Class: Bio::Blast::Report

Inherits:
Object show all
Defined in:
lib/bio/appl/blast/report.rb,
lib/bio/appl/blast/rexml.rb,
lib/bio/appl/blast/format8.rb,
lib/bio/appl/blast/xmlparser.rb

Overview

Bio::Blast::Report

Parsed results of the blast execution for Tab-delimited and XML output format. Tab-delimited reports are consists of

Query id,
Subject id,
percent of identity,
alignment length,
number of mismatches (not including gaps),
number of gap openings,
start of alignment in query,
end of alignment in query,
start of alignment in subject,
end of alignment in subject,
expected value,
bit score.

according to the MEGABLAST document (README.mbl). As for XML output, see the following DTDs.

* http://www.ncbi.nlm.nih.gov/dtd/NCBI_BlastOutput.dtd
* http://www.ncbi.nlm.nih.gov/dtd/NCBI_BlastOutput.mod
* http://www.ncbi.nlm.nih.gov/dtd/NCBI_Entity.mod

Direct Known Subclasses

Report_tab

Defined Under Namespace

Classes: BlastXmlSplitter, Hit, Hsp, Iteration

Constant Summary collapse

DELIMITER =

for Bio::FlatFile support (only for XML data)

RS = "</BlastOutput>\n"

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(data, parser = nil) ⇒ Report

Passing a BLAST output from ‘blastall -m 7’ or ‘-m 8’ as a String. Formats are auto detected.



81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
 
# File 'lib/bio/appl/blast/report.rb', line 81

def initialize(data, parser = nil)
  @iterations = []
  @parameters = {}
  case parser
  when :xmlparser		# format 7
    xmlparser_parse(data)
    @reports = blastxml_split_reports
  when :rexml		# format 7
    rexml_parse(data)
    @reports = blastxml_split_reports
  when :tab		# format 8
    tab_parse(data)
  when false
    # do not parse, creates an empty object
  else
    auto_parse(data)
  end
end

Instance Attribute Details

#db ⇒ Object (readonly)

database name or title (String)



122
123
124
 
# File 'lib/bio/appl/blast/report.rb', line 122

def db
  @db
end

#iterations ⇒ Object (readonly)

Returns an Array of Bio::Blast::Report::Iteration objects.



101
102
103
 
# File 'lib/bio/appl/blast/report.rb', line 101

def iterations
  @iterations
end

#parameters ⇒ Object (readonly)

Returns a Hash containing execution parameters. Valid keys are: ‘matrix’, ‘expect’, ‘include’, ‘sc-match’, ‘sc-mismatch’, ‘gap-open’, ‘gap-extend’, ‘filter’



106
107
108
 
# File 'lib/bio/appl/blast/report.rb', line 106

def parameters
  @parameters
end

#program ⇒ Object (readonly)

program name (e.g. “blastp”) (String)



113
114
115
 
# File 'lib/bio/appl/blast/report.rb', line 113

def program
  @program
end

#query_def ⇒ Object (readonly)

query definition line (String)



128
129
130
 
# File 'lib/bio/appl/blast/report.rb', line 128

def query_def
  @query_def
end

#query_id ⇒ Object (readonly)

query ID (String)



125
126
127
 
# File 'lib/bio/appl/blast/report.rb', line 125

def query_id
  @query_id
end

#query_len ⇒ Object (readonly)

query length (Integer)



131
132
133
 
# File 'lib/bio/appl/blast/report.rb', line 131

def query_len
  @query_len
end

#reference ⇒ Object (readonly)

reference (String)



119
120
121
 
# File 'lib/bio/appl/blast/report.rb', line 119

def reference
  @reference
end

#reports ⇒ Object (readonly)

When the report contains results for multiple query sequences, returns an array of Bio::Blast::Report objects corresponding to the multiple queries. Otherwise, returns nil.

Note for “No hits found”: When no hits found for a query sequence, the result for the query is completely void and no information available in the result XML, including query ID and query definition. The only trace is that iteration number is skipped. This means that if the no-hit query is the last query, the query can not be detected, because the result XML is completely the same as the result XML without the query.



379
380
381
 
# File 'lib/bio/appl/blast/report.rb', line 379

def reports
  @reports
end

#version ⇒ Object (readonly)

BLAST version (e.g. “blastp 2.2.18 [Mar-02-2008]”) (String)



116
117
118
 
# File 'lib/bio/appl/blast/report.rb', line 116

def version
  @version
end

Class Method Details

.rexml(data) ⇒ Object

Specify to use REXML to parse XML (-m 7) output.



55
56
57
 
# File 'lib/bio/appl/blast/report.rb', line 55

def self.rexml(data)
  self.new(data, :rexml)
end

.tab(data) ⇒ Object

Specify to use tab delimited output parser.



60
61
62
 
# File 'lib/bio/appl/blast/report.rb', line 60

def self.tab(data)
  self.new(data, :tab)
end

.xmlparser(data) ⇒ Object

Specify to use XMLParser to parse XML (-m 7) output.



50
51
52
 
# File 'lib/bio/appl/blast/report.rb', line 50

def self.xmlparser(data)
  self.new(data, :xmlparser)
end

Instance Method Details

#db_len ⇒ Object

Length of BLAST db



187
 
# File 'lib/bio/appl/blast/report.rb', line 187

def db_len;    statistics['db-len'];    end

#db_num ⇒ Object

Number of sequences in BLAST db



185
 
# File 'lib/bio/appl/blast/report.rb', line 185

def db_num;    statistics['db-num'];    end

#each_hit ⇒ Object Also known as: each

Iterates on each Bio::Blast::Report::Hit object of the the last Iteration. Shortcut for the last iteration’s hits (for blastall)



163
164
165
166
167
 
# File 'lib/bio/appl/blast/report.rb', line 163

def each_hit
  @iterations.last.each do |x|
    yield x
  end
end

#each_iteration ⇒ Object

Iterates on each Bio::Blast::Report::Iteration object. (for blastpgp)



155
156
157
158
159
 
# File 'lib/bio/appl/blast/report.rb', line 155

def each_iteration
  @iterations.each do |x|
    yield x
  end
end

#eff_space ⇒ Object

Effective search space



191
 
# File 'lib/bio/appl/blast/report.rb', line 191

def eff_space; statistics['eff-space']; end

#entrez_query ⇒ Object

Limit of request to Entrez : shortcuts for @parameters



152
 
# File 'lib/bio/appl/blast/report.rb', line 152

def entrez_query; @parameters['entrez-query'];     end

#entropy ⇒ Object

Karlin-Altschul parameter H



197
 
# File 'lib/bio/appl/blast/report.rb', line 197

def entropy;   statistics['entropy'];   end

#expect ⇒ Object

Expectation threshold (-e) : shortcuts for @parameters



136
 
# File 'lib/bio/appl/blast/report.rb', line 136

def expect;       @parameters['expect'];           end

#filter ⇒ Object

Filtering options (-F) : shortcuts for @parameters



148
 
# File 'lib/bio/appl/blast/report.rb', line 148

def filter;       @parameters['filter'];           end

#gap_extend ⇒ Object

Gap extension cost (-E) : shortcuts for @parameters



146
 
# File 'lib/bio/appl/blast/report.rb', line 146

def gap_extend;   @parameters['gap-extend'];       end

#gap_open ⇒ Object

Gap opening cost (-G) : shortcuts for @parameters



144
 
# File 'lib/bio/appl/blast/report.rb', line 144

def gap_open;     @parameters['gap-open'];         end

#hits ⇒ Object

Returns a Array of Bio::Blast::Report::Hits of the last iteration. Shortcut for the last iteration’s hits



172
173
174
 
# File 'lib/bio/appl/blast/report.rb', line 172

def hits
  @iterations.last.hits
end

#hsp_len ⇒ Object

Effective HSP length



189
 
# File 'lib/bio/appl/blast/report.rb', line 189

def hsp_len;   statistics['hsp-len'];   end

#inclusion ⇒ Object

Inclusion threshold (-h) : shortcuts for @parameters



138
 
# File 'lib/bio/appl/blast/report.rb', line 138

def inclusion;    @parameters['include'];          end

#kappa ⇒ Object

Karlin-Altschul parameter K



193
 
# File 'lib/bio/appl/blast/report.rb', line 193

def kappa;     statistics['kappa'];     end

#lambda ⇒ Object

Karlin-Altschul parameter Lamba



195
 
# File 'lib/bio/appl/blast/report.rb', line 195

def lambda;    statistics['lambda'];    end

#matrix ⇒ Object

Matrix used (-M) : shortcuts for @parameters



134
 
# File 'lib/bio/appl/blast/report.rb', line 134

def matrix;       @parameters['matrix'];           end

#message ⇒ Object

Returns a String (or nil) containing execution message of the last iteration (typically “CONVERGED”). Shortcut for the last iteration’s message (for checking ‘CONVERGED’)



202
203
204
 
# File 'lib/bio/appl/blast/report.rb', line 202

def message
  @iterations.last.message
end

#pattern ⇒ Object

PHI-BLAST pattern : shortcuts for @parameters



150
 
# File 'lib/bio/appl/blast/report.rb', line 150

def pattern;      @parameters['pattern'];          end

#sc_match ⇒ Object

Match score for NT (-r) : shortcuts for @parameters



140
 
# File 'lib/bio/appl/blast/report.rb', line 140

def sc_match;     @parameters['sc-match'];         end

#sc_mismatch ⇒ Object

Mismatch score for NT (-q) : shortcuts for @parameters



142
 
# File 'lib/bio/appl/blast/report.rb', line 142

def sc_mismatch;  @parameters['sc-mismatch'];      end

#statistics ⇒ Object

Returns a Hash containing execution statistics of the last iteration. Valid keys are: ‘db-num’, ‘db-len’, ‘hsp-len’, ‘eff-space’, ‘kappa’, ‘lambda’, ‘entropy’ Shortcut for the last iteration’s statistics.



180
181
182
 
# File 'lib/bio/appl/blast/report.rb', line 180

def statistics
  @iterations.last.statistics
end