genevalidator 1.6.9 → 1.6.10

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 3dda4f4b115d164e1f19d3fed6865bd67837f894
-  data.tar.gz: c66c07f28778a63c402f443e93a526426406d45b
+  metadata.gz: 385bdeb501c790a57b5fd22fb431f8fcbff04b4f
+  data.tar.gz: 38297d81546366272db08cb00a7f2a4ae3319026
 SHA512:
-  metadata.gz: 5a63f6a26a4539a98c2b331cfbb8976aa18d1014d0e1b409c7bc1c25c6739972e7863bd2e85447a2ade706c021f805ce9defeccb1f3f25c423a139fd1797f116
-  data.tar.gz: 156ffae45cd5777f77374f3cdfb17f4946f1ad01b2c2c99d21dc955c65de08d03f8f6cb7f174afbacdcd042e5a741002b74f62eaa02d00e84725259f55c55b90
+  metadata.gz: 1bfbc522536e0a08bbed42adba67110dd9193c315c3446dbfee1b54e3bce2e3b71ade70a8b18a28b232e952c4ca25f3a12bf166ca398bed8f67b9e740b7196f1
+  data.tar.gz: 388ed6ee18a07bec1ccecf71c3c99b6aad76da5a2c65255c0bc16fb489850a349056b2374a209d2052bd1a2fbe0a0fd17e298d75c3d433912c39277040a810e9

data/README.md

@@ -44,11 +44,18 @@ Each analysis of each query returns a binary result (good vs. potential problem)
 ### Installation Requirements
 * Ruby (>= 2.0.0)
 * NCBI BLAST+ (>= 2.2.30+) (download [here](http://blast.ncbi.nlm.nih.gov/Blast.cgi?PAGE_TYPE=BlastDocs&DOC_TYPE=Download)).
-* MAFFT installation (download [here](http://mafft.cbrc.jp/alignment/software/)).
+* MAFFT installation (>=7.273) (download [here](http://mafft.cbrc.jp/alignment/software/)).
 * A web browser - [Mozilla FireFox](https://www.mozilla.org/en-GB/firefox/new/) & Safari are recommended. At the moment, it is not possible to use Chrome to view the results locally (as chrome does not allow ajax to local files). To avoid this, simply use a different browser (like Firefox or Safari) or start a local server in the results folder.
 
 Please see [here](https://gist.github.com/IsmailM/b783e8a06565197084e6) for more help with installing the prerequisites.
 
+#### Setting up a BLAST database
+GeneValidator requires a protein BLAST database in order to fully analyse all sequences. The BLAST database needs to be set up with the `-parse_seqids` argument as follows:
+
+```bash
+makeblastdb -in input_db -dbtype prot -parse_seqids
+```
+
 ### Installation
 Simply run the following command in the terminal.
 
@@ -224,7 +231,7 @@ Lastly, a tabular summary of the results is also outputted in the terminal to pr
 
 ## Analysing the JSON output
 
-There are numerous methods to analyse the JSON output including the [streamable JSON command line program](http://trentm.com/json/). The below examples use this tool.
+There are numerous methods to analyse the JSON output including the [streamable JSON command line program](http://trentm.com/json/) or [jq](https://stedolan.github.io/jq/). The below examples use the JSON tool.
 
 ### Examplar JSON CLI Installation
 After installing node:
@@ -253,7 +260,11 @@ $ json -f INPUT_JSON_FILE -A -e 'this.sort(function(a,b) {return (a.overall_scor
 json -f INPUT_JSON_FILE -A -e 'this.sort(function(a,b) {return (a.overall_score < b.overall_score) ? 1 : ((b.overall_score < a.overall_score) ? -1 : 0);} );' > OUTPUT_JSON_FILE
 ```
 
+The subsetted/sorted JSON file can then be passed back into GeneValidator (using the `-j` command line argument) to generate the HTML report for the sequences in the JSON file.
 
+```bash
+genevalidator -j SORTED_JSON_FILE
+```
 
 
 ## Related projects

data/lib/genevalidator/exceptions.rb

@@ -68,6 +68,14 @@ module GeneValidator
     end
   end
 
+  # Exception raised when the BLAST is not set up with the '-parse-seqids' arg.
+  class BLASTDBError < Exception
+  end
+
+  # Error raised by QI Validation when the query does not have QI tag
+  class NotEnoughEvidence < Exception
+  end
+
   # Exception raised when the are alias duplications
   class NoPIdentError < Exception
   end

data/lib/genevalidator/get_raw_sequences.rb

@@ -75,6 +75,12 @@ module GeneValidator
         file = File.open(output_file, 'w+')
         iterate_xml(file, db_type) if opt[:blast_xml_file]
         iterate_tabular(file, db_type) if opt[:blast_tabular_file]
+      rescue BLASTDBError
+        $stderr.puts "*** BLAST Database Error: Genevalidator requires BLAST" \
+        " databases to be created with the '-parse_seqids argument."
+        $stderr.puts "    See https://github.com/wurmlab/genevalidator" \
+        "#setting-up-a-blast-database for more information"
+        exit 1
       rescue
         $stderr.puts '*** Error: There was an error in analysing the BLAST'
         $stderr.puts '    output file. Please ensure that BLAST output file'
@@ -92,6 +98,7 @@ module GeneValidator
         n = Bio::BlastXMLParser::XmlIterator.new(opt[:blast_xml_file]).to_enum
         n.each do |iter|
           iter.each do |hit|
+            fail BLASTDBError if hit.hit_id =~ /\|BL_ORD_ID\|/
             if db_type == 'remote' || hit.hit_id.nil?
               file.puts FetchRawSequences.extract_from_remote_db(hit.accession)
             else
@@ -109,6 +116,7 @@ module GeneValidator
                                    headers: table_headers)
 
         rows.each do |row|
+          fail BLASTDBError if row['sseqid'] =~ /\|BL_ORD_ID\|/
           if db_type == 'remote' || row['sseqid'].nil?
             file.puts FetchRawSequences.extract_from_remote_db(row['sacc'])
           else

data/lib/genevalidator/validation.rb

@@ -86,7 +86,7 @@ module GeneValidator
       query        = IO.binread(input_file, @query_idx[1], @query_idx[0])
       parse_query  = query.scan(/>([^\n]*)\n([A-Za-z\n]*)/)[0]
       definition   = parse_query[0].gsub("\n", '')
-      number       = '\d*\.?\d*'
+      number       = '-?\d*\.?\d*'
       qi_match     = definition.match(/QI:#{number}\|#{number}\|#{number}\|
                                       #{number}\|#{number}\|#{number}\|
                                       #{number}\|#{number}\|#{number}/x)

data/lib/genevalidator/validation_maker_qi.rb

@@ -75,7 +75,7 @@ module GeneValidator
 
       start  = Time.now
 
-      number = '\d*\.?\d*'
+      number = '-?\d*\.?\d*'
       match  = @prediction.definition.match(/QI:#{number}\|(#{number})\|
                                              (#{number})\|#{number}\|
                                              #{number}\|#{number}\|#{number}\|
@@ -95,7 +95,7 @@ module GeneValidator
       @validation_report
 
     rescue NotEnoughEvidence
-      @validation_report =  ValidationReport.new('Not enough evidence',
+      @validation_report =  ValidationReport.new('No MAKER Quality Index',
                                                  :warning, @short_header,
                                                  @header, @description)
     rescue

data/lib/genevalidator/version.rb

@@ -1,3 +1,3 @@
 module GeneValidator
-  VERSION = '1.6.9'
+  VERSION = '1.6.10'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: genevalidator
 version: !ruby/object:Gem::Version
-  version: 1.6.9
+  version: 1.6.10
 platform: ruby
 authors:
 - Monica Dragan
@@ -11,7 +11,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-03-14 00:00:00.000000000 Z
+date: 2016-05-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler