rbbt-study 0.2.30 → 0.2.31

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 634c54bf8560389b8c5c49e996d968f37883b720
-  data.tar.gz: c848a8dd97e570a123b913a747cb3bb63787538e
+  metadata.gz: ef1247f0c3941dd61e65fcb4a198e42967b30b95
+  data.tar.gz: 0008d2cf03e10e104a86631d387fb53fd825c639
 SHA512:
-  metadata.gz: 005e523b4449ef10dc05bf470b60ad713990e47d904dababdbb5d0a682db3782df5f1f713565fb6d2281c745281521856d930bd283b4691ee89ffa8776b79345
-  data.tar.gz: dd9ce8ac4736a08d5c4bee8786b843f3c0796bb8e8cb8ca81d4d0d08218888785cb49aaa76a221d4cfbb49379b766e6b5577417d8e1566c612e42536c26686db
+  metadata.gz: f7b4c891e0500ad8bb18dc098aa5830fd4d80d8d201722139b298567aaf7dcbb02c48d2e8f964bc85649d385fe587a40d49635ba3b83b46feb36606d3f10acc3
+  data.tar.gz: 65ca74cc1659633d89eec772c36d3860bbac75744033c891c5cc77c8d0ba048dd75436345d549b1824f22d5fc858350e65ec72b4cf1535c5c276c587f0f9cdfa

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rbbt-study
 version: !ruby/object:Gem::Version
-  version: 0.2.30
+  version: 0.2.31
 platform: ruby
 authors:
 - Miguel Vazquez
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-07-14 00:00:00.000000000 Z
+date: 2014-08-13 00:00:00.000000000 Z
 dependencies: []
 description: This gem add the study entity with suport for NGS, Microarray and other
   types of data
@@ -21,28 +21,6 @@ extra_rdoc_files:
 files:
 - LICENSE.txt
 - README.rdoc
-- 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
-- lib/rbbt/entity/study/features.rb
-- lib/rbbt/entity/study/genes.rb
-- lib/rbbt/entity/study/genotypes.rb
-- lib/rbbt/entity/study/genotypes/enrichment.rb
-- lib/rbbt/entity/study/genotypes/genes.rb
-- lib/rbbt/entity/study/genotypes/knowledge_base.rb
-- lib/rbbt/entity/study/genotypes/mutations.rb
-- lib/rbbt/entity/study/genotypes/samples.rb
-- lib/rbbt/entity/study/knowledge_base.rb
-- lib/rbbt/entity/study/methylation.rb
-- lib/rbbt/entity/study/methylation/samples.rb
-- lib/rbbt/entity/study/mutations.rb
-- lib/rbbt/entity/study/plots.rb
-- lib/rbbt/entity/study/samples.rb
-- lib/rbbt/entity/study/snp.rb
 - share/R/data.R
 - share/R/plots.R
 homepage: http://github.com/mikisvaz/rbbt-study

data/lib/rbbt/entity/study.rb

@@ -1,172 +0,0 @@
-require 'rbbt'
-require 'rbbt/util/misc'
-
-require 'rbbt/entity'
-require 'rbbt/resource'
-require 'rbbt/workflow'
-
-Workflow.require_workflow "Genomics"
-
-require 'rbbt/entity/study'
-require 'rbbt/entity/study/knowledge_base'
-require 'rbbt/entity/study/samples'
-
-
-module StudyWorkflow
-  extend Workflow
-
-  class << self
-    attr_accessor :study
-  end
-
-  def self.workdir
-    @workdir ||= Rbbt.var.jobs["Study"].find
-  end
-
-  helper :study do 
-    @study
-  end
-
-  helper :dir do
-    study.dir
-  end
-
-  helper :organism do
-    study.metadata[:organism]
-  end
-
-  def self.job(*args)
-    super(*args).tap{|s| s.instance_variable_set("@study", @study) }
-  end
-end
-
-module Study
-  extend Entity
-  extend Resource
-  include LocalPersist
-
-  class << self
-    attr_accessor :study_dir
-    def study_dir
-      @study_dir ||= begin
-                       case
-                       when (not defined?(Rbbt))
-                         Path.setup(File.join(ENV["HOME"], '.studies'))
-                       when Rbbt.etc.study_dir.exists?
-                         Path.setup(Rbbt.etc.study_dir.read.chomp)
-                       else
-                         Rbbt.studies.find
-                       end
-                     end
-    end
-  end
-
-  attr_accessor :workflow, :dir
-
-  def job(task, *args)
-    name, inputs = args
-    if inputs.nil? and Hash === name
-      inputs = name
-      name = nil
-    end
-    name = self if name.nil? or name == :self or name == "self"
-    step = workflow.job(task, name, {:organism => metadata[:organism], :watson => metadata[:watson]}.merge(inputs || {}))
-    step.instance_variable_set(:@study, self)
-    step
-  end
-
-  def workflow(&block)
-    if block_given?
-      @workflow.instance_eval &block
-    else
-      @workflow
-    end
-  end
-
-  def self.annotation_repo
-    @annotation_repo ||= Rbbt.var.cache.annotation_repo.find
-  end
-
-  def self.extended(base)
-    base.workflow = StudyWorkflow.clone
-    base.workflow.study = base
-
-    if File.exists?(setup_file = File.join(base.dir, 'setup.rb'))
-      base.instance_eval Open.read(setup_file), setup_file
-    end
-
-    base.local_persist_dir = Rbbt.var.cache.studies[base].persistence.find
-
-    base
-  end
-
-  def self.studies
-    Dir.glob(File.join(Path === study_dir ? study_dir.find : study_dir, '*')).
-      select{|f| File.directory? f}.sort.collect{|s| Study.setup(File.basename(s))}
-  end
-
-  def self.studies
-    case study_dir
-    when nil
-      []
-    when Path 
-      study_dir.find_all.collect do |study_path| 
-        study_path.glob('*').select{|f| f.directory? }
-      end.flatten.collect{|f| self.annotate f} 
-    else
-      Dir.glob(File.join(study_dir, "*"))
-    end.sort.collect do |dir| 
-      study = Study.setup(File.basename(dir))
-      study.dir = study_dir.annotate(dir)
-      study
-    end
-  end
-
-  def dir
-    @dir ||= if Path === Study.study_dir
-               Study.study_dir[self] 
-             else
-               Path.setup(File.join(Study.study_dir.dup, self), nil, Study)
-             end
-    @dir
-  end
-
-  def metadata
-    @metadata ||= (dir["metadata.yaml"].yaml.extend IndiferentHash)
-  end
-
-  def users
-    @users ||= metadata[:users] || []
-  end
-
-  #{{{ Attributes
-  attr_accessor :organism
-  def organism
-    @organism ||= metadata["organism"]
-  end
-
-  def matrix_file(name)
-    dir.matrices[name.to_s].produce.find
-  end
-
-  def matrices
-    dir.matrices.glob('*').collect{|f| f.basename}
-  end
-
-  def matrix(type, format = "Ensembl Gene ID", organism = nil)
-    organism = self.metadata[:organism] if organism.nil?
-    raise "No matrices defined for study #{ self }" unless defined? matrices.empty?
-    raise "No type specified" if type.nil?
-    type = type.to_s
-    raise "No matrix #{ type } defined for study #{ self }" unless matrices.include? type
-    data = dir.matrices[type].data.find if dir.matrices[type].data.exists?
-    if dir.matrices[type].identifiers.exists?
-      identifiers = dir.matrices[type].identifiers.find 
-    else
-      identifiers = Organism.identifiers(organism).find
-    end
-    samples = dir.matrices[type].samples.find if dir.matrices[type].samples.exists?
-    samples = dir.samples.find if samples.nil? and dir.samples.exist?
-    Matrix.new(data, samples, "count", format, organism, identifiers)
-  end
-end

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

@@ -1,170 +0,0 @@
-require 'rbbt/entity/cnv'
-
-require 'rbbt/entity/study/cnv/genes'
-require 'rbbt/entity/study/cnv/samples'
-
-module StudyWorkflow
-  helper :organism do
-    study.metadata[:organism]
-  end
-
-  task :cnv_overview => :tsv do
-    gene_overview = TSV.setup({}, 
-                          :key_field => "Ensembl Gene ID", 
-                          :fields => ["Samples with gene lost", "Samples with gene gained"],
-                          :type => :double
-                         )
-
-    cnv_samples = study.samples.select_by(:has_cnv?)
-
-    log :samples, "Gathering affected samples"
-    samples_gene_status = {}
-    all_genes = []
-    cnv_samples.each do |sample|
-      samples_gene_status[sample] = {}
-
-      lost_genes = sample.lost_genes
-      lost_genes.clean_annotations.each do |gene|
-        samples_gene_status[sample][gene] ||= [false, false]
-        samples_gene_status[sample][gene][0] = true
-        all_genes << gene
-      end if lost_genes.any?
-
-      gained_genes = sample.gained_genes
-      gained_genes.clean_annotations.each do |gene|
-        samples_gene_status[sample][gene] ||= [false, false]
-        samples_gene_status[sample][gene][1] = true
-        all_genes << gene
-      end if gained_genes.any?
-    end
-
-    log :compiling, "Compiling result"
-    all_genes.uniq.sort.each do |gene|
-      gene_overview[gene] = []
-      gene_overview[gene] << samples_gene_status.select{|sample, gene_status| gene_status.include? gene and gene_status[gene][0]}.collect{|sample, gene_status| sample}
-      gene_overview[gene] << samples_gene_status.select{|sample, gene_status| gene_status.include? gene and gene_status[gene][1]}.collect{|sample, gene_status| sample} 
-    end
-
-    gene_overview
-  end
-end
-
-module Study
-  def has_cnv?
-    dir.cnv.exists?
-  end
-
-  def cnv_files
-    dir.cnv.find.glob("*")
-  end
-
-  def cnv_cohort
-    if @cnv_cohort.nil?
-      @cnv_cohort = {}
-      cnv_files.each do |f| 
-        sample = File.basename(f)
-        Sample.setup(sample, self)
-        cnvs = Open.read(f).split("\n").sort
-        CNV.setup(cnvs, organism)
-        @cnv_cohort[sample] =  cnvs
-      end
-    end
-    @cnv_cohort
-  end
-end
-
-module Study
-  property :recurrently_lost_genes => :single do |threshold|
-    counts = {}
-    self.samples.each do |sample|
-      next unless sample.has_cnvs?
-      puts sample
-
-      genes = nil
-      genes = sample.lost_genes.clean_annotations
-      genes.each do |gene|
-        counts[gene] ||= 0
-        counts[gene] += 1 
-      end
-    end
-
-    recurrent = counts.select{|k,c| c >= threshold }.collect{|k,v| k }
-    Gene.setup(recurrent, "Ensembl Gene ID", organism)
-  end
-
-  property :recurrently_gained_genes => :single do |threshold|
-    counts = {}
-    self.samples.each do |sample|
-      next unless sample.has_cnvs?
-      puts sample
-
-      genes = nil
-      genes = sample.gained_genes.clean_annotations
-      genes.each do |gene|
-        counts[gene] ||= 0
-        counts[gene] += 1 
-      end
-    end
-
-    recurrent = counts.select{|k,c| c >= threshold }.collect{|k,v| k }
-    Gene.setup(recurrent, "Ensembl Gene ID", organism)
-  end
-
-  property :gene_sample_cnv_matrix => :single do
-    tsv = TSV.setup({}, :key_field => "Ensembl Gene ID", :namespace => organism, :type => :list)
-    samples = []
-    i = 0
-    num_samples = cohort.length
-    cnv_cohort.each do |sample,cnvs|
-      cnvs.genes.compact.flatten.uniq.each do |gene|
-        tsv[gene] ||= ["FALSE"] * num_samples
-        tsv[gene][i] = "TRUE"
-      end
-      samples << sample
-      i += 1
-    end
-
-    tsv.fields = samples
-
-    tsv
-  end
-
-  property :gene_sample_gain_matrix => :single do
-    tsv = TSV.setup({}, :key_field => "Ensembl Gene ID", :namespace => organism, :type => :list)
-    samples = []
-    i = 0
-    num_samples = cohort.length
-    cnv_cohort.each do |sample,cnvs|
-      cnvs.select_by(:gain?).genes.compact.flatten.uniq.each do |gene|
-        tsv[gene] ||= ["FALSE"] * num_samples
-        tsv[gene][i] = "TRUE"
-      end
-      samples << sample
-      i += 1
-    end
-
-    tsv.fields = samples
-
-    tsv
-  end
-
-
-  property :gene_sample_loss_matrix => :single do
-    tsv = TSV.setup({}, :key_field => "Ensembl Gene ID", :namespace => organism, :type => :list)
-    samples = []
-    i = 0
-    num_samples = cohort.length
-    cnv_cohort.each do |sample,cnvs|
-      cnvs.select_by(:loss?).genes.compact.flatten.uniq.each do |gene|
-        tsv[gene] ||= ["FALSE"] * num_samples
-        tsv[gene][i] = "TRUE"
-      end
-      samples << sample
-      i += 1
-    end
-
-    tsv.fields = samples
-
-    tsv
-  end
-end

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

@@ -1,28 +0,0 @@
-module Study
-
-  property :samples_with_gene_gained => :single do
-    samples_with_gene_gained = {}
-    self.job(:cnv_overview).run.through do |gene, values|
-      values.fields.zip(values).each do |sample, value|
-        next unless value == "Gained"
-        samples_with_gene_gained[gene] ||= []
-        samples_with_gene_gained[gene] << sample
-      end
-    end
-    samples_with_gene_gained
-  end
-  
-
-  property :samples_with_gene_lost => :single do
-    samples_with_gene_lost = {}
-    self.job(:cnv_overview).run.through do |gene, values|
-      values.fields.zip(values).each do |sample, value|
-        next unless value == "Lost"
-        samples_with_gene_lost[gene] ||= []
-        samples_with_gene_lost[gene] << sample
-      end
-    end
-    samples_with_gene_lost
-  end
-  
-end

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

@@ -1,39 +0,0 @@
-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