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



121
122
123
124
125
126
127
 
# File 'lib/genevalidator/validation.rb', line 121

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

Instance Method Details

#check_hit_coverage(prediction, hit) ⇒ Object 



165
166
167
168
169
170
171
172
173
174
 
# File 'lib/genevalidator/validation.rb', line 165

def check_hit_coverage(prediction, hit)
  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
  coverage
end

#check_validations(vals) ⇒ Object 



194
195
196
197
198
199
200
201
202
203
204
205
206
 
# File 'lib/genevalidator/validation.rb', line 194

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

#check_validations_output(vals) ⇒ Object 



208
209
210
211
212
213
214
215
216
217
218
219
 
# File 'lib/genevalidator/validation.rb', line 208

def check_validations_output(vals)
  raise NoValidationError if @run_output.validations.empty?
  vals.each do |v|
    raise ReportClassError unless v.validation_report.is_a? ValidationReport
  end
rescue NoValidationError => e
  warn e
  exit 1
rescue ReportClassError => e
  warn e
  exit 1
end

#compute_run_score ⇒ Object 



221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
 
# File 'lib/genevalidator/validation.rb', line 221

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

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

#create_validation_tests(prediction, hits) ⇒ Object 



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

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

#generate_run_output ⇒ Object 



261
262
263
264
 
# File 'lib/genevalidator/validation.rb', line 261

def generate_run_output
  @run_output.print_output_console
  @run_output.generate_json
end

#init_nucleotide_only_validations(val, prediction, hits) ⇒ Object 



188
189
190
191
192
 
# File 'lib/genevalidator/validation.rb', line 188

def init_nucleotide_only_validations(val, prediction, hits)
  return unless @config[:type] == :nucleotide
  val.push BlastReadingFrameValidation.new(prediction, hits)
  val.push OpenReadingFrameValidation.new(prediction, hits)
end

#length_validation_scores(validations, scores) ⇒ Object

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

scores accordingly



243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
 
# File 'lib/genevalidator/validation.rb', line 243

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



155
156
157
158
159
160
161
162
163
 
# File 'lib/genevalidator/validation.rb', line 155

def remove_identical_hits(prediction, hits)
  hits.delete_if 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
    coverage      = check_hit_coverage(prediction, hit)
    low_identity.empty? && coverage.uniq.length == 1
  end
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



135
136
137
138
139
140
141
142
143
144
145
146
 
# File 'lib/genevalidator/validation.rb', line 135

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_run_score
  generate_run_output
end