macroape 3.3.4 → 3.3.5

data/README.md

@@ -20,7 +20,7 @@ Or install it yourself as:
   For more information read manual at https://docs.google.com/document/pub?id=1_jsxhMNzMzy4d2d_byAd3n6Szg5gEcqG_Sf7w9tEqWw (not last version but comprehensive description of approach)
 
 ## Basic usage as a command-line tool
-  MacroAPE have 6 command line tools:
+  MacroAPE have 7 command line tools:
   
 ### Tools for calculating thresholds and pvalues:
   * find_threshold \<PWM file\> [-p \<pvalue\> (by default: 0.0005)]
@@ -34,8 +34,12 @@ Or install it yourself as:
   * preprocess_collection \<folder with motif files\> [-o \<collection output file\>]
   * scan_collection \<query PWM file\> \<collection file\>
   
+### Tool for finding mutual alignment of several motifs relative to first(leader) motif. It's designed to use with sequence_logo to draw logos of clusters
+  * align_motifs \<pwm_leader\> \<pwm_2\> \<pwm_3\> ...
+  
   Also you can use -h option to print help for a tool in console.
   There are lots of different command line options. Most useful option is -d <discretization=1|10|100|1000>. You can vary precision/speed rate by specifing a discretization. For more information look through a manual.
+  Some of tools also can process PCMs in addition to PWMs.
 
 ## Basic usage in your code
     require 'macroape'
@@ -51,7 +55,7 @@ Or install it yourself as:
     similarity_info = cmp.jaccard(first_threshold, second_threshold)
     puts "Jaccard similarity: #{similarity_info[:similarity]}"
     
-  For more details look a source code of utilities in lib/exec/ folder
+  For more details look a source code of utilities in lib/macroape/cli/ folder
 
 ## Contributing
 

data/TODO.txt

@@ -1,6 +1,3 @@
-Absolutely necessary:
-  (already work in preprocess_colleсtion and align_motifs) Make it available to load PCM files with (it should be first preprocessed to PWMs in a standardized way) -- may be it's better to use pipeline 
-
 Specs and tests:
   create spec on use of MaxHashSize, MaxHashSizeDouble
   create spec for testing case when {real_pvalue == 0, threshold == best_score + 1}
@@ -17,5 +14,5 @@ Usability issues:
 
 remove .stdin placeholder. Use tty? method instead
 
-use OptionParser (??? can OptionParser get stub ARGV ???)
+use OptionParser or docopt
 make options more uniform so that some of them were reusable(and the question: can I apply two option parsers consequently?)

data/lib/macroape/cli/eval_alignment.rb

@@ -44,7 +44,8 @@ module Macroape
         second_background = [1,1,1,1]
         max_hash_size = 1000000
         max_pair_hash_size = 1000
-
+        
+        data_model = argv.delete('--pcm') ? Bioinform::PCM : Bioinform::PWM
 
         first_file = argv.shift
         second_file = argv.shift
@@ -93,18 +94,20 @@ module Macroape
         parser = Bioinform::StringParser.new($stdin.read)  if first_file == '.stdin' || second_file == '.stdin'
       
         if first_file == '.stdin'
-          pwm_first = Bioinform::PWM.new( parser.parse )
+          input_first = parser.parse
         else
           raise "Error! File #{first_file} don't exist" unless File.exist?(first_file)
-          pwm_first = Bioinform::PWM.new(File.read(first_file))
+          input_first = File.read(first_file)
         end
+        pwm_first = data_model.new(input_first).to_pwm
 
         if second_file == '.stdin'
-          pwm_second = Bioinform::PWM.new( parser.parse )
+          input_second = parser.parse
         else
           raise "Error! File #{second_file} don't exist" unless File.exist?(second_file)
-          pwm_second = Bioinform::PWM.new(File.read(second_file))
+          input_second = File.read(second_file)
         end
+        pwm_second = data_model.new(input_second).to_pwm
         
         pwm_first.background!(first_background).max_hash_size!(max_hash_size).discrete!(discretization)
         pwm_second.background!(second_background).max_hash_size!(max_hash_size).discrete!(discretization)

data/lib/macroape/cli/eval_similarity.rb

@@ -47,7 +47,7 @@ module Macroape
         max_hash_size = 1000000
         max_pair_hash_size = 1000
 
-      
+        data_model = argv.delete('--pcm') ? Bioinform::PCM : Bioinform::PWM      
         first_file = argv.shift
         second_file = argv.shift
         raise "You'd specify two input sources (each is filename or .stdin)" unless first_file and second_file
@@ -76,18 +76,20 @@ module Macroape
         parser = Bioinform::StringParser.new($stdin.read)  if first_file == '.stdin' || second_file == '.stdin'
         
         if first_file == '.stdin'
-          pwm_first = Bioinform::PWM.new( parser.parse )
+          input_first = parser.parse
         else
           raise "Error! File #{first_file} don't exist" unless File.exist?(first_file)
-          pwm_first = Bioinform::PWM.new(File.read(first_file))
+          input_first = File.read(first_file)
         end
+        pwm_first = data_model.new(input_first).to_pwm
 
         if second_file == '.stdin'
-          pwm_second = Bioinform::PWM.new( parser.parse )
+          input_second = parser.parse
         else
           raise "Error! File #{second_file} don't exist" unless File.exist?(second_file)
-          pwm_second = Bioinform::PWM.new(File.read(second_file))
+          input_second = File.read(second_file)
         end
+        pwm_second = data_model.new(input_second).to_pwm
         
         pwm_first.background!(first_background).max_hash_size!(max_hash_size).discrete!(discretization)
         pwm_second.background!(second_background).max_hash_size!(max_hash_size).discrete!(discretization)

data/lib/macroape/cli/find_pvalue.rb

@@ -41,6 +41,7 @@ module Macroape
         thresholds = []
         max_hash_size = 1000000
 
+        data_model = argv.delete('--pcm') ? Bioinform::PCM : Bioinform::PWM
         filename = argv.shift
 
         loop do
@@ -68,11 +69,12 @@ module Macroape
 
         
         if filename == '.stdin'
-          pwm = Bioinform::PWM.new( $stdin.read )
+          input = $stdin.read
         else
           raise "Error! File #{filename} doesn't exist" unless File.exist?(filename)
-          pwm = Bioinform::PWM.new( File.read(filename) )
+          input = File.read(filename)
         end
+        pwm = data_model.new(input).to_pwm
         pwm.background!(background).max_hash_size!(max_hash_size).discrete!(discretization)
 
         counts = pwm.counts_by_thresholds(* thresholds.map{|count| count * discretization})

data/lib/macroape/cli/find_threshold.rb

@@ -36,6 +36,7 @@ module Macroape
         default_pvalues = [0.0005]
         discretization = 10000
         max_hash_size = 1000000
+        data_model = argv.delete('--pcm') ? Bioinform::PCM : Bioinform::PWM      
 
         filename = argv.shift
         raise "No input. You'd specify input source: filename or .stdin" unless filename
@@ -63,12 +64,12 @@ module Macroape
         pvalues = default_pvalues if pvalues.empty?
 
         if filename == '.stdin'
-          pwm = Bioinform::PWM.new( $stdin.read )
+          input = $stdin.read
         else
           raise "Error! File #{filename} doesn't exist" unless File.exist?(filename)
-          pwm = Bioinform::PWM.new( File.read(filename) )
+          input = File.read(filename)
         end
-
+        pwm = data_model.new(input).to_pwm
         pwm.background!(background).max_hash_size!(max_hash_size).discrete!(discretization)
 
         pwm.thresholds(*pvalues) do |pvalue, threshold, real_pvalue|

data/lib/macroape/cli/preprocess_collection.rb

@@ -74,7 +74,7 @@ module Macroape
         collection = Macroape::Collection.new(rough_discretization, precise_discretization, background, pvalues)
         
         if File.directory?(data_source)
-            motifs = Dir.glob(File.join(data_source,'*')).map do |filename|
+          motifs = Dir.glob(File.join(data_source,'*')).map do |filename|
             pwm = data_model.new(File.read(filename))
             pwm.name ||= File.basename(filename, File.extname(filename))
             pwm

data/lib/macroape/cli/scan_collection.rb

@@ -36,6 +36,7 @@ module Macroape
           exit
         end
 
+        data_model = argv.delete('--pcm') ? Bioinform::PCM : Bioinform::PWM
         filename = argv.shift
         collection_file = argv.shift
         raise "No input. You'd specify input source for pat: filename or .stdin" unless filename
@@ -82,12 +83,13 @@ module Macroape
         raise "Thresholds for pvalue #{pvalue} aren't presented in collection (#{collection.pvalues.join(', ')}). Use one of listed pvalues or recalculate the collection with needed pvalue" unless collection.pvalues.include? pvalue
         
         if filename == '.stdin'
-          query_pwm = Bioinform::PWM.new( $stdin.read )
+          query_input = $stdin.read
         else
           raise "Error! File #{filename} doesn't exist" unless File.exist?(filename)
-          query_pwm = Bioinform::PWM.new(File.read(filename))
+          query_input = File.read(filename)
         end
 
+        query_pwm = data_model.new(query_input).to_pwm
         query_pwm.background(background_query).max_hash_size(max_hash_size)
         
         query_pwm_rough = query_pwm.discrete(collection.rough_discretization)

data/lib/macroape/version.rb

@@ -1,3 +1,3 @@
 module Macroape
-  VERSION = "3.3.4"
+  VERSION = "3.3.5"
 end

data/test/eval_alignment_test.rb

@@ -1,6 +1,10 @@
 require 'test_helper'
 
 class TestEvalAlignment < Test::Unit::TestCase
+  def test_process_pcm_files
+    assert_equal "0.2420758234928527\n779.0\t11\n.>>>>>>>>>>\n>>>>>>>>>>>\n-1\tdirect\n", Helpers.eval_alignment_output('test/data/KLF4_f2.pcm test/data/SP1_f1.pcm -1 direct --pcm')
+  end
+
   def test_process_at_optimal_alignment
     assert_equal "0.2420758234928527\n779.0\t11\n.>>>>>>>>>>\n>>>>>>>>>>>\n-1\tdirect\n", Helpers.eval_alignment_output('test/data/KLF4_f2.pat test/data/SP1_f1.pat -1 direct')
   end

data/test/eval_similarity_test.rb

@@ -1,6 +1,9 @@
 require 'test_helper'
 
 class TestEvalSimilarity < Test::Unit::TestCase
+  def test_process_pair_of_pcms
+    assert_equal "0.2420758234928527\n779.0\t11\n.>>>>>>>>>>\n>>>>>>>>>>>\n-1\tdirect\n", Helpers.eval_similarity_output('test/data/KLF4_f2.pcm test/data/SP1_f1.pcm --pcm')
+  end
   def test_process_pair_of_pwms
     assert_equal "0.2420758234928527\n779.0\t11\n.>>>>>>>>>>\n>>>>>>>>>>>\n-1\tdirect\n", Helpers.eval_similarity_output('test/data/KLF4_f2.pat test/data/SP1_f1.pat')
   end

data/test/find_pvalue_test.rb

@@ -1,6 +1,9 @@
 require 'test_helper'
 
 class FindPvalueTest < Test::Unit::TestCase
+  def test_process_pcm
+    assert_equal "4.1719\t1048.0\t0.00099945068359375\n", Helpers.find_pvalue_output('test/data/KLF4_f2.pcm 4.1719 --pcm')
+  end
   def test_process_one_threshold
     assert_equal "4.1719\t1048.0\t0.00099945068359375\n", Helpers.find_pvalue_output('test/data/KLF4_f2.pat 4.1719')
   end

data/test/find_threshold_test.rb

@@ -10,6 +10,11 @@ class FindThresholdTest < Test::Unit::TestCase
     }
     assert_equal pvalues, ['0.0005', '0.001']
   end
+  def test_process_pcm
+    pvalue, threshold, real_pvalue = Helpers.find_threshold_output('test/data/KLF4_f2.pcm -p 0.001 --pcm').strip.split("\t")
+    assert_equal '0.001', pvalue
+    assert_equal Helpers.obtain_pvalue_by_threshold("test/data/KLF4_f2.pat #{threshold}"), real_pvalue
+  end
   def test_process_one_pvalue
     pvalue, threshold, real_pvalue = Helpers.find_threshold_output('test/data/KLF4_f2.pat -p 0.001').strip.split("\t")
     assert_equal '0.001', pvalue

data/test/scan_collection_test.rb

@@ -1,6 +1,10 @@
 require 'test_helper'
 
 class TestScanCollection < Test::Unit::TestCase
+  def test_scan_pcm
+    assert_equal File.read('test/data/KLF4_f2_scan_results_default_cutoff.txt').gsub("\r\n", "\n"),
+                 Helpers.scan_collection_output('test/data/KLF4_f2.pcm test/data/test_collection.yaml --silent --pcm').gsub("\r\n","\n")
+  end
   def test_scan_default_cutoff
     assert_equal File.read('test/data/KLF4_f2_scan_results_default_cutoff.txt').gsub("\r\n", "\n"),
                  Helpers.scan_collection_output('test/data/KLF4_f2.pat test/data/test_collection.yaml --silent').gsub("\r\n","\n")

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: macroape
 version: !ruby/object:Gem::Version
-  version: 3.3.4
+  version: 3.3.5
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-09-01 00:00:00.000000000 Z
+date: 2012-09-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bioinform