rbbt-phgx 0.2.0 → 0.3.0

data/lib/phgx.rb

@@ -1,5 +1,5 @@
-require 'rbbt-util'
-require 'rbbt/util/resource'
+require 'rbbt'
+require 'rbbt/resource'
 
 module PhGx
   extend Resource

data/lib/rbbt/mutation/mutation_assessor.rb

@@ -0,0 +1,211 @@
+require 'rbbt/util/open'
+require 'rbbt/tsv'
+require 'nokogiri'
+require 'digest/md5'
+module MutationAssessor
+
+  class NotDone < StandardError; end
+  URL="http://mutationassessor.org/"
+  ASTERISK = "*"[0]
+
+  # mutations is a hash of genes in Uniprot protein accession pointing to lists
+  # of aminoacid substitutions
+  def self.predict(mutations)
+    vars = mutations.collect{|gene, list|
+      list = [list] unless Array === list
+      list.collect do |mut|
+        [gene, mut] * "\t"
+      end
+    }.flatten.sort.uniq * "\n" + "\n"
+
+    post_data = { :beenQ => "1",
+      :info=> "on",
+      :tableQ=> "on",
+      :chr=> "on",
+      :bsites=> "on",
+      :timeout => 600,
+      :vars => vars}.collect{|k,v| [k,v] * "="} * "&"
+
+    Log.debug "Querying Mutation Assessor for: #{vars.split(/\n/).length}"
+    tries = 0
+    begin
+      doc = nil
+      TmpFile.with_file(post_data) do |post_file|
+        doc = Nokogiri::HTML(Open.read(URL, :wget_options => {"--post-file" => post_file }, :nocache => false))
+      end
+
+      textareas = doc.css('textarea')
+      result = textareas.last.content
+
+      if result =~ /Cannot parse variant/
+        tmp = TmpFile.tmp_file
+        variants = tmp + ".list"
+        Open.write(variants, post_data )
+        raise "Cannot parse variants. Variants in file #{ variants }"
+      end
+
+      raise NotDone, "Not done" if result =~ /\t.sent\t./
+    rescue NotDone
+      Log.debug "Mutation Assessor not done, waiting:"
+      Log.debug result
+      
+      sleep 30
+      tries += 1
+      if tries < 10
+        retry
+      else
+        raise "Error processing Mutation Assessor response"
+      end
+    end
+
+    if result.empty?
+      tmp = TmpFile.tmp_file
+      html = tmp + ".html"
+      variants = tmp + ".list"
+      Open.write(tmp, doc.content)
+      Open.write(variants, post_data )
+      raise "Result empty. Possible error. html in #{ html }, variants in #{variants}" 
+    end
+
+    result.sub! /^\t/, ''
+    result.gsub! /\n\s*\d+\s*\t/s, "\n"
+
+    if result.empty?
+      TSV.setup({}, :header_hash => "", :type => :list)
+    else
+      TSV.open(StringIO.new(result), :header_hash => "", :type => :list)
+    end
+  end
+
+  def self.chunked_predict(mutations)
+    chunks = mutations.length.to_f / 1000
+    chunks = chunks.ceil
+    Misc.divide(mutations.sort, chunks).inject(nil) do |acc, list|
+      if acc.nil?
+        acc = predict(list)
+      else
+        acc = TSV.setup(acc.merge(predict(list)))
+      end
+      acc
+    end || {}
+  end
+
+  def self.add_predictions(tsv)
+    raise "Input not TSV" unless TSV === tsv
+
+    raise "Field 'UniProt/SwissProt ID' Not in TSV" unless tsv.all_fields.include? "UniProt/SwissProt ID" 
+
+    raise "Field 'Protein Mutation' Not in TSV" unless tsv.fields.include? "Protein Mutation" 
+
+    data = []
+    if tsv.type == :double
+      tsv.through :key, ["UniProt/SwissProt ID", "Protein Mutation"] do |key,values|
+        uni_accs, mutations = values
+        mutations = mutations.reject{|mutation| mutation =~ /Indel/ or mutation[0] == mutation[-1] or mutation[-1] == ASTERISK or mutation[0] == ASTERISK }
+        next if uni_accs.nil? or uni_accs.compact.reject{|v| v.nil? or v.empty?}.empty? or mutations.empty?
+
+        uni_accs.compact.uniq.each do |uni_acc|
+          data << [uni_acc, mutations]
+        end
+      end
+    else
+      tsv.through :key, ["UniProt/SwissProt ID", "Protein Mutation"] do |key,values|
+        uni_acc, mutation = values
+        next if uni_acc.nil? or uni_acc.empty?
+        next if mutation[0] == mutation[-1] or mutation[-1] == ASTERISK or mutation[0] == ASTERISK
+        data << [uni_acc, mutation]
+      end
+    end
+
+    data.sort!
+
+
+    predictions = {}
+    predict(data).each{|uni_acc, values| 
+      protein, mutation = uni_acc.split(/\s+/)
+
+      values = values.zip_fields
+      values.each do |v|
+        pred     = v["Func. Impact"]
+        predictions[protein] ||= {}
+        predictions[protein][mutation] = pred
+      end
+    }
+
+    uni_acc_pos = tsv.identify_field "UniProt/SwissProt ID" 
+    protein_field = tsv.identify_field "Protein Mutation" 
+ 
+    if tsv.type == :double
+      tsv.add_field "MutationAssessor:Prediction" do |key,values|
+        uni_accs = if uni_acc_pos === :key
+                    [key]
+                  else
+                    values[uni_acc_pos] || []
+                  end
+
+        next if uni_accs.compact.reject{|v| v.nil? or v.empty?}.empty?
+
+        ddd uni_accs
+
+        mutations = values[protein_field]
+        ddd mutations
+
+        uni_accs.zip(mutations).collect do |uni_acc,mutation|
+          ddd uni_acc
+          ddd mutation
+          res = case
+                when (mutation.nil? or mutation.empty?)
+                  "No Prediction"
+                when mutation[0] == mutation[-1]
+                  "TOLERATED"
+                when (uni_acc.nil? or uni_acc.empty?)
+                  "No Prediction"
+                else
+                  list = []
+                  list = predictions[uni_acc][mutation] if predictions.include? uni_acc
+                  if list.nil?
+                    "No Prediction"
+                  else
+                    list.first
+                  end
+                end
+          res
+        end
+      end
+    else
+      tsv.add_field "MutationAssessor:Prediction" do |key,values|
+        uni_acc = if uni_acc_pos === :key
+                    key
+                  else
+                    values[uni_acc_pos]
+                  end
+
+        next if uni_acc.nil? or uni_acc.empty?
+
+        mutation = values[protein_field]
+
+        case
+        when (mutation.nil? or mutation.empty?)
+          "No Prediction"
+        when mutation[0] == mutation[-1]
+          "TOLERATED"
+        when (uni_acc.nil? or uni_acc.empty?)
+          "No Prediction"
+        else
+          list = []
+          list = predictions[uni_acc][mutation] if predictions.include? uni_acc
+          if list.nil?
+            "No Prediction"
+          else
+            list.first
+          end
+        end
+      end
+ 
+    end
+
+    tsv
+  end
+
+
+end

data/lib/rbbt/mutation/polyphen.rb

@@ -1,5 +1,5 @@
 require 'rbbt/util/open'
-require 'rbbt/util/tsv'
+require 'rbbt/tsv'
 require 'nokogiri'
 require 'digest/md5'
 
@@ -37,8 +37,6 @@ module Polyphen2
     desc =  Digest::MD5.hexdigest(options.inspect)
     options["description"] = desc
 
-    ddd desc
-
     doc = Nokogiri::HTML(Open.read(Polyphen2::URL, :wget_options => {"--post-data" => "'#{options.collect{|k,v| [k,v] * "="} * "&"}'"}, :nocache => true))
 
     sid = doc.css('input[name=sid]').attr('value')
@@ -67,12 +65,14 @@ module Polyphen2
         break
       end
 
-      sleep 1
+      sleep 3
     end
 
     return nil if view_link.nil?
 
-    tsv = TSV.new Open.open(Polyphen2::URL_BASE + view_link, :nocache => true), :double, :key => 'acc', :merge => true
+    tsv = TSV.open Open.open(Polyphen2::URL_BASE + view_link, :nocache => true), :double, :merge => true, :fix => Proc.new{|l| l.gsub(/ *\t */, "\t")}
+    tsv.fields = tsv.fields.collect{|f| f.strip}
+    tsv.key_field = tsv.key_field.strip
 
     return tsv
   end
@@ -150,7 +150,7 @@ module Polyphen2
         break
       end
 
-      sleep 1
+      sleep 3
     end
 
     return nil if view_link.nil?

data/lib/rbbt/mutation/sift.rb

@@ -3,6 +3,24 @@ require 'nokogiri'
 module SIFT
   URL_AMINOACID="http://sift.jcvi.org/sift-bin/SIFT_pid_subst_all_submit.pl"
   URL_GENOMIC="http://sift.jcvi.org/sift-bin/SIFT_feed_to_chr_coords.pl"
+  URL_ENSP="http://sift.jcvi.org/sift-bin/retrieve_enst.pl"
+
+  def self.predict(mutations)
+    doc = Nokogiri::HTML(Open.read(URL_ENSP, :wget_options => {"--post-data" => "'ENSP=#{mutations.collect{|p| p * ","} * "\n"}'"}, :nocache => false))
+
+    rows = []
+    doc.css('tr').each do |row|
+      rows << row.css('td').collect{|cell| cell.content.strip.sub "\302\240\302\240&nbsp", ""}
+    end
+
+    rows.shift
+
+    if Array === mutations
+      rows
+    else
+      rows.first
+    end
+  end
 
   def self.predict_aminoacid_mutation(accession, mutations)
     doc = Nokogiri::HTML(Open.read(URL_AMINOACID, :wget_options => {"--post-data" => "'GI=#{[accession, mutations].flatten * ","}&sequences_to_select=BEST&seq_identity_filter=90'"}, :nocache => false))
@@ -52,42 +70,79 @@ module SIFT
   def self.add_predictions(tsv)
     raise "Input not TSV" unless TSV === tsv
 
-    raise "Field 'Refseq Protein ID' Not in TSV" unless tsv.fields.include? "Refseq Protein ID" 
+    raise "Field 'RefSeq Protein ID' Not in TSV" unless tsv.fields.include? "RefSeq Protein ID" 
 
     raise "Field 'Protein Mutation' Not in TSV" unless tsv.fields.include? "Protein Mutation" 
 
     data = []
-    tsv.through :key, ["Refseq Protein ID", "Protein Mutation"] do |key,values|
-      refseqs, mutations = values
-      mutations = mutations.reject{|mutation| mutation[0] == mutation[-1]}
-      next if refseqs.nil? or refseqs.compact.reject{|v| v.nil? or v.empty?}.empty? or mutations.empty?
-
-      refseqs.compact.uniq.each do |refseq|
-        data << [refseq, mutations]
+    if tsv.type == :double
+      tsv.through :key, ["Refseq Protein ID", "Protein Mutation"] do |key,values|
+        refseqs, mutations = values
+        mutations = mutations.reject{|mutation| mutation[0] == mutation[-1]}
+        next if refseqs.nil? or refseqs.compact.reject{|v| v.nil? or v.empty?}.empty? or mutations.empty?
+        refseqs.compact.uniq.each do |refseq|
+          data << [refseq, mutations]
+        end
+      end
+    else
+      tsv.through :key, ["Refseq Protein ID", "Protein Mutation"] do |key,values|
+        refseq, mutation = values
+        next if refseq.nil? or refseq.empty?
+        next if mutation[0] == mutation[-1]
+        data << [refseq, mutation]
       end
     end
 
     data.sort!
 
-
     predictions = {}
     predict_aminoacid_mutation_batch(data).each{|values| predictions[values[0] + ":" << values[1]] = values.values_at 3,4,5,6}
 
-    refseq_field = tsv.identify_field "Refseq Protein ID" 
+    refseq_field = tsv.identify_field "RefSeq Protein ID" 
     protein_field = tsv.identify_field "Protein Mutation" 
  
-    tsv.add_field "SIFT:Prediction" do |key,values|
-      refseqs = if refseq_field === :key
-                  [key]
-                else
-                  values[refseq_field] || []
-                end
+    if tsv.type == :double
+      tsv.add_field "SIFT:Prediction" do |key,values|
+        refseqs = if refseq_field === :key
+                    [key]
+                  else
+                    values[refseq_field] || []
+                  end
 
-      next if refseqs.compact.reject{|v| v.nil? or v.empty?}.empty?
+        next if refseqs.compact.reject{|v| v.nil? or v.empty?}.empty?
 
-      mutations = values[protein_field]
+        mutations = values[protein_field]
+
+        refseqs.zip(mutations).collect do |refseq,mutation|
+          case
+          when (mutation.nil? or mutation.empty?)
+            "No Prediction"
+          when mutation[0] == mutation[-1]
+            "TOLERATED"
+          when (refseq.nil? or refseq.empty?)
+            "No Prediction"
+          else
+            list = predictions[refseq + ":" << mutation]
+            if list.nil?
+              "No Prediction"
+            else
+              list.first
+            end
+          end
+        end
+      end
+    else
+      tsv.add_field "SIFT:Prediction" do |key,values|
+        refseq = if refseq_field === :key
+                    key
+                  else
+                    values[refseq_field]
+                  end
+
+        next if refseq.nil? or refseq.empty?
+
+        mutation = values[protein_field]
 
-      refseqs.zip(mutations).collect do |refseq,mutation|
         case
         when (mutation.nil? or mutation.empty?)
           "No Prediction"
@@ -104,6 +159,7 @@ module SIFT
           end
         end
       end
+ 
     end
 
     tsv

data/lib/rbbt/mutation/snps_and_go.rb

@@ -29,21 +29,49 @@ module SNPSandGO
     raise "Field 'Protein Mutation' Not in TSV" if protein_field.nil?
 
 
-    tsv.add_field "SNPs&GO:Prediction" do |key,values|
-      uniprots = if uniprot_field === :key
-                   [key]
-                 else
-                   values[uniprot_field] || []
-                 end
+    if tsv.type == :double
+      tsv.add_field "SNPs&GO:Prediction" do |key,values|
+        uniprots = if uniprot_field === :key
+                     [key]
+                   else
+                     values[uniprot_field] || []
+                   end
 
-      mutations = values[protein_field]
+        mutations = values[protein_field]
 
-      uniprots.zip(mutations).collect{|uniprot,mutation| 
+        uniprots.zip(mutations).collect{|uniprot,mutation| 
+          case
+          when mutation.nil?
+            "No Prediction" 
+          when mutation[0] == mutation[-1]
+            "Neutral"
+          when (uniprot.nil? or uniprot.empty?)
+            "No Prediction" 
+          else
+            begin
+              SNPSandGO.predict(uniprot, mutation).first
+            rescue
+              "No Prediction"
+            end
+          end
+        }
+      end
+    else
+      tsv.add_field "SNPs&GO:Prediction" do |key,values|
+        uniprot = if uniprot_field === :key
+                     key
+                   else
+                     values[uniprot_field]
+                   end
+
+        next if uniprot.nil? or uniprot.empty?
+        
+        mutation = values[protein_field]
         case
         when mutation.nil?
           "No Prediction" 
         when mutation[0] == mutation[-1]
-            "Neutral"
+          "Neutral"
         when (uniprot.nil? or uniprot.empty?)
           "No Prediction" 
         else
@@ -53,7 +81,7 @@ module SNPSandGO
             "No Prediction"
           end
         end
-      }
+      end
     end
 
     tsv

data/lib/rbbt/sources/cancer.rb

@@ -2,6 +2,6 @@ require 'phgx'
 
 module Cancer
   extend Resource
-  relative_to Rbbt, "share/Cancer"
-  @namespace = "Cancer"
+  self.pkgdir = "phgx"
+  self.subdir = self["share/Cancer"].find :lib
 end

data/lib/rbbt/sources/kegg.rb

@@ -1,6 +1,10 @@
-require 'phgx'
+require 'rbbt'
+require 'rbbt/resource'
 
 module KEGG
   extend Resource
-  data_module(PhGx)
+  self.pkgdir = "phgx"
+  self.subdir = "share/kegg"
+
+  KEGG.claim KEGG.root.find, :rake, Rbbt.share.install.KEGG.Rakefile.find(:lib)
 end

data/lib/rbbt/sources/matador.rb

@@ -2,5 +2,9 @@ require 'phgx'
 
 module Matador
   extend Resource
-  data_module PhGx
+  self.pkgdir = "phgx"
+  self.subdir = "share/matador"
+
+  Matador.claim Matador.root.find, :rake, Rbbt.share.install.Matador.Rakefile.find(:lib)
+
 end

data/lib/rbbt/sources/pharmagkb.rb

@@ -2,5 +2,8 @@ require 'phgx'
 
 module PharmaGKB
   extend Resource
-  data_module PhGx
+  self.pkgdir = "phgx"
+  self.subdir = "share/pharmagkb"
+
+  PharmaGKB.claim PharmaGKB.root.find, :rake, Rbbt.share.install.PharmaGKB.Rakefile.find(:lib)
 end

data/share/Cancer/anais_annotations

@@ -1,3 +1,4 @@
+#: :merge=true
 #Ensembl Gene ID	Tumor Type
 ENSG00000087460	Adrenocortical
 ENSG00000108946	Adrenocortical
@@ -7946,4 +7947,3 @@ ENSG00000154803	Renal
 ENSG00000135100	Renal
 ENSG00000108753	Renal
 ENSG00000114026	Renal
-

data/share/Cancer/anais_interactions

@@ -1,3 +1,4 @@
+#Tumor Type	Term	Database	Score	Name
 Bladder	GO:0000902	GeneOntology	0.0614214465	cell morphogenesis
 Bladder	GO:0001503	GeneOntology	0.0734366145	ossification
 Bladder	GO:0001569	GeneOntology	0.0847152522	patterning of blood vessels
@@ -3399,4 +3400,4 @@ Sarcoma	IPR000418	Interpro	0.0528577740	Ets
 Sarcoma	IPR001876	Interpro	0.0253276834	Zinc finger, RanBP2-type
 Sarcoma	IPR003655	Interpro	0.0528577740	KRAB-related
 Sarcoma	IPR011991	Interpro	0.0528577740	Winged helix repressor DNA-binding
-Sarcoma	REACT_1046	Reactome	0.0320454129	Pyruvate metabolism and TCA cycle
+Sarcoma	REACT_1046	Reactome	0.0320454129	Pyruvate metabolism and TCA cycle

data/share/Cancer/cancer_genes.tsv

@@ -1,4 +1,4 @@
-Symbol	Name	GeneID	Chr	Chr Band	Cancer Somatic Mut	Cancer Germline Mut	Tumour Types  (Somatic Mutations)	Tumour Types (Germline Mutations)	Cancer Syndrome	Tissue Type	Cancer Molecular Genetics	Mutation Type 	Translocation Partner	Other Germline Mut	Other Syndrome/Disease
+#Symbol	Name	GeneID	Chr	Chr Band	Cancer Somatic Mut	Cancer Germline Mut	Tumour Types  (Somatic Mutations)	Tumour Types (Germline Mutations)	Cancer Syndrome	Tissue Type	Cancer Molecular Genetics	Mutation Type 	Translocation Partner	Other Germline Mut	Other Syndrome/Disease
 ABL1	v-abl Abelson murine leukemia viral oncogene homolog 1	25	9	9q34.1 	yes		CML, ALL, T-ALL			L	Dom	T, Mis	BCR, ETV6, NUP214		
 ABL2	v-abl Abelson murine leukemia viral oncogene homolog 2	27	1	1q24-q25 	yes		AML			L	Dom	T	ETV6		
 ACSL3	acyl-CoA synthetase long-chain family member 3	2181	2	2q36	yes		prostate			E	Dom	T	ETV1		

data/share/install/KEGG/Rakefile

@@ -78,6 +78,7 @@ end
 file :pathways => 'source/pathways' do |t|
   descs = {}
   names = {}
+  klass = {}
   pathway = nil
   Open.read(t.prerequisites.first).split(/\n/).each do |line|
     if line =~ /ENTRY\s+(\w+)/
@@ -91,9 +92,13 @@ file :pathways => 'source/pathways' do |t|
     if line =~ /DESCRIPTION (.*)/
       descs[pathway] = $1.strip
     end
+
+    if line =~ /CLASS (.*)/
+      klass[pathway] = $1.strip
+    end
   end
   
-  Open.write(t.name, ['#KEGG Pathway ID', 'Pathway Name', 'Pathway Description'] * "\t" + "\n" + names.keys.collect{|pathway| [pathway, names[pathway], descs[pathway]] * "\t"} * "\n")
+  Open.write(t.name, "#: :type=:list\n" + ['#KEGG Pathway ID', 'Pathway Name', 'Pathway Description', 'Pathway Class'] * "\t" + "\n" + names.keys.collect{|pathway| [pathway, names[pathway], descs[pathway], klass[pathway]] * "\t"} * "\n")
 end
 
 process_tsv :gene_pathway, 'hsa_gene_map.tab',

data/share/install/PharmaGKB/Rakefile

@@ -30,7 +30,7 @@ end
 
 process_tsv :gene_drug, 'relationships',
   :select => proc{|l| l =~ /Gene:/ && l =~ /Drug:/}, 
-  :key => 'Entity1_id', 
+  :key_field => 'Entity1_id', 
   :fields => ['Entity2_id','Relationship'], 
   :header_hash => "",
   :merge => true,
@@ -42,7 +42,7 @@ end
 
 process_tsv :gene_disease, 'relationships', 
   :select => proc{|l| l =~ /Gene:/ && l =~ /Disease:/}, 
-  :key => 1, 
+  :key_field => 1, 
   :fields => 3, 
   :merge => true,
   :header_hash => "",
@@ -53,7 +53,7 @@ process_tsv :gene_disease, 'relationships',
 end
 
 process_tsv :variants, 'variants', 
-  :key => 1, 
+  :key_field => 1, 
   :fields => [3,7,8,9,10,4,6,5], 
   :header_hash => "",
   :merge => true,
@@ -90,7 +90,7 @@ file :gene_pathway => 'source/pathways' do |t|
   end
 
   File.open(t.name, 'w') do |f|
-    f.puts "#" + ['Pathway ID',  'Pathway Name',  'Associated Gene Name'] * "\t"
+    f.puts "#" + ['PhGKB Pathway ID',  'Pathway Name',  'Associated Gene Name'] * "\t"
     pathways.each do |pathway, info|
       next if info[:genes].nil?
       f.puts "#{ pathway }\t#{info[:name]}\t#{info[:genes] * "|"}"

data/share/install/lib/rake_helper.rb

@@ -1,7 +1,7 @@
 $LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '../../../lib'))
 $LOAD_PATH.unshift(File.dirname(__FILE__))
 
-require 'rbbt/util/tsv'
+require 'rbbt/tsv'
 require 'rbbt/util/open'
 require 'rbbt/util/log'
 
@@ -43,7 +43,7 @@ def process_tsv(file, source, options = {}, &block)
   file file => File.join(SOURCE_DIR, source) do |t|
     block.call
 
-    d = TSV.new(t.prerequisites.first, options)
+    d = TSV.open(t.prerequisites.first, options)
 
     if d.fields != nil
       data_fields = d.fields.dup.unshift d.key_field

data/test/rbbt/mutation/test_mutation_assessor.rb

@@ -0,0 +1,36 @@
+require File.join(File.expand_path(File.dirname(__FILE__)), '../..', 'test_helper.rb')
+require 'rbbt/mutation/mutation_assessor'
+
+class TestMutationAssessor < Test::Unit::TestCase
+
+  def _test_predict_aminoacid_mutation
+    mutations = {
+      "EGFR_HUMAN" => %w(R521K)
+    }
+
+    puts MutationAssessor.predict(mutations)
+    assert_equal 1, MutationAssessor.predict(mutations).length
+  end
+
+  def _test_predict_aminoacid_mutation_tsv
+    tsv = TSV.setup({"EGFR_HUMAN" => [%w(R521K)]}, :key_field => "UniProt/SwissProt ID", :fields => ["Protein Mutation"], :type => :double)
+
+    assert_equal "neutral", MutationAssessor.add_predictions(tsv).slice("MutationAssessor:Prediction").values.first.flatten.first
+    assert_equal 1, MutationAssessor.add_predictions(tsv).slice(["MutationAssessor:Prediction", "Protein Mutation"]).length
+  end
+
+
+  def test_predict_chunked
+    mutations = {
+      "EGFR_HUMAN" => %w(R521K),
+      "P53_HUMAN" => %w(R21K),
+    }
+
+    puts MutationAssessor.chunked_predict(mutations)
+  end
+
+
+
+
+end
+

data/test/rbbt/mutation/test_polyphen.rb

@@ -6,7 +6,7 @@ class TestPolyphen2 < Test::Unit::TestCase
     accession = "A6NFZ4"
     mutation =  "Y34D"
 
-    puts Polyphen2.predict(accession, mutation)
+    assert_equal "probably damaging", Polyphen2.predict(accession, mutation).first
   end
 
   def test_batch
@@ -14,7 +14,7 @@ class TestPolyphen2 < Test::Unit::TestCase
 A6NFZ4 Y34D
     EOF
 
-    puts Polyphen2::Batch.predict(query)
+    assert_equal "probably damaging", Polyphen2::Batch.predict(query)["A6NFZ4_Y34D"]["prediction"].first
   end
 end
 

data/test/rbbt/mutation/test_sift.rb

@@ -14,10 +14,12 @@ class TestSIFT < Test::Unit::TestCase
     accession = "NP_001008502"
     mutation =  "Q554P"
 
-    ddd SIFT.predict_aminoacid_mutation_batch( [[accession, mutation]])
     assert_equal "TOLERATED", SIFT.predict_aminoacid_mutation_batch( [[accession, mutation]]).first[3]
   end
-
+  def test_predict_aminoacid_mutation_batch
+    ensp = "ENSP00000224605"
+    mutation = "A63T"
+    assert_equal "TOLERATED", SIFT.predict( [[ensp, mutation]]).first[5]
+  end
 
 end
-

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: rbbt-phgx
 version: !ruby/object:Gem::Version 
-  hash: 23
+  hash: 19
   prerelease: false
   segments: 
   - 0
-  - 2
+  - 3
   - 0
-  version: 0.2.0
+  version: 0.3.0
 platform: ruby
 authors: 
 - Miguel Vazquez
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-07-05 00:00:00 +02:00
+date: 2011-09-07 00:00:00 +02:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -26,10 +26,12 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        hash: 3
+        hash: 63
         segments: 
+        - 4
         - 0
-        version: "0"
+        - 0
+        version: 4.0.0
   type: :runtime
   version_requirements: *id001
 description: Pharmaco-genomics related data sources
@@ -44,6 +46,7 @@ files:
 - LICENSE
 - lib/phgx.rb
 - lib/rbbt/mutation/fireDB.rb
+- lib/rbbt/mutation/mutation_assessor.rb
 - lib/rbbt/mutation/polyphen.rb
 - lib/rbbt/mutation/sift.rb
 - lib/rbbt/mutation/snps_and_go.rb
@@ -83,6 +86,7 @@ files:
 - test/rbbt/mutation/test_fireDB.rb
 - test/rbbt/mutation/test_sift.rb
 - test/rbbt/mutation/test_polyphen.rb
+- test/rbbt/mutation/test_mutation_assessor.rb
 - test/test_helper.rb
 has_rdoc: true
 homepage: http://github.com/mikisvaz/rbbt-phgx
@@ -127,4 +131,5 @@ test_files:
 - test/rbbt/mutation/test_fireDB.rb
 - test/rbbt/mutation/test_sift.rb
 - test/rbbt/mutation/test_polyphen.rb
+- test/rbbt/mutation/test_mutation_assessor.rb
 - test/test_helper.rb