rbbt-sources 3.1.52 → 3.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 19722279e8b56d1b0cb9e72001e11333e8e436d3a59bf746be3ed744afd047e1
-  data.tar.gz: 7eca716d5a2ee5ab6ba35547230d01466417f373df775fda110cae79366b56d5
+  metadata.gz: 973d827d476c42023692f813a588ad500da04dd27f6903e1da9c74673985b40e
+  data.tar.gz: ed995de19a62f17908c2b7ed3f327782c75ece60aa0f7c5f373cc9309228c8b5
 SHA512:
-  metadata.gz: 9acfd6f4718444fed3891d431e49396d42293105767915375bf86d485e84ed58c5dbb81eff6509ced77e6ae15c38bbbcf91d52590aca6d53e0b3feb4db8c90b6
-  data.tar.gz: 572c173002d2bad704df755542448fc294071c0849bfbac997ce254001591fb463ea8244c167066953224b1e758108ef91417a10b22c02bd0991d819efc68453
+  metadata.gz: cff68ce8c57381ec1581a6df61b56d40384b108030f87858ea1a735a82b8922b9d71a8b8a42930846f30186610058cbf738dccfb788ebf49e3f4d5e1b000809f
+  data.tar.gz: 771625cad70732c54cc2a1b798f6c0ac44004e73a9435e6699a7988a0904e987fecd9e375e6f888061b0f88a4c03ff3200322c59ca75a7f8f83dcdad8b19b156

data/LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2010-2022 Miguel Vázquez García
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/etc/allowed_biomart_archives

@@ -2,3 +2,4 @@ may2009
 feb2014
 may2017
 apr2019
+feb2021

data/lib/rbbt/sources/clinvar.rb

@@ -58,8 +58,10 @@ module ClinVar
     require 'rbbt/workflow'
     Workflow.require_workflow "Sequence"
     variants = ClinVar.hg19.snv_summary.produce
-    muts = CMD.cmd('cut -f 1', :in => variants.open, :pipe => true)
-    consequence = Sequence.job(:mutated_isoforms_fast, "Clinvar", :mutations => muts, :non_synonymous => true, :organism => ClinVar.organism_hg19).clean.run(true)
+    muts = CMD.cmd("cut -f 1 #{ variants.find }",  :pipe => true)
+    consequence = Sequence.job(:mutated_isoforms_fast, "Clinvar", :mutations => muts, :non_synonymous => true, :organism => ClinVar.organism_hg19)
+    consequence.run
+    iif consequence
 
     options = TSV.parse_header(variants).options.merge({:key_field => "Mutated Isoform"})
     fields = options[:fields].length

data/lib/rbbt/sources/organism.rb

@@ -72,9 +72,10 @@ module Organism
 
   def self.hg_build(organism)
     require 'rbbt/sources/ensembl_ftp'
+    organism = organism.strip 
     return organism if organism =~ /^hg\d\d$/
 
-    return 'hg19' unless organism =~ /\//
+    return organism unless organism =~ /\//
 
     species, date = organism.split("/")
 
@@ -101,35 +102,43 @@ module Organism
     end
   end
 
-  def self.GRC_build(organism)
+  def self.GRC_build(organism, with_release = false)
     require 'rbbt/sources/ensembl_ftp'
-    return organism if organism =~ /^hg\d\d$/
+    return organism if organism =~ /^GRC$/
 
-    return 'hg19' unless organism =~ /\//
+    if organism == "hg19" || organism == "b37"
+      return "GRCh37"
+    elsif organism == "hg38"
+      return "GRCh38"
+    end
 
-    species, date = organism.split("/")
+    return self.GRC_build(default_code(organism)) unless organism =~ /\//
 
-    case species
-    when "Hsa"
-      date = organism.split("/")[1] 
+    species, date = organism.split("/")
 
-      release = Ensembl.releases[date]
+    build = case species
+            when "Hsa"
+              date = organism.split("/")[1] 
+
+              release = Ensembl.releases[date]
+
+              release_number = release.sub(/.*-/,'').to_i
+              if release_number <= 54 
+                'GRCh36'
+              elsif release_number <= 75
+                'GRCh37'
+              else
+                'GRCh38'
+              end
+            when "Mmu"
+              "GRCm38"
+            when "Rno"
+              "Rnor_6.0"
+            else
+              raise "Only organism 'Hsa' (Homo sapiens) and Mmu (Mus musculus) supported" 
+            end
 
-      release_number = release.sub(/.*-/,'').to_i
-      if release_number <= 54 
-        'GRCh36'
-      elsif release_number <= 75
-        'GRCh37'
-      else
-        'GRCh38'
-      end
-    when "Mmu"
-      "GRCm38"
-    when "Rno"
-      "Rnor_6.0"
-    else
-      raise "Only organism 'Hsa' (Homo sapiens) and Mmu (Mus musculus) supported" 
-    end
+    (release_number && with_release) ? build + "." + release_number.to_s : build
   end
 
   def self.organism_for_build(build)
@@ -332,4 +341,5 @@ module Organism
 
     chromosome_sizes
   end
+
 end

data/lib/rbbt/sources/pubmed.rb

@@ -1,5 +1,4 @@
 require 'rbbt-util'
-require 'libxml'
 require 'rbbt/sources/gscholar'
 require 'rbbt/util/filecache'
 
@@ -53,32 +52,38 @@ module PubMed
       [lastname.gsub(/\s/,'_'), year || "NOYEAR", abrev] * ""
     end
     def self.parse_xml(xml)
-      parser  = LibXML::XML::Parser.string(xml)
-      pubmed  = parser.parse.find("/PubmedArticle").first
-      medline = pubmed.find("MedlineCitation").first
-      article = medline.find("Article").first
+      require 'nokogiri'
+
+      #parser  = LibXML::XML::Parser.string(xml)
+      #pubmed  = parser.parse.find("/PubmedArticle").first
+      #medline = parser.find("MedlineCitation").first
+      #article = medline.find("Article").first
+
+      parser  = Nokogiri.XML(xml)
+      medline = parser.search("MedlineCitation").first
+      article = medline.search("Article").first
 
       info = {}
 
-      info[:pmid] = medline.find("PMID").first.content
+      info[:pmid] = medline.search("PMID").first.content
 
       XML_KEYS.each do |p|
         name, key = p
-        node = article.find(key).first
+        nodes = article.search(key)
 
-        next if node.nil?
+        next if nodes.nil? || nodes.empty?
 
-        info[name] = node.content
+        info[name] = nodes.collect{|n| n.content } * "\n\n"
       end
 
       bibentry = nil
-      info[:author] = article.find("AuthorList/Author").collect do |author|
+      info[:author] = article.search("AuthorList/Author").collect do |author|
         begin
-          lastname = author.find("LastName").first.content
-          if author.find("ForeName").first.nil?
+          lastname = author.search("LastName").first.content
+          if author.search("ForeName").first.nil?
             forename = nil
           else
-            forename = author.find("ForeName").first.content.split(/\s/).collect{|word| if word.length == 1; then word + '.'; else word; end} * " "
+            forename = author.search("ForeName").first.content.split(/\s/).collect{|word| if word.length == 1; then word + '.'; else word; end} * " "
           end
           bibentry ||= make_bibentry lastname, info[:year], info[:title]
         rescue
@@ -88,7 +93,7 @@ module PubMed
 
       info[:bibentry] = bibentry.downcase if bibentry
 
-      info[:pmc_pdf] = pubmed.find("PubmedData/ArticleIdList/ArticleId").select{|id| id[:IdType] == "pmc"}.first
+      info[:pmc_pdf] = parser.search("PubmedData/ArticleIdList/ArticleId").select{|id| id[:IdType] == "pmc"}.first
 
       if info[:pmc_pdf]
         info[:pmc_pdf] = PMC_PDF_URL.sub(/PMCID/, info[:pmc_pdf].content)
@@ -270,7 +275,7 @@ module PubMed
         result[pmid] = xml
       end
 
-      ids.each{|id| next if id.nil? or result[id]; fid = id.sub(/^0+/,''); next unless result[fid]; result[id] = result[fid]}
+      ids.each{|id| next if id.nil? or result[id]; fid = String === id ? id.sub(/^0+/,'') : id; next unless result[fid]; result[id] = result[fid]}
       ids.each{|id| next if id.nil? or result[id]; result[id] = ""}
 
       result

data/lib/rbbt/sources/uniprot.rb

@@ -33,6 +33,8 @@ module UniProt
         "Ensembl Transcript ID"
       when "Ensembl_PRO"
         "Ensembl Protein ID"
+      when "GeneID"
+        "Entrez Gene ID"
       else
         field
       end
@@ -64,6 +66,11 @@ module UniProt
     tsv.to_s
   end
 
+  UniProt.claim UniProt.identifiers.Rno, :proc do
+    url = "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/idmapping/by_organism/RAT_10116_idmapping.dat.gz"
+    tsv = UniProt.get_organism_ids(url, "Rno")
+    tsv.to_s
+  end
 
   UniProt.claim UniProt.annotated_variants, :proc do
     url = "https://www.uniprot.org/docs/humsavar.txt"

data/share/Ensembl/release_dates

@@ -1,5 +1,8 @@
 #: :type=:single
 #Release	build
+release-103	feb2021
+release-102	nov2020
+release-101	aug2020
 release-100	apr2020
 release-99	jan2020
 release-98	sep2019

data/share/install/Organism/organism_helpers.rb

@@ -169,11 +169,11 @@ end
 file 'lexicon' => 'identifiers' do |t|
   tsv = TSV.open(t.prerequisites.first).slice(["Associated Gene Name", "Entrez Gene Name Synonyms"])
 
-  entrez_description = Rbbt.share.databases.entrez.gene_info.tsv :grep => $taxs.collect{|tax| "^#{tax}"}, :key_field => 1, :fields => 8
+  entrez_description = Rbbt.share.databases.entrez.gene_info.tsv :grep => $taxs.collect{|tax| "^#{tax}"}, :fixed_grep => false, :key_field => 1, :fields => 8
   entrez_description.key_field = "Entrez Gene ID"
   entrez_description.fields = ["Entrez Gene Description"]
 
-  tsv.attach entrez_description
+  tsv = tsv.attach entrez_description
   Misc.sensiblewrite(t.name, tsv.to_s)
 end
 
@@ -220,7 +220,7 @@ file 'transcript_cds' do |t|
 end
 
 file 'gene_positions' do |t|
-  sequences = BioMart.tsv($biomart_db, $biomart_ensembl_gene, $biomart_gene_positions, [])
+  sequences = BioMart.tsv($biomart_db, $biomart_ensembl_gene, $biomart_gene_positions, [], nil, :type => :list, :namespace => Thread.current['namespace'])
 
   Misc.sensiblewrite(t.name, sequences.to_s)
 end

data/test/rbbt/sources/test_pubmed.rb

@@ -12,6 +12,12 @@ class TestPubMed < Test::Unit::TestCase
     pmids = ['16438716', 17204154]
     assert(PubMed.get_article(pmids)[pmid].title == "Discovering semantic features in the literature: a foundation for building functional associations.")
   end
+
+  def test_get_multi_abstract
+    pmid = "32141403"
+
+    assert PubMed.get_article(pmid).abstract.include?("This study shows PCOS patients are at increased risk of incident schizophrenia, and the metformin treatment has a protective effect against incident schizophrenia.")
+  end
  
   def test_full_text
     pmid = '16438716'

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rbbt-sources
 version: !ruby/object:Gem::Version
-  version: 3.1.52
+  version: 3.2.1
 platform: ruby
 authors:
 - Miguel Vazquez
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2021-04-06 00:00:00.000000000 Z
+date: 2022-12-15 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rbbt-util
@@ -39,7 +39,7 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: libxml-ruby
+  name: nokogiri
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -70,8 +70,10 @@ description: Data sources like PubMed, Entrez Gene, or Gene Ontology
 email: miguel.vazquez@fdi.ucm.es
 executables: []
 extensions: []
-extra_rdoc_files: []
+extra_rdoc_files:
+- LICENSE
 files:
+- LICENSE
 - etc/allowed_biomart_archives
 - etc/biomart/missing_in_archive
 - etc/build_organism