bio-publisci 0.0.8 → 0.1.0

data/lib/bio-publisci/query/query_helper.rb

@@ -37,10 +37,10 @@ module PubliSci
     # end
 
     def execute(string,store,type=:fourstore)
-    	if type == :graph || store.is_a?(RDF::Graph) || store.is_a?(RDF::Repository)
-				sparql = SPARQL::Client.new(store)
-			elsif store.is_a? PubliSci::Store
+			if store.is_a?(PubliSci::Store) || store.is_a?(RDF::FourStore)
 				sparql = SPARQL::Client.new(store.url+"/sparql/")
+      elsif type == :graph || store.is_a?(RDF::Graph) || store.is_a?(RDF::Repository)
+        sparql = SPARQL::Client.new(store)
 			elsif type == :fourstore
 				sparql = SPARQL::Client.new(store+"/sparql/")
       end
@@ -48,12 +48,17 @@ module PubliSci
     end
 
     def execute_from_file(file,store,type=:fourstore,substitutions={})
+      if Gem::Dependency.new('bio-publisci').matching_specs.size > 0
+        queries_dir = Gem::Specification.find_by_name("bio-publisci").gem_dir + "/resources/queries/"
+      else
+        queries_dir = File.dirname(__FILE__) + '/../../../resources/queries/'
+      end
       if File.exist?(file)
         string = IO.read(file)
-      elsif File.exist?(File.dirname(__FILE__) + '/../../../resources/queries/' + file)
-        string = IO.read(File.dirname(__FILE__) + '/../../../resources/queries/' + file)
-      elsif File.exist?(File.dirname(__FILE__) + '/../../../resources/queries/' + file + '.rq')
-        string = IO.read(File.dirname(__FILE__) + '/../../../resources/queries/' + file + '.rq')
+      elsif File.exist?(queries_dir + file)
+        string = IO.read(queries_dir + file)
+      elsif File.exist?(queries_dir + file + '.rq')
+        string = IO.read(queries_dir + file + '.rq')
       else
         raise "couldn't find query for #{file}"
       end
@@ -113,6 +118,6 @@ SELECT DISTINCT ?label WHERE {
   end
 
   class QueryHelper
-    include PubliSci::Query
+    extend PubliSci::Query
   end
 end

data/lib/bio-publisci/readers/arff.rb

@@ -1,5 +1,5 @@
 module PubliSci
-		module Reader
+		module Readers
 		class ARFF
 			include PubliSci::Dataset::DataCube
 

data/lib/bio-publisci/readers/base.rb

@@ -0,0 +1,57 @@
+module PubliSci
+  module Readers
+    class Base
+      include PubliSci::Query
+      include PubliSci::Parser
+      include PubliSci::Analyzer
+      include PubliSci::Interactive
+      include PubliSci::Dataset::DataCube
+
+      #should be overridden if extra processing/input is required
+      def automatic(*args)
+        generate_n3(args[0],Hash[*args[1..-2]])
+      end
+
+      def generate_n3(*args)
+        raise "#{self} does not implement a generate_n3 method!"
+      end
+
+      def sio_value(type,value)
+        [
+          ["a", type],
+          ["http://semanticscience.org/resource/SIO_000300",value]
+        ]
+      end
+
+      def sio_attribute(attribute_type,value,data_type=nil)
+        inner = [
+          "http://semanticscience.org/resource/SIO_000300",value
+        ]
+        if data_type
+          inner = [["a", data_type], inner]
+        end
+        
+        outer = 
+        [
+          "http://semanticscience.org/resource/SIO_000008",
+            inner
+        ]
+
+        if attribute_type
+          outer = [["a", attribute_type], outer] 
+        end
+
+        # puts "#{outer}"
+        outer
+      end
+
+      def next_label
+        if @__current_label
+          @__current_label += 1
+        else
+          @__current_label = 0
+        end
+      end
+    end
+  end
+end

data/lib/bio-publisci/readers/csv.rb

@@ -1,9 +1,6 @@
 module PubliSci
-	module Reader
-		class CSV
-      include PubliSci::Dataset::DataCube
-			include PubliSci::Interactive
-
+	module Readers
+		class CSV < Base
       def automatic(file=nil,dataset_name=nil,options={},interactive=true)
         #to do
         # puts "f #{file} \n ds #{dataset_name} opts #{options}"

data/lib/bio-publisci/readers/dataframe.rb

@@ -1,8 +1,8 @@
 module PubliSci
-	module Reader
+	module Readers
 		class Dataframe
       include PubliSci::Dataset::DataCube
-			include PubliSci::Reader::Output
+			include PubliSci::Readers::Output
 
 			# def initialize(var)
 			# 	@var = var

data/lib/bio-publisci/readers/maf.rb

@@ -0,0 +1,199 @@
+module PubliSci
+  module Readers
+    class MAF < Base
+    COLUMN_NAMES = %w{ Hugo_Symbol Entrez_Gene_Id Center NCBI_Build Chromosome Start_Position End_Position Strand Variant_Classification Variant_Type Reference_Allele Tumor_Seq_Allele1 Tumor_Seq_Allele2 dbSNP_RS  dbSNP_Val_Status Tumor_Sample_Barcode Matched_Norm_Sample_Barcode Match_Norm_Seq_Allele1  Match_Norm_Seq_Allele2  Tumor_Validation_Allele1  Tumor_Validation_Allele2  Match_Norm_Validation_Allele1 Match_Norm_Validation_Allele2 Verification_Status Validation_Status Mutation_Status Sequencing_Phase  Sequence_Source Validation_Method Score BAM_File  Sequencer Tumor_Sample_UUID Matched_Norm_Sample_UUID patient_id sample_id}
+
+    COMPONENT_RANGES = { "Tumor_Sample_Barcode" => "xsd:string", "Start_position" => "xsd:int", "Center" => "xsd:string", "NCBI_Build" => "xsd:int", "Chromosome" => "xsd:int" }
+
+    TCGA_CODES =
+      {
+        "Variant_Classification" => %w{Frame_Shift_Del Frame_Shift_Ins In_Frame_Del In_Frame_Ins Missense_Mutation Nonsense_Mutation Silent Splice_Site Translation_Start_Site Nonstop_Mutation 3'UTR 3'Flank 5'UTR 5'Flank IGR1  Intron RNA Targeted_Region},
+        "Variant_Type" => %w{SNP DNP TNP ONP INS DEL Consolidated},
+        "dbSNP_Val_Status" => %w{by1000genomes by2Hit2Allele byCluster byFrequency byHapMap byOtherPop bySubmitter alternate_allele},
+        "Verification_Status" => %w{Verified, Unknown},
+        "Validation_Status" => %w{Untested Inconclusive Valid Invalid},
+        "Mutation_Status" => %w{None Germline Somatic LOH Post-transcriptional modification Unknown},
+        "Sequence_Source" => %w{WGS WGA WXS RNA-Seq miRNA-Seq Bisulfite-Seq VALIDATION Other ncRNA-Seq WCS CLONE POOLCLONE AMPLICON CLONEEND FINISHING ChIP-Seq MNase-Seq DNase-Hypersensitivity EST FL-cDNA CTS MRE-Seq MeDIP-Seq MBD-Seq Tn-Seq FAIRE-seq SELEX RIP-Seq ChIA-PET},
+        "Sequencer" => ["Illumina GAIIx", "Illumina HiSeq", "SOLID", "454", "ABI 3730xl", "Ion Torrent PGM", "Ion Torrent Proton", "PacBio RS", "Illumina MiSeq", "Illumina HiSeq 2500", "454 GS FLX Titanium", "AB SOLiD 4 System" ]
+      }
+
+      def generate_n3(input_file, options={})
+
+        dataset_name = options[:dataset_name] || nil
+        output = options[:output] || :file
+        output_base = options[:output_base] || nil
+
+        @dimensions = %w{Variant_Classification Variant_Type dbSNP_Val_Status Verification_Status Validation_Status Mutation_Status Sequence_Source Sequencer}
+        # @codes = %w{Variant_Classification Variant_Type}
+        @codes = @dimensions
+        @measures = (COLUMN_NAMES - @dimensions - @codes)
+        @dataset_name ||= File.basename(input_file,'.*')
+        @barcode_index = COLUMN_NAMES.index('Tumor_Sample_Barcode')
+
+        options[:no_labels] ||= true
+        options[:lookup_hugo] ||= false
+        options[:complex_objects] ||= false
+        options[:ranges] ||= COMPONENT_RANGES
+
+
+        if output == :print
+          str = structure(options)
+          f = open(input_file)
+          n = 0
+          f.each_line{|line|
+            processed = process_line(line,n.to_s,options)
+            str << processed.first if processed
+            n +=1
+          }
+          str
+        else
+          # TODO - allow multi file / separate structure output for very large datasets
+          # open("#{file_base}_structure.ttl",'w'){|f| f.write structure(options)}
+          file_base = output_base || @dataset_name
+
+          out = open("#{file_base}.ttl",'w')
+          out.write(structure(options))
+          f = open(input_file)
+          n = 0
+          f.each_line{|line|
+            processed = process_line(line,n.to_s,options)
+            out.write(processed.first) if processed
+            n += 1
+          }
+          if options[:lookup_hugo]
+            post_process(out)
+          else
+            out
+          end
+        end
+      end
+
+      def process_line(line,label,options)
+        unless line[0] == "#" || line[0..3] == "Hugo"
+          entry = ::CSV.parse(line, {col_sep: "\t"}).flatten[0..(COLUMN_NAMES.length-3)]
+
+          entry = (entry.fill(nil,entry.length...COLUMN_NAMES.length-2) + parse_barcode(entry[@barcode_index])).flatten
+
+          entry[0] = "http://identifiers.org/hgnc.symbol/#{entry[0]}" if entry[0]
+
+          # A 0 in the entrez-id column appears to mean null
+          col=1
+          entry[col] = nil if entry[col] == '0'
+          entry[col] = "http://identifiers.org/ncbigene/#{entry[col]}" if entry[col]
+
+          # Only link non-novel dbSNP entries
+          col = COLUMN_NAMES.index('dbSNP_RS')
+          if entry[col] && entry[col][0..1] == "rs"
+            entry[col] = "http://identifiers.org/dbsnp/#{entry[col].gsub('rs','')}"
+          end
+
+          # optionally create typed objects using sio nodes
+          if options[:complex_objects]
+            entry = sio_values(entry)
+          end
+
+          data = {}
+          COLUMN_NAMES.each_with_index{|col,i|
+            data[col] = [entry[i]]
+          }
+
+          observations(@measures,@dimensions,@codes,data,[label],@dataset_name,options)
+        end
+      end
+
+      def sio_values(entry)
+        entry[0] = sio_value('http://edamontology.org/data_1791',entry[0]) if entry[0]
+
+        # Link entrez genes
+        col=1
+        entry[col] = sio_value("http://identifiers.org/ncbigene",entry[col]) if entry[col]
+
+        col = COLUMN_NAMES.index('dbSNP_RS')
+        entry[col] = sio_value("http://identifiers.org/dbsnp", entry[col])
+
+        # test SIO attributes for chromosome
+        col = COLUMN_NAMES.index('Chromosome')
+        entry[col] = sio_value("http://purl.org/obo/owl/SO#SO_0000340",entry[col])
+
+
+
+        # More SIO attrtibutes for alleles
+        %w{Reference_Allele Tumor_Seq_Allele1 Tumor_Seq_Allele2 Match_Norm_Seq_Allele1 Match_Norm_Seq_Allele2}.each{|name|
+          col = COLUMN_NAMES.index(name)
+          entry[col] = sio_value("http://purl.org/obo/owl/SO#SO_0001023",entry[col])
+        }
+
+        col = COLUMN_NAMES.index("Strand")
+        entry[col] = sio_attribute("http://edamontology.org/data_0853",entry[col])
+
+        col = COLUMN_NAMES.index("Center")
+        entry[col] = sio_attribute("foaf:homepage",entry[col])
+        # entry[col] = [
+        #   ["a", "foaf:Organization"],
+        #   ["foaf:homepage", entry[col]],
+        # ]
+
+        # Use faldo for locations End_Position
+        col = COLUMN_NAMES.index("Start_Position")
+        entry[col] = sio_attribute("http://biohackathon.org/resource/faldo#begin", entry[col],"http://biohackathon.org/resource/faldo#Position")
+
+        col = COLUMN_NAMES.index("End_Position")
+        entry[col] = sio_attribute("http://biohackathon.org/resource/faldo#end", entry[col],"http://biohackathon.org/resource/faldo#Position")
+
+        entry
+      end
+
+      def column_replace(entry,column,prefix,value=nil)
+        if value
+          entry[COLUMN_NAMES.index(column)] = prefix + value
+        else
+          entry[COLUMN_NAMES.index(column)] += prefix
+        end
+      end
+
+      def official_symbol(hugo_symbol)
+        qry = <<-EOF
+
+        SELECT distinct ?official where {
+         {?hgnc <http://bio2rdf.org/hgnc_vocabulary:approved_symbol> "#{hugo_symbol}"}
+         UNION
+         {?hgnc <http://bio2rdf.org/hgnc_vocabulary:synonym> "#{hugo_symbol}"}
+
+         ?hgnc <http://bio2rdf.org/hgnc_vocabulary:approved_symbol> ?official
+        }
+
+        EOF
+
+        sparql = SPARQL::Client.new("http://cu.hgnc.bio2rdf.org/sparql")
+        sparql.query(qry).map(&:official).first.to_s
+      end
+
+      def parse_barcode(code)
+      	#TCGA-E9-A22B-01A-11D-A159-09
+      	[code[5..11], code[13..-1]]
+      end
+
+      def structure(options={})
+
+        str = prefixes(@dataset_name,options)
+        str << data_structure_definition(@measures,@dimensions,@codes,@dataset_name,options)
+        str << dataset(@dataset_name,options)
+        component_specifications(@measures, @dimensions, @codes, @dataset_name, options).map{ |c| str << c }
+        measure_properties(@measures,@dataset_name,options).map{|m| str << m}
+        dimension_properties(@dimensions,@codes, @dataset_name,options).map{|d| str << d}
+        code_lists(@codes,TCGA_CODES,@dataset_name,options).map{|c| str << c}
+        concept_codes(@codes,TCGA_CODES,@dataset_name,options).map{|c| str << c}
+        str
+      end
+
+      def post_process(file)
+        reg = %r{http://identifiers.org/hgnc.symbol/(\w+)}
+        @@hugo_cache ||= {}
+        PubliSci::PostProcessor.process(file,file,reg){|g|
+          @@hugo_cache[g] ||= official_symbol(g)
+         'http://identifiers.org/hgnc.symbol/' + cache[g]
+       }
+      end
+    end
+  end
+end

data/lib/bio-publisci/readers/r_cross.rb

@@ -1,8 +1,8 @@
 module PubliSci
-  module Reader
+  module Readers
     class RCross
       include PubliSci::Dataset::DataCube
-      include PubliSci::Reader::Output
+      include PubliSci::Readers::Output
 
       def generate_n3(client, var, outfile_base, options={})
         meas = measures(client,var,options)
@@ -75,33 +75,29 @@ module PubliSci
 
       def observation_data(client, var, chr, row_individ, geno_chr, entries_per_individual, options={})
         data = {}
-        # geno_chr = client.eval("#{var}$geno$'#{chr}'")
-        # n_individuals = client.eval("#{var}$pheno[[1]]").to_ruby.size
-        # entries_per_individual = @rexp.payload["geno"].payload[row_individ].payload["map"].payload.size * @rexp.payload["geno"].payload.names.size
+
         data["chr"] = []
         data["genotype"] = []
         data["individual"] = []
         data["marker"] = []
         data["markerpos"] = []
+
         pheno_names = client.eval("names(#{var}$pheno)").to_ruby
         pheno_names.map{|name|
           data[name] = []
         }
-        # n_individuals.times{|row_individ|
-          # puts "#{row_individ}/#{n_individuals}"
         data["individual"] << (1..entries_per_individual).to_a.fill(row_individ)
 
         pheno_names.map{|name|
           data[name] << (1..entries_per_individual).to_a.fill(client.eval("#{var}$pheno$#{name}").to_ruby[row_individ])
         }
-        # @rexp.payload["geno"].payload.names.map { |chr|
+
         num_markers = geno_chr.payload.first.to_ruby.column_size
         data["chr"] << (1..num_markers).to_a.fill(chr)
         data["genotype"] << geno_chr.payload["data"].to_ruby.row(row_individ).to_a
         data["marker"] << client.eval("names(#{var}$geno$'#{chr}'$map)").payload
         data["markerpos"] << geno_chr.payload["map"].to_a
-          # }
-        # }
+
         data.map{|k,v| v.flatten!}
         data
       end

data/lib/bio-publisci/readers/r_matrix.rb

@@ -1,5 +1,5 @@
 module PubliSci
-	module Reader
+	module Readers
 		class RMatrix
 			include PubliSci::Dataset::DataCube
 

data/lib/bio-publisci/writers/base.rb

@@ -63,6 +63,7 @@ module PubliSci
 
       def codes(input, data_set = nil, select = :label)
         repo = handle_input(input)
+
         if data_set
           codes = execute_from_file("codes.rq",repo,:graph,{"?dataSet"=>"<#{data_set}>"}).to_h
         else
@@ -72,6 +73,21 @@ module PubliSci
           (h[el.first]||=[]) << el.last; h
         }
       end
+
+      def turtle_to_ruby(turtle_file, select_dataset=nil, shorten_url=true)
+        repo = RDF::Repository.load(turtle_file)
+
+        repo_to_ruby(repo,select_dataset,shorten_url)
+      end
+
+      def repo_to_ruby(repo,select_dataset=nil, shorten_url=true)
+        select_dataset = dataSet(repo,:dataset) unless select_dataset
+        dims = dimensions(repo,select_dataset)
+        meas = measures(repo,select_dataset)
+        codes = codes(repo,select_dataset)
+        data = observations(repo,select_dataset,shorten_url)
+        {measures: meas, dimensions: dims, coded_dimensions: codes, data: data}
+      end
     end
   end
 end

data/lib/bio-publisci/writers/json.rb

@@ -0,0 +1,18 @@
+module PubliSci
+  module Writers
+    class JSON < Base
+      def build_json(data)
+        data.values.to_json
+      end
+
+      def from_turtle(file,select_dataset=nil,shorten_url=true)
+        rb = turtle_to_ruby(file,select_dataset,shorten_url)
+        build_json(rb[:data])
+      end
+
+      def from_store(file,select_dataset=nil,shorten_url=true)
+        build_json(repo_to_ruby(file,select_dataset,shorten_url)[:data])
+      end
+    end
+  end
+end

data/resources/maf_example.maf

@@ -0,0 +1,10 @@
+#version 2.4
+Hugo_Symbol	Entrez_Gene_Id	Center	NCBI_Build	Chromosome	Start_Position	End_Position	Strand	Variant_Classification	Variant_Type	Reference_Allele	Tumor_Seq_Allele1	Tumor_Seq_Allele2	dbSNP_RS	dbSNP_Val_Status	Tumor_Sample_Barcode	Matched_Norm_Sample_Barcode	Match_Norm_Seq_Allele1	Match_Norm_Seq_Allele2	Tumor_Validation_Allele1	Tumor_Validation_Allele2	Match_Norm_Validation_Allele1	Match_Norm_Validation_Allele2	Verification_Status	Validation_Status	Mutation_Status	Sequencing_Phase	Sequence_Source	Validation_Method	Score	BAM_File	Sequencer	Tumor_Sample_UUID	Matched_Norm_Sample_UUID	chromosome_name_WU	start_WU	stop_WU	reference_WU	variant_WU	type_WU	gene_name_WU	transcript_name_WU	transcript_species_WU	transcript_source_WU	transcript_version_WU	strand_WU	transcript_status_WU	trv_type_WU	c_position_WU	amino_acid_change_WU	ucsc_cons_WU	domain_WU	all_domains_WU	deletion_substructures_WU	transcript_error
+A1BG	0	genome.wustl.edu	37	19	58862784	58862784	+	Missense_Mutation	SNP	C	C	T	novel		TCGA-E9-A22B-01A-11D-A159-09	TCGA-E9-A22B-10A-01D-A159-09	C	C					Unknown	Untested	Somatic	Phase_IV	WXS	none	1	dbGAP	Illumina GAIIx	e46a5d19-2dd7-4c34-8fff-6276278c58b3	f948182a-f814-4e3c-83ee-82b78aa423c1	19	58862784	58862784	C	T	SNP	A1BG	NM_130786.3	human	genbank	58_37c	-1	reviewed	missense	c.883	p.A295T	0.915	HMMSmart_SM00409,superfamily_Immunoglobulin	HMMSmart_SM00408,HMMSmart_SM00409,HMMPfam_ig,superfamily_Immunoglobulin	-	no_errors
+A1BG	0	genome.wustl.edu	37	19	58864366	58864366	+	Missense_Mutation	SNP	G	G	A	rs151098196	byFrequency	TCGA-E9-A1NH-01A-11D-A14G-09	TCGA-E9-A1NH-11A-33D-A14G-09	G	G					Unknown	Untested	Somatic	Phase_IV	WXS	none	1	dbGAP	Illumina GAIIx	13c312ec-0add-4758-ab8d-c193e2e08c6d	0ee95056-a7cc-415c-a487-3ad08604dfc0	19	58864366	58864366	G	A	SNP	A1BG	NM_130786.3	human	genbank	58_37c	-1	reviewed	missense	c.268	p.R90C	0.950	HMMSmart_SM00408,HMMSmart_SM00409,superfamily_Immunoglobulin	HMMSmart_SM00408,HMMSmart_SM00409,HMMPfam_ig,superfamily_Immunoglobulin	-	no_errors
+A1CF	29974	genome.wustl.edu	37	10	52595854	52595854	+	Missense_Mutation	SNP	G	G	A	novel		TCGA-BH-A0HP-01A-12D-A099-09	TCGA-BH-A0HP-10A-01D-A099-09	G	G					Unknown	Untested	Somatic	Phase_IV	WXS	none	1	dbGAP	Illumina GAIIx	ad52a8fb-7a76-4aa0-95fb-d6edab0fe2b2	8c059d33-23de-439a-914a-290527c5efbe	10	52595854	52595854	G	A	SNP	A1CF	NM_138932.1	human	genbank	58_37c	-1	reviewed	missense	c.584	p.A195V	1.000	HMMPfam_RRM_1,HMMSmart_SM00360,superfamily_RNA-binding domain RBD	HMMPfam_RRM_1,HMMSmart_SM00360,superfamily_dsRNA-binding domain-like,superfamily_RNA-binding domain RBD	-	no_errors
+A1CF	29974	genome.wustl.edu	37	10	52595937	52595937	+	Silent	SNP	G	G	A	novel		TCGA-BH-A18P-01A-11D-A12B-09	TCGA-BH-A18P-11A-43D-A12B-09	G	G					Unknown	Untested	Somatic	Phase_IV	WXS	none	1	dbGAP	Illumina GAIIx	add624a3-57e9-46be-9bcc-3e53d7c2dfb7	5cae8dca-b28a-4483-9c03-6f0645161c04	10	52595937	52595937	G	A	SNP	A1CF	NM_138932.1	human	genbank	58_37c	-1	reviewed	silent	c.501	p.I167	0.615	HMMPfam_RRM_1,HMMSmart_SM00360,superfamily_RNA-binding domain RBD	HMMPfam_RRM_1,HMMSmart_SM00360,superfamily_dsRNA-binding domain-like,superfamily_RNA-binding domain RBD	-	no_errors
+A2BP1	0	genome.wustl.edu	37	16	7568361	7568361	+	Silent	SNP	G	G	C	novel		TCGA-D8-A1JN-01A-11D-A13L-09	TCGA-D8-A1JN-10A-01D-A13O-09	G	G					Unknown	Untested	Somatic	Phase_IV	WXS	none	1	dbGAP	Illumina GAIIx	c83c7d48-8671-4f27-b3dd-05411fa2f784	c14cac2a-e308-44fa-b1af-ee51511ee0ee	16	7568361	7568361	G	C	SNP	A2BP1	NM_145891.2	human	genbank	58_37c	+1	reviewed	silent	c.300	p.T100	0.995	NULL	HMMPfam_RRM_1,HMMSmart_RRM,superfamily_SSF54928	-	no_errors
+A2BP1	54715	genome.wustl.edu	37	16	7102099	7102099	+	Missense_Mutation	SNP	G	G	T	novel		TCGA-E2-A1BC-01A-11D-A14G-09	TCGA-E2-A1BC-10A-01D-A12Q-09	G	G	G	T	G	G	Unknown	Valid	Somatic	Phase_IV	WXS	Illumina_WXS_gDNA	1	dbGAP	Illumina GAIIx	5947a9db-7d13-44ff-86ad-eb5e6c8dcec5	6a4cd52f-2247-4caf-9b37-e90b02fd4d8b	16	7102099	7102099	G	T	SNP	A2BP1	NM_001142334.1	human	genbank	58_37c	+1	reviewed	missense	c.27	p.R9S	1.000	NULL	HMMPfam_RRM_1,HMMSmart_SM00360,superfamily_RNA-binding domain RBD	-	no_errors
+A2BP1	54715	genome.wustl.edu	37	16	7383011	7383011	+	Silent	SNP	G	G	A	novel		TCGA-AR-A1AJ-01A-21D-A12Q-09	TCGA-AR-A1AJ-10A-01D-A12Q-09	G	G	G	A	G	G	Unknown	Valid	Somatic	Phase_IV	WXS	Illumina_WXS_gDNA	1	dbGAP	Illumina GAIIx	4e1f9084-4729-4b3f-b036-6226d64fd25b	63ee3781-4578-4d19-88e4-c8785fc7987e	16	7383011	7383011	G	A	SNP	A2BP1	NM_145891.2	human	genbank	58_37c	+1	reviewed	silent	c.9	p.A3	1.000	NULL	HMMPfam_RRM_1,HMMSmart_RRM,superfamily_SSF54928	-	no_errors
+A2M	2	genome.wustl.edu	37	12	9251298	9251298	+	Nonsense_Mutation	SNP	G	G	A	novel		TCGA-A8-A08G-01A-11W-A019-09	TCGA-A8-A08G-10A-01W-A021-09	G	G	G	A	G	G	Unknown	Valid	Somatic	Phase_IV	WXS	Illumina_WXS_gDNA	1	dbGAP	Illumina GAIIx	8da61928-e935-4a33-8e46-840e637163d7	74a3a4af-c93a-4fcd-af11-1f5eeb847c3c	12	9251298	9251298	G	A	SNP	A2M	NM_000014.4	human	genbank	58_37c	-1	reviewed	nonsense	c.1756	p.R586*	0.003	HMMPfam_A2M_N_2	HMMPfam_A2M,HMMPfam_A2M_N,superfamily_Terpenoid cyclases/Protein prenyltransferases,HMMPfam_A2M_recep,superfamily_Alpha-macroglobulin receptor domain,PatternScan_TONB_DEPENDENT_REC_1,HMMPfam_A2M_N_2,HMMPfam_A2M_comp,HMMPfam_Thiol-ester_cl,PatternScan_ALPHA_2_MACROGLOBULIN	-	no_errors