Class: Bio::DTASelect::OutputFile

Inherits:
Object
  • Object
show all
Defined in:
lib/dta_select_output.rb

Defined Under Namespace

Classes: Peptide, Result, SelectedProtein

Class Method Summary collapse

Class Method Details

.log ⇒ Object 



12
13
14
 
# File 'lib/dta_select_output.rb', line 12

def self.log
  SelectedProtein.new.log
end

.parse(io) ⇒ Object 



110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
 
# File 'lib/dta_select_output.rb', line 110

def self.parse(io)
  result = Result.new

  # Hashes of identifiers to objects
  result.protein_name_to_object = {}
  result.peptide_name_to_object = {}

  # Read in the tab separated file
  reading_header = true
  current_proteins = []
  last_line_was_protein_name = false
  peptide_attribute_names = nil

  # Parse each line of the DTAselect file
  io.each_line do |line|
    splits = line.chomp.split("\t")
    log.debug "Parsing line `#{line.chomp}'"

    if reading_header
      log.debug "reading header"
      if splits[0] == 'Unique'
        reading_header = false

        # Current line describes the peptide attributes
        peptide_attribute_names = splits

        # This field has special importance, so be picky
        raise "Badly parsed file at this line: #{line.inspect}, expected 2nd field to be 'FileName', found #{splits[1]}" unless splits[1] == 'FileName'
      end
      next
    end

    # OK, now we are reading the actual table, not the header
    if splits[0] != '' and splits[11].nil?
      ident = splits[0]

      if !last_line_was_protein_name
        # Sometimes several proteins are given all in the one header line
        # start a new protein
        log.debug "New protein now being parsed"
        current_proteins = []
      end

      current_protein = SelectedProtein.new
      last_line_was_protein_name = true
      current_proteins.push current_protein

      current_protein.identifier = ident

      i = 1
      current_protein.sequence_count = splits[i].to_i; i+=1
      current_protein.spectrum_count = splits[i].to_i; i+=1
      current_protein.sequence_coverage = splits[i].to_f; i+=1
      current_protein.length = splits[i].to_i; i+=1
      current_protein.molwt = splits[i].to_f; i+=1
      current_protein.pi = splits[i].to_f; i+=1
      current_protein.validation_status = splits[i].to_f; i+=1
      current_protein.descriptive_name = splits[i]

      if result.protein_name_to_object[ident]
        raise "Unexpectedly found the same protein identifier twice: #{ident}, from line #{line.chomp}"
      end
      result.protein_name_to_object[ident] = current_protein



    elsif splits[1] == 'Proteins'
      # Done processing, except for the bits down the bottom which aren't parsed (yet)
      break



    else
      log.debug "New spectra now being parsed"
      last_line_was_protein_name = false

      # Record a spectra
      ident = splits[1]
      raise "Unexpected hits name `#{ident}', from line `#{line.chomp}'" unless ident.length > 10

      pep = result.peptide_name_to_object[ident]
      if pep.nil?
        pep = Peptide.new
        pep.identifier = ident

        peptide_attribute_names.each_with_index do |attribute_name,i|
          pep.dtaselect_attributes ||= {}
          pep.dtaselect_attributes[attribute_name] = splits[i]
        end

        result.peptide_name_to_object[ident] = pep
      end

      current_proteins.each do |current_protein|
        pep.parent_proteins.push current_protein
        current_protein.peptides.push pep
      end
      log.debug "Parsed this peptide #{pep.inspect}"
    end
  end

  log.debug "Proteins parsed: #{result.protein_name_to_object.inspect}"
  return result
end