macroape 3.2.2

data/lib/macroape/threshold_by_pvalue.rb

@@ -0,0 +1,68 @@
+module PWM
+  module ThresholdByPvalue
+    def threshold(pvalue)
+      thresholds(pvalue){|_, thresh, _| return thresh }
+    end
+    
+    def thresholds(*pvalues)
+      thresholds_by_pvalues(*pvalues).each do |pvalue,(left_threshold, left_count, right_threshold, right_count)|
+        threshold = left_threshold + 0.1
+        real_pvalue = right_count.to_f / number_of_words
+        yield pvalue, threshold, real_pvalue
+      end
+    end
+  
+    # ret-value: hash {pvalue => [left_threshold, left_count, right_threshold, right_count]}
+    def thresholds_by_pvalues(*pvalues)
+      max_pvalue = pvalues.max
+      max_look_for_count = max_pvalue * sum_of_probabilities ** length
+      scores={}
+      until scores.inject(0){|sum,(score,count)| sum + count} >= max_look_for_count
+        scores = calculate_count_distribution_after_threshold(threshold_gauss_estimation(max_pvalue))
+        max_pvalue *=2 # if estimation counted too small amount of words - try to lower threshold estimation by doubling pvalue
+      end
+      pvalue_counts = pvalues.sort.inject(Hash.new){|h, pvalue| h.merge pvalue => pvalue * sum_of_probabilities**length }
+      look_for_counts = pvalue_counts.to_a
+      sum_count = 0
+      scores = scores.sort.reverse
+      results = {}
+      scores.size.times do |i|
+        while !look_for_counts.empty? and sum_count + scores[i][1] > look_for_counts.first[1] # usually this 'while' works as 'if'
+          cnt = look_for_counts.shift
+          pval = cnt[0]
+          score = cnt[1]
+          
+          threshold_2 = scores[i][0]
+          sum_count_2 = sum_count + scores[i][1]
+          if i>0
+            threshold = scores[i-1][0]
+            results[pval] = [threshold_2.to_f, sum_count_2, threshold.to_f, sum_count.to_f]
+          else          
+            results[pval] = [threshold_2.to_f, sum_count_2.to_f, best_score + 1.0, 0.0]
+          end
+        end
+        sum_count += scores[i][1]
+      end
+      results
+    end
+    
+    def calculate_count_distribution_after_threshold(threshold)
+      scores = { 0 => 1 }
+      length.times do |column|
+        new_scores = Hash.new(0);
+        scores.each do |score, count|
+          4.times do |letter|
+            new_score = score + matrix[column][letter]
+            if new_score + best_suffix[column + 1] >= threshold
+              new_scores[new_score] += count * probabilities[letter]
+            end
+          end
+        end
+        raise 'Hash overflow in PWM::ThresholdByPvalue#calculate_count_distribution_after_threshold' if defined? MaxHashSize and new_scores.size > MaxHashSize
+        scores = new_scores
+      end
+      scores
+    end
+    
+  end
+end

data/lib/macroape/version.rb

@@ -0,0 +1,3 @@
+module Macroape
+  VERSION = "3.2.2"
+end

data/lib/macroape.rb

@@ -0,0 +1,26 @@
+require 'macroape/version'
+require 'yaml'
+
+require 'macroape/extract_pwm'
+require 'macroape/support'
+require 'macroape/matrix_transformations'
+require 'macroape/matrix_information'
+require 'macroape/gauss_estimation'
+require 'macroape/threshold_by_pvalue'
+require 'macroape/single_matrix'
+require 'macroape/count_by_threshold'
+require 'macroape/matrix_on_background'
+
+require 'macroape/aligned_pair_transformations'
+require 'macroape/aligned_pair_metrics'
+require 'macroape/aligned_pair_intersection'
+require 'macroape/pwm_compare_aligned'
+
+require 'macroape/pair_transformations'
+require 'macroape/pair_metrics'
+require 'macroape/pwm_compare'
+require 'macroape/collection'
+
+module Macroape
+  # Your code goes here...
+end

data/macroape.gemspec

@@ -0,0 +1,17 @@
+# -*- encoding: utf-8 -*-
+require File.expand_path('../lib/macroape/version', __FILE__)
+
+Gem::Specification.new do |gem|
+  gem.authors       = ["Ilya Vorontsov"]
+  gem.email         = ["prijutme4ty@gmail.com"]
+  gem.description   = %q{Macroape is an abbreviation for MAtrix CompaRisOn by Approximate P-value Estimation. It's a bioinformatic tool for evaluating similarity measure and best alignment between a pair of Position Weight Matrices(PWM), finding thresholds by P-values and inside out and even searching a collection of motifs for the most similar ones. Used approach and application described in manual at https://docs.google.com/document/pub?id=1_jsxhMNzMzy4d2d_byAd3n6Szg5gEcqG_Sf7w9tEqWw}
+  gem.summary       = %q{PWM comparison tool using MACROAPE approach}
+  gem.homepage      = "http://autosome.ru/macroape/"
+
+  gem.files         = `git ls-files`.split($\)
+  gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
+  gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
+  gem.name          = "macroape"
+  gem.require_paths = ["lib"]
+  gem.version       = Macroape::VERSION
+end

data/test/data/AHR_si.pat

@@ -0,0 +1,10 @@
+AHR_si
+0.049659785047588834 -0.7112292711652757 0.3721858143748157 0.007118345755728267 
+-1.1863517717347094 -1.107677589450009 -0.10122262270571995 0.9004092051347228 
+-0.5481419620395529 0.12723771473208506 -0.5930888656288792 0.5502420250441413 
+-2.3460850844035757 -2.7362137930742167 1.3086872088653387 -1.9795601218727432 
+-3.45212725495741 1.3387809407527818 -2.67026944276278 -2.46866856874775 
+-2.1349735467777395 -2.965000508388952 1.3322808172765488 -3.206089427067848 
+-3.45212725495741 -2.1349735467777395 -3.0087911229263207 1.335191259740944 
+-3.45212725495741 -3.45212725495741 1.3622489404156526 -3.45212725495741 
+0.10927007207680632 0.5389064901558549 -0.8250174241334556 -0.3117320885632525 

data/test/data/KLF4_f2.pat

@@ -0,0 +1,11 @@
+KLF4_f2.xml
+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/test/data/KLF4_f2_scan_results_all.txt

@@ -0,0 +1,4 @@
+#pwm	similarity	shift	overlap	orientation
+KLF4_f2	1.0	0	10	direct
+SP1_f1	0.22754919499105544	-1	10	direct
+GABPA_f1	0.00043527658136684877	-8	5	direct

data/test/data/KLF4_f2_scan_results_default_cutoff.txt

@@ -0,0 +1,3 @@
+#pwm	similarity	shift	overlap	orientation
+KLF4_f2	1.0	0	10	direct
+SP1_f1	0.22754919499105544	-1	10	direct

data/test/data/KLF4_f2_scan_results_precise_mode.txt

@@ -0,0 +1,4 @@
+#pwm	similarity	shift	overlap	orientation
+KLF4_f2	1.0	0	10	direct	*
+SP1_f1	0.2420758234928527	-1	10	direct	*
+GABPA_f1	0.00043527658136684877	-8	5	direct

data/test/data/SP1_f1.pat

@@ -0,0 +1,12 @@
+> SP1_f1
+-0.24435707885585334  -0.6748234046937317  0.8657012535789861  -1.1060188862599292
+-1.0631255752097801  -2.1119259694238686  1.0960627561110399  -0.6138563775211981
+-0.387227623476054  -2.973985191321805  1.1807800242010371  -4.338927525031567
+-4.563896055436894  -2.916163300253228  1.3684371349982631  -5.077972423609655
+-2.2369752892820087  -3.719643631330185  1.3510439136452728  -4.8899306705082335
+-0.07473964149330914  0.9449196547620103  -2.624685764808605  -0.851098348782244
+-1.9643526491643326  -2.9784027708801153  1.3113096718240569  -2.3243342594990253
+-4.015548413965584  -3.138426807809667  1.338748858978805  -2.0846739035376483
+-0.4450938582835542  -2.2510053061629707  1.126543157436868  -1.7780413702431377
+-1.1896356092245055  -1.2251832285630033  1.163676006374752  -1.6080243648157357
+-0.5166047365590577  0.7641033353626651  -0.28626775700282125  -0.6825482097865606

data/test/data/SP1_f1_revcomp.pat

@@ -0,0 +1,12 @@
+SP1_f1_revcomp
+-0.6825482097865606 -0.28626775700282125 0.7641033353626651 -0.5166047365590577
+-1.6080243648157357 1.163676006374752 -1.2251832285630033 -1.1896356092245055
+-1.7780413702431377 1.126543157436868 -2.2510053061629707 -0.4450938582835542
+-2.0846739035376483 1.338748858978805 -3.138426807809667 -4.015548413965584
+-2.3243342594990253 1.3113096718240569 -2.9784027708801153 -1.9643526491643326
+-0.851098348782244 -2.624685764808605 0.9449196547620103 -0.07473964149330914
+-4.8899306705082335 1.3510439136452728 -3.719643631330185 -2.2369752892820087
+-5.077972423609655 1.3684371349982631 -2.916163300253228 -4.563896055436894
+-4.338927525031567 1.1807800242010371 -2.973985191321805 -0.387227623476054
+-0.6138563775211981 1.0960627561110399 -2.1119259694238686 -1.0631255752097801
+-1.1060188862599292 0.8657012535789861 -0.6748234046937317 -0.24435707885585334

data/test/data/test_collection/GABPA_f1.pat

@@ -0,0 +1,14 @@
+GABPA_f1
+-0.1106670158341858 0.013801606113892391 0.6054596108973699 -1.3518085041421573 
+0.37030668921643345 0.15761121480429963 0.009069314183831202 -0.9888619717703562 
+0.47526546359546684 -0.3011678534572083 0.4031522994412777 -1.8638752827041059 
+-1.5544255540164373 1.1082369687811506 -0.2814091552834454 -5.30708531823271 
+-0.6362037835776368 1.235338189985594 -3.5801322928552253 -5.717323067092849 
+-5.852906870733575 -5.852906870733575 1.3841383838057746 -5.852906870733575 
+-5.852906870733575 -5.852906870733575 1.3841383838057746 -5.852906870733575 
+1.3835219739184708 -5.2341956006430985 -5.852906870733575 -5.852906870733575 
+1.3756340514956562 -5.394962755562375 -5.394962755562375 -3.401117964959733 
+-1.2176198315414444 -3.109079898175411 1.2964067931472216 -5.717323067092849 
+-1.3716559438167257 -0.2761401935045069 -1.8504445165866068 1.0404320473626856 
+-0.5440863133031895 -0.48103682561971345 0.907381908447086 -1.1280642594012078 
+0.10557340209290218 -0.01814819455289191 0.4381106695354074 -1.0304105539540915 

data/test/data/test_collection/KLF4_f2.pat

@@ -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/test/data/test_collection/SP1_f1.pat

@@ -0,0 +1,12 @@
+> SP1_f1
+-0.24435707885585334  -0.6748234046937317  0.8657012535789861  -1.1060188862599292
+-1.0631255752097801  -2.1119259694238686  1.0960627561110399  -0.6138563775211981
+-0.387227623476054  -2.973985191321805  1.1807800242010371  -4.338927525031567
+-4.563896055436894  -2.916163300253228  1.3684371349982631  -5.077972423609655
+-2.2369752892820087  -3.719643631330185  1.3510439136452728  -4.8899306705082335
+-0.07473964149330914  0.9449196547620103  -2.624685764808605  -0.851098348782244
+-1.9643526491643326  -2.9784027708801153  1.3113096718240569  -2.3243342594990253
+-4.015548413965584  -3.138426807809667  1.338748858978805  -2.0846739035376483
+-0.4450938582835542  -2.2510053061629707  1.126543157436868  -1.7780413702431377
+-1.1896356092245055  -1.2251832285630033  1.163676006374752  -1.6080243648157357
+-0.5166047365590577  0.7641033353626651  -0.28626775700282125  -0.6825482097865606

data/test/data/test_collection.yaml

@@ -0,0 +1,186 @@
+--- !ruby/object:PWM::Collection
+pvalues:
+- 0.0005
+- 0.0001
+- 5.0e-05
+background:
+- 1
+- 1
+- 1
+- 1
+precise_discretization: 10
+rough_discretization: 1
+pwms:
+  GABPA_f1: !ruby/object:PWM::SingleMatrix
+    matrix:
+    - - -0.1106670158341858
+      - 0.013801606113892391
+      - 0.6054596108973699
+      - -1.3518085041421573
+    - - 0.37030668921643345
+      - 0.15761121480429963
+      - 0.009069314183831202
+      - -0.9888619717703562
+    - - 0.47526546359546684
+      - -0.3011678534572083
+      - 0.4031522994412777
+      - -1.8638752827041059
+    - - -1.5544255540164373
+      - 1.1082369687811506
+      - -0.2814091552834454
+      - -5.30708531823271
+    - - -0.6362037835776368
+      - 1.235338189985594
+      - -3.5801322928552253
+      - -5.717323067092849
+    - - -5.852906870733575
+      - -5.852906870733575
+      - 1.3841383838057746
+      - -5.852906870733575
+    - - -5.852906870733575
+      - -5.852906870733575
+      - 1.3841383838057746
+      - -5.852906870733575
+    - - 1.3835219739184708
+      - -5.2341956006430985
+      - -5.852906870733575
+      - -5.852906870733575
+    - - 1.3756340514956562
+      - -5.394962755562375
+      - -5.394962755562375
+      - -3.401117964959733
+    - - -1.2176198315414444
+      - -3.109079898175411
+      - 1.2964067931472216
+      - -5.717323067092849
+    - - -1.3716559438167257
+      - -0.2761401935045069
+      - -1.8504445165866068
+      - 1.0404320473626856
+    - - -0.5440863133031895
+      - -0.48103682561971345
+      - 0.907381908447086
+      - -1.1280642594012078
+    - - 0.10557340209290218
+      - -0.01814819455289191
+      - 0.4381106695354074
+      - -1.0304105539540915
+    name: GABPA_f1
+  KLF4_f2: !ruby/object:PWM::SingleMatrix
+    matrix:
+    - - 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
+    name: KLF4_f2
+  SP1_f1: !ruby/object:PWM::SingleMatrix
+    matrix:
+    - - -0.24435707885585334
+      - -0.6748234046937317
+      - 0.8657012535789861
+      - -1.1060188862599292
+    - - -1.0631255752097801
+      - -2.1119259694238686
+      - 1.0960627561110399
+      - -0.6138563775211981
+    - - -0.387227623476054
+      - -2.973985191321805
+      - 1.1807800242010371
+      - -4.338927525031567
+    - - -4.563896055436894
+      - -2.916163300253228
+      - 1.3684371349982631
+      - -5.077972423609655
+    - - -2.2369752892820087
+      - -3.719643631330185
+      - 1.3510439136452728
+      - -4.8899306705082335
+    - - -0.07473964149330914
+      - 0.9449196547620103
+      - -2.624685764808605
+      - -0.851098348782244
+    - - -1.9643526491643326
+      - -2.9784027708801153
+      - 1.3113096718240569
+      - -2.3243342594990253
+    - - -4.015548413965584
+      - -3.138426807809667
+      - 1.338748858978805
+      - -2.0846739035376483
+    - - -0.4450938582835542
+      - -2.2510053061629707
+      - 1.126543157436868
+      - -1.7780413702431377
+    - - -1.1896356092245055
+      - -1.2251832285630033
+      - 1.163676006374752
+      - -1.6080243648157357
+    - - -0.5166047365590577
+      - 0.7641033353626651
+      - -0.28626775700282125
+      - -0.6825482097865606
+    name: SP1_f1
+infos:
+  GABPA_f1:
+    :rough:
+      5.0e-05: 16.1
+      0.0001: 15.1
+      0.0005: 12.1
+    :precise:
+      5.0e-05: 8.61
+      0.0001: 7.609999999999999
+      0.0005: 4.51
+  KLF4_f2:
+    :rough:
+      5.0e-05: 14.1
+      0.0001: 13.1
+      0.0005: 11.1
+    :precise:
+      5.0e-05: 8.51
+      0.0001: 7.909999999999999
+      0.0005: 5.8100000000000005
+  SP1_f1:
+    :rough:
+      5.0e-05: 14.1
+      0.0001: 14.1
+      0.0005: 11.1
+    :precise:
+      5.0e-05: 8.51
+      0.0001: 7.709999999999999
+      0.0005: 5.61

data/test/macroape_test.rb

@@ -0,0 +1,125 @@
+require 'test/unit'
+
+module Helpers
+  def self.obtain_pvalue_by_threshold(args)
+    IO.popen("find_pvalue #{args}",&:read).strip.split.last
+  end
+end
+
+class FindThresholdTest < Test::Unit::TestCase
+  def test_process_several_pvalues
+    pvalues = []
+    IO.popen('find_threshold test/data/KLF4_f2.pat -p 0.001 0.0005', &:read).lines.each{|line| 
+      pvalue, threshold, real_pvalue = line.strip.split("\t")
+      pvalues << pvalue
+      assert_equal Helpers.obtain_pvalue_by_threshold("test/data/KLF4_f2.pat #{threshold}"), real_pvalue
+    }
+    assert_equal pvalues, ['0.0005', '0.001']
+  end
+  def test_process_one_pvalue
+    pvalue, threshold, real_pvalue = IO.popen('find_threshold test/data/KLF4_f2.pat -p 0.001', &:read).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_default_pvalue
+    pvalue, threshold, real_pvalue = IO.popen('find_threshold test/data/KLF4_f2.pat', &:read).strip.split("\t")
+    assert_equal '0.0005', pvalue
+    assert_equal Helpers.obtain_pvalue_by_threshold("test/data/KLF4_f2.pat #{threshold}"), real_pvalue
+  end
+  def test_custom_discretization
+    pvalue, threshold, real_pvalue = IO.popen('find_threshold test/data/KLF4_f2.pat -d 100',&:read).strip.split("\t")
+    assert_equal '0.0005', pvalue
+    assert_equal Helpers.obtain_pvalue_by_threshold("test/data/KLF4_f2.pat #{threshold} -d 100"), real_pvalue
+  end
+end
+
+class FindPvalueTest < Test::Unit::TestCase
+  def test_process_one_threshold
+    IO.popen('find_pvalue test/data/KLF4_f2.pat 4.1719'){|f|
+      assert_equal "4.1719\t1048.0\t0.00099945068359375\n", f.read
+    }
+  end
+  def test_process_several_thresholds
+    IO.popen('find_pvalue test/data/KLF4_f2.pat 4.1719 5.2403'){|f|
+      assert_equal "4.1719\t1048.0\t0.00099945068359375\n5.2403\t524.0\t0.000499725341796875\n", f.read
+    }
+  end
+  def test_process_several_thresholds_result_is_ordered
+    IO.popen('find_pvalue test/data/KLF4_f2.pat 5.2403 4.1719'){|f|
+      assert_equal "5.2403\t524.0\t0.000499725341796875\n4.1719\t1048.0\t0.00099945068359375\n", f.read
+    }
+  end
+  def test_custom_discretization
+    IO.popen('find_pvalue test/data/KLF4_f2.pat 5.2403 -d 100'){|f|
+      assert_equal "5.2403\t527.0\t0.0005025863647460938\n", f.read
+    }
+  end
+end
+
+
+class TestEvalSimilarity < Test::Unit::TestCase
+  def test_process_pair_of_pwms
+    IO.popen('eval_similarity test/data/KLF4_f2.pat test/data/SP1_f1.pat'){|f|
+      assert_equal "0.2420758234928527\n779.0\t11\n.>>>>>>>>>>\n>>>>>>>>>>>\n-1\tdirect\n", f.read
+    }
+  end
+  def test_process_another_pair_of_pwms
+    IO.popen('eval_similarity test/data/SP1_f1.pat test/data/AHR_si.pat'){|f|
+      assert_equal "0.0037332005973120955\n15.0\t11\n>>>>>>>>>>>\n.>>>>>>>>>.\n1\tdirect\n", f.read
+    }
+  end
+  
+  def test_recognize_orientation_of_alignment
+    IO.popen('eval_similarity test/data/SP1_f1_revcomp.pat test/data/SP1_f1.pat'){|f|
+      assert_equal "1.0\n2033.0\t11\n>>>>>>>>>>>\n<<<<<<<<<<<\n0\trevcomp\n", f.read
+    }
+  end
+
+  def test_process_custom_discretization
+    IO.popen('eval_similarity test/data/SP1_f1.pat test/data/KLF4_f2.pat -d 1'){|f|
+      assert_equal "0.22754919499105544\n636.0\t11\n>>>>>>>>>>>\n.>>>>>>>>>>\n1\tdirect\n", f.read
+    }
+  end
+end
+
+class TestEvalAlignmentSimilarity < Test::Unit::TestCase
+  def test_process_at_optimal_alignment
+    IO.popen('eval_alignment test/data/KLF4_f2.pat test/data/SP1_f1.pat -1 direct '){|f|
+      assert_equal "0.2420758234928527\n779.0\t11\n.>>>>>>>>>>\n>>>>>>>>>>>\n-1\tdirect\n", f.read
+    }
+  end
+  def test_process_not_optimal_alignment
+    IO.popen('eval_alignment test/data/KLF4_f2.pat test/data/SP1_f1.pat 0 direct '){|f|
+      assert_equal "0.0017543859649122807\n7.0\t11\n>>>>>>>>>>.\n>>>>>>>>>>>\n0\tdirect\n", f.read
+    }
+  end
+  def test_process_at_optimal_alignment_reversed
+    IO.popen('eval_alignment test/data/KLF4_f2.pat test/data/SP1_f1.pat -1 revcomp '){|f|
+      assert_equal "0.0\n0.0\t11\n.>>>>>>>>>>\n<<<<<<<<<<<\n-1\trevcomp\n", f.read
+    }
+  end
+end
+
+class TestPreprocessCollection < Test::Unit::TestCase
+  def test_multipvalue_preproceessing
+    system('preprocess_collection ./test/data/test_collection -o test/data/test_collection.yaml.tmp -p 0.0005 0.0001 0.00005 --silent')
+    assert_equal File.read('test/data/test_collection.yaml'), File.read('test/data/test_collection.yaml.tmp')
+    File.delete 'test/data/test_collection.yaml.tmp'
+  end
+end
+
+class TestScanCollection < Test::Unit::TestCase
+  def test_scan_default_cutoff
+    assert_equal File.read('test/data/KLF4_f2_scan_results_default_cutoff.txt'), 
+                 IO.popen('scan_collection test/data/KLF4_f2.pat test/data/test_collection.yaml --silent', &:read)
+  end
+  def test_scan_and_output_all_results
+    assert_equal File.read('test/data/KLF4_f2_scan_results_all.txt'), 
+                 IO.popen('scan_collection test/data/KLF4_f2.pat test/data/test_collection.yaml --all --silent', &:read)
+      
+  end
+  def test_scan_precise_mode
+    assert_equal File.read('test/data/KLF4_f2_scan_results_precise_mode.txt'),
+                 IO.popen('scan_collection test/data/KLF4_f2.pat test/data/test_collection.yaml --precise --all --silent', &:read)
+  end
+end

metadata

@@ -0,0 +1,116 @@
+--- !ruby/object:Gem::Specification
+name: macroape
+version: !ruby/object:Gem::Version
+  version: 3.2.2
+  prerelease: 
+platform: ruby
+authors:
+- Ilya Vorontsov
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2012-05-28 00:00:00.000000000 Z
+dependencies: []
+description: Macroape is an abbreviation for MAtrix CompaRisOn by Approximate P-value
+  Estimation. It's a bioinformatic tool for evaluating similarity measure and best
+  alignment between a pair of Position Weight Matrices(PWM), finding thresholds by
+  P-values and inside out and even searching a collection of motifs for the most similar
+  ones. Used approach and application described in manual at https://docs.google.com/document/pub?id=1_jsxhMNzMzy4d2d_byAd3n6Szg5gEcqG_Sf7w9tEqWw
+email:
+- prijutme4ty@gmail.com
+executables:
+- eval_alignment
+- eval_similarity
+- find_pvalue
+- find_threshold
+- preprocess_collection
+- scan_collection
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- LICENSE
+- README.md
+- Rakefile
+- bin/eval_alignment
+- bin/eval_similarity
+- bin/find_pvalue
+- bin/find_threshold
+- bin/preprocess_collection
+- bin/scan_collection
+- lib/macroape.rb
+- lib/macroape/aligned_pair_intersection.rb
+- lib/macroape/aligned_pair_metrics.rb
+- lib/macroape/aligned_pair_transformations.rb
+- lib/macroape/collection.rb
+- lib/macroape/count_by_threshold.rb
+- lib/macroape/exec/eval_alignment.rb
+- lib/macroape/exec/eval_similarity.rb
+- lib/macroape/exec/find_pvalue.rb
+- lib/macroape/exec/find_threshold.rb
+- lib/macroape/exec/preprocess_collection.rb
+- lib/macroape/exec/scan_collection.rb
+- lib/macroape/extract_pwm.rb
+- lib/macroape/gauss_estimation.rb
+- lib/macroape/matrix_information.rb
+- lib/macroape/matrix_on_background.rb
+- lib/macroape/matrix_transformations.rb
+- lib/macroape/pair_metrics.rb
+- lib/macroape/pair_transformations.rb
+- lib/macroape/pwm_compare.rb
+- lib/macroape/pwm_compare_aligned.rb
+- lib/macroape/single_matrix.rb
+- lib/macroape/support.rb
+- lib/macroape/threshold_by_pvalue.rb
+- lib/macroape/version.rb
+- macroape.gemspec
+- test/data/AHR_si.pat
+- test/data/KLF4_f2.pat
+- test/data/KLF4_f2_scan_results_all.txt
+- test/data/KLF4_f2_scan_results_default_cutoff.txt
+- test/data/KLF4_f2_scan_results_precise_mode.txt
+- test/data/SP1_f1.pat
+- test/data/SP1_f1_revcomp.pat
+- test/data/test_collection.yaml
+- test/data/test_collection/GABPA_f1.pat
+- test/data/test_collection/KLF4_f2.pat
+- test/data/test_collection/SP1_f1.pat
+- test/macroape_test.rb
+homepage: http://autosome.ru/macroape/
+licenses: []
+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
+signing_key: 
+specification_version: 3
+summary: PWM comparison tool using MACROAPE approach
+test_files:
+- test/data/AHR_si.pat
+- test/data/KLF4_f2.pat
+- test/data/KLF4_f2_scan_results_all.txt
+- test/data/KLF4_f2_scan_results_default_cutoff.txt
+- test/data/KLF4_f2_scan_results_precise_mode.txt
+- test/data/SP1_f1.pat
+- test/data/SP1_f1_revcomp.pat
+- test/data/test_collection.yaml
+- test/data/test_collection/GABPA_f1.pat
+- test/data/test_collection/KLF4_f2.pat
+- test/data/test_collection/SP1_f1.pat
+- test/macroape_test.rb