Class: ExonerateResult

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

Overview

Extracts results from blast table's file and uses it to create instances of "BlastQuery" and "BlastHit"

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(input, seqs = nil, query_seqs = nil, all = true) ⇒ ExonerateResult

Parser initialization



42
43
44
45
46
47
48
49
50
51
52
53
54
55
 
# File 'lib/full_lengther_next/exonerate_result.rb', line 42

def initialize(input, seqs= nil, query_seqs = nil, all = true)
  @querys = []
  @seqs = seqs #unigenes
  @prot_seqs = query_seqs#prot

  if input.is_a?(Array)
    input.each do |file|
      parse_file(File.open(file).readlines, all)
    end
  else
    parse_file(File.open(input).readlines, all)
  end
  query_name=''
end

Instance Attribute Details

#querys ⇒ Object

Returns the value of attribute querys.



256
257
258
 
# File 'lib/full_lengther_next/exonerate_result.rb', line 256

def querys
  @querys
end

Instance Method Details

#convert_parsed_lines(lines_parsed) ⇒ Object 



81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
 
# File 'lib/full_lengther_next/exonerate_result.rb', line 81

def convert_parsed_lines(lines_parsed)
  last_query = nil
  query = nil
  lines_parsed.each_with_index do |line|
    begin
      if lines_parsed.class.to_s=='Array'
        align_data=line['align_data']
        features=line
      else #hash
        align_data=line[1]['align_data']
        features=line[1]        
      end
      tags = align_data.scan(/([MFG53S]) ([0-9]+) ([0-9]+)/)
      tags.map!{|tag| [tag[0], tag[1].to_i, tag[2].to_i]}
      if features['target_id'] != last_query
        last_query = features['target_id']
        query = BlastQuery.new(features['target_id'])
        @querys << query
      end
        hiting(features,tags, query)
    rescue
      puts "Result: #{features['target_id']} => #{features['query_id']} hasn't been parsed\n#{line}"
    end
  end    
end

#define_hit_parameters(hit, features, tags) ⇒ Object 



203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
 
# File 'lib/full_lengther_next/exonerate_result.rb', line 203

def define_hit_parameters(hit, features, tags)
  hit.gaps = 0
  tags.map{|aln| hit.gaps += 1 if aln[0] == 'G'}
  hit.reversed = false
  hit.align_len =(features['query_end_align'] - features['query_start_align']).abs+1 
  hit.mismatches=0
  hit.e_val=0
  hit.bit_score=0
  hit.score = features['score']
  hit.s_frame = nil
  strand = 1
  strand = -1 if features['target_strand'] == '-'
  hit.q_frame = (((features['target_start_align']) % 3) +1) *strand
  hit.subject_id = features['query_id']
  hit.full_subject_length=0
  hit.definition=''
  hit.acc=features['query_id']
  hit.q_seq=''
  hit.s_seq=''
end

#do_reverso_complementary(counter_target, target_seq) ⇒ Object

def



186
187
188
189
190
 
# File 'lib/full_lengther_next/exonerate_result.rb', line 186

def do_reverso_complementary(counter_target, target_seq)
  counter_target = target_seq.length - 1 - counter_target 
  target_seq = target_seq.complementary_dna
  return counter_target, target_seq
end

#empty? ⇒ Boolean

check if there are querys

Returns:

  • (Boolean) 


246
247
248
249
 
# File 'lib/full_lengther_next/exonerate_result.rb', line 246

def empty?

  return @querys.empty?
end

#find_query(querys, name_q) ⇒ Object

find query by name



234
235
236
237
238
239
240
241
242
243
 
# File 'lib/full_lengther_next/exonerate_result.rb', line 234

def find_query(querys,name_q)
  #  newq = querys.find{|q| ( q.find{|h| (h.subject_id)})}
  new_q=nil

  if !querys.empty?
    new_q=querys.find{|q| (q.query_id==name_q)}
  end

  return new_q
end

#hiting(features, tags, query) ⇒ Object

this method only works fine with --model protein2dna parameter of exonerate



108
109
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
 
# File 'lib/full_lengther_next/exonerate_result.rb', line 108

def hiting(features, tags, query) #Convierte las coordenadas relativas del exonerate a absolutas tipo blast, definiendo solo los hits   
  do_align = false
  do_align = true if !@prot_seqs.nil? && !@seqs.nil?
  start_target = features['target_start_align']#Unigen
  start_query = features['query_start_align'] #proteina
  ends_target = features['target_end_align']
  ends_query = features['query_end_align']-1 # -> Exonerate don't set to 0 position the ends of target and query
  if features['target_strand'] == '-' #-> Exonerate don't set to 0 position the ends of target and query
    start_target -= 1 # Start target is end target when mathc is in reversed complementary strand
  else
    ends_target -= 1
  end
  hit = ExoBlastHit.new(start_target+1, ends_target+1, start_query+1, ends_query+1)
  define_hit_parameters(hit, features, tags)
  query.add_hit(hit)
  
  #Define alignment and blast like parameters
  target_alignment = ''
  query_alignment = ''
  counter_target = start_target
  counter_query = start_query
  if do_align #get seqs
    query_seq = @prot_seqs[features['query_id']]
    target_seq = @seqs[features['target_id']]
  end
  counter_target, target_seq = do_reverso_complementary(counter_target, target_seq) if features['target_strand'] == '-'
  query_frameshift = []
  target_frameshift = []
  gap_shift = 0
  #puts features['query_id']+ ' ' +features['target_strand'], '-----------------------'
  tags.each_with_index do |tag, n_operation|
    #puts tag.inspect
    if do_align
      gap_shift = 0 if tag[OPERATION] != 'G'
      query_alignment << query_seq[counter_query, tag[QUERY]]
      target_alignment << target_seq[counter_target, tag[TARGET]].translate
    end
    if tag[OPERATION] == 'F'
      if tag[TARGET] > 0 && tag[TARGET] < 3 #true FRAMESHIFT
        gap_shift += 1
        if tags[n_operation+1][OPERATION] != 'G' #there are frameshift that not insert a gap, we do it
          query_alignment <<  '-' if do_align
        end
      else
        query_alignment <<  '-' * (tag[TARGET]/3.0).ceil if do_align
      end
      query_frameshift << counter_query
      fs_counter_target = counter_target
      fs_counter_target = target_seq.length - counter_target if features['target_strand'] == '-' # ESto es un apaño, habria que plantear el parseo de las reversas como reduccion en el contador del formato del exonerate, en vez de como adiccion
      if tag[TARGET] > 3
        real_fs = tag[TARGET]%3
        real_gap = tag[TARGET] - real_fs
        fs = [fs_counter_target + real_gap, real_fs]
      else
        fs = [fs_counter_target, tag[TARGET]]
      end
      target_frameshift << fs
    elsif tag[OPERATION] == 'G'
      query_alignment <<  '-' * (tag[TARGET]/3.0).ceil if do_align
      diff = tag[QUERY] - gap_shift
      target_alignment << '-' * diff if do_align && diff > 0
      gap_shift = 0
    end 
    counter_query += tag[QUERY]
    counter_target += tag[TARGET]
  end
  hit.s_frameshift = query_frameshift
  hit.q_frameshift = target_frameshift

  #puts "\e[33m#{target_alignment}\e[0m", "\e[36m#{query_alignment}\e[0m"
  if do_align
    hit.q_seq = target_alignment
    hit.s_seq = query_alignment
    hit.align_len = query_alignment.length
    hit.ident = set_ident(target_alignment,query_alignment)
  end
end

#inspect ⇒ Object

inspect results



225
226
227
228
229
230
231
 
# File 'lib/full_lengther_next/exonerate_result.rb', line 225

def inspect
  res = "Exonerate results:\n"
  res+= '-'*20
  res+= "\nQuerys: #{@querys.count}\n"
  @querys.each{|q| res+=q.inspect+"\n"}
  return res
end

#parse_file(lines, all) ⇒ Object 



57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
 
# File 'lib/full_lengther_next/exonerate_result.rb', line 57

def parse_file(lines, all)
  lines_parsed=[] 
  lines_parsed={} if !all
  lines.each do |line|
if line=~ /^vulgar:/
  line.chomp!
  fields=line.split(' ', 11)
  features={'query_id'=> fields[1], 'query_start_align'=> fields[2].to_i, 'query_end_align'=> fields[3].to_i, 'query_strand'=> fields[4],'target_id'=> fields[5], 'target_start_align'=> fields[6].to_i, 'target_end_align'=> fields[7].to_i, 'target_strand'=> fields[8], 'score'=> fields[9].to_i, 'align_data'=> fields[10]}
  if all
    lines_parsed << features
  else
    if !lines_parsed.key?(features['target_id']) # Añadir valor si no existe
      lines_parsed[features['target_id']]=features
    else
      if features['score']>lines_parsed[features['target_id']]['score'] # Si ya existe una query, ver si la nueva presenta un mayor score y reemplazar la antigua
       lines_parsed[features['target_id']]=features
      end
    end
  end
end
    end   
    convert_parsed_lines(lines_parsed)  
end

#set_ident(target_alignment, query_alignment) ⇒ Object 



192
193
194
195
196
197
198
199
200
201
 
# File 'lib/full_lengther_next/exonerate_result.rb', line 192

def set_ident(target_alignment, query_alignment)
  matchs = 0
  position = 0
  target_alignment.each_char do |char|
    matchs +=1 if char == query_alignment[position]
    position +=1
  end
  perc_ident = ('%.2f' % (matchs*100.0/target_alignment.length)).to_f
  return perc_ident
end

#size ⇒ Object

get query count



252
253
254
 
# File 'lib/full_lengther_next/exonerate_result.rb', line 252

def size
  @querys.size
end