rbbt-sources 3.2.15 → 3.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: df44bcf0d03a785f8aa9b36b123491ed49187f710e70a346b645f257701a0ac2
-  data.tar.gz: feef523710ea56093cdf4ff2df36d28f57a426a906e13ce3edbe6f71f7272452
+  metadata.gz: b10dbe140b4c0733476823e5f5d94e57a3d9a755fc370f6b9640d1e7b8efc368
+  data.tar.gz: 38aaf56670a07537ad0ef0c025d17e655fc5d7fb87d97ee1c08d0af82c44fbbd
 SHA512:
-  metadata.gz: 3766aa7ce01f4ad44b7f759faa7b2790d4cdd3808a546978a06312f95662aa1ba6dc8d916c8b29d3d8f10699adc21cb80e55a496a2d8c9ec5a39191cdcd415d0
-  data.tar.gz: 4882abf0ac721753c7f31e2f85d66e3f537c6b28b4cb62337b76031d1109a89c1cfb7c6409c535a3f49990c6ce4b32a76c476da6c7736361480ea423d0b0a1c9
+  metadata.gz: a8ac9df1da30fc7aec3c54a5a200a0c7a9629807b9238089a1e8064e78b0ecd5bad36c4b6a77fac7e7cfdf332ad56be06149b12d0e0fd7f6506b0b82d2e03bcf
+  data.tar.gz: acff50e8bdb0d4443c3e1dbd237539953206b7d5dcb886db64ec0677f7bba43cf3a9782e4147985a9b3fc1b34df692e89fb2b7185f2aa0f93ccd196a4d19d54a

data/etc/allowed_biomart_archives

@@ -1,6 +1,8 @@
 may2009
 feb2014
 may2017
+oct2018
 apr2019
 feb2021
 feb2023
+oct2016

data/lib/rbbt/sources/PRO.rb

@@ -14,7 +14,7 @@ module PRO
   #self.search_paths[:default] = :lib
 
   PRO.claim PRO.identifiers, :proc do 
-    url = "ftp://ftp.pir.georgetown.edu/databases/ontology/pro_obo/PRO_mappings/uniprotmapping.txt"
+    url = "ftp://ftp.proteininformationresource.org/databases/ontology/pro_obo/PRO_mappings/uniprotmapping.txt"
 
     dumper = TSV::Dumper.new :key_field => "PRO ID", :fields => ["UniProt/SwissProt Accession"], :type => :double, :namespace => PRO.organism
     dumper.init
@@ -22,7 +22,7 @@ module PRO
       pro, uni = line.split("\t")
       [pro, [uni.split(":").last]]
     end
-    TSV.collapse_stream dumper
+    dumper.tsv merge: true
   end
 
   PRO.claim PRO.uniprot_equivalences, :proc do

data/lib/rbbt/sources/biomart.rb

@@ -15,7 +15,7 @@ module BioMart
 
   BIOMART_URL = 'http://www.ensembl.org/biomart/martservice?query='
 
-  MISSING_IN_ARCHIVE = Rbbt.etc.biomart.missing_in_archive.exists? ? Rbbt.etc.biomart.missing_in_archive.yaml : {}
+  MISSING_IN_ARCHIVE = Rbbt.etc.biomart.missing_in_archive.exists? ? Rbbt.etc.biomart.missing_in_archive.find.yaml : {}
 
   private
 
@@ -33,7 +33,7 @@ module BioMart
    
   def self.set_archive(date)
     if defined? Rbbt and Rbbt.etc.allowed_biomart_archives.exists?
-      raise "Biomart archive #{ date } is not allowed in this installation" unless Rbbt.etc.allowed_biomart_archives.read.split("\n").include? date
+      raise "Biomart archive #{ date } is not allowed in this installation" unless Rbbt.etc.allowed_biomart_archives.find.read.split("\n").include? date
     end
     Thread.current['archive'] = date
     Thread.current['archive_url'] = BIOMART_URL.sub(/www/, date + '.archive')

data/lib/rbbt/sources/go.rb

@@ -18,7 +18,7 @@ module GO
 
 
   MULTIPLE_VALUE_FIELDS = %w(is_a)
-  TSV_GENE_ONTOLOGY = File.join(Persist.cachedir, 'gene_ontology')
+  #TSV_GENE_ONTOLOGY = File.join(Persist.cachedir, 'gene_ontology')
 
   # This method needs to be called before any translations can be made, it is
   # called automatically the first time the id2name method is called. It loads

data/lib/rbbt/sources/pubmed.rb

@@ -241,11 +241,13 @@ module PubMed
     pmids = [pmids] unless Array === pmids
     pmids = pmids.compact.collect{|id| id}
 
+    chunk_size = 50
     result_files = FileCache.cache_online_elements(pmids, 'pubmed-{ID}.xml') do |ids|
       result = {}
       values = []
-      chunks = Misc.divide(ids, (ids.length / 20) + 1)
+      chunks = Misc.divide(ids, (ids.length / chunk_size) + 1)
       Log::ProgressBar.with_bar(chunks.length, :desc => "Downloading articles from PubMed") do |bar|
+        bar.init
         chunks.each do |list|
           begin
             Misc.try3times do

data/lib/rbbt/sources/signor.rb

@@ -19,7 +19,11 @@ module Signor
   end
   
   Signor.claim Signor.data, :proc do
-    Signor[".source/all.csv"].tsv :header_hash => '', :merge => true, :zipped => true
+    begin
+      Signor[".source/all.csv"].tsv :header_hash => '', :merge => true, :zipped => true
+    rescue
+      Signor[".source/all.csv"].tsv :header_hash => '', :merge => true, :one2one => true
+    end
   end
 
   Signor.claim Signor.protein_protein, :proc do 
@@ -57,7 +61,7 @@ module Signor
     #uni2name = Organism.identifiers(organism).index :target => "Associated Gene Name", :fields => ["UniProt/SwissProt Accession"], :persist => true
     uni2name = UniProt.identifiers.Hsa.index :target => "Associated Gene Name", :fields => ["UniProt/SwissProt Accession"], :persist => true
 
-    parser = TSV::Parser.new Signor.data
+    parser = TSV::Parser.new Signor.data.produce
     fields = parser.fields
     dumper = TSV::Dumper.new :key_field => "Source (UniProt/SwissProt Accession)", :fields => ["Target (Associated Gene Name)", "Effect", "Sign", "PMID"], :type => :double, :merge => true, :organism => Signor.organism
     dumper.init

data/lib/rbbt/sources/tfacts.rb

@@ -114,6 +114,7 @@ module TFactS
         pmids = "" if pmids.nil?
 
         values = [target, "", species, source, pmids]
+        values = values.collect{|v| [v]}
         tsv.zip_new(tf, values)
       end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rbbt-sources
 version: !ruby/object:Gem::Version
-  version: 3.2.15
+  version: 3.3.0
 platform: ruby
 authors:
 - Miguel Vazquez
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2023-03-29 00:00:00.000000000 Z
+date: 2023-12-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rbbt-util
@@ -24,20 +24,6 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: 4.0.0
-- !ruby/object:Gem::Dependency
-  name: nokogiri
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
 - !ruby/object:Gem::Dependency
   name: net-ftp
   requirement: !ruby/object:Gem::Requirement
@@ -178,24 +164,24 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.4.8
+rubygems_version: 3.5.0.dev
 signing_key: 
 specification_version: 4
 summary: Data sources for the Ruby Bioinformatics Toolkit (rbbt)
 test_files:
+- test/rbbt/sources/test_HPRD.rb
+- test/rbbt/sources/test_biomart.rb
+- test/rbbt/sources/test_entrez.rb
 - test/rbbt/sources/test_go.rb
-- test/rbbt/sources/test_pubmed.rb
-- test/rbbt/sources/test_pina.rb
-- test/rbbt/sources/test_pharmagkb.rb
+- test/rbbt/sources/test_gscholar.rb
+- test/rbbt/sources/test_kegg.rb
+- test/rbbt/sources/test_matador.rb
 - test/rbbt/sources/test_organism.rb
-- test/rbbt/sources/test_synapse.rb
-- test/rbbt/sources/test_entrez.rb
+- test/rbbt/sources/test_pharmagkb.rb
+- test/rbbt/sources/test_pina.rb
+- test/rbbt/sources/test_pubmed.rb
 - test/rbbt/sources/test_stitch.rb
-- test/rbbt/sources/test_biomart.rb
-- test/rbbt/sources/test_HPRD.rb
 - test/rbbt/sources/test_string.rb
-- test/rbbt/sources/test_kegg.rb
+- test/rbbt/sources/test_synapse.rb
 - test/rbbt/sources/test_tfacts.rb
-- test/rbbt/sources/test_matador.rb
-- test/rbbt/sources/test_gscholar.rb
 - test/test_helper.rb