bio-gemma-wrapper 0.97 → 0.97.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 9339be44d799349592c257f655bfe3e94ced5011
-  data.tar.gz: '09ec3c233405a6481bd19dade1ee03fa71362df8'
+  metadata.gz: 740af7561d0fb801b810713cd623f3d25e78971a
+  data.tar.gz: ce3aaae3418073dc1365bc8755ac73745ef4b01a
 SHA512:
-  metadata.gz: 13829ee7a9a78b56695a02b9c0fe8a4aeab0454b7a6887def6452351bf455e935944664976df9642e4657ef7ffad64b53c1f865f0d08e8520d0b72eac0eba5fc
-  data.tar.gz: ad92a7187e829869122030615f56354e14a44f91135b29a7f84dc869819639723dd15c6757cc0d9141cf82edcfc4acb1542d8bc9c9f61760ff1038f18fcd742b
+  metadata.gz: 30043473cf8b09ecf8a6fdcfa97468ba5d169bc7a0b6b6ab2102f7f978b8cb2c63fb5c5cefd7267cfe526e4748b6481aa9b6dbe7309dceff62f0351f79b16b0e
+  data.tar.gz: 07e50ab7b2b2d87bed1ce21b5b2d123693898163ff9a175841db190fcc22b43ee37ecc1df7cbc697e89b3dcaa193c489c299d3c50c1aa557d9512c4d494adec6

data/VERSION

@@ -1 +1 @@
-0.97
+0.97.1

data/bin/gemma-wrapper

@@ -6,7 +6,8 @@
 #
 # Copyright (C) 2017,2018 Pjotr Prins <pjotr.prins@thebird.nl>
 
-USAGE = "GEMMA wrapper example:
+USAGE = "
+GEMMA wrapper example:
 
     Simple caching of K computation with
 
@@ -63,6 +64,7 @@ end
 require 'fileutils'
 require 'optparse'
 require 'tmpdir'
+require 'tempfile'
 
 split_at = ARGV.index('--')
 if split_at
@@ -72,7 +74,17 @@ end
 options = { show_help: false, source: 'https://github.com/genetics-statistics/gemma-wrapper', version: version+' (Pjotr Prins)', date: Time.now.to_s, gemma_command: gemma_command, cache_dir: Dir.tmpdir() }
 
 opts = OptionParser.new do |o|
-  o.banner = "Usage: #{File.basename($0)} [options] -- [gemma-options]"
+  o.banner = "\nUsage: #{File.basename($0)} [options] -- [gemma-options]"
+
+  o.on('--permutate n', Integer, 'Permutate by shuffling phenotypes') do |lst|
+    options[:permutate] = lst
+    options[:force] = true
+  end
+
+  o.on('--phenotypes filen',String, 'Phenotypes to be shuffled in permutations') do |phenotypes|
+    options[:phenotypes] = phenotypes
+    raise "Phenotype input file #{phenotypes} does not exist" if !File.exist?(phenotypes)
+  end
 
   o.on('--loco [x,y,1,2,3...]', Array, 'Run full LOCO') do |lst|
     options[:loco] = lst
@@ -91,7 +103,7 @@ opts = OptionParser.new do |o|
     options[:json] = b
   end
 
-  o.on("--force", "Force computation") do |q|
+  o.on("--force", "Force computation (override cache)") do |q|
     options[:force] = true
   end
 
@@ -130,6 +142,7 @@ json_out = lambda do
   print record.to_json if options[:json]
 end
 
+# ---- Some error handlers
 error = lambda do |*msg|
   if options[:json]
     record[:error] = *msg.join(" ")
@@ -138,12 +151,14 @@ error = lambda do |*msg|
   end
   raise *msg
 end
+
 debug = lambda do |*msg|
   if options[:debug]
     record[:debug].push *msg.join("") if options[:json]
     OUTPUT.print "DEBUG: ",*msg,"\n"
   end
 end
+
 warning = lambda do |*msg|
   record[:warnings].push *msg.join("")
   OUTPUT.print "WARNING: ",*msg,"\n"
@@ -153,6 +168,8 @@ info = lambda do |*msg|
   OUTPUT.print *msg,"\n" if !options[:quiet]
 end
 
+# ---- Start banner
+
 GEMMA_K_VERSION=version
 GEMMA_K_BANNER = "gemma-wrapper #{version} (Ruby #{RUBY_VERSION}) by Pjotr Prins 2017,2018\n"
 info.call GEMMA_K_BANNER
@@ -160,7 +177,7 @@ info.call GEMMA_K_BANNER
 # Check gemma version
 GEMMA_COMMAND=options[:gemma_command]
 gemma_version_header = `#{GEMMA_COMMAND}`.split("\n").grep(/GEMMA|Version/)[0].strip
-info.call "Using GEMMA ",gemma_version_header,"\n"
+info.call "Using ",gemma_version_header,"\n"
 gemma_version = gemma_version_header.split(/[,\s]+/)[1]
 v_version, v_major, v_minor = gemma_version.split(".")
 info.call "Found #{gemma_version}, comparing against expected v0.#{GEMMA_V_MAJOR}.#{GEMMA_V_MINOR}"
@@ -185,6 +202,7 @@ hashme = []
 geno_idx = gemma_args.index '-g'
 raise "Expected GEMMA -g switch" if geno_idx == nil
 hashme = gemma_args
+hashme += ['-p', options[:phenotypes]] if options[:phenotypes]
 
 require 'digest/sha1'
 debug.call "Hashing on ",hashme,"\n"
@@ -230,6 +248,7 @@ invoke_gemma = lambda do |extra_args, cache_hit = false|
       end
       err
     else
+      debug.call("Invoking ",cmd) if options[:debug]
       system(cmd)
       $?.exitstatus
     end
@@ -244,7 +263,7 @@ end
 # returns datafn, logfn, cache_hit
 cache = lambda do | chr, ext |
   inject = (chr==nil ? "" : ".#{chr}" )+ext
-  hashi = HASH+inject
+  hashi = (chr==nil ? HASH : HASH+inject)
   prefix = options[:cache_dir]+'/'+hashi
   logfn  = prefix+".log.txt"
   datafn = prefix+ext
@@ -262,6 +281,7 @@ cache = lambda do | chr, ext |
   return hashi,false
 end
 
+# ---- Compute K
 kinship = lambda do | chr = nil |
   record[:type] = "K"
   ext = case (GEMMA_ARGS[GEMMA_ARGS.index('-gk')+1]).to_i
@@ -279,16 +299,16 @@ kinship = lambda do | chr = nil |
   end
 end
 
-gwas = lambda do | chr, kfn |
+# ---- Run GWA
+gwas = lambda do | chr, kfn, pfn |
   record[:type] = "GWA"
-  error.call "Do not use the GEMMA -k switch!" if GEMMA_ARGS.include? '-k'
+  error.call "Do not use the GEMMA -k switch with gemma-wrapper!" if GEMMA_ARGS.include? '-k' # K is automatic
   hashi, cache_hit = cache.call chr,".assoc.txt"
   if not cache_hit
-    if chr != nil
-      invoke_gemma.call [ '-loco', chr, '-k', kfn, '-o', hashi ]
-    else
-      error.call "Not supported"
-    end
+    args = [ '-k', kfn, '-o', hashi ]
+    args << [ '-loco', chr ] if chr != nil
+    args << [ '-p', pfn ] if pfn
+    invoke_gemma.call args
   end
 end
 
@@ -308,9 +328,53 @@ else
   # GWAS
   json_in = JSON.parse(File.read(options[:input]))
   raise "JSON problem, file #{options[:input]} is not -gk derived" if json_in["type"] != "K"
+
+  pfn = options[:phenotypes] # can be nil
   k_files = json_in["files"].map { |rec| [rec[0],rec[2]] }
-  k_files.each do | chr, kfn |
-    gwas.call(chr,kfn)
+  k_files.each do | chr, kfn | # call a GWA for each chromosome
+    gwas.call(chr,kfn,pfn)
+  end
+  # Permute
+  if options[:permutate]
+    ps = []
+    raise "You should supply --phenotype with gemma-wrapper --permutate" if not pfn
+    File.foreach(pfn).with_index do |line, line_num|
+      ps << line
+    end
+    score_list = []
+    debug.call(options[:permutate],"x permutations")
+    (1..options[:permutate]).each do |i|
+      $stderr.print "Iteration ",i,"\n"
+      # Create a shuffled phenotype file
+      file = File.open("phenotypes-#{i}","w")
+      tmp_pfn = file.path
+      p tmp_pfn
+      ps.shuffle.each do | l |
+        file.print(l)
+      end
+      file.close
+      k_files.each do | chr, kfn | # call a GWA for each chromosome
+        gwas.call(chr,kfn,tmp_pfn)
+      end
+      # p [:HEY,record[:files].last]
+      assocfn = record[:files].last[2]
+      debug.call("Reading ",assocfn)
+      score_min = 1000.0
+      File.foreach(assocfn).with_index do |assoc, assoc_line_num|
+        if assoc_line_num > 0
+          value = assoc.strip.split(/\t/).last.to_f
+          score_min = value if value < score_min
+        end
+      end
+      score_list << score_min
+    end
+    ls = score_list.sort
+    p ls
+    significant = ls[(ls.size - ls.size*0.95).floor]
+    suggestive = ls[(ls.size - ls.size*0.67).floor]
+    p ["95 percentile (significant) ",significant,(-Math.log10(significant)).round(1)]
+    p ["67 percentile (suggestive)  ",suggestive,(-Math.log10(suggestive)).round(1)]
+    exit 0
   end
 end
 

data/gemma-wrapper.gemspec

@@ -1,8 +1,8 @@
 Gem::Specification.new do |s|
   s.name        = 'bio-gemma-wrapper'
   s.version     = File.read('VERSION')
-  s.summary     = "Cache GEMMA with LOCO"
-  s.description = "GEMMA wrapper caches K between runs with LOCO support"
+  s.summary     = "GEMMA with LOCO and permutations"
+  s.description = "GEMMA wrapper adds LOCO and permutation support. Also caches K between runs with LOCO support"
   s.authors     = ["Pjotr Prins"]
   s.email       = 'pjotr.public01@thebird.nl'
   s.files       = ["bin/gemma-wrapper",

metadata

@@ -1,16 +1,17 @@
 --- !ruby/object:Gem::Specification
 name: bio-gemma-wrapper
 version: !ruby/object:Gem::Version
-  version: '0.97'
+  version: 0.97.1
 platform: ruby
 authors:
 - Pjotr Prins
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-02-10 00:00:00.000000000 Z
+date: 2018-07-19 00:00:00.000000000 Z
 dependencies: []
-description: GEMMA wrapper caches K between runs with LOCO support
+description: GEMMA wrapper adds LOCO and permutation support. Also caches K between
+  runs with LOCO support
 email: pjotr.public01@thebird.nl
 executables:
 - gemma-wrapper
@@ -46,5 +47,5 @@ rubyforge_project:
 rubygems_version: 2.6.8
 signing_key: 
 specification_version: 4
-summary: Cache GEMMA with LOCO
+summary: GEMMA with LOCO and permutations
 test_files: []