Class: PepXML

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

Overview

require 'rexml/document' require 'rexml/xpath'

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(file_name) ⇒ PepXML

Returns a new instance of PepXML.


13
14
15
16
17
18
19
20
21
22
23
24
25
26
# File 'lib/protk/pepxml.rb', line 13

def initialize(file_name)
  @file_name=file_name

  XML::Error.set_handler(&XML::Error::QUIET_HANDLER)
  pepxml_parser=XML::Parser.file("#{file_name}")

  @pepxml_ns_prefix="xmlns:"
  @pepxml_ns="xmlns:http://regis-web.systemsbiology.net/pepXML"
  @pepxml_doc=pepxml_parser.parse
  if not @pepxml_doc.root.namespaces.default
    @pepxml_ns_prefix=""
    @pepxml_ns=nil
  end
end

Instance Attribute Details

#file_nameObject

Returns the value of attribute file_name


11
12
13
# File 'lib/protk/pepxml.rb', line 11

def file_name
  @file_name
end

Instance Method Details

#extract_dbObject

Obtain the database name from the given input file


32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
# File 'lib/protk/pepxml.rb', line 32

def extract_db()
  reader = XML::Reader.file(self.file_name)
  throw "Failed to open xml file #{file_name}" unless reader!=nil

  while(reader.read)
    # For pep.xml files
    #
    if ( reader.name == "search_database" )
      dbnode=reader.expand
      dbvalue=dbnode['local_path']
      reader.close
      return dbvalue
    end

    # For prot.xml files
    #
    if ( reader.name == "protein_summary_header" )
      dbnode=reader.expand
      dbvalue=dbnode['reference_database']
      reader.close
      return dbvalue
    end
    
    
    
  end

end

#extract_engineObject

Obtain the search engine name from the input file The name of the engine is returned in lowercase and should contain no spaces Names of common engines are searched for and extracted in simplified form if possible


67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
# File 'lib/protk/pepxml.rb', line 67

def extract_engine()
  reader = XML::Reader.file(self.file_name)
  throw "Failed to open xml file #{file_name}" unless reader!=nil

  while(reader.read)
    if ( reader.name == "search_summary" )
      dbnode=reader.expand
      dbvalue=dbnode['search_engine']
      reader.close
      engine_name=dbvalue.gsub(/ /,"_")
      engine_name=engine_name.gsub(/\(/,"")
      engine_name=engine_name.gsub(/\)/,"")
      engine_name=engine_name.gsub(/\!/,"")        
      return engine_name.downcase
    end
  end
end

#extract_enzymeObject


86
87
88
89
90
91
92
93
94
95
96
97
98
# File 'lib/protk/pepxml.rb', line 86

def extract_enzyme()
  reader = XML::Reader.file(self.file_name)
  throw "Failed to open xml file #{file_name}" unless reader!=nil

  while(reader.read)
    if ( reader.name == "sample_enzyme" )
      dbnode=reader.expand
      dbvalue=dbnode['name']
      reader.close        
      return dbvalue.downcase
    end
  end
end

#find_runsObject

TODO: Make this faster and more memory efficient by using XML::Reader as in the functions above


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
# File 'lib/protk/pepxml.rb', line 146

def find_runs()


  run_summaries = @pepxml_doc.find("//#{@pepxml_ns_prefix}msms_run_summary", @pepxml_ns)

  runs = {}
  run_summaries.each do |summary|
    base_name = summary.attributes["base_name"]
    if not runs.has_key?(base_name)
      bn = summary.attributes["base_name"]

      runs[base_name] = {:base_name => summary.attributes["base_name"]}

      if is_valid_type(type_from_summary_attributes(summary.attributes))
        runs[base_name][:type] = type_from_summary_attributes(summary.attributes)
      elsif is_valid_type(type_from_base_name(bn))
        runs[base_name][:type] = type_from_base_name(bn)
      else
        runs[base_name][:type] = "mzML" # Same guess as peptide prophet makes
      end

    end
  end
  runs
end

#is_valid_type(type) ⇒ Object


130
131
132
133
134
135
136
137
138
139
140
141
# File 'lib/protk/pepxml.rb', line 130

def is_valid_type(type)
  case type
  when /^mgf$/i
    return true
  when /^mzML$/i
    return true
  when /^mzXML$/i
    return true
  else
    return false
  end
end

#type_from_base_name(basename) ⇒ Object


102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
# File 'lib/protk/pepxml.rb', line 102

def type_from_base_name(basename)
  # A common error is for tools to include the extension in the base_name attribute.
  # We exploit this to guess the type
  ext_guess=""
  case basename
  when /.mgf$/
    ext_guess="mgf"
  when /.mzML$/
    ext_guess="mzML"
  when /.mzXML$/
    ext_guess="mzXML"
  else
    ext_guess=""
  end
  ext_guess
end

#type_from_summary_attributes(atts) ⇒ Object


119
120
121
122
123
124
125
126
127
128
# File 'lib/protk/pepxml.rb', line 119

def type_from_summary_attributes(atts)
  if is_valid_type(atts["raw_data_type"])
    return  atts["raw_data_type"]
  end

  if is_valid_type(atts["raw_data"])
    return atts["raw_data"]
  end
  return ""
end