possible arguments, see
|
59
|
+
#
|
60
|
+
# * http://eutils.ncbi.nlm.nih.gov/entrez/query/static/esearch_help.html
|
61
|
+
#
|
62
|
+
# ---
|
63
|
+
# *Arguments*:
|
64
|
+
# * _str_: query string (required)
|
65
|
+
# * _hash_: hash of E-Utils option {"db" => "nuccore", "rettype" => "gb"}
|
66
|
+
# * _db_: "nuccore", "nucleotide", "protein", "pubmed", ...
|
67
|
+
# * _retmode_: "text", "xml", "html", ...
|
68
|
+
# * _rettype_: "gb", "medline", "count", ...
|
69
|
+
# * _retmax_: integer (default 100)
|
70
|
+
# * _retstart_: integer
|
71
|
+
# * _field_
|
72
|
+
# * _reldate_
|
73
|
+
# * _mindate_
|
74
|
+
# * _maxdate_
|
75
|
+
# * _datetype_
|
76
|
+
# *Returns*:: array of entry IDs or a number of results
|
77
|
+
def esearch(str, hash = {})
|
78
|
+
return nil if str.empty?
|
79
|
+
|
80
|
+
serv = "http://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi"
|
81
|
+
opts = {
|
82
|
+
"retmax" => 100,
|
83
|
+
"tool" => "bioruby",
|
84
|
+
"term" => str
|
85
|
+
}
|
86
|
+
opts.update(hash)
|
87
|
+
|
88
|
+
ncbi_access_wait
|
89
|
+
|
90
|
+
response, = Bio::Command.post_form(serv, opts)
|
91
|
+
result = response.body
|
92
|
+
if opts['rettype'] == 'count'
|
93
|
+
result = result.scan(/<Count>(.*?)<\/Count>/m).flatten.first.to_i
|
94
|
+
else
|
95
|
+
result = result.scan(/<Id>(.*?)<\/Id>/m).flatten
|
96
|
+
end
|
97
|
+
return result
|
98
|
+
end
|
99
|
+
|
100
|
+
# Retrieve a database entry by given ID and using E-Utils (efetch) and
|
101
|
+
# returns an array of entry string. Multiple IDs can be supplied.
|
102
|
+
#
|
103
|
+
# For information on the possible arguments, see
|
104
|
+
#
|
105
|
+
# * http://eutils.ncbi.nlm.nih.gov/entrez/query/static/efetch_help.html
|
106
|
+
#
|
107
|
+
# ---
|
108
|
+
# *Arguments*:
|
109
|
+
# * _ids_: list of NCBI entry IDs (required)
|
110
|
+
# * _hash_: hash of E-Utils option {"db" => "nuccore", "rettype" => "gb"}
|
111
|
+
# * _db_: "nuccore", "nucleotide", "protein", "pubmed", ...
|
112
|
+
# * _retmode_: "text", "xml", "html", ...
|
113
|
+
# * _rettype_: "gb", "medline", "count",...
|
114
|
+
# * _retmax_: integer (default 100)
|
115
|
+
# * _retstart_: integer
|
116
|
+
# * _field_
|
117
|
+
# * _reldate_
|
118
|
+
# * _mindate_
|
119
|
+
# * _maxdate_
|
120
|
+
# * _datetype_
|
121
|
+
# *Returns*:: Array of entry String
|
122
|
+
def efetch(ids, hash = {})
|
123
|
+
return nil if ids.to_s.empty?
|
124
|
+
ids = ids.join(",") if ids === Array
|
125
|
+
|
126
|
+
serv = "http://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi"
|
127
|
+
opts = {
|
128
|
+
"tool" => "bioruby",
|
129
|
+
"retmode" => "text",
|
130
|
+
"id" => ids,
|
131
|
+
}
|
132
|
+
opts.update(hash)
|
133
|
+
|
134
|
+
ncbi_access_wait
|
135
|
+
|
136
|
+
response, = Bio::Command.post_form(serv, opts)
|
137
|
+
result = response.body
|
138
|
+
if opts["retmode"] == "text"
|
139
|
+
result = result.split(/\n\n+/)
|
140
|
+
end
|
141
|
+
return result
|
142
|
+
end
|
143
|
+
|
144
|
+
def self.esearch(*args)
|
145
|
+
self.new.esearch(*args)
|
146
|
+
end
|
147
|
+
|
148
|
+
def self.efetch(*args)
|
149
|
+
self.new.efetch(*args)
|
150
|
+
end
|
151
|
+
|
152
|
+
end # REST
|
153
|
+
end # NCBI
|
154
|
+
end # Bio
|
155
|
+
|
156
|
+
|
157
|
+
if __FILE__ == $0
|
158
|
+
|
159
|
+
gbopts = {"db"=>"nuccore", "rettype"=>"gb"}
|
160
|
+
pmopts = {"db"=>"pubmed", "rettype"=>"medline"}
|
161
|
+
count = {"rettype" => "count"}
|
162
|
+
xml = {"retmode"=>"xml"}
|
163
|
+
max = {"retmax"=>5}
|
164
|
+
|
165
|
+
puts "=== class methods ==="
|
166
|
+
|
167
|
+
puts "--- Search NCBI by E-Utils ---"
|
168
|
+
|
169
|
+
puts Time.now
|
170
|
+
puts "# count of 'tardigrada' in nuccore"
|
171
|
+
puts Bio::NCBI::REST.esearch("tardigrada", gbopts.merge(count))
|
172
|
+
|
173
|
+
puts Time.now
|
174
|
+
puts "# max 5 'tardigrada' entries in nuccore"
|
175
|
+
puts Bio::NCBI::REST.esearch("tardigrada", gbopts.merge(max))
|
176
|
+
|
177
|
+
puts Time.now
|
178
|
+
puts "# count of 'yeast kinase' in nuccore"
|
179
|
+
puts Bio::NCBI::REST.esearch("yeast kinase", gbopts.merge(count))
|
180
|
+
|
181
|
+
puts Time.now
|
182
|
+
puts "# max 5 'yeast kinase' entries in nuccore (XML)"
|
183
|
+
puts Bio::NCBI::REST.esearch("yeast kinase", gbopts.merge(xml).merge(max))
|
184
|
+
|
185
|
+
puts Time.now
|
186
|
+
puts "# count of 'genome&analysis|bioinformatics' in pubmed"
|
187
|
+
puts Bio::NCBI::REST.esearch("(genome AND analysis) OR bioinformatics", pmopts.merge(count))
|
188
|
+
|
189
|
+
puts Time.now
|
190
|
+
puts "# max 5 'genome&analysis|bioinformatics' entries in pubmed (XML)"
|
191
|
+
puts Bio::NCBI::REST.esearch("(genome AND analysis) OR bioinformatics", pmopts.merge(xml).merge(max))
|
192
|
+
|
193
|
+
puts Time.now
|
194
|
+
Bio::NCBI::REST.esearch("(genome AND analysis) OR bioinformatics", pmopts.merge(max)).each do |x|
|
195
|
+
puts "# each of 5 'genome&analysis|bioinformatics' entries in pubmed"
|
196
|
+
puts x
|
197
|
+
end
|
198
|
+
|
199
|
+
puts "--- Retrieve NCBI entry by E-Utils ---"
|
200
|
+
|
201
|
+
puts Time.now
|
202
|
+
puts "# '185041' entry in nuccore"
|
203
|
+
puts Bio::NCBI::REST.efetch("185041", gbopts)
|
204
|
+
|
205
|
+
puts Time.now
|
206
|
+
puts "# 'J00231' entry in nuccore (XML)"
|
207
|
+
puts Bio::NCBI::REST.efetch("J00231", gbopts.merge(xml))
|
208
|
+
|
209
|
+
puts Time.now
|
210
|
+
puts "# 16381885 entry in pubmed"
|
211
|
+
puts Bio::NCBI::REST.efetch(16381885, pmopts)
|
212
|
+
|
213
|
+
puts Time.now
|
214
|
+
puts "# '16381885' entry in pubmed"
|
215
|
+
puts Bio::NCBI::REST.efetch("16381885", pmopts)
|
216
|
+
|
217
|
+
puts Time.now
|
218
|
+
puts "# [10592173,14693808] entries in pubmed"
|
219
|
+
puts Bio::NCBI::REST.efetch([10592173, 14693808], pmopts)
|
220
|
+
|
221
|
+
puts Time.now
|
222
|
+
puts "# [10592173,14693808] entries in pubmed (XML)"
|
223
|
+
puts Bio::NCBI::REST.efetch([10592173, 14693808], pmopts.merge(xml))
|
224
|
+
|
225
|
+
|
226
|
+
puts "=== instance methods ==="
|
227
|
+
|
228
|
+
ncbi = Bio::NCBI::REST.new
|
229
|
+
|
230
|
+
puts "--- Search NCBI by E-Utils ---"
|
231
|
+
|
232
|
+
puts Time.now
|
233
|
+
puts "# count of 'genome&analysis|bioinformatics' in pubmed"
|
234
|
+
puts ncbi.esearch("(genome AND analysis) OR bioinformatics", pmopts.merge(count))
|
235
|
+
|
236
|
+
puts Time.now
|
237
|
+
puts "# max 5 'genome&analysis|bioinformatics' entries in pubmed"
|
238
|
+
puts ncbi.esearch("(genome AND analysis) OR bioinformatics", pmopts.merge(max))
|
239
|
+
|
240
|
+
puts Time.now
|
241
|
+
ncbi.esearch("(genome AND analysis) OR bioinformatics", pmopts).each do |x|
|
242
|
+
puts "# each 'genome&analysis|bioinformatics' entries in pubmed"
|
243
|
+
puts x
|
244
|
+
end
|
245
|
+
|
246
|
+
puts "--- Retrieve NCBI entry by E-Utils ---"
|
247
|
+
|
248
|
+
puts Time.now
|
249
|
+
puts "# 16381885 entry in pubmed"
|
250
|
+
puts ncbi.efetch(16381885, pmopts)
|
251
|
+
|
252
|
+
puts Time.now
|
253
|
+
puts "# [10592173,14693808] entries in pubmed"
|
254
|
+
puts ncbi.efetch([10592173, 14693808], pmopts)
|
255
|
+
|
256
|
+
end
|
@@ -0,0 +1,155 @@
|
|
1
|
+
#
|
2
|
+
# = bio/io/ncbisoap.rb - SOAP interface for NCBI Entrez Utilities
|
3
|
+
#
|
4
|
+
# Copyright:: Copyright (C) 2004, 2006
|
5
|
+
# Toshiaki Katayama <k@bioruby.org>
|
6
|
+
# License:: The Ruby License
|
7
|
+
#
|
8
|
+
# $Id: ncbisoap.rb,v 1.3 2007/04/05 23:35:41 trevor Exp $
|
9
|
+
#
|
10
|
+
|
11
|
+
require 'bio/io/soapwsdl'
|
12
|
+
|
13
|
+
module Bio
|
14
|
+
class NCBI
|
15
|
+
|
16
|
+
# == References
|
17
|
+
#
|
18
|
+
# * http://eutils.ncbi.nlm.nih.gov/entrez/query/static/esoap_help.html
|
19
|
+
#
|
20
|
+
# == Methods
|
21
|
+
#
|
22
|
+
# All methods accept a hash as its argument and most of the keys can be
|
23
|
+
# ommited (values are string).
|
24
|
+
#
|
25
|
+
# Note: Methods which name ends with _MS are designed for use with
|
26
|
+
# Microsoft Visual Studio and SOAP Toolkit 3.0
|
27
|
+
#
|
28
|
+
# * http://www.ncbi.nlm.nih.gov/entrez/query/static/esoap_ms_help.html
|
29
|
+
#
|
30
|
+
# * run_eFetch(_MS)
|
31
|
+
# * "db", "id", "WebEnv", "query_key", "tool", "email", "retstart",
|
32
|
+
# "retmax", "rettype", "strand", "seq_start", "seq_stop", "complexity",
|
33
|
+
# "report"
|
34
|
+
#
|
35
|
+
# * run_eGquery(_MS)
|
36
|
+
# * "term", "tool", "email"
|
37
|
+
#
|
38
|
+
# * run_eInfo(_MS)
|
39
|
+
# * "db", "tool", "email"
|
40
|
+
#
|
41
|
+
# * run_eSpell(_MS)
|
42
|
+
# * "db", "term", "tool", "email"
|
43
|
+
#
|
44
|
+
# * run_eLink(_MS)
|
45
|
+
# * "db", "id", "reldate", "mindate", "maxdate", "datetype", "term"
|
46
|
+
# "dbfrom", "WebEnv", "query_key", "cmd", "tool", "email"
|
47
|
+
#
|
48
|
+
# * run_eSearch(_MS)
|
49
|
+
# * "db", "term", "WebEnv", "QueryKey", "usehistory", "tool", "email",
|
50
|
+
# "field", "reldate", "mindate", "maxdate", "datetype", "RetStart",
|
51
|
+
# "RetMax", "rettype", "sort"
|
52
|
+
#
|
53
|
+
# * run_eSummary(_MS)
|
54
|
+
# * "db", "id", "WebEnv", "query_key", "retstart", "retmax", "tool", "email"
|
55
|
+
#
|
56
|
+
# == Complex data types
|
57
|
+
#
|
58
|
+
# * http://www.ncbi.nlm.nih.gov/entrez/eutils/soap/egquery.xsd
|
59
|
+
# * http://www.ncbi.nlm.nih.gov/entrez/eutils/soap/einfo.xsd
|
60
|
+
# * http://www.ncbi.nlm.nih.gov/entrez/eutils/soap/esearch.xsd
|
61
|
+
# * http://www.ncbi.nlm.nih.gov/entrez/eutils/soap/esummary.xsd
|
62
|
+
# * http://www.ncbi.nlm.nih.gov/entrez/eutils/soap/elink.xsd
|
63
|
+
# * http://www.ncbi.nlm.nih.gov/entrez/eutils/soap/efetch.xsd
|
64
|
+
# * http://www.ncbi.nlm.nih.gov/entrez/eutils/soap/espell.xsd
|
65
|
+
#
|
66
|
+
class SOAP < Bio::SOAPWSDL
|
67
|
+
|
68
|
+
BASE_URI = "http://www.ncbi.nlm.nih.gov/entrez/eutils/soap/"
|
69
|
+
|
70
|
+
# set default to EUtils
|
71
|
+
SERVER_URI = BASE_URI + "eutils.wsdl"
|
72
|
+
|
73
|
+
def initialize(wsdl = nil)
|
74
|
+
super(wsdl || self.class::SERVER_URI)
|
75
|
+
end
|
76
|
+
|
77
|
+
def method_missing(*arg)
|
78
|
+
sleep 3 # make sure to rest for 3 seconds per request
|
79
|
+
@driver.send(*arg)
|
80
|
+
end
|
81
|
+
|
82
|
+
class EUtils < Bio::NCBI::SOAP
|
83
|
+
SERVER_URI = BASE_URI + "eutils.wsdl"
|
84
|
+
end
|
85
|
+
|
86
|
+
class EUtilsLite < Bio::NCBI::SOAP
|
87
|
+
SERVER_URI = BASE_URI + "eutils_lite.wsdl"
|
88
|
+
end
|
89
|
+
|
90
|
+
class EFetch < Bio::NCBI::SOAP
|
91
|
+
SERVER_URI = BASE_URI + "efetch.wsdl"
|
92
|
+
end
|
93
|
+
|
94
|
+
class EFetchLite < Bio::NCBI::SOAP
|
95
|
+
SERVER_URI = BASE_URI + "efetch_lit.wsdl"
|
96
|
+
end
|
97
|
+
|
98
|
+
end # SOAP
|
99
|
+
end # NCBI
|
100
|
+
end # Bio
|
101
|
+
|
102
|
+
|
103
|
+
if __FILE__ == $0
|
104
|
+
|
105
|
+
puts ">>> Bio::NCBI::SOAP::EFetch"
|
106
|
+
efetch = Bio::NCBI::SOAP::EFetch.new
|
107
|
+
|
108
|
+
puts "### run_eFetch in EFetch"
|
109
|
+
hash = {"db" => "protein", "id" => "37776955"}
|
110
|
+
result = efetch.run_eFetch(hash)
|
111
|
+
p result
|
112
|
+
|
113
|
+
puts ">>> Bio::NCBI::SOAP::EUtils"
|
114
|
+
eutils = Bio::NCBI::SOAP::EUtils.new
|
115
|
+
|
116
|
+
puts "### run_eFetch in EUtils"
|
117
|
+
hash = {"db" => "pubmed", "id" => "12345"}
|
118
|
+
result = eutils.run_eFetch(hash)
|
119
|
+
p result
|
120
|
+
|
121
|
+
puts "### run_eGquery - Entrez meta search to count hits in each DB"
|
122
|
+
hash = {"term" => "kinase"}
|
123
|
+
result = eutils.run_eGquery(hash) # working?
|
124
|
+
p result
|
125
|
+
|
126
|
+
puts "### run_eInfo - listing of the databases"
|
127
|
+
hash = {"db" => "protein"}
|
128
|
+
result = eutils.run_eInfo(hash)
|
129
|
+
p result
|
130
|
+
|
131
|
+
puts "### run_eSpell"
|
132
|
+
hash = {"db" => "pubmed", "term" => "kinas"}
|
133
|
+
result = eutils.run_eSpell(hash)
|
134
|
+
p result
|
135
|
+
p result["CorrectedQuery"]
|
136
|
+
|
137
|
+
puts "### run_eLink"
|
138
|
+
hash = {"db" => "protein", "id" => "37776955"}
|
139
|
+
result = eutils.run_eLink(hash) # working?
|
140
|
+
p result
|
141
|
+
|
142
|
+
puts "### run_eSearch"
|
143
|
+
hash = {"db" => "pubmed", "term" => "kinase"}
|
144
|
+
result = eutils.run_eSearch(hash)
|
145
|
+
p result
|
146
|
+
|
147
|
+
puts "### run_eSummary"
|
148
|
+
hash = {"db" => "protein", "id" => "37776955"}
|
149
|
+
result = eutils.run_eSummary(hash)
|
150
|
+
p result
|
151
|
+
|
152
|
+
end
|
153
|
+
|
154
|
+
|
155
|
+
|
@@ -0,0 +1,307 @@
|
|
1
|
+
#
|
2
|
+
# = bio/io/pubmed.rb - NCBI Entrez/PubMed client module
|
3
|
+
#
|
4
|
+
# Copyright:: Copyright (C) 2001, 2007, 2008 Toshiaki Katayama <k@bioruby.org>
|
5
|
+
# Copyright:: Copyright (C) 2006 Jan Aerts <jan.aerts@bbsrc.ac.uk>
|
6
|
+
# License:: The Ruby License
|
7
|
+
#
|
8
|
+
# $Id: pubmed.rb,v 1.24 2008/02/19 03:36:52 k Exp $
|
9
|
+
#
|
10
|
+
|
11
|
+
require 'bio/io/ncbirest'
|
12
|
+
require 'bio/command'
|
13
|
+
require 'cgi' unless defined?(CGI)
|
14
|
+
|
15
|
+
module Bio
|
16
|
+
|
17
|
+
# == Description
|
18
|
+
#
|
19
|
+
# The Bio::PubMed class provides several ways to retrieve bibliographic
|
20
|
+
# information from the PubMed database at
|
21
|
+
# http://www.ncbi.nlm.nih.gov/sites/entrez?db=PubMed
|
22
|
+
#
|
23
|
+
# Basically, two types of queries are possible:
|
24
|
+
#
|
25
|
+
# * searching for PubMed IDs given a query string:
|
26
|
+
# * Bio::PubMed#esearch (recommended)
|
27
|
+
# * Bio::PubMed#search (only retrieves top 20 hits)
|
28
|
+
#
|
29
|
+
# * retrieving the MEDLINE text (i.e. authors, journal, abstract, ...)
|
30
|
+
# given a PubMed ID
|
31
|
+
# * Bio::PubMed#efetch (recommended)
|
32
|
+
# * Bio::PubMed#query (unstable for the change of the HTML design)
|
33
|
+
# * Bio::PubMed#pmfetch (still working but could be obsoleted by NCBI)
|
34
|
+
#
|
35
|
+
# The different methods within the same group are interchangeable and should
|
36
|
+
# return the same result.
|
37
|
+
#
|
38
|
+
# Additional information about the MEDLINE format and PubMed programmable
|
39
|
+
# APIs can be found on the following websites:
|
40
|
+
#
|
41
|
+
# * PubMed Overview:
|
42
|
+
# http://www.ncbi.nlm.nih.gov/entrez/query/static/overview.html
|
43
|
+
# * PubMed help:
|
44
|
+
# http://www.ncbi.nlm.nih.gov/entrez/query/static/help/pmhelp.html
|
45
|
+
# * Entrez utilities index:
|
46
|
+
# http://www.ncbi.nlm.nih.gov/entrez/utils/utils_index.html
|
47
|
+
# * How to link:
|
48
|
+
# http://www.ncbi.nlm.nih.gov/books/bv.fcgi?rid=helplinks.chapter.linkshelp
|
49
|
+
#
|
50
|
+
# == Usage
|
51
|
+
#
|
52
|
+
# require 'bio'
|
53
|
+
#
|
54
|
+
# # If you don't know the pubmed ID:
|
55
|
+
# Bio::PubMed.esearch("(genome AND analysis) OR bioinformatics").each do |x|
|
56
|
+
# p x
|
57
|
+
# end
|
58
|
+
#
|
59
|
+
# Bio::PubMed.search("(genome AND analysis) OR bioinformatics").each do |x|
|
60
|
+
# p x
|
61
|
+
# end
|
62
|
+
#
|
63
|
+
# # To retrieve the MEDLINE entry for a given PubMed ID:
|
64
|
+
# puts Bio::PubMed.efetch("10592173", "14693808")
|
65
|
+
# puts Bio::PubMed.query("10592173")
|
66
|
+
# puts Bio::PubMed.pmfetch("10592173")
|
67
|
+
#
|
68
|
+
# # This can be converted into a Bio::MEDLINE object:
|
69
|
+
# manuscript = Bio::PubMed.query("10592173")
|
70
|
+
# medline = Bio::MEDLINE.new(manuscript)
|
71
|
+
#
|
72
|
+
class PubMed < Bio::NCBI::REST
|
73
|
+
|
74
|
+
# Search the PubMed database by given keywords using E-Utils and returns
|
75
|
+
# an array of PubMed IDs.
|
76
|
+
#
|
77
|
+
# For information on the possible arguments, see
|
78
|
+
# http://eutils.ncbi.nlm.nih.gov/entrez/query/static/esearch_help.html#PubMed
|
79
|
+
# ---
|
80
|
+
# *Arguments*:
|
81
|
+
# * _str_: query string (required)
|
82
|
+
# * _hash_: hash of E-Utils options
|
83
|
+
# * _retmode_: "xml", "html", ...
|
84
|
+
# * _rettype_: "medline", ...
|
85
|
+
# * _retmax_: integer (default 100)
|
86
|
+
# * _retstart_: integer
|
87
|
+
# * _field_
|
88
|
+
# * _reldate_
|
89
|
+
# * _mindate_
|
90
|
+
# * _maxdate_
|
91
|
+
# * _datetype_
|
92
|
+
# *Returns*:: array of PubMed IDs or a number of results
|
93
|
+
def esearch(str, hash = {})
|
94
|
+
opts = { "db" => "pubmed" }
|
95
|
+
opts.update(hash)
|
96
|
+
super(str, opts)
|
97
|
+
end
|
98
|
+
|
99
|
+
# Retrieve PubMed entry by PMID and returns MEDLINE formatted string using
|
100
|
+
# entrez efetch. Multiple PubMed IDs can be provided:
|
101
|
+
# Bio::PubMed.efetch(123)
|
102
|
+
# Bio::PubMed.efetch([123,456,789])
|
103
|
+
# ---
|
104
|
+
# *Arguments*:
|
105
|
+
# * _ids_: list of PubMed IDs (required)
|
106
|
+
# * _hash_: hash of E-Utils options
|
107
|
+
# * _retmode_: "xml", "html", ...
|
108
|
+
# * _rettype_: "medline", ...
|
109
|
+
# * _retmax_: integer (default 100)
|
110
|
+
# * _retstart_: integer
|
111
|
+
# * _field_
|
112
|
+
# * _reldate_
|
113
|
+
# * _mindate_
|
114
|
+
# * _maxdate_
|
115
|
+
# * _datetype_
|
116
|
+
# *Returns*:: Array of MEDLINE formatted String
|
117
|
+
def efetch(ids, hash = {})
|
118
|
+
opts = { "db" => "pubmed", "rettype" => "medline" }
|
119
|
+
opts.update(hash)
|
120
|
+
super(ids, opts)
|
121
|
+
end
|
122
|
+
|
123
|
+
# Search the PubMed database by given keywords using entrez query and returns
|
124
|
+
# an array of PubMed IDs. Caution: this method returns the first 20 hits only.
|
125
|
+
# Instead, use of the 'esearch' method is strongly recomended.
|
126
|
+
# ---
|
127
|
+
# *Arguments*:
|
128
|
+
# * _id_: query string (required)
|
129
|
+
# *Returns*:: array of PubMed IDs
|
130
|
+
def search(str)
|
131
|
+
host = "www.ncbi.nlm.nih.gov"
|
132
|
+
path = "/sites/entrez?tool=bioruby&cmd=Search&doptcmdl=Brief&db=PubMed&term="
|
133
|
+
|
134
|
+
ncbi_access_wait
|
135
|
+
|
136
|
+
http = Bio::Command.new_http(host)
|
137
|
+
response, = http.get(path + CGI.escape(str))
|
138
|
+
result = response.body
|
139
|
+
result = result.scan(/value="(\d+)" id="UidCheckBox"/m).flatten
|
140
|
+
return result
|
141
|
+
end
|
142
|
+
|
143
|
+
# Retrieve PubMed entry by PMID and returns MEDLINE formatted string using
|
144
|
+
# entrez query.
|
145
|
+
# ---
|
146
|
+
# *Arguments*:
|
147
|
+
# * _id_: PubMed ID (required)
|
148
|
+
# *Returns*:: MEDLINE formatted String
|
149
|
+
def query(*ids)
|
150
|
+
host = "www.ncbi.nlm.nih.gov"
|
151
|
+
path = "/sites/entrez?tool=bioruby&cmd=Text&dopt=MEDLINE&db=PubMed&uid="
|
152
|
+
list = ids.join(",")
|
153
|
+
|
154
|
+
ncbi_access_wait
|
155
|
+
|
156
|
+
http = Bio::Command.new_http(host)
|
157
|
+
response, = http.get(path + list)
|
158
|
+
result = response.body
|
159
|
+
result = result.scan(/<pre>\s*(.*?)<\/pre>/m).flatten
|
160
|
+
|
161
|
+
if result =~ /id:.*Error occurred/
|
162
|
+
# id: xxxxx Error occurred: Article does not exist
|
163
|
+
raise( result )
|
164
|
+
else
|
165
|
+
if ids.size > 1
|
166
|
+
return result
|
167
|
+
else
|
168
|
+
return result.first
|
169
|
+
end
|
170
|
+
end
|
171
|
+
end
|
172
|
+
|
173
|
+
# Retrieve PubMed entry by PMID and returns MEDLINE formatted string using
|
174
|
+
# entrez pmfetch.
|
175
|
+
# ---
|
176
|
+
# *Arguments*:
|
177
|
+
# * _id_: PubMed ID (required)
|
178
|
+
# *Returns*:: MEDLINE formatted String
|
179
|
+
def pmfetch(id)
|
180
|
+
host = "www.ncbi.nlm.nih.gov"
|
181
|
+
path = "/entrez/utils/pmfetch.fcgi?tool=bioruby&mode=text&report=medline&db=PubMed&id="
|
182
|
+
|
183
|
+
ncbi_access_wait
|
184
|
+
|
185
|
+
http = Bio::Command.new_http(host)
|
186
|
+
response, = http.get(path + id.to_s)
|
187
|
+
result = response.body
|
188
|
+
if result =~ /#{id}\s+Error/
|
189
|
+
raise( result )
|
190
|
+
else
|
191
|
+
result = result.gsub("\r", "\n").squeeze("\n").gsub(/<\/?pre>/, '')
|
192
|
+
return result
|
193
|
+
end
|
194
|
+
end
|
195
|
+
|
196
|
+
def self.esearch(*args)
|
197
|
+
self.new.esearch(*args)
|
198
|
+
end
|
199
|
+
|
200
|
+
def self.efetch(*args)
|
201
|
+
self.new.efetch(*args)
|
202
|
+
end
|
203
|
+
|
204
|
+
def self.search(*args)
|
205
|
+
self.new.search(*args)
|
206
|
+
end
|
207
|
+
|
208
|
+
def self.query(*args)
|
209
|
+
self.new.query(*args)
|
210
|
+
end
|
211
|
+
|
212
|
+
def self.pmfetch(*args)
|
213
|
+
self.new.pmfetch(*args)
|
214
|
+
end
|
215
|
+
|
216
|
+
end # PubMed
|
217
|
+
|
218
|
+
end # Bio
|
219
|
+
|
220
|
+
|
221
|
+
if __FILE__ == $0
|
222
|
+
|
223
|
+
puts "=== instance methods ==="
|
224
|
+
|
225
|
+
pubmed = Bio::PubMed.new
|
226
|
+
|
227
|
+
puts "--- Search PubMed by E-Utils ---"
|
228
|
+
opts = {"rettype" => "count"}
|
229
|
+
puts Time.now
|
230
|
+
puts pubmed.esearch("(genome AND analysis) OR bioinformatics", opts)
|
231
|
+
puts Time.now
|
232
|
+
puts pubmed.esearch("(genome AND analysis) OR bioinformatics", opts)
|
233
|
+
puts Time.now
|
234
|
+
puts pubmed.esearch("(genome AND analysis) OR bioinformatics", opts)
|
235
|
+
puts Time.now
|
236
|
+
pubmed.esearch("(genome AND analysis) OR bioinformatics").each do |x|
|
237
|
+
puts x
|
238
|
+
end
|
239
|
+
|
240
|
+
puts "--- Retrieve PubMed entry by E-Utils ---"
|
241
|
+
puts Time.now
|
242
|
+
puts pubmed.efetch(16381885)
|
243
|
+
puts Time.now
|
244
|
+
puts pubmed.efetch("16381885")
|
245
|
+
puts Time.now
|
246
|
+
puts pubmed.efetch("16381885")
|
247
|
+
puts Time.now
|
248
|
+
opts = {"retmode" => "xml"}
|
249
|
+
puts pubmed.efetch([10592173, 14693808], opts)
|
250
|
+
puts Time.now
|
251
|
+
puts pubmed.efetch(["10592173", "14693808"], opts)
|
252
|
+
|
253
|
+
puts "--- Search PubMed by Entrez CGI ---"
|
254
|
+
pubmed.search("(genome AND analysis) OR bioinformatics").each do |x|
|
255
|
+
p x
|
256
|
+
end
|
257
|
+
|
258
|
+
puts "--- Retrieve PubMed entry by Entrez CGI ---"
|
259
|
+
puts pubmed.query("16381885")
|
260
|
+
|
261
|
+
|
262
|
+
puts "--- Retrieve PubMed entry by PMfetch ---"
|
263
|
+
puts pubmed.pmfetch("16381885")
|
264
|
+
|
265
|
+
|
266
|
+
puts "=== class methods ==="
|
267
|
+
|
268
|
+
|
269
|
+
puts "--- Search PubMed by E-Utils ---"
|
270
|
+
opts = {"rettype" => "count"}
|
271
|
+
puts Time.now
|
272
|
+
puts Bio::PubMed.esearch("(genome AND analysis) OR bioinformatics", opts)
|
273
|
+
puts Time.now
|
274
|
+
puts Bio::PubMed.esearch("(genome AND analysis) OR bioinformatics", opts)
|
275
|
+
puts Time.now
|
276
|
+
puts Bio::PubMed.esearch("(genome AND analysis) OR bioinformatics", opts)
|
277
|
+
puts Time.now
|
278
|
+
Bio::PubMed.esearch("(genome AND analysis) OR bioinformatics").each do |x|
|
279
|
+
puts x
|
280
|
+
end
|
281
|
+
|
282
|
+
puts "--- Retrieve PubMed entry by E-Utils ---"
|
283
|
+
puts Time.now
|
284
|
+
puts Bio::PubMed.efetch(16381885)
|
285
|
+
puts Time.now
|
286
|
+
puts Bio::PubMed.efetch("16381885")
|
287
|
+
puts Time.now
|
288
|
+
puts Bio::PubMed.efetch("16381885")
|
289
|
+
puts Time.now
|
290
|
+
opts = {"retmode" => "xml"}
|
291
|
+
puts Bio::PubMed.efetch([10592173, 14693808], opts)
|
292
|
+
puts Time.now
|
293
|
+
puts Bio::PubMed.efetch(["10592173", "14693808"], opts)
|
294
|
+
|
295
|
+
puts "--- Search PubMed by Entrez CGI ---"
|
296
|
+
Bio::PubMed.search("(genome AND analysis) OR bioinformatics").each do |x|
|
297
|
+
p x
|
298
|
+
end
|
299
|
+
|
300
|
+
puts "--- Retrieve PubMed entry by Entrez CGI ---"
|
301
|
+
puts Bio::PubMed.query("16381885")
|
302
|
+
|
303
|
+
|
304
|
+
puts "--- Retrieve PubMed entry by PMfetch ---"
|
305
|
+
puts Bio::PubMed.pmfetch("16381885")
|
306
|
+
|
307
|
+
end
|