publisci 0.1.3 → 0.1.4

data/lib/publisci/readers/r_matrix.rb

@@ -1,54 +1,54 @@
 module PubliSci
-	module Readers
-		class RMatrix
-			include PubliSci::Dataset::DataCube
+  module Readers
+    class RMatrix
+      include PubliSci::Dataset::DataCube
 
-			#NOTE; this is pretty much hard coded for Karl's application right now, and doesn't
-			# do any dimension or code generation. Since its a set of LOD scores indexed by dimension
-			# and marker the usual datacube generator wont work (I think). In the future adding an option
-			# to specify this kind of a dataset would probably be useful
+      #NOTE; this is pretty much hard coded for Karl's application right now, and doesn't
+      # do any dimension or code generation. Since its a set of LOD scores indexed by dimension
+      # and marker the usual datacube generator wont work (I think). In the future adding an option
+      # to specify this kind of a dataset would probably be useful
 
 
-			def generate_n3(client, var, outfile_base, options={})
-				meas = measures(client,var,options)
-				dim = dimensions(client,var,options)
-				codes = codes(client,var,options)
+      def generate_n3(client, var, outfile_base, options={})
+        meas = measures(client,var,options)
+        dim = dimensions(client,var,options)
+        codes = codes(client,var,options)
 
-				outvar = sanitize([var]).first
+        outvar = sanitize([var]).first
 
-				probes_per_file = options[:probes_per_file] || 100
-				col_select = "colnames"
-				col_select = "names" if options[:type] == :dataframe
+        probes_per_file = options[:probes_per_file] || 100
+        col_select = "colnames"
+        col_select = "names" if options[:type] == :dataframe
 
-				#write structure
-				open(outfile_base+'_structure.ttl','w'){|f| f.write structure(client,var,outvar,options)}
+        #write structure
+        open(outfile_base+'_structure.ttl','w'){|f| f.write structure(client,var,outvar,options)}
 
-				probes=client.eval("#{col_select}(#{var})").to_ruby
-				if probes == nil
-					client.eval("colnames(#{var})=1:ncol(#{var})")
-					probes=client.eval("#{col_select}(#{var})").to_ruby
-				end
-				markers = rows(client,var,options)
+        probes=client.eval("#{col_select}(#{var})").to_ruby
+        if probes == nil
+          client.eval("colnames(#{var})=1:ncol(#{var})")
+          probes=client.eval("#{col_select}(#{var})").to_ruby
+        end
+        markers = rows(client,var,options)
 
         if options[:print]
-            puts prefixes(var,options)
+          puts prefixes(var,options)
         end
 
         if options[:output] == :string
-            str = prefixes(var,options)
+          str = prefixes(var,options)
         end
 
-				probes.each_with_index{|probe,i|
-					#write prefixes and erase old file on first run
+        probes.each_with_index{|probe,i|
+          #write prefixes and erase old file on first run
           unless options[:print] || options[:output] == :string
-  					open(outfile_base+"_#{i/probes_per_file}.ttl",'w'){|f| f.write prefixes(var,options)} if i % probes_per_file == 0
+            open(outfile_base+"_#{i/probes_per_file}.ttl",'w'){|f| f.write prefixes(var,options)} if i % probes_per_file == 0
           end
-					i+=1
-					obs_data = observation_data(client,var,i,markers,options)
-					labels = labels_for(client,var,probe)
+          i+=1
+          obs_data = observation_data(client,var,i,markers,options)
+          labels = labels_for(client,var,probe)
 
-					# labels = sanitize(labels)
-					# return obs_data
+          # labels = sanitize(labels)
+          # return obs_data
           if options[:print]
             observations(meas,dim,codes,obs_data,labels,outvar,options).each{|obs| puts obs}
           end
@@ -58,119 +58,119 @@ module PubliSci
           end
 
           unless options[:print] || options[:output] == :string
-  					open(outfile_base+"_#{i/probes_per_file}.ttl",'a'){|f| observations(meas,dim,codes,obs_data,labels,outvar,options).map{|obs| f.write obs}}
-  					puts "#{i}/#{probes.size}" unless options[:quiet]
+            open(outfile_base+"_#{i/probes_per_file}.ttl",'a'){|f| observations(meas,dim,codes,obs_data,labels,outvar,options).map{|obs| f.write obs}}
+            puts "#{i}/#{probes.size}" unless options[:quiet]
           end
-				}
+        }
 
         if options[:output] == :string
           str
         end
-			end
-
-			def structure(client,var,outvar,options={})
-				meas = measures(client,var,options)
-				dim = dimensions(client,var,options)
-				codes = codes(client,var,options)
-
-				str = prefixes(var, options)
-				str << data_structure_definition(meas,[],codes,outvar,options)
-				str << dataset(outvar,options)
-    		component_specifications(meas, dim, codes, var, options).map{ |c| str << c }
-				measure_properties(meas,var,options).map{|m| str << m}
-
-				str
-			end
-
-			#for now just make everything a measure
-			def measures(client, var, options={})
-				if options[:measures]
-						options[:measures]
-				else
-					["probe","marker","value"]
-				end
-				# measure_properties(measures,var,options)
-			end
-
-			def dimensions(client, var, options={})
-				# dimension_properties([""],var)
-				[]
-			end
-
-			def codes(client, var, options={})
-				[]
-			end
-
-			def labels_for(connection,var,probe_id,options={})
-				row_names = connection.eval("row.names(#{var})")
-				# row_names = (1..@rexp.payload.first.to_ruby.size).to_a unless row_names.first
-				if row_names == connection.eval('NULL')
-					row_names = (1..connection.eval("nrow(#{var})").payload.first).to_a
-				else
-					row_names = row_names.payload
-				end
-
-	      labels = (1..(row_names.size)).to_a.map(&:to_s)
-	      labels = labels.map{|l|
-	      	l.insert(0,probe_id.to_s + "_")
-	      }
-
-	      labels
-			end
-
-			def rows(connection,var,options={})
-				row_names = connection.eval("row.names(#{var})")
-				#hacky solution because rserve client's .to_ruby method doesn't fully work
-				if row_names == connection.eval('NULL')
-					row_names = (1..connection.eval("nrow(#{var})").payload.first).to_a
-				else
-					row_names = row_names.payload
-				end
-	      row_names
-			end
-
-			def observation_data(client, var, probe_number, row_names, options={})
-
-				data = {}
-				# geno_chr = client.eval("#{var}$geno$'#{chr}'")
-				# n_individuals = client.eval("#{var}$pheno[[1]]").to_ruby.size
-				# entries_per_individual = @rexp.payload["geno"].payload[row_individ].payload["map"].payload.size * @rexp.payload["geno"].payload.names.size
-				col_label = "probe"
-				row_label = "marker"
-				val_label = "value"
-
-				if options[:measures]
-					col_label = options[:measures][0] || "probe"
-					row_label = options[:measures][1] || "marker"
-					val_label = options[:measures][2] || "value"
-				end
-
-				data["#{col_label}"] = []
-				data["#{row_label}"] = []
-				data["#{val_label}"] = []
-
-				# n_individuals.times{|row_individ|
-					# puts "#{row_individ}/#{n_individuals}"
-
-				col_select = "colnames"
-				col_select = "names" if options[:type] == :dataframe
-
-				if options[:type] == :dataframe
-					probe_obj = client.eval("#{var}[[#{probe_number}]]").to_ruby
-				else
-					probe_obj = client.eval("#{var}[,#{probe_number}]").to_ruby
-				end
-				# puts probe_obj
-				probe_id = client.eval("#{col_select}(#{var})[[#{probe_number}]]").to_ruby
-				data["#{col_label}"] = (1..(probe_obj.size)).to_a.fill(probe_id)
-				probe_obj.each_with_index{|lod,i|
-					data["#{row_label}"] << row_names[i]
-					data["#{val_label}"] << lod
-				}
-
-				data.map{|k,v| v.flatten!}
-				data
-			end
-		end
-	end
+      end
+
+      def structure(client,var,outvar,options={})
+        meas = measures(client,var,options)
+        dim = dimensions(client,var,options)
+        codes = codes(client,var,options)
+
+        str = prefixes(var, options)
+        str << data_structure_definition(meas,[],codes,outvar,options)
+        str << dataset(outvar,options)
+        component_specifications(meas, dim, codes, var, options).map{ |c| str << c }
+        measure_properties(meas,var,options).map{|m| str << m}
+
+        str
+      end
+
+      #for now just make everything a measure
+      def measures(client, var, options={})
+        if options[:measures]
+          options[:measures]
+        else
+          ["probe","marker","value"]
+        end
+        # measure_properties(measures,var,options)
+      end
+
+      def dimensions(client, var, options={})
+        # dimension_properties([""],var)
+        []
+      end
+
+      def codes(client, var, options={})
+        []
+      end
+
+      def labels_for(connection,var,probe_id,options={})
+        row_names = connection.eval("row.names(#{var})")
+        # row_names = (1..@rexp.payload.first.to_ruby.size).to_a unless row_names.first
+        if row_names == connection.eval('NULL')
+          row_names = (1..connection.eval("nrow(#{var})").payload.first).to_a
+        else
+          row_names = row_names.payload
+        end
+
+        labels = (1..(row_names.size)).to_a.map(&:to_s)
+        labels = labels.map{|l|
+          l.insert(0,probe_id.to_s + "_")
+        }
+
+        labels
+      end
+
+      def rows(connection,var,options={})
+        row_names = connection.eval("row.names(#{var})")
+        #hacky solution because rserve client's .to_ruby method doesn't fully work
+        if row_names == connection.eval('NULL')
+          row_names = (1..connection.eval("nrow(#{var})").payload.first).to_a
+        else
+          row_names = row_names.payload
+        end
+        row_names
+      end
+
+      def observation_data(client, var, probe_number, row_names, options={})
+
+        data = {}
+        # geno_chr = client.eval("#{var}$geno$'#{chr}'")
+        # n_individuals = client.eval("#{var}$pheno[[1]]").to_ruby.size
+        # entries_per_individual = @rexp.payload["geno"].payload[row_individ].payload["map"].payload.size * @rexp.payload["geno"].payload.names.size
+        col_label = "probe"
+        row_label = "marker"
+        val_label = "value"
+
+        if options[:measures]
+          col_label = options[:measures][0] || "probe"
+          row_label = options[:measures][1] || "marker"
+          val_label = options[:measures][2] || "value"
+        end
+
+        data["#{col_label}"] = []
+        data["#{row_label}"] = []
+        data["#{val_label}"] = []
+
+        # n_individuals.times{|row_individ|
+        # puts "#{row_individ}/#{n_individuals}"
+
+        col_select = "colnames"
+        col_select = "names" if options[:type] == :dataframe
+
+        if options[:type] == :dataframe
+          probe_obj = client.eval("#{var}[[#{probe_number}]]").to_ruby
+        else
+          probe_obj = client.eval("#{var}[,#{probe_number}]").to_ruby
+        end
+        # puts probe_obj
+        probe_id = client.eval("#{col_select}(#{var})[[#{probe_number}]]").to_ruby
+        data["#{col_label}"] = (1..(probe_obj.size)).to_a.fill(probe_id)
+        probe_obj.each_with_index{|lod,i|
+          data["#{row_label}"] << row_names[i]
+          data["#{val_label}"] << lod
+        }
+
+        data.map{|k,v| v.flatten!}
+        data
+      end
+    end
+  end
 end

data/lib/publisci/writers/arff.rb

@@ -2,7 +2,7 @@ module PubliSci
   module Writers
     class ARFF < Base
       # include PubliSci::Query
-      # include PubliSci::Parser
+      # include PubliSci::RDFParser
       # include PubliSci::Analyzer
 
       def build_arff(relation, attributes, data, source)

data/lib/publisci/writers/base.rb

@@ -2,7 +2,7 @@ module PubliSci
   module Writers
     class Base
       include PubliSci::Query
-      include PubliSci::Parser
+      include PubliSci::RDFParser
       include PubliSci::Analyzer
 
       def handle_input(input)

data/resources/maf_rdf.ttl

@@ -1,20 +1,20 @@
-@base <http://onto.strinz.me/dc/dataset/maf_example/> .
-@prefix ns:    <http://onto.strinz.me/dc/dataset/maf_example/> .
+@base <http://onto.strinz.me/dc/dataset/MAF_ah1iit/> .
+@prefix ns:    <http://onto.strinz.me/dc/dataset/MAF_ah1iit/> .
 @prefix qb:    <http://purl.org/linked-data/cube#> .
 @prefix rdf:   <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
 @prefix rdfs:  <http://www.w3.org/2000/01/rdf-schema#> .
 @prefix prop:  <http://onto.strinz.me/properties/> .
 @prefix dct:   <http://purl.org/dc/terms/> .
 @prefix xsd:   <http://www.w3.org/2001/XMLSchema#> .
-@prefix cs:    <http://onto.strinz.me/dc/dataset/maf_example/cs/> .
-@prefix code:  <http://onto.strinz.me/dc/dataset/maf_example/code/> .
+@prefix cs:    <http://onto.strinz.me/dc/dataset/MAF_ah1iit/cs/> .
+@prefix code:  <http://onto.strinz.me/dc/dataset/MAF_ah1iit/code/> .
 @prefix owl:   <http://www.w3.org/2002/07/owl#> .
 @prefix skos:  <http://www.w3.org/2004/02/skos/core#> .
 @prefix foaf:     <http://xmlns.com/foaf/0.1/> .
 @prefix org:      <http://www.w3.org/ns/org#> .
 @prefix prov:     <http://www.w3.org/ns/prov#> .
 
-ns:dsd-maf_example a qb:DataStructureDefinition;
+ns:dsd-MAF_ah1iit a qb:DataStructureDefinition;
   qb:component cs:Variant_Classification ;
   qb:component cs:Variant_Type ;
   qb:component cs:dbSNP_Val_Status ;
@@ -52,9 +52,9 @@ ns:dsd-maf_example a qb:DataStructureDefinition;
   qb:component cs:patient_id ;
   qb:component cs:sample_id .
 
-ns:dataset-maf_example a qb:DataSet ;
-  rdfs:label "maf_example"@en ;
-  qb:structure ns:dsd-maf_example .
+ns:dataset-MAF_ah1iit a qb:DataSet ;
+  rdfs:label "MAF_ah1iit"@en ;
+  qb:structure ns:dsd-MAF_ah1iit .
 
 cs:Variant_Classification a qb:ComponentSpecification ;
   rdfs:label "Variant_Classification" ;
@@ -207,16 +207,13 @@ prop:Entrez_Gene_Id a rdf:Property, qb:MeasureProperty ;
   rdfs:label "Entrez_Gene_Id"@en .
 
 prop:Center a rdf:Property, qb:MeasureProperty ;
-  rdfs:label "Center"@en ;
-  rdfs:range xsd:string .
+  rdfs:label "Center"@en .
 
 prop:NCBI_Build a rdf:Property, qb:MeasureProperty ;
-  rdfs:label "NCBI_Build"@en ;
-  rdfs:range xsd:int .
+  rdfs:label "NCBI_Build"@en .
 
 prop:Chromosome a rdf:Property, qb:MeasureProperty ;
-  rdfs:label "Chromosome"@en ;
-  rdfs:range xsd:int .
+  rdfs:label "Chromosome"@en .
 
 prop:Start_Position a rdf:Property, qb:MeasureProperty ;
   rdfs:label "Start_Position"@en .
@@ -240,8 +237,7 @@ prop:dbSNP_RS a rdf:Property, qb:MeasureProperty ;
   rdfs:label "dbSNP_RS"@en .
 
 prop:Tumor_Sample_Barcode a rdf:Property, qb:MeasureProperty ;
-  rdfs:label "Tumor_Sample_Barcode"@en ;
-  rdfs:range xsd:string .
+  rdfs:label "Tumor_Sample_Barcode"@en .
 
 prop:Matched_Norm_Sample_Barcode a rdf:Property, qb:MeasureProperty ;
   rdfs:label "Matched_Norm_Sample_Barcode"@en .
@@ -955,7 +951,7 @@ code:sequencer a skos:ConceptScheme;
   skos:inScheme code:sequencer .
 
 ns:obs2 a qb:Observation ;
-  qb:dataSet ns:dataset-maf_example ;
+  qb:dataSet ns:dataset-MAF_ah1iit ;
   prop:Variant_Classification <code/variant_classification/Missense_Mutation> ;
   prop:Variant_Type <code/variant_type/SNP> ;
   prop:dbSNP_Val_Status <code/dbsnp_val_status/> ;
@@ -990,7 +986,7 @@ ns:obs2 a qb:Observation ;
   .
 
 ns:obs3 a qb:Observation ;
-  qb:dataSet ns:dataset-maf_example ;
+  qb:dataSet ns:dataset-MAF_ah1iit ;
   prop:Variant_Classification <code/variant_classification/Missense_Mutation> ;
   prop:Variant_Type <code/variant_type/SNP> ;
   prop:dbSNP_Val_Status <code/dbsnp_val_status/byFrequency> ;
@@ -1025,7 +1021,7 @@ ns:obs3 a qb:Observation ;
   .
 
 ns:obs4 a qb:Observation ;
-  qb:dataSet ns:dataset-maf_example ;
+  qb:dataSet ns:dataset-MAF_ah1iit ;
   prop:Variant_Classification <code/variant_classification/Missense_Mutation> ;
   prop:Variant_Type <code/variant_type/SNP> ;
   prop:dbSNP_Val_Status <code/dbsnp_val_status/> ;
@@ -1061,7 +1057,7 @@ ns:obs4 a qb:Observation ;
   .
 
 ns:obs5 a qb:Observation ;
-  qb:dataSet ns:dataset-maf_example ;
+  qb:dataSet ns:dataset-MAF_ah1iit ;
   prop:Variant_Classification <code/variant_classification/Silent> ;
   prop:Variant_Type <code/variant_type/SNP> ;
   prop:dbSNP_Val_Status <code/dbsnp_val_status/> ;
@@ -1097,7 +1093,7 @@ ns:obs5 a qb:Observation ;
   .
 
 ns:obs6 a qb:Observation ;
-  qb:dataSet ns:dataset-maf_example ;
+  qb:dataSet ns:dataset-MAF_ah1iit ;
   prop:Variant_Classification <code/variant_classification/Silent> ;
   prop:Variant_Type <code/variant_type/SNP> ;
   prop:dbSNP_Val_Status <code/dbsnp_val_status/> ;
@@ -1132,7 +1128,7 @@ ns:obs6 a qb:Observation ;
   .
 
 ns:obs7 a qb:Observation ;
-  qb:dataSet ns:dataset-maf_example ;
+  qb:dataSet ns:dataset-MAF_ah1iit ;
   prop:Variant_Classification <code/variant_classification/Missense_Mutation> ;
   prop:Variant_Type <code/variant_type/SNP> ;
   prop:dbSNP_Val_Status <code/dbsnp_val_status/> ;
@@ -1171,3 +1167,83 @@ ns:obs7 a qb:Observation ;
   prop:sample_id "01A-11D-A14G-09" ;
   .
 
+ns:obs8 a qb:Observation ;
+  qb:dataSet ns:dataset-MAF_ah1iit ;
+  prop:Variant_Classification <code/variant_classification/Silent> ;
+  prop:Variant_Type <code/variant_type/SNP> ;
+  prop:dbSNP_Val_Status <code/dbsnp_val_status/> ;
+  prop:Verification_Status <code/verification_status/Unknown> ;
+  prop:Validation_Status <code/validation_status/Valid> ;
+  prop:Mutation_Status <code/mutation_status/Somatic> ;
+  prop:Sequence_Source <code/sequence_source/WXS> ;
+  prop:Sequencer <code/sequencer/Illumina_GAIIx> ;
+  prop:Hugo_Symbol <http://identifiers.org/hgnc.symbol/A2BP1> ;
+  prop:Entrez_Gene_Id <http://identifiers.org/ncbigene/54715> ;
+  prop:Center "genome.wustl.edu" ;
+  prop:NCBI_Build 37 ;
+  prop:Chromosome 16 ;
+  prop:Start_Position 7383011 ;
+  prop:End_Position 7383011 ;
+  prop:Strand "+" ;
+  prop:Reference_Allele "G" ;
+  prop:Tumor_Seq_Allele1 "G" ;
+  prop:Tumor_Seq_Allele2 "A" ;
+  prop:dbSNP_RS "novel" ;
+  prop:Tumor_Sample_Barcode "TCGA-AR-A1AJ-01A-21D-A12Q-09" ;
+  prop:Matched_Norm_Sample_Barcode "TCGA-AR-A1AJ-10A-01D-A12Q-09" ;
+  prop:Match_Norm_Seq_Allele1 "G" ;
+  prop:Match_Norm_Seq_Allele2 "G" ;
+  prop:Tumor_Validation_Allele1 "G" ;
+  prop:Tumor_Validation_Allele2 "A" ;
+  prop:Match_Norm_Validation_Allele1 "G" ;
+  prop:Match_Norm_Validation_Allele2 "G" ;
+  prop:Sequencing_Phase "Phase_IV" ;
+  prop:Validation_Method "Illumina_WXS_gDNA" ;
+  prop:Score 1 ;
+  prop:BAM_File "dbGAP" ;
+  prop:Tumor_Sample_UUID "4e1f9084-4729-4b3f-b036-6226d64fd25b" ;
+  prop:Matched_Norm_Sample_UUID "63ee3781-4578-4d19-88e4-c8785fc7987e" ;
+  prop:patient_id "AR-A1AJ" ;
+  prop:sample_id "01A-21D-A12Q-09" ;
+  .
+
+ns:obs9 a qb:Observation ;
+  qb:dataSet ns:dataset-MAF_ah1iit ;
+  prop:Variant_Classification <code/variant_classification/Nonsense_Mutation> ;
+  prop:Variant_Type <code/variant_type/SNP> ;
+  prop:dbSNP_Val_Status <code/dbsnp_val_status/> ;
+  prop:Verification_Status <code/verification_status/Unknown> ;
+  prop:Validation_Status <code/validation_status/Valid> ;
+  prop:Mutation_Status <code/mutation_status/Somatic> ;
+  prop:Sequence_Source <code/sequence_source/WXS> ;
+  prop:Sequencer <code/sequencer/Illumina_GAIIx> ;
+  prop:Hugo_Symbol <http://identifiers.org/hgnc.symbol/A2M> ;
+  prop:Entrez_Gene_Id <http://identifiers.org/ncbigene/2> ;
+  prop:Center "genome.wustl.edu" ;
+  prop:NCBI_Build 37 ;
+  prop:Chromosome 12 ;
+  prop:Start_Position 9251298 ;
+  prop:End_Position 9251298 ;
+  prop:Strand "+" ;
+  prop:Reference_Allele "G" ;
+  prop:Tumor_Seq_Allele1 "G" ;
+  prop:Tumor_Seq_Allele2 "A" ;
+  prop:dbSNP_RS "novel" ;
+  prop:Tumor_Sample_Barcode "TCGA-A8-A08G-01A-11W-A019-09" ;
+  prop:Matched_Norm_Sample_Barcode "TCGA-A8-A08G-10A-01W-A021-09" ;
+  prop:Match_Norm_Seq_Allele1 "G" ;
+  prop:Match_Norm_Seq_Allele2 "G" ;
+  prop:Tumor_Validation_Allele1 "G" ;
+  prop:Tumor_Validation_Allele2 "A" ;
+  prop:Match_Norm_Validation_Allele1 "G" ;
+  prop:Match_Norm_Validation_Allele2 "G" ;
+  prop:Sequencing_Phase "Phase_IV" ;
+  prop:Validation_Method "Illumina_WXS_gDNA" ;
+  prop:Score 1 ;
+  prop:BAM_File "dbGAP" ;
+  prop:Tumor_Sample_UUID "8da61928-e935-4a33-8e46-840e637163d7" ;
+  prop:Matched_Norm_Sample_UUID "74a3a4af-c93a-4fcd-af11-1f5eeb847c3c" ;
+  prop:patient_id "A8-A08G" ;
+  prop:sample_id "01A-11W-A019-09" ;
+  .
+