rbbt-phgx 2.0.1 → 2.1.0

checksums.yaml

@@ -0,0 +1,15 @@
+---
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    ZTQ0NDhjZjM0ODlmNmY4MTJjNzk5NmM4Yjg0ZjExN2Y4NGJkMmUwYQ==
+  data.tar.gz: !binary |-
+    MjY5NTQyNWE0Njk4OGZmNjUwYWI2YzM5MzBkODdhMzcyMDNjZDM5MQ==
+!binary "U0hBNTEy":
+  metadata.gz: !binary |-
+    YzQ3NDlmNzA2OWE5MmE3NGUzYTI5MTIyNzViYzQ0NGQxZDViZjI3ZTE4YmQ1
+    ODFlZTk3OWU1NWFhN2U0NWE5YzI3MGE0YTM1ZjFkZGIzYzVkNjI3MDBjMzhl
+    MjA4MmNkNjczN2Q0NzdhZjY1YWZiOWM2OTFkNTVjMDU2M2MwZGE=
+  data.tar.gz: !binary |-
+    OGY4ZjY0YjViYjc2MGU1MTM0MGFmODg0MWQ1YjQwOTJjOTk3MmIxMWUyNjE0
+    NTNkZTNlNTI2YzY0MGFiOWYyMzFhMWVhYjY2MmNhMTJiYzI2NWQ2YjE1YjIx
+    Yzk3NmM1MmFkMDk2MGNkNmVmYzZkMGExZjVkZDVmZmVjZDQ5ZTY=

data/LICENSE

@@ -1,4 +1,4 @@
-Copyright (c) 2010-2011 Miguel Vázquez García
+Copyright (c) 2010-2013 Miguel Vázquez García
 
 Permission is hereby granted, free of charge, to any person obtaining
 a copy of this software and associated documentation files (the

data/lib/rbbt/sources/kegg.rb

@@ -65,7 +65,6 @@ if defined? Entity
       name = KEGG.id2name(self)
       name.sub(/ - Homo.*/,'') unless name.nil?
     end
-    persist :name
 
     property :description => :single2array do
       KEGG.description(self)
@@ -76,7 +75,6 @@ if defined? Entity
       KEGG.index2genes.values_at(*self).
         each{|gene| gene.organism = organism if gene.respond_to? :organism }
     end
-    persist :genes
   end
 
   if defined? Gene and Entity === Gene
@@ -86,18 +84,18 @@ if defined? Entity
       def to_kegg
         return self if format == "KEGG Gene ID"
         if Array === self
-          Gene.setup(KEGG.index2kegg.values_at(*to("Ensembl Gene ID")), "KEGG Gene ID", organism)
+          Gene.setup(KEGG.index2kegg.values_at(*to("Ensembl Gene ID")), "KEGG Gene ID", organism).tap{|o| o.extend AnnotatedArray if AnnotatedArray === self }
         else
-          Gene.setup(KEGG.index2kegg[to("Ensembl Gene ID")], "KEGG Gene ID", organism)
+          Gene.setup(KEGG.index2kegg[to("Ensembl Gene ID")], "KEGG Gene ID", organism).tap{|o| o.extend AnnotatedArray if AnnotatedArray === self }
         end
       end
 
       def from_kegg
         return self unless format == "KEGG Gene ID"
         if Array === self
-          Gene.setup KEGG.index2ens.values_at(*self), "Ensembl Gene ID", organism
+          Gene.setup(KEGG.index2ens.values_at(*self), "Ensembl Gene ID", organism).tap{|o| o.extend AnnotatedArray if AnnotatedArray === self }
         else
-          Gene.setup KEGG.index2ens[self], "Ensembl Gene ID", organism
+          Gene.setup(KEGG.index2ens[self], "Ensembl Gene ID", organism).tap{|o| o.extend AnnotatedArray if AnnotatedArray === self }
         end
       end
 
@@ -112,19 +110,13 @@ if defined? Entity
           self 
         when format == "KEGG Gene ID"
           ensembl = from_kegg.clean_annotations
-          Gene.setup(Translation.job(:tsv_translate, "", :organism => organism, :genes => ensembl, :format => new_format).exec.values_at(*ensembl), new_format, organism)
+          Gene.setup(Translation.job(:tsv_translate, "", :organism => organism, :genes => ensembl, :format => new_format).exec.chunked_values_at(ensembl), new_format, organism).tap{|o| o.extend AnnotatedArray if AnnotatedArray === self }
         when new_format == "KEGG Gene ID"
           to_kegg
         else
-          Gene.setup(Translation.job(:tsv_translate, "", :organism => organism, :genes => self, :format => new_format).exec.values_at(*self), new_format, organism)
+          Gene.setup(Translation.job(:tsv_translate, "", :organism => organism, :genes => self, :format => new_format).exec.chunked_values_at(self), new_format, organism).tap{|o| o.extend AnnotatedArray if AnnotatedArray === self }
         end
       end
-      persist :to
-
-      #property :to => :array2single do |new_format|
-      #  return self if format == new_format
-      #  to!(new_format).collect!{|v| Array === v ? v.first : v}
-      #end
 
       property :kegg_pathways => :array2single do
         @kegg_pathways ||= Gene.gene_kegg_pathway_index.values_at(*self.to_kegg).

data/lib/rbbt/sources/string.rb

@@ -22,7 +22,6 @@ if defined? Entity and defined? Gene and Entity === Gene
 
       all
     end
-    #persist :_ary_string_interactors
   end
 end
 

metadata

@@ -1,20 +1,18 @@
 --- !ruby/object:Gem::Specification
 name: rbbt-phgx
 version: !ruby/object:Gem::Version
-  version: 2.0.1
-  prerelease: 
+  version: 2.1.0
 platform: ruby
 authors:
 - Miguel Vazquez
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-01-09 00:00:00.000000000 Z
+date: 2013-10-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rbbt-util
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
@@ -22,7 +20,6 @@ dependencies:
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
@@ -39,7 +36,6 @@ files:
 - lib/rbbt/mutation/chasm.rb
 - lib/rbbt/mutation/fireDB.rb
 - lib/rbbt/mutation/mutation_assessor.rb
-- lib/rbbt/mutation/oncodriveFM.rb
 - lib/rbbt/mutation/polyphen.rb
 - lib/rbbt/mutation/sift.rb
 - lib/rbbt/mutation/snps_and_go.rb
@@ -66,7 +62,6 @@ files:
 - share/install/STITCH/Rakefile
 - share/install/STRING/Rakefile
 - share/install/lib/rake_helper.rb
-- share/install/software/OncodriveFM
 - test/rbbt/sources/test_matador.rb
 - test/rbbt/sources/test_cancer.rb
 - test/rbbt/sources/test_stitch.rb
@@ -83,27 +78,26 @@ files:
 - test/test_helper.rb
 homepage: http://github.com/mikisvaz/rbbt-phgx
 licenses: []
+metadata: {}
 post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
   - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
   - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.24
+rubygems_version: 2.0.3
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: Pharmaco-genomics for the Ruby Bioinformatics Toolkit (rbbt)
 test_files:
 - test/rbbt/sources/test_matador.rb

data/lib/rbbt/mutation/oncodriveFM.rb

@@ -1,146 +0,0 @@
-require 'rbbt-util'
-require 'rbbt/util/open'
-require 'rbbt/tsv'
-require 'digest/md5'
-require 'rbbt/sources/organism'
-
-module OncodriveFM
-
-  Rbbt.claim Rbbt.software.opt.OncodriveFM, :install, Rbbt.share.install.software.OncodriveFM.find
-
-
-  def self.process_cohort(cohort)
-
-    all_mutated_isoforms = cohort.metagenotype.mutated_isoforms.compact.flatten.uniq
-    nonsense = all_mutated_isoforms.select{|mi| mi.consequence == "MISS-SENSE"}
-
-    mutation_assessor = MutEval.job(:mutation_assessor, "OncodriveFM", :mutations => all_mutated_isoforms.subset(nonsense)).run
-    sift              = MutEval.job(:sift, "OncodriveFM", :mutations => all_mutated_isoforms.subset(nonsense)).run
-    polyphen          = MutEval.job(:polyphen, "OncodriveFM", :mutations => all_mutated_isoforms.subset(nonsense)).run
-
-    mutation_assessor_max = mutation_assessor.slice("Mutation Assessor Score").values.flatten.collect{|v| (v.nil? or v.empty?) ? nil : v.to_f}.compact.max
-    sift_max              = sift.slice("SIFT Score").values.flatten.collect{|v| (v.nil? or v.empty?) ? nil : v.to_f}.compact.max
-    polyphen_max          = polyphen.slice("Polyphen Score").values.flatten.collect{|v| (v.nil? or v.empty?) ? nil : v.to_f}.compact.max
-
-    mutation_file = []
-    cohort.each do |genotype|
-      sample = genotype.jobname
-      genotype.each do |mutation|
-        genes = mutation.genes
-        next if genes.empty?
-        mut_mis = mutation.mutated_isoforms 
-        next if mut_mis.nil? or mut_mis.empty?
-        genes.each do |gene|
-          mis = mut_mis.select{|mi| mi.protein and mi.protein.gene == gene}
-
-          mutation_assessor.values_at(*mis)
-          ma_score       = mutation_assessor.values_at(*mis).compact.collect{|v| v["Mutation Assessor Score"]}.first
-          sift_score     = sift.values_at(*mis).compact.collect{|v| v["SIFT Score"]}.first
-          polyphen_score = polyphen.values_at(*mis).compact.collect{|v| v["Polyphen Score"]}.first
-
-          ma_score       = mutation_assessor_max if mis.select{|mi| mi.truncated}.any?
-          sift_score     = sift_max            if mis.select{|mi| mi.truncated}.any?
-          polyphen_score = polyphen_max    if mis.select{|mi| mi.truncated}.any?
-
-          mutation_file << [gene, sift_score || "NA", polyphen_score || "NA", ma_score || "NA", sample] * "\t"
-        end
-      end
-    end
-
-    TmpFile.with_file(mutation_file * "\n") do |fmuts|
-      TmpFile.with_file do |outdir|
-        FileUtils.mkdir_p outdir unless File.exists? outdir
-        name = "Tumor"
-
-        TmpFile.with_file(config(fmuts, outdir, "[TUMOR]" => name)) do |fconf|
-          puts Open.read(fconf)
-          CMD.cmd("cd #{Rbbt.software.opt.OncodriveFM.bin.find}; ./pipeline_launcher.pl '#{fconf}'").read
-        end
-
-        outfile = File.join(outdir, name + '.fimp')
-        text = Open.read(outfile).gsub(/WARNING.*?\n/m,'').gsub(/\t-\t/,"\t\t").gsub(/\t-$/,"\t")
-        tsv = TSV.open(StringIO.new(text), :type => :list)
-        tsv.key_field = "Ensembl Gene ID"
-        tsv.fields = ["Associated Gene Name", "Sample count", "p-value", "unknown"]
-
-        tsv
-      end
-    end
-
-  end
-
-  CONFIG_TEMPLATE=<<-EOF
-###########################################################################################
-# Input data specific for the tumor under analysis
-
-#tumor: This name will be used as prefix to name all intermediate and final pipeline files
-tumor='[TUMOR]'
-
-#mutfile: File that contains the mutations data of the tumor you want to analyze. Each row corresponds to the mutation of one gene in one sample. Its format should be:
-#
-####Ensembl_Gene_ID MA_Zscore CHASM_Zscore  Sample_ID
-mutfile='[MUTFILE]'
-
-####numFIS: number of functional scores included in the mutations file and used to compute the functional impact bias
-numFIS='[NUMFIS]'
-
-###########################################################################################
-
-###########################################################################################
-# Common input data (change these only if you have downloaded different info files)
-
-#genes2gos: File that contains the genes2gos mapping
-genes2gos='[DATA_DIR]/common/slimgos_distrib/genes2gos'
-
-#gosdistribs: Directory with the files that contain the distributions of SIFT, PPH2 and MA scores for each slimGOA obtained from 1000genomes.
-gosdistribs='[DATA_DIR]/common/slimgos_distrib/'
-
-#genes2symbols: File that contains the genes2symbols mapping obtained from BioMart. Its format should be:
-#
-####Ensembl_Gene_ID Gene_Symbol
-genes2symbols='[DATA_DIR]/common/genes2symbols.txt'
-
-extrec='NONE'
-
-#genes2probes: File that contains the genes2probes mapping obtained from BioMart. Its format should be:
-#
-####Ensembl_Gene_ID Probe_ID
-cp='[DATA_DIR]/common/cp.format'
-
-#genesattr: File that contains genes' longest CDS' lengths obtained from BioMart and genes' basal nsSNVs rates computed from 1000genomes. This are used to assess the statistical significance of genes' mutations recurrence and genes' overmutation rates. Its format should be:
-#
-####Ensembl_Gene_ID Longest_CDS_length  Basal_nsSNVs_rate
-genesattr='[DATA_DIR]/common/ensgenes_cds.recurrence'
-
-#outdir: Directory to write output files
-outdir='[OUTDIR]'
-
-#tmpdir: Directory to write intermediate files
-tmpdir='[TMPDIR]'
-
-#internal: whether the null distribution will be taken from variants observed in the tumor
-internal='[INTERNAL]'
-###########################################################################################
-  EOF
-
-  def self.config(mutfile, outdir, options = {})
-    options = Misc.add_defaults options, 
-      "[TUMOR]" => "Tumor",
-      "[MUTFILE]" => mutfile,
-      "[NUMFIS]" => 3,
-      "[DATA_DIR]" => Rbbt.software.opt.OncodriveFM.data.find,
-      "[OUTDIR]" => outdir,
-      "[TMPDIR]" => Rbbt.tmp.OncodriveFM.find,
-      "[INTERNAL]" => 1
-
-    FileUtils.mkdir_p options["[TMPDIR]"] unless File.exists? options["[TMPDIR]"]
-
-    txt = CONFIG_TEMPLATE.dup
-    options.each do |key,value|
-      txt.gsub!(key, value.to_s)
-    end
-
-    txt
-  end
-
-end

data/share/install/software/OncodriveFM

@@ -1,13 +0,0 @@
-#!/bin/bash
-
-INSTALL_HELPER_FILE="$1"
-RBBT_SOFTWARE_DIR="$2"
-
-source "$INSTALL_HELPER_FILE"
-
-name='OncodriveFM'
-url="http://bg.upf.edu/group/projects/oncodrivefm-1.1.0.tar.gz"
-
-
-install_src "$name" "$url"
-