Class: GeneValidator::Validate

Inherits:
Object
  • Object
show all
Extended by:
Forwardable
Defined in:
lib/genevalidator/validation.rb

Overview

Class that runs the validations (Instatiated for each query)

Instance Method Summary collapse

Constructor Details

#initialize ⇒ Validate

Initilizes the object Params: opt: A hash with the following keys: validations:, blast_tabular_file:, blast_tabular_options:, blast_xml_file:, db:, raw_sequences:, num_threads:, fast:} start_idx: number of the sequence from the file to start with overall_evaluation: boolean variable for printing overall evaluation



101
102
103
104
105
106
107
108
 
# File 'lib/genevalidator/validation.rb', line 101

def initialize
  @opt         = opt
  @config      = config
  @mutex_array = mutex_array
  @run_output  = nil
  @overview    = overview
  @query_idx   = query_idx
end

Instance Method Details

#check_validations(vals) ⇒ Object 



174
175
176
177
178
179
180
181
182
183
184
185
186
 
# File 'lib/genevalidator/validation.rb', line 174

def check_validations(vals)
  # check the class type of the elements in the list
  vals.each { |v| fail ValidationClassError unless v.is_a? ValidationTest }
  # check alias duplication
  aliases = vals.map(&:cli_name)
  fail AliasDuplicationError unless aliases.length == aliases.uniq.length
rescue ValidationClassError => e
  $stderr.puts e
  exit 1
rescue AliasDuplicationError => e
  $stderr.puts e
  exit 1
end

#check_validations_output(vals) ⇒ Object 



188
189
190
191
192
193
194
195
196
197
198
199
 
# File 'lib/genevalidator/validation.rb', line 188

def check_validations_output(vals)
  fail NoValidationError if @run_output.validations.length == 0
  vals.each do |v|
    fail ReportClassError unless v.validation_report.is_a? ValidationReport
  end
rescue NoValidationError => e
  $stderr.puts e
  exit 1
rescue ReportClassError => e
  $stderr.puts e
  exit 1
end

#compute_scores ⇒ Object 



201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
 
# File 'lib/genevalidator/validation.rb', line 201

def compute_scores
  validations        = @run_output.validations
  scores             = {}
  scores[:successes] = validations.count { |v| v.result == v.expected }
  scores[:fails] = validations.count { |v| v.validation != :unapplicable && v.validation != :error && v.result != v.expected }
  scores         = length_validation_scores(validations, scores)

  @run_output.successes     = scores[:successes]
  @run_output.fails         = scores[:fails]
  total_query               = scores[:successes].to_i + scores[:fails]
  if total_query == 0
    @run_output.overall_score = 0
  else
    @run_output.overall_score = (scores[:successes] * 90 / total_query).round
  end
end

#create_validation_tests(prediction, hits) ⇒ Object 



160
161
162
163
164
165
166
167
168
169
170
171
172
 
# File 'lib/genevalidator/validation.rb', line 160

def create_validation_tests(prediction, hits)
  val = []
  val.push LengthClusterValidation.new(prediction, hits)
  val.push LengthRankValidation.new(prediction, hits)
  val.push GeneMergeValidation.new(prediction, hits)
  val.push DuplicationValidation.new(prediction, hits)
  if @config[:type] == :nucleotide
    val.push BlastReadingFrameValidation.new(prediction, hits)
    val.push OpenReadingFrameValidation.new(prediction, hits)
  end
  val.push AlignmentValidation.new(prediction, hits)
  val.select { |v| @opt[:validations].include? v.cli_name.downcase }
end

#generate_run_output ⇒ Object 



238
239
240
241
242
243
 
# File 'lib/genevalidator/validation.rb', line 238

def generate_run_output
  @run_output.generate_html
  @run_output.generate_json
  @run_output.print_output_console
  generate_run_overview
end

#generate_run_overview ⇒ Object 



245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
 
# File 'lib/genevalidator/validation.rb', line 245

def generate_run_overview
  vals        = @run_output.validations
  no_mafft    = 0
  no_internet = 0
  errors      = []
  vals.each do |v|
    unless v.errors.nil?
      no_mafft += v.errors.count { |e| e == NoMafftInstallationError }
      no_internet += v.errors.count { |e| e == NoInternetError }
    end
    errors.push(v.short_header) if v.validation == :error
  end

  no_evidence = vals.count { |v| v.result == :unapplicable || v.result == :warning } == vals.length
  nee = (no_evidence) ? 1 : 0

  good_scores = (@run_output.overall_score >= 75) ? 1 : 0
  bad_scores  = (@run_output.overall_score >= 75) ? 0 : 1

  @mutex_array.synchronize do
    @overview[:no_queries] += 1
    @overview[:scores].push(@run_output.overall_score)
    @overview[:good_scores] += good_scores
    @overview[:bad_scores] += bad_scores
    @overview[:nee] += nee
    @overview[:no_mafft] += no_mafft
    @overview[:no_internet] += no_internet
    errors.each { |err| @overview[:map_errors][err] += 1 }

    vals.each do |v|
      next if v.run_time == 0 || v.run_time.nil?
      next if v.validation == :unapplicable || v.validation == :error
      p = Pair1.new(@overview[:run_time][v.short_header].x + v.run_time,
                    @overview[:run_time][v.short_header].y + 1)
      @overview[:run_time][v.short_header] = p
    end
  end
end

#length_validation_scores(validations, scores) ⇒ Object

Since there are two length validations, it is necessary to adjust the

scores accordingly



220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
 
# File 'lib/genevalidator/validation.rb', line 220

def length_validation_scores(validations, scores)
  lcv = validations.select { |v| v.class == LengthClusterValidationOutput }
  lrv = validations.select { |v| v.class == LengthRankValidationOutput }
  if lcv.length == 1 && lrv.length == 1
    score_lcv = (lcv[0].result == lcv[0].expected)
    score_lrv = (lrv[0].result == lrv[0].expected)
    if score_lcv == true && score_lrv == true
      scores[:successes] -= 1 # if both are true: counted as 1 success
    elsif score_lcv == false && score_lrv == false
      scores[:fails] -= 1 # if both are false: counted as 1 fail
    else
      scores[:successes] -= 0.5
      scores[:fails] -= 0.5
    end
  end
  scores
end

#remove_identical_hits(prediction, hits) ⇒ Object

Removes identical hits (100% coverage and >99% identity) Params: prediction: Sequence object hits: Array of Sequence objects Output: new array of hit Sequence objects



136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
 
# File 'lib/genevalidator/validation.rb', line 136

def remove_identical_hits(prediction, hits)
  identical_hits = []
  hits.each do |hit|
    low_identity = hit.hsp_list.select { |hsp| hsp.pidentity < 99 }
    no_data      = hit.hsp_list.select { |hsp| hsp.pidentity.nil? }
    low_identity += no_data
    # check the coverage
    coverage = Array.new(prediction.length_protein, 0)
    hit.hsp_list.each do |hsp|
      match_to   = hsp.match_query_to
      match_from = hsp.match_query_from
      len        = match_to - match_from + 1
      coverage[match_from - 1..match_to - 1] = Array.new(len, 1)
    end

    if low_identity.length == 0 && coverage.uniq.length == 1
      identical_hits.push(hit)
    end
  end

  identical_hits.each { |hit| hits.delete(hit) }
  hits
end

#validate(prediction, hits, current_idx) ⇒ Object

Validate one query and create validation report Params: prediction: Sequence object hits: Array of Sequence objects current_idx: the index number of the query



116
117
118
119
120
121
122
123
124
125
126
127
 
# File 'lib/genevalidator/validation.rb', line 116

def validate(prediction, hits, current_idx)
  hits = remove_identical_hits(prediction, hits)
  vals = create_validation_tests(prediction, hits)
  check_validations(vals)
  vals.each(&:run)
  @run_output = Output.new(current_idx, hits.length, prediction.definition)
  @run_output.validations = vals.map(&:validation_report)
  check_validations_output(vals)

  compute_scores
  generate_run_output
end