rbbt-sources 3.1.16 → 3.1.17

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: feef731c1d37abc9fcaf618086634f4bebde968c
-  data.tar.gz: 58d28f8048a043d406c0cc1f72fe3b44186ead5e
+  metadata.gz: bf8a7403301523a87252057d4be1ac9e0f348708
+  data.tar.gz: '0939814d7b68cb713e05b5f1af2a572a8fffee75'
 SHA512:
-  metadata.gz: b5fa5a78fe7e152691a92b6119202fdb0066fcf7377bafeb907b02519477221762c8b563239c26024700ee48f301e4377527f95441d87cadb50a26bc884dc626
-  data.tar.gz: cdb897373677da35b65aa93964af005ac1048a4097643a4ae0b1a67024f67dc90da5204b5eea928429039cc63c9da275c6faf3b99cc920f3e46ca893c8f3dcab
+  metadata.gz: 779c0aa427ee0335a2533533179e05ef0c42c543316ea7cd9eb3c5b793f6603ea46cf63bffba71df9aed9cec0fc08df984255c1c3a83fe85c9bb5b51048395d1
+  data.tar.gz: 8a78a7bc1e4ba4819849c0375a1d6744e20bce89cdaf91e1c21cd26d4541f2ff91bd1d5aa9bed05e38b211051cc51774df2b0d2eb198bd4500d94c95196d48ac

data/etc/allowed_biomart_archives

@@ -1,5 +1,6 @@
 may2009
 may2012
+sep2013
 jan2013
 feb2014
 dec2013

data/lib/rbbt/sources/CASCADE.rb

@@ -0,0 +1,177 @@
+require 'rbbt-util'
+require 'rbbt/resource'
+
+module CASCADE
+  extend Resource
+  self.subdir = 'share/databases/CASCADE'
+
+  #def self.organism(org="Hsa")
+  #  Organism.default_code(org)
+  #end
+
+  #self.search_paths = {}
+  #self.search_paths[:default] = :lib
+
+
+  URL = 'https://bitbucket.org/asmundf/cascade'
+  CASCADE.claim CASCADE.interactions, :proc do 
+    io = nil
+    TmpFile.with_file do |tmp|
+      Misc.in_dir tmp do
+        Log.warn "Please enter bitbucket credentials to access the asmundf/cascade repo"
+        `git clone #{URL}`
+        io = Open.open("cascade/cascade.tsv")
+      end
+    end
+
+    tsv = TSV.open(io, :merge => true, :header_hash => '')
+
+    new_fields = ["ENTITYB"] + (tsv.fields - ["ENTITYB"])
+    tsv = tsv.reorder :key, new_fields
+
+    tsv.key_field = "ENTITYA (Associated Gene Name)"
+    tsv.rename_field "ENTITYB", "ENTITYB (Associated Gene Name)"
+
+    tsv.process "PMID" do |values|
+      values.collect{|v| v.scan(/\d+/) * ";;"}
+    end
+
+    tsv.to_s
+  end
+
+  CASCADE.claim CASCADE.members, :proc do 
+    io = nil
+    TmpFile.with_file do |tmp|
+      Misc.in_dir tmp do
+        Log.warn "Please enter bitbucket credentials to access the asmundf/cascade repo"
+        `git clone #{URL}`
+        io = Open.open("cascade/cascade_translation.tsv")
+      end
+    end
+
+    tsv = TSV.open(io, :merge => true, :header_hash => '', :type => :flat, :sep2 => /[,.]\s*/)
+
+  end
+
+  CASCADE.claim CASCADE.paradigm, :proc do
+
+    tsv = CASCADE.interactions.tsv 
+    members = CASCADE.members.tsv 
+
+    proteins = Set.new members.values.flatten.uniq
+    outputs = Set.new
+    associations = {}
+
+    tsv.through do |source, values|
+      values.zip_fields.each do |target,typea,ida,databasea,typeb,idb,databaseb,effect|
+        next if typea == 'gene'
+
+        if typeb == 'gene'
+          target.sub!('_g','')
+          type = '-t'
+        elsif typeb == 'output' or typea == 'output'
+          type = '-ap'
+        else
+          type = '-a'
+        end
+
+        proteins << source unless source.include? '_f' or source.include? '_c'
+        proteins << target unless target.include? '_f' or target.include? '_c'
+
+        outputs << source if typea == 'output'
+        outputs << target if typeb == 'output'
+
+        effect_symbol = '>' 
+        effect_symbol = '|' if effect.include? 'inhibit'
+
+        associations[[source,target]] = [type, effect_symbol]
+      end
+    end
+
+    str = StringIO.new
+
+    proteins.each do |p|
+      next if outputs.include? p
+      str.puts ["protein", p] * "\t"
+    end
+
+    outputs.each do |o|
+      str.puts ["abstract", o] * "\t"
+    end
+
+    members.each do |e, targets|
+      e = e.dup
+      case 
+      when e.include?('_c')
+        str.puts ["complex", e] * "\t"
+        type = 'component'
+      when e.include?('_f')
+        str.puts ["family", e] * "\t"
+        type = 'member'
+      else
+        next
+      end
+
+      targets.each do |target|
+        associations[[target,e]] = [type, '>']
+      end
+    end
+
+
+    associations.each do |p,i|
+      source, target = p
+      type, symbol = i
+
+      str.puts [source, target, [type,symbol]*""] * "\t"
+    end
+
+    str.rewind
+    str
+  end
+
+  CASCADE.claim CASCADE["topology.sif"], :proc do
+
+    tsv = CASCADE.interactions.tsv 
+
+    str = StringIO.new
+
+    tsv.through do |source, values|
+      values.zip_fields.each do |target,typea,ida,databasea,typeb,idb,databaseb,effect|
+
+        effect_symbol = '->' 
+        effect_symbol = '-|' if effect.include? 'inhibit' 
+
+        str.puts [source, effect_symbol, target] * " "
+      end
+    end
+
+    str.rewind
+    str
+  end
+
+  CASCADE.claim CASCADE.output_nodes, :proc do
+    tsv = CASCADE.interactions.tsv 
+
+    output = TSV.setup({}, :key_field => "Node", :fields => ["Sign"], :type => :single)
+
+    tsv.through do |source, values|
+      values.zip_fields.each do |target,typea,ida,databasea,typeb,idb,databaseb,effect|
+        case target
+        when "Antisurvival"
+          output[source] = -1
+        when "Prosurvival"
+          output[source] = 1
+        end
+      end
+    end
+
+    output.to_s
+  end
+end
+
+iif CASCADE.interactions.produce.find if __FILE__ == $0
+iif CASCADE.members.produce.find if __FILE__ == $0
+iif CASCADE.paradigm.produce.find if __FILE__ == $0
+iif CASCADE["topology.sif"].produce.find if __FILE__ == $0
+iif CASCADE.output_nodes.produce(true).find if __FILE__ == $0
+

data/lib/rbbt/sources/phospho_ELM.rb

@@ -0,0 +1,59 @@
+require 'rbbt-util'
+require 'rbbt/resource'
+
+module PhosphoELM
+  extend Resource
+  self.subdir = 'share/databases/PhosphoELM'
+
+  def self.organism(org="Hsa")
+    require 'rbbt/sources/organism'
+    Organism.default_code(org)
+  end
+
+  #self.search_paths = {}
+  #self.search_paths[:default] = :lib
+
+  PhosphoELM.claim PhosphoELM[".source/dump.tgz"], :proc do |file|
+    raise "Place phosphoELM_all_latest.dump.tgz from http://phospho.elm.eu.org at #{file}. Please consult license."
+  end
+
+  PhosphoELM.claim PhosphoELM.data, :proc do 
+    tgz = PhosphoELM[".source/dump.tgz"].produce.find
+
+    organism = PhosphoELM.organism
+    uni2ensp = Organism.identifiers(organism).tsv :key_field => "UniProt/SwissProt Accession", :fields => ["Ensembl Protein ID"], :type => :flat, :persist => true
+    ensp2seq = Organism.protein_sequence(organism).tsv :persist => true
+
+    dumper = TSV::Dumper.new(:key_field => "Phosphosite", :fields => ["Kinases", "Source", "PMID"], :type => :list)
+    dumper.init
+    TmpFile.with_file do |dir|
+      Misc.in_dir dir do
+        CMD.cmd("tar xvfz #{tgz}")
+        f = Dir.glob("*.dump").first
+        TSV.traverse Open.open(f), :type => :array, :into => dumper do |line|
+          next unless line =~ /Homo sapiens/
+          acc, sequence, position, code, pmids, kinases, source, species, entry_date = line.split("\t")
+          ensps = uni2ensp[acc]
+          Log.warn "No Ensembl Protein ID for #{acc}" if ensps.nil?
+          next if ensps.nil?
+          sequence << "*"
+          good = ensps.select{|ensp| sequence == ensp2seq[ensp]}
+          Log.warn "No sequence match for #{acc} - #{ensps*", "}" if good.empty?
+          next if good.empty?
+          res = []
+          good.each do |ensp|
+            phospho_site = [ensp,":", code, position] * ""
+            res << [phospho_site, [kinases, source, pmids]]
+          end
+          res.extend MultipleResult
+
+          res
+        end
+      end
+    end
+    dumper.stream
+  end
+end
+
+iif PhosphoELM.data.produce(true).find if __FILE__ == $0
+

data/lib/rbbt/sources/phospho_site_plus.rb

@@ -0,0 +1,39 @@
+require 'rbbt-util'
+require 'rbbt/resource'
+
+module PhosphoSitePlues
+  extend Resource
+  self.subdir = 'share/databases/PhosphoSitePlues'
+
+  def self.organism(org="Hsa")
+    require 'rbbt/sources/organism'
+    Organism.default_code(org)
+  end
+
+  #self.search_paths = {}
+  #self.search_paths[:default] = :lib
+  
+  #self.search_paths = {}
+  #self.search_paths[:default] = :lib
+
+
+
+  ALL_FILES = %(Acetylation_site_dataset.gz Disease-associated_sites.gz
+Kinase_Substrate_Dataset.gz Methylation_site_dataset.gz
+O-GalNAc_site_dataset.gz O-GlcNAc_site_dataset.gz
+Phosphorylation_site_dataset.gz Phosphosite_PTM_seq.fasta.gz
+Phosphosite_seq.fasta.gz Regulatory_sites.gz Sumoylation_site_dataset.gz
+Ubiquitination_site_dataset.gz)
+  
+  ALL_FILES.each do |file|
+    PhosphoSitePlues.claim PhosphoSitePlues[".source"][file], :proc do |f|
+      raise "Place #{file} from http://www.phosphosite.org/ at #{f}. Please consult license."
+    end
+  end
+
+  PhosphoSitePlues.claim PhosphoSitePlues.kinase_substrate, :proc do 
+    PhosphoSitePlues[".source/Kinase_Substrate_Dataset.gz"]
+  end
+end
+
+iif PhosphoSitePlues.data.produce.find if __FILE__ == $0

data/lib/rbbt/sources/reactome.rb

@@ -1,27 +1,53 @@
-require 'rbbt'
+require 'rbbt-util'
 require 'rbbt/resource'
 
 module Reactome
   extend Resource
   self.subdir = "share/databases/Reactome"
 
+  def self.organism(org="Hsa")
+    require 'rbbt/sources/organism'
+    Organism.default_code(org)
+  end
+
   Reactome.claim Reactome.protein_pathways, :proc  do
     #url = "http://www.reactome.org/download/current/uniprot_2_pathways.stid.txt"
-    url = "http://www.reactome.org/download/current/UniProt2Reactome.txt"
-    tsv = TSV.open(Open.open(url), :key_field => 0, :fields => [1], :merge => true, :type => :double)
-    tsv.key_field = "UniProt/SwissProt Accession"
+    url = "http://reactome.org/download/current/Ensembl2Reactome.txt"
+    tsv = TSV.open(url, :key_field => 0, :fields => [1], :merge => true, :type => :flat, :tsv_grep => "Homo sapiens")
+    tsv.key_field = "Ensembl Gene ID"
+    tsv.fields = ["Reactome Pathway ID"]
+    tsv.namespace = Reactome.organism
+    tsv.to_s
+  end
+
+  Reactome.claim Reactome.protein_pathways_all, :proc  do
+    #url = "http://www.reactome.org/download/current/uniprot_2_pathways.stid.txt"
+    url = "http://reactome.org/download/current/Ensembl2Reactome_All_Levels.txt"
+    tsv = TSV.open(url, :key_field => 0, :fields => [1], :merge => true, :type => :flat, :tsv_grep => "Homo sapiens")
+    tsv.key_field = "Ensembl Gene ID"
     tsv.fields = ["Reactome Pathway ID"]
-    tsv.namespace = "Hsa"
+    tsv.namespace = Reactome.organism
     tsv.to_s
   end
 
+
   Reactome.claim Reactome.pathway_names, :proc  do
     #url = "http://www.reactome.org/download/current/uniprot_2_pathways.stid.txt"
     url = "http://www.reactome.org/download/current/UniProt2Reactome.txt"
-    tsv = TSV.open(Open.open(url), :key_field => 1, :fields => [2], :type => :single)
+    tsv = TSV.open(Open.open(url), :key_field => 1, :fields => [3], :type => :single)
     tsv.key_field = "Reactome Pathway ID"
     tsv.fields = ["Pathway Name"]
-    tsv.namespace = "Hsa"
+    tsv.namespace = Reactome.organism
+    tsv.to_s
+  end
+
+  Reactome.claim Reactome.pathway_pathway, :proc  do
+    #url = "http://www.reactome.org/download/current/uniprot_2_pathways.stid.txt"
+    url = "http://reactome.org/download/current/ReactomePathwaysRelation.txt"
+    tsv = TSV.open(Open.open(url), :type => :flat, :merge => true)
+    tsv.key_field = "Reactome Pathway ID"
+    tsv.fields = ["Reactome Pathway ID"]
+    tsv.namespace = Reactome.organism
     tsv.to_s
   end
 
@@ -30,10 +56,39 @@ module Reactome
     tsv = TSV.open(CMD.cmd('cut -f 1,4,7,8,9|sed "s/UniProt://g;s/,/;/g"', :in => Open.open(url), :pipe => true), :type => :double, :merge => true)
     tsv.key_field = "UniProt/SwissProt Accession"
     tsv.fields = ["Interactor UniProt/SwissProt Accession", "Interaction type", "Reactions", "PMID"]
-    tsv.namespace = "Hsa"
+    tsv.namespace = Reactome.organism
     tsv.to_s
   end
 
+  #Reactome.claim Reactome.protein_pathways, :proc  do
+  #  #url = "http://www.reactome.org/download/current/uniprot_2_pathways.stid.txt"
+  #  url = "http://www.reactome.org/download/current/UniProt2Reactome.txt"
+  #  tsv = TSV.open(Open.open(url), :key_field => 0, :fields => [1], :merge => true, :type => :double)
+  #  tsv.key_field = "UniProt/SwissProt Accession"
+  #  tsv.fields = ["Reactome Pathway ID"]
+  #  tsv.namespace = Reactome.organism
+  #  tsv.to_s
+  #end
+
+  #Reactome.claim Reactome.pathway_names, :proc  do
+  #  #url = "http://www.reactome.org/download/current/uniprot_2_pathways.stid.txt"
+  #  url = "http://www.reactome.org/download/current/UniProt2Reactome.txt"
+  #  tsv = TSV.open(Open.open(url), :key_field => 1, :fields => [2], :type => :single)
+  #  tsv.key_field = "Reactome Pathway ID"
+  #  tsv.fields = ["Pathway Name"]
+  #  tsv.namespace = Reactome.organism
+  #  tsv.to_s
+  #end
+
+  #Reactome.claim Reactome.protein_protein, :proc  do
+  #  url = "http://www.reactome.org/download/current/homo_sapiens.interactions.txt.gz"
+  #  tsv = TSV.open(CMD.cmd('cut -f 1,4,7,8,9|sed "s/UniProt://g;s/,/;/g"', :in => Open.open(url), :pipe => true), :type => :double, :merge => true)
+  #  tsv.key_field = "UniProt/SwissProt Accession"
+  #  tsv.fields = ["Interactor UniProt/SwissProt Accession", "Interaction type", "Reactions", "PMID"]
+  #  tsv.namespace = Reactome.organism
+  #  tsv.to_s
+  #end
+
 end
 
 if defined? Entity 
@@ -82,3 +137,8 @@ if defined? Entity
     end
   end
 end
+
+Log.tsv Reactome.protein_pathways.produce.tsv if __FILE__ == $0
+Log.tsv Reactome.protein_pathways_all.produce.tsv if __FILE__ == $0
+Log.tsv Reactome.pathway_names.produce(true).tsv if __FILE__ == $0
+Log.tsv Reactome.pathway_pathway.produce.tsv if __FILE__ == $0

data/lib/rbbt/sources/signor.rb

@@ -0,0 +1,77 @@
+require 'rbbt-util'
+require 'rbbt/resource'
+
+module Signor
+  extend Resource
+  self.subdir = 'share/databases/Signor'
+
+  def self.organism(org="Hsa")
+    require 'rbbt/sources/organism'
+    Organism.default_code(org)
+  end
+
+  #self.search_paths = {}
+  #self.search_paths[:default] = :lib
+
+  Signor.claim Signor[".source/all.csv"], :proc do |file|
+    raise "Download all human data in CSV format from 'http://signor.uniroma2.it/downloads.php#all_download' and place in #{file}"
+  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--')
+    
+    tsv = TSV.open io, :header_hash => "", :sep => ";", :merge => true, :type => :double, :zipped => true, :monitor => true
+    tsv.each do |k,values|
+      clean_values = values.collect{|vs| vs.collect{|v| (v[0] == '"' and v[-1] = '"') ? v[1..-2] : v }.collect{|v| v.gsub("--SEMICOLON--", ';') } }
+
+      values.replace clean_values
+    end
+    tsv
+  end
+
+  Signor.claim Signor.protein_protein, :proc do 
+    parser = TSV::Parser.new Signor.data
+    fields = parser.fields
+    dumper = TSV::Dumper.new :key_field => "Source (UniProt/SwissProt Accession)", :fields => ["Target (UniProt/SwissProt Accession)", "Effect", "Mechanism", "Residue"], :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["RESIDUE"]).each do |v|
+        typeb,idb,eff,mech,resi = v.flatten
+        next unless typeb == "protein"
+        res << [unia, [idb, eff, mech,resi]]
+      end
+
+      res
+    end
+
+    Misc.collapse_stream dumper.stream
+  end
+end
+
+iif Signor.protein_protein.produce(true).find if __FILE__ == $0
+

data/share/Ensembl/release_dates

@@ -1,5 +1,15 @@
 #: :type=:single
 #Release	build
+release-89	may2017
+release-88	mar2017
+release-87	dec2016
+release-86	oct2016
+release-85	jul2016
+release-84	mar2016
+release-83	dec2015
+release-82	sep2015
+release-81	jul2015
+release-80	may2015
 release-79	mar2015
 release-78	dec2014
 release-77	oct2014

data/share/install/Organism/organism_helpers.rb

@@ -672,6 +672,8 @@ file 'transcript_5utr' => ["exons", "transcript_exons", "transcripts"] do |t|
     transcript = transcript2ensembl[transcript_id]
     protein    = transcript_protein[transcript]
 
+    next if transcript =~ /^LRG/
+
     start_exon = exon2ensembl[start_exon]
     eend_exon = exon2ensembl[eend_exon]
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rbbt-sources
 version: !ruby/object:Gem::Version
-  version: 3.1.16
+  version: 3.1.17
 platform: ruby
 authors:
 - Miguel Vazquez
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-06-15 00:00:00.000000000 Z
+date: 2017-08-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rbbt-util
@@ -89,6 +89,7 @@ files:
 - etc/allowed_biomart_archives
 - etc/biomart/missing_in_archive
 - etc/organisms
+- lib/rbbt/sources/CASCADE.rb
 - lib/rbbt/sources/COSTART.rb
 - lib/rbbt/sources/CTCAE.rb
 - lib/rbbt/sources/HPRD.rb
@@ -115,10 +116,13 @@ files:
 - lib/rbbt/sources/organism.rb
 - lib/rbbt/sources/pfam.rb
 - lib/rbbt/sources/pharmagkb.rb
+- lib/rbbt/sources/phospho_ELM.rb
+- lib/rbbt/sources/phospho_site_plus.rb
 - lib/rbbt/sources/pina.rb
 - lib/rbbt/sources/polysearch.rb
 - lib/rbbt/sources/pubmed.rb
 - lib/rbbt/sources/reactome.rb
+- lib/rbbt/sources/signor.rb
 - lib/rbbt/sources/stitch.rb
 - lib/rbbt/sources/string.rb
 - lib/rbbt/sources/synapse.rb