rbbt-sources 3.1.20 → 3.1.21

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: e0d1135b2d31c8801bd915bd416feafec1443966
-  data.tar.gz: 272bc72050bc2f739ca9460c10e405b45cfdca2d
+  metadata.gz: 2bdca7fd8c0c9f60055453c7f318a699eae54738
+  data.tar.gz: c0b08856ddd9668b6dbbadd2035653ce24506f04
 SHA512:
-  metadata.gz: 9a6e516f2d0188889fedbc4dd6f0e4d88b1c5efe1b0a01c8182e9489387ce92bea658b89d02f22e2e2a326c8529336917693fe5023f8228b4e24e83fbad71b57
-  data.tar.gz: 8b2bf37685804053dd25fa3de734ab62e886199253290d0dff75c1aa2ecdb24c0f62925a5102191c98e3e8b1f0025f593a02b919c17221f454a958ab607c241f
+  metadata.gz: 4e515516855aa249e758a23da1d1d16915697cf3647bf88c0791b5593b435c2adf4b44006081473d4068a76b55d8b018093cba49070144044c68aa3d9611450c
+  data.tar.gz: eed95d673673f5ec047b37911c44d6876fbd55d7efdc4884863902f6d76bdeda22e5ac5a1982344488ff8fb68808c8233df78eb0baa1e9fa5a2d712485296577

data/etc/allowed_biomart_archives

@@ -5,3 +5,4 @@ feb2014
 dec2014
 dec2015
 oct2016
+may2017

data/lib/rbbt/sources/go.rb

@@ -6,8 +6,9 @@ require 'rbbt/persist/tsv'
 # now all it does is provide a translation form id to the actual names.
 module GO
 
-  Rbbt.claim Rbbt.share.databases.GO.gene_ontology, :url, 'ftp://ftp.geneontology.org/pub/go/ontology/gene_ontology.obo'
-  Rbbt.claim Rbbt.share.databases.GO.gslim_generic, :url, 'http://www.geneontology.org/GO_slims/goslim_generic.obo'
+  #Rbbt.claim Rbbt.share.databases.GO.gslim_generic, :url, 'http://www.geneontology.org/GO_slims/goslim_generic.obo'
+  Rbbt.claim Rbbt.share.databases.GO.gene_ontology, :url, 'http://purl.obolibrary.org/obo/go.obo'
+  Rbbt.claim Rbbt.share.databases.GO.annotations, :url, 'http://geneontology.org/gene-associations/goa_human.gaf.gz'
 
   MULTIPLE_VALUE_FIELDS = %w(is_a)
   TSV_GENE_ONTOLOGY = File.join(Persist.cachedir, 'gene_ontology')
@@ -57,6 +58,21 @@ module GO
     end
   end
 
+  def self.descendants(id)
+    list = Set.new
+    new = Set.new
+    new << id
+    while new.any?
+      list += new
+      new = Set.new
+      info.each do |new_id,values|
+        next unless values['is_a']
+        new << new_id if values['is_a'].select{|e| list.include? e.split("!").first[/GO:\d+/] }.any? && ! list.include?(new_id)
+      end
+    end
+    list
+  end
+
   def self.id2ancestors_by_type(id, type='is_a')
     if id.kind_of? Array
       info.values_at(*id).
@@ -93,7 +109,7 @@ module GO
     end
   end
 
-  def self.ancestors_in(term, valid)
+  def self.ancestors_in(term, valid = false)
     ancestors = id2ancestors(term)
     return ancestors if FalseClass === valid
     valid_ancestors = ancestors & valid

data/lib/rbbt/sources/oreganno.rb

@@ -0,0 +1,38 @@
+require 'rbbt-util'
+require 'rbbt/resource'
+
+module Oreganno
+  extend Resource
+  self.subdir = 'share/databases/Oreganno'
+
+  def self.organism(org="Hsa")
+    require 'rbbt/sources/organism'
+    Organism.default_code(org)
+  end
+
+  #self.search_paths = {}
+  #self.search_paths[:default] = :lib
+
+
+  Oreganno.claim Oreganno.data, :proc do 
+    url = "http://www.oreganno.org/dump/ORegAnno_Combined_2016.01.19.tsv"
+    TSV.open(url, :header_hash => '', :type => :list).to_s
+  end
+
+  Oreganno.claim Oreganno.tf_tg, :proc do
+    dumper = TSV::Dumper.new :key_field => "Transcription Factor (Associated Gene Name)", :fields => ["Target Gene (Associated Gene Name)"], :type => :flat, :namespace => Oreganno.organism
+    dumper.init
+    TSV.traverse Oreganno.data, :type => :array, :into => dumper, :bar => true do |line|
+      parts = line.split("\t")
+      next unless parts[1] == "Homo sapiens"
+      tf = parts[4]
+      tg = parts[7]
+      next if tf == "N/A" or tg == "N/A"
+      [tf, [tg]]
+    end
+    TSV.collapse_stream dumper
+  end
+end
+
+iif Oreganno.tf_tg.produce(true).find if __FILE__ == $0
+

data/lib/rbbt/sources/organism.rb

@@ -79,7 +79,7 @@ module Organism
     elsif release_number <= 75
       'hg19'
     else
-      'hg20'
+      'hg38'
     end
   end
 
@@ -88,14 +88,7 @@ module Organism
     source_hg = hg_build(source)
     target_hg = hg_build(target)
 
-    case
-    when (source_hg == 'hg19' and target_hg == 'hg18')
-      map_url = "http://hgdownload.cse.ucsc.edu/goldenPath/hg19/liftOver/hg19ToHg18.over.chain.gz" 
-    when (source_hg == 'hg18' and target_hg == 'hg19')
-      map_url = "http://hgdownload.cse.ucsc.edu/goldenPath/hg18/liftOver/hg18ToHg19.over.chain.gz" 
-    else
-      return positions
-    end
+    map_url = "http://hgdownload.cse.ucsc.edu/goldenPath/#{source_hg}/liftOver/#{source_hg}To#{target_hg.sub('h', 'H')}.over.chain.gz" 
 
     positions_bed = positions.collect{|position| 
       chr, pos = position.split(":").values_at(0,1)

data/lib/rbbt/sources/signor.rb

@@ -18,19 +18,6 @@ module Signor
   end
   
   Signor.claim Signor.data, :proc do
-    #io = Misc.open_pipe do |sin|
-    #  Signor[".source/all.csv"].open do |f|
-    #    quoted = false
-    #    while c = f.getc
-    #      if c == '"'
-    #        quoted = ! quoted
-    #      end
-    #      c = " " if c == "\n" and quoted
-    #      sin << c
-    #    end
-    #  end
-    #end
-
     sio = Signor[".source/all.csv"].open
     io_tmp = Misc.remove_quoted_new_line(sio)
     io = Misc.swap_quoted_character(io_tmp, ';', '--SEMICOLON--')
@@ -71,7 +58,47 @@ module Signor
 
     Misc.collapse_stream dumper.stream
   end
+
+  Signor.claim Signor.tf_tg, :proc do 
+    require 'rbbt/sources/organism'
+
+    organism = Organism.default_code("Hsa")
+    uni2name = Organism.identifiers(organism).index :target => "Associated Gene Name", :fields => ["UniProt/SwissProt Accession"], :persist => true
+
+    parser = TSV::Parser.new Signor.data
+    fields = parser.fields
+    dumper = TSV::Dumper.new :key_field => "Source (UniProt/SwissProt Accession)", :fields => ["Target (Associated Gene Name)", "Effect", "Sign", "PMID"], :type => :double, :organism => Signor.organism
+    dumper.init
+    TSV.traverse parser, :into => dumper do |k,values|
+      info = {}
+      fields.zip(values).each do |field, value|
+        info[field] = value
+      end
+      next unless info["TYPEA"].first == "protein"
+      unia = info["IDA"].first
+
+      res = []
+      res.extend MultipleResult
+
+      info["TYPEB"].zip(info["IDB"]).zip(info["EFFECT"]).zip(info["MECHANISM"]).zip(info["PMID"]).each do |v|
+        typeb,idb,eff,mech,pmid = v.flatten
+        
+        next unless typeb == "protein"
+        next unless mech == "transcriptional regulation"
+        nameb = uni2name[idb]
+        next if nameb.nil?
+        sign = "Unknown"
+        sign = "UP" if eff.include? 'up-regulates'
+        sign = "DOWN" if eff.include? 'down-regulates'
+        res << [unia, [nameb, eff, sign, pmid]]
+      end
+
+      res
+    end
+
+    Misc.collapse_stream dumper.stream
+  end
 end
 
-iif Signor.protein_protein.produce(true).find if __FILE__ == $0
+iif Signor.tf_tg.produce(true).find if __FILE__ == $0
 

data/test/rbbt/sources/test_go.rb

@@ -34,8 +34,6 @@ class TestGo < Test::Unit::TestCase
   def test_ancestors_in
     term = GOTerm.setup("GO:0005730")
     valid = %w(GO:0005886 GO:0005634 GO:0005730 GO:0005829)
-    iii term.name
-    iii GO.ancestors_in(term, valid)
   end
 
   def test_groups
@@ -44,12 +42,13 @@ class TestGo < Test::Unit::TestCase
 
     valid = %w(GO:0005886 GO:0005634 GO:0005730 GO:0005829 )
     valid = %w(GO:0005634 GO:0005730)
-    iii GO.group_genes(list, valid)
+    assert_equal GO.group_genes(list, valid)["GO:0005730"][:name], "nucleolus"
+    assert_equal GO.group_genes(list, valid)["GO:0005730"][:items].sort, %w(FBXW7 SP140)
   end
 
-  def test_nucleolus
-    nuo = "GO:0005730"
-    nu = "GO:0005634"
+  def test_descendants
+    assert GO.descendants("GO:0006281").include? "GO:0000012"
+    assert GO.descendants("GO:0006281").include? "GO:1990396"
   end
 end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rbbt-sources
 version: !ruby/object:Gem::Version
-  version: 3.1.20
+  version: 3.1.21
 platform: ruby
 authors:
 - Miguel Vazquez
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-10-20 00:00:00.000000000 Z
+date: 2017-12-01 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rbbt-util
@@ -114,6 +114,7 @@ files:
 - lib/rbbt/sources/kegg.rb
 - lib/rbbt/sources/matador.rb
 - lib/rbbt/sources/oncodrive_role.rb
+- lib/rbbt/sources/oreganno.rb
 - lib/rbbt/sources/organism.rb
 - lib/rbbt/sources/pfam.rb
 - lib/rbbt/sources/pharmagkb.rb