bioinform 0.1.6 → 0.1.7

data/lib/bioinform/data_models/pwm.rb

@@ -11,13 +11,13 @@ module Bioinform
                     position.each_index.inject(0) { |sum,letter| sum + position[letter]    * probability[letter] }**2
       end
     end
-    
+
     def threshold_gauss_estimation(pvalue)
       sigma = Math.sqrt(score_variance)
       n_ = Math.inverf(1 - 2 * pvalue) * Math.sqrt(2)
       score_mean + n_ * sigma
     end
-    
+
     def score(word)
       word = word.upcase
       raise ArgumentError, 'word in PWM#score(word) should have the same length as matrix'  unless word.length == length
@@ -32,7 +32,7 @@ module Bioinform
         end
       end.inject(&:+)
     end
-    
+
     def to_pwm
       self
     end

data/lib/bioinform/parsers/parser.rb

@@ -4,7 +4,7 @@ require 'bioinform/data_models/pm'
 module Bioinform
   class Parser
     attr_reader :input
-    
+
     def initialize(*input)
       if input.size == 1  # [ [1,2,3,4] ],  [  [[1,2,3,4],[5,6,7,8]] ]
         if input.first.is_a?(Array) && input.first.all?{|el| el.is_a? Numeric}  # [ [1,2,3,4] ]
@@ -16,21 +16,21 @@ module Bioinform
         @input = input
       end
     end
-    
+
     def parse!
       matrix = self.class.transform_input(input)
       raise 'Parsing error' unless self.class.valid_matrix?(matrix)
       {matrix: matrix}
     end
-    
+
     def parse
       parse! rescue nil
     end
-    
+
     def self.choose(input, data_model = PM)
       data_model.choose_parser(input).new(input)
     end
-    
+
     def self.parse!(*input)
       self.new(*input).parse!
     end
@@ -41,7 +41,7 @@ module Bioinform
     def self.valid_matrix?(matrix)
       PM.valid_matrix?(matrix)
     end
-    
+
     # {A: 1, C: 2, G: 3, T: 4}  -->  [1,2,3,4]
     # {A: [1,2], C: [3,4], G: [5,6], T: [7,8]}  --> [[1,3,5,7],[2,4,6,8]] ( == [[1,2], [3,4], [5,6], [7,8]].transpose)
     def self.array_from_acgt_hash(hsh)
@@ -50,12 +50,12 @@ module Bioinform
       result = [:A,:C,:G,:T].collect{|letter| hsh[letter] }
       result.all?{|el| el.is_a?(Array)} ? result.transpose : result
     end
-    
+
     # {a: 1, C: 2, 'g' => 3, 'T' => 4} --> {A: 1, C: 2, G: 3, T: 4}
     def self.normalize_hash_keys(hsh)
       hsh.collect_hash{|key,value| [key.to_s.upcase.to_sym, value] }
     end
-    
+
     # [[1,2,3,4], [2,3,4,5]] --> [[1,2,3,4], [2,3,4,5]]
     # [{A:1, C:2, G:3, T:4}, {A:2, C:3, G:4, T:5}] --> [{A:1, C:2, G:3, T:4}, {A:2, C:3, G:4, T:5}]
     # {:A => [1,2,3], :c => [2,3,4], 'g' => [3,4,5], 'T' => [4,5,6]} --> [[1,2,3],[2,3,4],[3,4,5],[4,5,6]].transpose
@@ -66,18 +66,18 @@ module Bioinform
       else raise TypeError, 'input of Bioinform::Parser::array_from_acgt_hash should be Array or Hash'
       end
     end
-    
+
     def self.transform_input(input)
       result = try_convert_to_array(input).map{|el| try_convert_to_array(el)}
       need_tranpose?(result) ? result.transpose : result
     end
-    
+
     # point whether matrix input positions(need not be transposed -- false) or letters(need -- true) as first index
     # [[1,3,5,7], [2,4,6,8]] --> false
     # [[1,2],[3,4],[5,6],[7,8]] --> true
     def self.need_tranpose?(input)
       (input.size == 4) && input.any?{|x| x.size != 4}
     end
-    
+
   end
 end

data/lib/bioinform/parsers/string_fantom_parser.rb

@@ -4,11 +4,32 @@ require 'bioinform/parsers/string_parser'
 module Bioinform
   class StringFantomParser < StringParser
     def header_pat
-      /NA (?<name>[\w.+:-]+)\n[\w\d]+ A C G T\n/
+      /NA (?<name>[\w.+:-]+)\n[\w\d]+ A C G T.*\n/
     end
-    
+
     def row_pat
       /[\w\d]+ (?<row>(#{number_pat} )*#{number_pat})\n?/
     end
+
+    def scan_splitter
+      scanner.scan(/(\/\/\n)+/)
+    end
+
+    def parse_matrix
+      matrix = []
+      while row_string = scan_row
+        matrix << split_row(row_string)[0,4]
+      end
+      matrix.transpose
+    end
+
+    def parse!
+      scan_any_spaces
+      scan_splitter
+      name = parse_name
+      matrix = parse_matrix
+      Parser.parse!(matrix).merge(name: name)
+    end
+
   end
 end

data/lib/bioinform/parsers/string_parser.rb

@@ -2,7 +2,7 @@ require 'strscan'
 require 'bioinform/support'
 require 'bioinform/parsers/parser'
 
-module Bioinform  
+module Bioinform
   class StringParser < Parser
     attr_reader :scanner, :row_acgt_markers
     def initialize(input)
@@ -10,40 +10,40 @@ module Bioinform
       super
       @scanner = StringScanner.new(input.multiline_squish)
     end
-  
+
     def number_pat
       /[+-]?\d+(\.\d+)?([eE][+-]?\d{1,3})?/
     end
-    
+
     def header_pat
       />?\s*(?<name>\S+)\n/
     end
-    
-    def row_pat 
+
+    def row_pat
       /([ACGT]\s*[:|]?\s*)?(?<row>(#{number_pat} )*#{number_pat})\n?/
     end
-    
+
     def scan_row
       match = scanner.advanced_scan(row_pat)
       match && match[:row]
     end
-    
+
     def split_row(row_string)
       row_string.split.map(&:to_f)
     end
-    
+
     def scan_any_spaces
       scanner.scan(/\s+/)
     end
-    
+
     def parse_name
       match = scanner.advanced_scan(header_pat)
       match && match[:name]
     end
-    
+
     def parse_matrix
       matrix = []
-      @row_acgt_markers = true  if scanner.check(/A.*\nC.*\nG.*\nT.*\n?/)        
+      @row_acgt_markers = true  if scanner.check(/A.*\nC.*\nG.*\nT.*\n?/)
       while row_string = scan_row
         matrix << split_row(row_string)
       end
@@ -53,7 +53,7 @@ module Bioinform
     def parse_acgt_header
       scanner.scan(/A\s*C\s*G\s*T\s*\n/i)
     end
-    
+
     def parse!
       scan_any_spaces
       name = parse_name
@@ -62,11 +62,11 @@ module Bioinform
       matrix = matrix.transpose if row_acgt_markers
       Parser.parse!(matrix).merge(name: name)
     end
-    
+
     def scanner_reset
       scanner.reset
     end
-    
+
     def each
       if block_given?
         scanner_reset
@@ -78,12 +78,12 @@ module Bioinform
       end
     end
     include Enumerable
-    
+
     alias_method :split, :to_a
     def self.split(input)
       self.new(input).split
     end
-    
+
     def self.split_on_motifs(input, pm_klass = PM)
       split(input).map{|el| pm_klass.new(el)}
     end

data/lib/bioinform/support/collect_hash.rb

@@ -2,6 +2,6 @@ module Enumerable
   # %w{A C G T}.collect_hash{|k| [k*2, k*3] }
   # # ==> {"AA" => "AAA", "CC" => "CCC", "GG" => "GGG", "TT" => "TTT"}
   def collect_hash(&block)
-    block_given?  ?  Hash[ collect(&block) ]  :  Hash[ collect{|k,v| [k,v]} ]    
+    block_given?  ?  Hash[ collect(&block) ]  :  Hash[ collect{|k,v| [k,v]} ]
   end
 end

data/lib/bioinform/version.rb

@@ -1,3 +1,3 @@
 module Bioinform
-  VERSION = "0.1.6"
+  VERSION = "0.1.7"
 end

data/spec/cli/data/KLF4 f2 spaced name.pcm

@@ -0,0 +1,11 @@
+KLF4_f2
+1233.46088405354  93.18173277811673  1036.6014857092885  1258.2948629970272
+263.979242343185  5.314520555872139  3347.5949971525274  4.650205486388122
+76.7700780003465  6.643150694840173  3529.4896409394937  8.636095903292224
+57.86097393406657  18.102585643439472  3520.3342027139347  25.24120324653207
+518.1947904009378  1545.9062946905135  22.396758181071043  1535.0411222654507
+137.98151691820345  9.300410972776241  3456.320530770924  17.936506876068467
+115.27647661640499  81.51802997128804  1861.9425868567278  1562.801872093553
+227.8095486111286  42.84555258785854  3278.6396005325996  72.244263806387
+108.73384179997886  134.47328134862394  3162.880454846513  215.45138754285665
+238.49636899561344  2225.9561104691043  402.40727964384774  754.6792064294074

data/spec/cli/data/KLF4_f2.pcm

@@ -0,0 +1,11 @@
+KLF4_f2
+1233.46088405354  93.18173277811673  1036.6014857092885  1258.2948629970272
+263.979242343185  5.314520555872139  3347.5949971525274  4.650205486388122
+76.7700780003465  6.643150694840173  3529.4896409394937  8.636095903292224
+57.86097393406657  18.102585643439472  3520.3342027139347  25.24120324653207
+518.1947904009378  1545.9062946905135  22.396758181071043  1535.0411222654507
+137.98151691820345  9.300410972776241  3456.320530770924  17.936506876068467
+115.27647661640499  81.51802997128804  1861.9425868567278  1562.801872093553
+227.8095486111286  42.84555258785854  3278.6396005325996  72.244263806387
+108.73384179997886  134.47328134862394  3162.880454846513  215.45138754285665
+238.49636899561344  2225.9561104691043  402.40727964384774  754.6792064294074

data/spec/cli/data/KLF4_f2.pwm.result

@@ -0,0 +1,11 @@
+KLF4_f2
+0.30861857265872605	-2.254321000121579	0.13505703522674192	0.3285194224375633
+-1.227018967707036	-4.814127713368663	1.3059890687390967	-4.908681463544344
+-2.443469374521196	-4.648238485031404	1.3588686548279805	-4.441801801188402
+-2.7177827948276123	-3.8073538975356565	1.356272809724262	-3.504104725510225
+-0.5563232977367343	0.5340697765121405	-3.61417723090579	0.5270259776377405
+-1.8687622060887386	-4.381483976582316	1.337932245336098	-3.815629658877517
+-2.045671123823928	-2.384975142213679	0.7198551207724355	0.5449254135616948
+-1.373157530374372	-3.0063112097748217	1.285188335493552	-2.5026044231773543
+-2.1030513122772208	-1.8941348100402244	1.249265758393991	-1.4284210948906104
+-1.3277128628152939	0.8982415633049462	-0.8080773665408135	-0.18161647647456935

data/spec/cli/data/SP1_f1.pcm

@@ -0,0 +1,12 @@
+SP1_f1
+682.6436366358055  443.1455214015781  2075.655346294993  287.211468117951
+299.8883246804867  103.74338315843572  2613.8927022405364  471.1315623708902
+591.4892493324709  42.631827541794564  2845.1654083148564  9.36948726124641
+7.071084742361592  45.29093411231232  3432.8847704374107  3.409183158303573
+91.308984085713  19.1536481364332  3373.656949880137  4.5363903481026
+809.2082973387932  2246.941954176211  61.30766021687515  371.19806071846244
+120.56476435866055  42.4349244403591  3242.1560628684038  83.50022078295852
+13.72524477409959  35.858220519297525  3332.4066864946167  106.66582066236779
+558.1188080161639  90.0084504200356  2694.854973210736  145.67374080342415
+264.0088462230318  254.7175868081866  2796.88087480315  173.0486646159857
+519.46013914282  1874.9349086474765  654.5411208373813  439.7198038226514

data/spec/cli/data/SP1_f1.pwm.result

@@ -0,0 +1,12 @@
+SP1_f1
+-0.24435707885585292	-0.674823404693731	0.8657012535789866	-1.1060188862599287
+-1.0631255752097797	-2.111925969423868	1.0960627561110403	-0.6138563775211977
+-0.3872276234760535	-2.9739851913218045	1.1807800242010378	-4.338927525031566
+-4.563896055436894	-2.9161633002532277	1.3684371349982638	-5.077972423609655
+-2.2369752892820083	-3.7196436313301846	1.3510439136452734	-4.889930670508233
+-0.07473964149330865	0.944919654762011	-2.6246857648086044	-0.8510983487822436
+-1.9643526491643322	-2.978402770880115	1.3113096718240573	-2.324334259499025
+-4.0155484139655835	-3.1384268078096667	1.3387488589788057	-2.084673903537648
+-0.44509385828355363	-2.2510053061629702	1.1265431574368685	-1.7780413702431372
+-1.1896356092245048	-1.2251832285630027	1.1636760063747527	-1.6080243648157353
+-0.5166047365590571	0.7641033353626657	-0.2862677570028208	-0.68254820978656

data/spec/cli/pcm2pwm_spec.rb

@@ -1,6 +1,80 @@
 require 'spec_helper'
+require 'shellwords'
 require 'bioinform/cli/pcm2pwm'
 
+
+def run_pcm2pwm(cmd)
+  Bioinform::CLI::PCM2PWM.main(cmd.shellsplit)
+end
+
 describe Bioinform::CLI::PCM2PWM do
+  before :each do
+    @start_dir = Dir.pwd
+    Dir.chdir File.join(File.dirname(__FILE__), 'data')
+  end
+  after :each do
+    File.delete('KLF4_f2.pwm')  if File.exist?('KLF4_f2.pwm')
+    File.delete('SP1_f1.pwm')  if File.exist?('SP1_f1.pwm')
+    File.delete('KLF4_f2.pat')  if File.exist?('KLF4_f2.pat')
+    File.delete('KLF4 f2 spaced name.pwm')  if File.exist?('KLF4 f2 spaced name.pwm')
+    FileUtils.rm_rf('pwm_folder')  if Dir.exist?('pwm_folder')
+    Dir.chdir(@start_dir)
+  end
+
+  it 'should transform single PCM to PWM' do
+    run_pcm2pwm('KLF4_f2.pcm')
+    File.exist?('KLF4_f2.pwm').should be_true
+    File.read('KLF4_f2.pwm').should == File.read('KLF4_f2.pwm.result')
+  end
+
+  it 'should transform multiple PCMs to PWMs' do
+    run_pcm2pwm('KLF4_f2.pcm SP1_f1.pcm')
+
+    File.exist?('KLF4_f2.pwm').should be_true
+    File.read('KLF4_f2.pwm').should == File.read('KLF4_f2.pwm.result')
+
+    File.exist?('SP1_f1.pwm').should be_true
+    File.read('SP1_f1.pwm').should == File.read('SP1_f1.pwm.result')
+  end
+
+  it 'should transform extension to specified with --extension option' do
+    run_pcm2pwm('KLF4_f2.pcm --extension=pat')
+    File.exist?('KLF4_f2.pat').should be_true
+    File.read('KLF4_f2.pat').should == File.read('KLF4_f2.pwm.result')
+  end
+
+  it 'should save PWMs into folder specified with --folder option when folder exists' do
+    Dir.mkdir('pwm_folder')  unless Dir.exist?('pwm_folder')
+    run_pcm2pwm('KLF4_f2.pcm --folder=pwm_folder')
+    File.exist?('pwm_folder/KLF4_f2.pwm').should be_true
+    File.read('pwm_folder/KLF4_f2.pwm').should == File.read('KLF4_f2.pwm.result')
+  end
+  it 'should save PWMs into folder specified with --folder option' do
+    FileUtils.rm_rf('pwm_folder')  if Dir.exist?('pwm_folder')
+    run_pcm2pwm('KLF4_f2.pcm --folder=pwm_folder')
+    File.exist?('pwm_folder/KLF4_f2.pwm').should be_true
+    File.read('pwm_folder/KLF4_f2.pwm').should == File.read('KLF4_f2.pwm.result')
+  end
+
+  it 'should process PCMs with names obtained from STDIN' do
+    provide_stdin('KLF4_f2.pcm SP1_f1.pcm') { run_pcm2pwm('') }
+    File.exist?('KLF4_f2.pwm').should be_true
+    File.read('KLF4_f2.pwm').should == File.read('KLF4_f2.pwm.result')
+
+    File.exist?('SP1_f1.pwm').should be_true
+    File.read('SP1_f1.pwm').should == File.read('SP1_f1.pwm.result')
+  end
+
+  it 'should process PCMs with names obtained from STDIN when there are some options' do
+    provide_stdin('KLF4_f2.pcm') { run_pcm2pwm('-e pat') }
+    File.exist?('KLF4_f2.pat').should be_true
+    File.read('KLF4_f2.pat').should == File.read('KLF4_f2.pwm.result')
+  end
+
+  it 'should process PCMs having filename with spaces' do
+    run_pcm2pwm('"KLF4 f2 spaced name.pcm"')
+    File.exist?('KLF4 f2 spaced name.pwm').should be_true
+    File.read('KLF4 f2 spaced name.pwm').should == File.read('KLF4_f2.pwm.result')
+  end
 
 end

data/spec/data_models/collection_spec.rb

@@ -0,0 +1,96 @@
+require 'spec_helper'
+require 'bioinform/data_models/collection'
+
+module Bioinform
+  describe Collection do
+    before :each do
+      @collection = Collection.new(name: 'Main collection')
+      @pm_1 = PM.new(matrix:[[1,1,1,1]],name:'Stub datamodel')
+      @pm_2 = PM.new(matrix:[[1,2,3,4],[4,3,2,1]],name:'Second stub')
+      @pm_3 = PM.new(matrix:[[11,12,13,14],[41,31,21,11]],name:'Third stub')
+    end
+    describe '#size' do
+      it 'should return size of collection' do
+        @collection << @pm_1 << @pm_2 << @pm_3
+        @collection.size.should == 3
+      end
+    end
+    describe '#<<' do
+      it 'should add element to collection' do
+        @collection << @pm_1
+        @collection << @pm_2
+        @collection << @pm_3
+        @collection.collection.map(&:first).should include(@pm_1, @pm_2, @pm_3)
+      end
+      it 'should be chainable' do
+        @collection << @pm_1 << @pm_2 << @pm_3
+        @collection.collection.map(&:first).should include(@pm_1, @pm_2, @pm_3)
+      end
+      it 'should mark motif with name' do
+        @collection << @pm_1 << @pm_2
+        @pm_1.should be_tagged('Main collection')
+        @pm_2.should be_tagged('Main collection')
+      end
+      it 'should mark motif with self' do
+        @collection << @pm_1 << @pm_2
+        @pm_1.should be_tagged(@collection)
+        @pm_2.should be_tagged(@collection)
+      end
+    end
+
+    describe '#each_pm' do
+      before :each do
+        @collection << @pm_1 << @pm_2 << @pm_3
+      end
+      context 'with block given' do
+        it 'should yield elements of collecton' do
+          expect{|b| @collection.each_pm(&b)}.to yield_successive_args(@pm_1, @pm_2, @pm_3)
+        end
+      end
+      context 'with block given' do
+        it 'return an Enumerator' do
+          @collection.each_pm.should be_kind_of(Enumerator)
+        end
+      end
+    end
+    describe '#each_pcm' do
+      before :each do
+        @collection << @pm_1 << @pm_2 << @pm_3
+      end
+      context 'with block given' do
+        it 'should yield elements of collecton converted to pcm' do
+          expect{|b| @collection.each_pcm(&b)}.to yield_successive_args(PCM, PCM, PCM)
+        end
+      end
+      context 'with block given' do
+        it 'return an Enumerator' do
+          @collection.each_pcm.should be_kind_of(Enumerator)
+        end
+      end
+    end
+
+    describe '#+' do
+      before :each do
+        @collection << @pm_1 << @pm_2 << @pm_3
+        @pm_sec_1 = PM.new(matrix: [[1,0,1,0],[0,0,0,0],[1,2,3,4]], name: 'Secondary collection matrix 1')
+        @pm_sec_2 = PM.new(matrix: [[1,2,1,2],[0,3,6,9],[1,2,3,4]], name: 'Secondary collection matrix 2')
+        @secondary_collection = Collection.new(name: 'Secondary collection')
+        @secondary_collection << @pm_sec_1 << @pm_sec_2
+        @summary_collection = @collection + @secondary_collection
+      end
+      it 'should create a collection consisting of all elements of both collections' do
+        @summary_collection.should be_kind_of(Collection)
+        @summary_collection.size.should == (@collection.size + @secondary_collection.size)
+        @summary_collection.collection.map(&:first).should include(@pm_1, @pm_2, @pm_3, @pm_sec_1, @pm_sec_2)
+      end
+      it 'should leave marks on motifs' do
+        @pm_1.should be_tagged('Main collection')
+        @pm_sec_1.should be_tagged('Secondary collection')
+      end
+      it 'should not mix marks of motifs in different collections' do
+        @pm_1.should_not be_tagged('Secondary collection')
+        @pm_sec_1.should_not be_tagged('Main collection')
+      end
+    end
+  end
+end