Class: MzID::StreamingParser

Inherits:
BatchParser show all
Defined in:
lib/mzid/streaming_parser.rb

Overview

class to parse an mzIdentML file in a streaming (i.e., mem-efficient) manner

Instance Method Summary collapse

Methods inherited from BatchParser

#cache_db_seq_entries, #each_spectrum

Constructor Details

#initialize(file, use_pbar = nil) ⇒ StreamingParser

Returns a new instance of StreamingParser.



12
13
14
15
16
# File 'lib/mzid/streaming_parser.rb', line 12

def initialize(file, use_pbar = nil)
  @use_pbar = use_pbar
  @num_spec = 0
  super(file)
end

Instance Method Details

#cache_ids(use_pbar = @use_pbar) ⇒ Object

store peptide sequences in hash for lookup



37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
# File 'lib/mzid/streaming_parser.rb', line 37

def cache_ids(use_pbar = @use_pbar)
  # num_pep = 0
  # num_db_seq = 0
  # num_pep_ev = 0
  # # once through file to count
  # tmp_reader = Nokogiri::XML::Reader(File.open(@mzid_file))
  # tmp_reader.each do |node|
  #   @num_spec += 1 if node.name == "SpectrumIdentificationResult"
  #   num_pep += 1 if node.name == "Peptide"
  #   num_db_seq += 1 if node.name == "DBSequence"
  #   num_pep_ev += 1 if node.name == "PeptideEvidence"
  # end
  num_pep, num_db_seq, num_pep_ev = get_num_elements(nil)
  # puts "SPEC:\t#{@num_spec}"
  # puts "PEP:\t#{num_pep}"
  # puts "DB:\t#{num_db_seq}"
  # puts "PEPEV:\t#{num_pep_ev}"

  @pep_h = Hash.new
  @mod_h = Hash.new
  pbar = ProgressBar.new("Caching", num_pep+num_db_seq+num_pep_ev) if use_pbar
  reader = Nokogiri::XML::Reader(File.open(@mzid_file))
  reader.each do |node|
    # @num_spec += 1 if node.name == "SpectrumIdentificationResult"
    
    if node.name == "Peptide" then
      # parse local peptide entry
      tmp_node = Nokogiri::XML.parse(node.outer_xml)
      tmp_node.remove_namespaces!
      root = tmp_node.root
      
      pep_id = root["id"]
      # skip if already handled PepID
      next if @pep_h.has_key?(pep_id)
      # parse sequence/mods if haven't seen it yet
      pep_seq = get_peptide_sequence(root)
      mod_line = get_modifications(root)
      @pep_h[pep_id] = pep_seq 
      @mod_h[pep_id] = mod_line 
      pbar.inc if use_pbar
    end
    #
    if node.name == "DBSequence" then
      # parse local DBSequence entry
      tmp_node = Nokogiri::XML.parse(node.outer_xml)
      tmp_node.remove_namespaces!
      root = tmp_node.root
      cache_db_seq_entries(root)
      pbar.inc if use_pbar
    end
    #
    if node.name == "PeptideEvidence" then
      # parse local DBSequence entry
      tmp_node = Nokogiri::XML.parse(node.outer_xml)
      tmp_node.remove_namespaces!
      root = tmp_node.root
      cache_pep_ev(root)
      pbar.inc if use_pbar
    end 

  end
  pbar.finish if use_pbar
end

#cache_pep_ev(root) ⇒ Object

store peptide evidence sequences in hash for lookup



103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
# File 'lib/mzid/streaming_parser.rb', line 103

def cache_pep_ev(root)
  pep_ev_lst = root.xpath('//PeptideEvidence')
  pep_ev_lst.each do |pnode|
    id = pnode["id"]
    @pep_ev_h[id] = 
      PeptideEvidence.new(#:id => pnode["id"],
                          :db_seq_ref => pnode["dBSequence_ref"],
                          #:pep_id => pnode["peptide_ref"],
                          :start_pos => pnode["start"].to_i,
                          :end_pos => pnode["end"].to_i,
                          #:pre => pnode["pre"],
                          #:post => pnode["post"],
                          :prot_id => @db_seq_h[pnode["dBSequence_ref"]].to_sym)
    # @pep_ev_h[id] = pnode["dBSequence_ref"]
  end
end

#each_psm(use_pbar = @use_pbar) ⇒ Object

iterate through each psm



122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
# File 'lib/mzid/streaming_parser.rb', line 122

def each_psm(use_pbar=@use_pbar)
  reader = Nokogiri::XML::Reader(File.open(@mzid_file))
  pbar = ProgressBar.new("PSMs", @num_spec) if use_pbar
  reader.each do |node|
    next if node.name != "SpectrumIdentificationResult"        
    # parse local spec result entry
    tmp_node = Nokogiri::XML.parse(node.outer_xml)
    tmp_node.remove_namespaces!
    root = tmp_node.root
    # parse spectrum id item
    psms_of_spec = root.xpath('.//SpectrumIdentificationItem')
    psms_of_spec.each do |psm_node|
      # get PSM object
      psm = get_psm(psm_node)
      # yield psm object
      yield psm
    end
    pbar.inc if use_pbar
  end
  pbar.finish if use_pbar
end