bioinform 0.2.0 → 0.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 41bb8dd19247a6f1b8e7643e5fbf1d0e03b823de
-  data.tar.gz: 7dbd3f01dbea7fe1ed3125bef775cc72e5dccf8e
+  metadata.gz: 70e322a8657abaa2fb242f0b7774dfc3b38a1e83
+  data.tar.gz: 65e5cdc14dec4d99cb0266d8d4bf589ef44efb99
 SHA512:
-  metadata.gz: a3e5c829bf134e07c7a03a56de61017ca9f3c7237e1c6a18e49d0cf57cdf1a3054c7501541070e85a756ae12231a84c6d04a6f94384b5d7dd57f93ceaf335e11
-  data.tar.gz: 84d64628b85fd7b5e757637de51c074baeb98ebd8053c83c4af4b77bcf7e843fca10e545b472e7fda781cc9b3fba4ccb9b8bd8055e254b5f7a1f83d1575f672f
+  metadata.gz: 10a503972ed0e5ec8f9aba819230991d9ef33704ff587e47a6b310b98f3429aa580245499b13e17f59d5023213764887cf8bf92834aed28717746acbd8a2c6ad
+  data.tar.gz: bce479c347c8f439c6e133e14f1379b75ed855b26553059c85f2e04a04344f3c2885b44f35ac146128ecb75054b35d0267801509f21719afecc922be999b5639

data/TODO.txt

@@ -1,3 +1,5 @@
+PCM2PWM не имеет возможности вычислить псевдокаунт для матриц с разными каунтами в столбцах. Может быть брать логарифм и корень максимума. Или конкретной колонки?
+
 сделать работу с ValidationError
 сделать ошибки тэгированными
 обобщить модели фона на разные алфавиты
@@ -28,4 +30,6 @@ Decide:
 -- Whether to cache suffices:  cache :best_suffix, obsolete: [:discrete!, :background!, ...]
 
 Specs
--- PWM#probabilities, #score_variance, #gauss_estimation
+-- PWM#probabilities, #score_variance, #gauss_estimation
+
+background#to_s and WordwiseBackground#to_s

data/lib/bioinform/background.rb

@@ -11,9 +11,14 @@ module Bioinform
       Bioinform::Background::Uniform
     end
 
+    def self.from_frequencies(frequencies)
+      Frequencies.new(frequencies)
+    end
+
     def self.from_gc_content(gc_content)
-      p_at = (1.0 - gc_content) / 2.0;
-      p_cg = gc_content / 2.0;
+      raise Error, 'GC-content should be withing range [0;1]'  unless (0..1).include?(gc_content)
+      p_at = (1.0 - gc_content) / 2.0
+      p_cg = gc_content / 2.0
       Frequencies.new([p_at, p_cg, p_cg, p_at])
     end
 
@@ -79,7 +84,7 @@ module Bioinform
     end
 
     def to_s
-      counts.join(',')
+      'wordwise'
     end
   end
 

data/lib/bioinform/parsers/motif_splitter.rb

@@ -17,7 +17,7 @@ module Bioinform
   # and by lines which will be retained.
   #
   class MotifSplitter
-    attr_reader :start_motif_pattern, :spliiter
+    attr_reader :start_motif_pattern, :splitter_pattern
 
     def initialize(options={})
       @start_motif_pattern = options.fetch(:start_motif_pattern, /^\s*([^-+\s\d.]+|>.*)/)

data/lib/bioinform/version.rb

@@ -1,3 +1,3 @@
 module Bioinform
-  VERSION = "0.2.0"
+  VERSION = "0.2.1"
 end

data/lib/bioinform.rb

@@ -11,65 +11,4 @@ require_relative 'bioinform/background'
 require_relative 'bioinform/alphabet'
 
 module Bioinform
-  def self.get_model(data_model, matrix, name)
-    Bioinform::MotifModel.const_get(data_model).new(matrix).named(name)
-  end
-
-  def self.get_model_from_string(data_model, matrix_string)
-    motif_infos = MatrixParser.new.parse(matrix_string)
-    get_model(data_model, motif_infos.matrix, name)
-  end
-
-  def self.get_pwm(data_model, matrix, background, pseudocount, effective_count)
-    input_model = get_model_from_string(data_model, matrix)
-    case input_model
-    when MotifModel::PPM
-      ppm2pcm_converter = ConversionAlgorithms::PPM2PCM.new(count: effective_count)
-      pcm2pwm_converter = ConversionAlgorithms::PCM2PWM.new(background: background, pseudocount: pseudocount)
-      pcm2pwm_converter.convert(ppm2pcm_converter.convert(input_model))
-    when MotifModel::PCM
-      pcm2pwm_converter = ConversionAlgorithms::PCM2PWM.new(background: background, pseudocount: pseudocount)
-      pcm2pwm_converter.convert(input_model)
-    when MotifModel::PWM
-      input_model
-    else
-      raise Error, "Unknown input `#{input_model}`"
-    end
-  rescue => e
-    raise Error, "PWM creation failed (#{e})"
-  end
-
-  def self.get_pcm(data_model, matrix, effective_count)
-    input_model = get_model_from_string(data_model, matrix)
-    case input_model
-    when MotifModel::PPM
-      ppm2pcm_converter = ConversionAlgorithms::PPM2PCM.new(count: effective_count)
-      ppm2pcm_converter.convert(input_model)
-    when MotifModel::PCM
-      input_model
-    when MotifModel::PWM
-      raise Error, 'Conversion PWM-->PCM not yet implemented'
-    else
-      raise Error, "Unknown input `#{input_model}`"
-    end
-  rescue => e
-    raise Error, "PCM creation failed (#{e})"
-  end
-
-  def self.get_ppm(data_model, matrix)
-    input_model = get_model_from_string(data_model, matrix)
-    case input_model
-    when MotifModel::PPM
-      input_model
-    when MotifModel::PCM
-      pcm2ppm_converter = ConversionAlgorithms::PCM2PPM.new
-      pcm2ppm_converter.convert(input_model)
-    when MotifModel::PWM
-      raise Error, 'Conversion PWM-->PPM not yet implemented'
-    else
-      raise Error, "Unknown input `#{input_model}`"
-    end
-  rescue => e
-    raise Error, "PPM creation failed (#{e})"
-  end
 end

data/spec/parsers/motif_splitter_spec.rb

@@ -30,6 +30,8 @@ describe Bioinform::MotifSplitter do
 
   context 'with specified pattern' do
     let(:motif_splitter) { Bioinform::MotifSplitter.new(start_motif_pattern: /^NA\s+\w+$/, splitter_pattern: /^\/\/\s$/) }
+    specify{ expect(motif_splitter.splitter_pattern).to eq(/^\/\/\s$/) }
+    specify{ expect(motif_splitter.start_motif_pattern).to eq(/^NA\s+\w+$/) }
 
     let(:input_1) {
       "NA  motif_1\n" +

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: bioinform
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.2.1
 platform: ruby
 authors:
 - Ilya Vorontsov
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-07-14 00:00:00.000000000 Z
+date: 2014-07-20 00:00:00.000000000 Z
 dependencies: []
 description: A bunch of useful classes for bioinformatics
 email:
@@ -120,7 +120,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.3.0
+rubygems_version: 2.4.1
 signing_key: 
 specification_version: 4
 summary: Classes for work with different input formats of positional matrices and