rbbt-study 0.2.18 → 0.2.19

checksums.yaml

@@ -1,15 +1,15 @@
 ---
 !binary "U0hBMQ==":
   metadata.gz: !binary |-
-    ODQxZGJlNDBmN2M4N2E3MDcwYzAyZDQwNTlhYjZkYmRjNTBmZDY2ZQ==
+    ODg5YzNlNzAzMDA4NjUzNzNlYTc0MTIxMzI3MmZiNzI4N2VhZjg0Yw==
   data.tar.gz: !binary |-
-    NmVlODQ5ZWFiNGE3NDBiOGNmMTI3Mzc4NDgzZWFhYTQ3M2Q5ZmY4Yw==
+    ZWNmM2VjZjJhY2FkMGYzM2JlOWMxYjBiYTEwNjA1YjVlYzM2N2Y0Yw==
 SHA512:
   metadata.gz: !binary |-
-    Njc1NDhmMzQ5NDc0ZTA0YjRjMGEzMzRiNzk1OGI3YjZmMGFlMzkyYTk4ZGFj
-    ZjQ3Y2Y5NWVjMDZhZjY5YjE4YzczZWVhYjZmYmI1ZjViZDQ4ZjVkM2E0Nzc4
-    NTllMDE4ODFiYWRjYzAxYjUxYzgyYzI5YjY4YWExNzQxYzk1NDU=
+    MmU0NjNlZGY0YzM3ZTBkYjQ1YWEyNjNkNzE0ODdkYTE4OWE1MzUxZjg4Y2Ji
+    NzRjOGZmODI5MTUxMzJlYzMyOWZlOTA0MjBmNmQyZDM1MDhiMzA4MTc1ZDgx
+    ZmJjZTYwMzM4ZTU3NzQzMzQ5ZWNiNTIwZTk1NjhjNzM0ZDYxMWQ=
   data.tar.gz: !binary |-
-    MDI0YmVlZmE4NDJhOTFmMWJiOWM0ZWE5ZWQ2NmM5NTZiYjk0N2UxM2YyZTRj
-    NGI2YzIzMzhmODZiYzVkNDdjYzQyODQxMzlhZjY4Njc3NGZhNDM3ZDM0OTE4
-    ZWY1MWEyZTU3ODkxMDdiNGMyZTc5YzA5Yjc4MTllMjExOWIwOGY=
+    MzUwNzIzYWM0MDE1MjNhNTFjMGZkYTdjNzU5ZjVhNDcwZGNiY2NlZGUwYTBj
+    ODY5ODZhMzMxMDUzOGFhM2M4ZDU4YzM2MzVhMTZkN2QyN2I1YzEwOTg1ZDJk
+    ZDNiYmM0OTExOWZhMjJmOGYxMmRlMDJmZTYxYTMyMDRkMWMzOTA=

data/lib/rbbt/entity/study/cnv/knowledge_base.rb

@@ -0,0 +1,39 @@
+require 'rbbt/knowledge_base'
+require 'rbbt/workflow'
+Workflow.require_workflow "Genomics"
+require 'rbbt/entity/study'
+require 'rbbt/entity/study/cnv'
+require 'rbbt/entity/gene'
+require 'rbbt/entity/genomic_mutation'
+
+module Study
+
+  self.study_registry[:sample_cnv_genes] = Proc.new{|study,database|
+    tsv = TSV.setup({}, :key_field => "Sample", :fields => ["Ensembl Gene ID", "CNV Variation"], :type => :double, :namespace => study.organism)
+
+    all_cnvs = CNV.setup(study.cnv_cohort.values.flatten, study.organism)
+    cnv2genes = Misc.process_to_hash(all_cnvs){|cnvs| cnvs.genes }
+
+    study.cnv_cohort.each do |sample,cnvs|
+      Log.info sample
+      genes = []
+      variations = []
+      cnvs.variation.zip(cnv2genes.chunked_values_at(cnvs)).each_with_index do |p,i|
+        variation, genes = p
+        Annotated.purge(genes).each{|gene| genes << gene; variations << variation }
+      end
+      tsv[sample] = [genes.to_a, variations.to_a]
+    end
+
+    tsv
+  }
+
+end
+
+if __FILE__ == $0
+  Workflow.require_workflow "ICGC"
+  Study.study_dir = ICGC.root
+  s = Study.setup("Glioblastoma_Multiforme-TCGA-US")
+  puts s.knowledge_base.get_database(:sample_cnv_genes).value_peek
+
+end

data/lib/rbbt/entity/study/cnv/samples.rb

@@ -11,7 +11,7 @@ module Sample
     gene_CN = {}
     cnvs.variation.zip(cnvs.genes).each do |var, genes|
       next if genes.empty?
-      genes = genes.clean_annotations
+      genes = Annotated.purge genes 
       case var
       when "loss"
         genes.each{|gene| gene_CN[gene] = "Lost"}
@@ -39,12 +39,10 @@ module Sample
     Gene.setup(gene_CN.select{|g,v| v == "Gained"}.collect{|g,v| g}, "Ensembl Gene ID", self.study.organism)
   end
 
-
   property :lost_genes => :single do
     Gene.setup(gene_CN.select{|g,v| v == "Lost"}.collect{|g,v| g}, "Ensembl Gene ID", self.study.organism)
   end
 
-
   property :cnv_genes => :single do
     return nil if lost_genes.nil? or gained_genes.nil?
     organism = study.metadata[:organism]

data/lib/rbbt/entity/study/genotypes.rb

@@ -29,7 +29,7 @@ module StudyWorkflow
       mutation_genes = Misc.process_to_hash(all_mutations){|all_mutations| all_mutations.genes}
       mutation_affected_genes = Misc.process_to_hash(all_mutations){|all_mutations| all_mutations.affected_genes}
       if all_mutations.length < 5000
-        log :damaged_genes, "Computing genes damaged genes"
+        log :damaged_genes, "Computing damaged genes"
         mutation_damaged_genes = Misc.process_to_hash(all_mutations){|all_mutations| all_mutations.damaged_genes}
       else
         mutation_damaged_genes = Misc.process_to_hash(all_mutations){|all_mutations| [nil] * all_mutations.length}

data/lib/rbbt/entity/study/plots.rb

@@ -51,8 +51,6 @@ pathway.enrichment = rbbt.ruby.substitutions(
 
     study = Study.setup('STUDY')
 
-    Log.severity = 0
-
     pathways = study.job(:mutation_pathway_enrichment, study, :baseline => :pathway_base_counts, :database => '#{database}', :fdr => false).run.select('p-value'){|pvalue| pvalue = pvalue.first.to_f if Array === pvalue; pvalue < 0.2}
     pathways.add_field 'Name' do |pathway, values|
         [pathway.name]

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rbbt-study
 version: !ruby/object:Gem::Version
-  version: 0.2.18
+  version: 0.2.19
 platform: ruby
 authors:
 - Miguel Vazquez
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-11-27 00:00:00.000000000 Z
+date: 2013-12-05 00:00:00.000000000 Z
 dependencies: []
 description: This gem add the study entity with suport for NGS, Microarray and other
   types of data
@@ -24,6 +24,7 @@ files:
 - lib/rbbt/entity/study.rb
 - lib/rbbt/entity/study/cnv.rb
 - lib/rbbt/entity/study/cnv/genes.rb
+- lib/rbbt/entity/study/cnv/knowledge_base.rb
 - lib/rbbt/entity/study/cnv/samples.rb
 - lib/rbbt/entity/study/enrichment.rb
 - lib/rbbt/entity/study/expression.rb