genevalidator 1.6.12 → 2.1.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 4847ad48911fc47c1e3f6a74f5c4c05d2b736d52
-  data.tar.gz: 0a198a16c9a31d89d12bce6b70e799d2071bbf3a
+SHA256:
+  metadata.gz: ac9af62bb53cde2f76ae700a0098437f064dd354f9c4649006e3770a13b346ea
+  data.tar.gz: f655a495a8e1638b035f47c5caae2e1f449477198435bba6561f7af1e71a5142
 SHA512:
-  metadata.gz: 6de4d4413f911a31fb840bfe13b942b7c3741e409e50a795be4e4edb009867f1347c1eda328bda759b26f66a88775bf10cb2defcb588f4662da69af88265cdf9
-  data.tar.gz: ff9d98fb9eeac013f69aa473cfb66a0d617fc911c41a862188c263d74c2ea719c292bd62c6f112eb7138efaccf61aa7990ccd324b50b2c1433b38117ade6e56e
+  metadata.gz: 8402a4e0f20fbc7d7765c01a8337ce5a425f5ed92f3616f10e6faa28fa24a4a8624fc6218d0bdf0773a7253934692baa6ae30cb2d87078415978600dacadc4db
+  data.tar.gz: 29fc2075baa01d90affa395b664adb884a4583ea4f50238fd6ecee9e5aa2e78f92c965256b4edc70590aaadd40cb61d4b206f7239c69da02e261882c4d689c6e

data/.gitignore

@@ -2,8 +2,37 @@
 *.~*~
 *.gem
 .DS_Store
-Gemfile.lock
 # Gemnasium gem configuration file
 config/gemnasium.yml
 doc
 .yardoc
+tmp
+*.rbc
+.bundle
+.config
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+*.bundle
+*.so
+*.o
+*.a
+mkmf.log
+*-linux-x86/
+*-linux-x86_64/
+*-osx/
+*-linux-x86.tar.gz
+*-linux-x86_64.tar.gz
+*-osx.tar.gz
+test/test_files/all_validations_prot/prot.fa.html/
+test/test_files/GV_*
+exemplar_data/GV*
+.vscode
+q/

data/.ruby-version

@@ -0,0 +1 @@
+2.2

data/.travis.yml

@@ -1,18 +1,19 @@
 language: ruby
 rvm:
-  - "2.0.0"
-  - "2.1.3"
-  - "2.2.0"
-before_install:
-  - wget -P ~ http://mafft.cbrc.jp/alignment/software/mafft-7.205-with-extensions-src.tgz
-  - tar -zxvf ~/mafft-7.205-with-extensions-src.tgz -C ~
-  - mkdir ~/mafft
-  - ruby -pi -e "gsub(/^PREFIX = \/usr\/local/, 'PREFIX = ~/mafft/')" ~/mafft-7.205-with-extensions/core/Makefile
-  - (cd ~/mafft-7.205-with-extensions/core/ && make clean && make && make install)
-  - export PATH=$PATH:~/mafft/bin
-cache: bundler
-sudo: false 
+  - "2.2.10"
+  - "2.3.7"
+  - "2.4.4"
+  - "2.5.1"
+before_script:
+  - wget -P ~ https://mafft.cbrc.jp/alignment/software/mafft-7.397-linux.tgz
+  - tar -zxvf ~/mafft-7.397-linux.tgz -C ~
+  - mkdir ~/mafft_bin
+  - echo "#!/bin/bash" > ~/mafft_bin/mafft
+  - echo '$HOME/mafft-linux64/mafft.bat "$@"' >> ~/mafft_bin/mafft
+  - chmod 755 ~/mafft_bin/mafft
+  - export PATH=$PATH:~/mafft_bin
 script: bundle exec rake test
+after_script: bundle exec codeclimate-test-reporter
 addons:
   code_climate:
     repo_token: 2177997ae2dd26804c32e1ec34a2221f94b71a2170f6c1db2c020f8858cd87f2

data/Gemfile

@@ -1,4 +1,7 @@
 source 'http://rubygems.org'
 
 gemspec
-gem 'codeclimate-test-reporter', group: :test, require: nil
+group :test do
+  gem 'codeclimate-test-reporter', '~> 1.0.0'
+  gem 'simplecov'
+end

data/Gemfile.lock

@@ -0,0 +1,135 @@
+PATH
+  remote: .
+  specs:
+    genevalidator (2.1.3)
+      bio (~> 1.4)
+      bio-blastxmlparser (~> 2.0)
+      genevalidatorapp (~> 2.1.3)
+      mechanize (= 2.7.5)
+      rack (~> 2.0)
+      slim (~> 3.0)
+      statsample (= 2.1.0)
+
+GEM
+  remote: http://rubygems.org/
+  specs:
+    awesome_print (1.8.0)
+    backports (3.11.3)
+    bio (1.5.1)
+    bio-blastxmlparser (2.0.4)
+      bio-logger
+      nokogiri
+    bio-logger (1.0.1)
+      log4r (>= 1.1.9)
+    clbustos-rtf (0.4.2)
+    codeclimate-test-reporter (1.0.8)
+      simplecov (<= 0.13)
+    daru (0.1.6)
+      backports
+    dirty-memoize (0.0.4)
+    distribution (0.7.3)
+    docile (1.1.5)
+    domain_name (0.5.20180417)
+      unf (>= 0.0.5, < 1.0.0)
+    extendmatrix (0.4)
+    genevalidatorapp (2.1.3)
+      bio (~> 1.4)
+      sinatra (~> 2.0)
+      sinatra-cross_origin (~> 0.3)
+      slim (~> 3.0)
+    http-cookie (1.0.3)
+      domain_name (~> 0.5)
+    json (2.1.0)
+    log4r (1.1.10)
+    mechanize (2.7.5)
+      domain_name (~> 0.5, >= 0.5.1)
+      http-cookie (~> 1.0)
+      mime-types (>= 1.17.2)
+      net-http-digest_auth (~> 1.1, >= 1.1.1)
+      net-http-persistent (~> 2.5, >= 2.5.2)
+      nokogiri (~> 1.6)
+      ntlm-http (~> 0.1, >= 0.1.1)
+      webrobots (>= 0.0.9, < 0.2)
+    mime-types (3.2.2)
+      mime-types-data (~> 3.2015)
+    mime-types-data (3.2018.0812)
+    mini_portile2 (2.3.0)
+    minimization (0.2.3)
+      text-table (~> 1.2)
+    minitest (5.11.3)
+    mustermann (1.0.2)
+    net-http-digest_auth (1.4.1)
+    net-http-persistent (2.9.4)
+    nokogiri (1.8.4)
+      mini_portile2 (~> 2.3.0)
+    ntlm-http (0.1.1)
+    prawn (0.8.4)
+      prawn-core (>= 0.8.4, < 0.9)
+      prawn-layout (>= 0.8.4, < 0.9)
+      prawn-security (>= 0.8.4, < 0.9)
+    prawn-core (0.8.4)
+    prawn-layout (0.8.4)
+    prawn-security (0.8.4)
+    prawn-svg (0.9.1.11)
+      prawn (>= 0.8.4)
+    rack (2.0.5)
+    rack-protection (2.0.3)
+      rack
+    rake (12.3.1)
+    reportbuilder (1.4.2)
+      clbustos-rtf (~> 0.4.0)
+      prawn (~> 0.8.4)
+      prawn-svg (~> 0.9.1)
+      text-table (~> 1.2)
+    rserve-client (0.3.5)
+    ruby-ole (1.2.12.1)
+    rubyvis (0.6.1)
+    simplecov (0.13.0)
+      docile (~> 1.1.0)
+      json (>= 1.8, < 3)
+      simplecov-html (~> 0.10.0)
+    simplecov-html (0.10.2)
+    sinatra (2.0.3)
+      mustermann (~> 1.0)
+      rack (~> 2.0)
+      rack-protection (= 2.0.3)
+      tilt (~> 2.0)
+    sinatra-cross_origin (0.4.0)
+    slim (3.0.9)
+      temple (>= 0.7.6, < 0.9)
+      tilt (>= 1.3.3, < 2.1)
+    spreadsheet (1.1.7)
+      ruby-ole (>= 1.0)
+    statsample (2.1.0)
+      awesome_print (~> 1.6)
+      daru (~> 0.1.6)
+      dirty-memoize (~> 0.0.4)
+      distribution (~> 0.7)
+      extendmatrix (~> 0.4)
+      minimization (~> 0.2)
+      reportbuilder (~> 1.4)
+      rserve-client (~> 0.3)
+      rubyvis (~> 0.6.1)
+      spreadsheet (~> 1.1)
+    temple (0.8.0)
+    text-table (1.2.4)
+    tilt (2.0.8)
+    unf (0.1.4)
+      unf_ext
+    unf_ext (0.0.7.5)
+    webrobots (0.1.2)
+    yard (0.9.16)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  codeclimate-test-reporter (~> 1.0.0)
+  genevalidator!
+  minitest (~> 5.10)
+  rake (~> 12.3)
+  simplecov
+  yard (~> 0.9.11)
+
+BUNDLED WITH
+   1.16.2

data/README.md

@@ -14,9 +14,7 @@ If you would like to use GeneValidator on a few sequences, see our online [GeneV
 
 
 If you use GeneValidator in your work, please cite us as follows:
-> [Dragan M<sup>&Dagger;</sup>, Moghul MI<sup>&Dagger;</sup>, Priyam A, Bustos C & Wurm Y. 2016. GeneValidator: identify problems with protein-coding gene predictions. <em>Bioinformatics</em>, doi: 10.1093/bioinformatics/btw015](http://bioinformatics.oxfordjournals.org/content/early/2016/02/26/bioinformatics.btw015).
-
-
+> [Dragan M<sup>&Dagger;</sup>, Moghul I<sup>&Dagger;</sup>, Priyam A, Bustos C & Wurm Y. 2016. GeneValidator: identify problems with protein-coding gene predictions. <em>Bioinformatics</em>, doi: 10.1093/bioinformatics/btw015](https://academic.oup.com/bioinformatics/article/32/10/1559/1742817/GeneValidator-identify-problems-with-protein).
 
 
 
@@ -37,86 +35,59 @@ GeneValidator also runs a further two validation on cDNA sequences:
 Each analysis of each query returns a binary result (good vs. potential problem) according to p-value or an empirically determined cutoff. The results for each query are combined into an overall quality score from 0 to 100. Each analysis of each query returns a binary result (good vs. potential problem) according to p-value or an empirically determined cutoff. The results for each query are combined into an overall quality score from 0 to 100.
 
 
-
-
-
 ## Installation
-### 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 (>=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:
+Run the following in your terminal:
 
 ```bash
-makeblastdb -in input_db -dbtype prot -parse_seqids
+sh -c "$(curl -fsSL https://raw.githubusercontent.com/wurmlab/genevalidator/master/install.sh)"
 ```
 
-### Installation
-Simply run the following command in the terminal.
+By default this will install in a folder called `genevalidator` in your current folder. If you wish to have GeneValidator installed in a different location, add the path to the end of the above install line. For example to install GeneValidator in a hidden folder in your home path
 
 ```bash
-gem install genevalidator
+sh -c "$(curl -fsSL https://raw.githubusercontent.com/wurmlab/genevalidator/master/install.sh)" ~/.genevalidator
 ```
 
-If that doesn't work, try `sudo gem install genevalidator` instead.
+Alternatively download and compress the standalone package from our [releases](https://github.com/wurmlab/genevalidator/releases/latest) page.
 
-##### Running From Source (Not Recommended)
-It is also possible to run from source. However, this is not recommended.
+The produced folder contains the following:
 
 ```bash
-# Clone the repository.
-git clone https://github.com/wurmlab/genevalidator.git
-
-# Move into GeneValidator source directory.
-cd GeneValidator
-
-# Install bundler
-gem install bundler
-
-# Use bundler to install dependencies
-bundle install
-
-# Optional: run tests, build documentation and build the gem from source
-bundle exec rake
-
-# Run GeneValidator.
-bundle exec genevalidator -h
-# note that `bundle exec` executes GeneValidator in the context of the bundle
-
-# Alternativaly, install GeneValidator as a gem
-bundle exec rake install
-genevalidator -h
+Readme.txt      # See Readme for version and basic usage information
+bin/            # bin folder for genevalidator, BLAST+ and JQ (can add to $PATH)
+blast_db/       # contains the SWISSPROT BLAST database.
+exemplar_data/  # contains exemplar mrna and protein fasta files
+lib/            # contains genevalidator dependencies
 ```
 
-
-
-
-
-
 ## Usage
-Verify GeneValidator installed by running the following command in the terminal:
+
+GeneValidator can be run immediately after the GeneValidator package has been downloaded and uncompressed.
 
 ```bash
-genevalidator
+genevalidator -h
 ```
 
 You should see the following output.
 
 ```bash
+SUMMARY:
+  GeneValidator - Identify problems with predicted genes
+
 USAGE:
-    genevalidator [OPTIONS] Input_File
+  genevalidator [OPTIONAL ARGUMENTS] INPUT_FILE
+
+  To run as a web application:
 
-ARGUMENTS:
-    Input_File: Path to the input fasta file containing the predicted sequences.
+    genevalidator app [OPTIONAL ARGUMENTS]
+
+    See 'genevalidator app --help' for more information
 
 OPTIONAL ARGUMENTS
-    -v, --validations <String>       The Validations to be applied.
-                                     Validation Options Available (separated by coma):
+
+        --validations [VALIDATIONS]  The Validations to be applied.
+                                     Validation Options Available (separated by comma):
                                        all   = All validations (default),
                                        lenc  = Length validation by clusterization,
                                        lenr  = Length validation by ranking,
@@ -125,46 +96,79 @@ OPTIONAL ARGUMENTS
                                        frame = Open reading frame (ORF) validation,
                                        orf   = Main ORF validation,
                                        align = Validating based on multiple alignment
-    -d, --db [BLAST_DATABASE]        Path to the BLAST database
+    -d, --db [PATH]                  Path to the BLAST database
+                                     e.g.   genevalidator -d /path/to/databasa.fa Input_File
                                      GeneValidator also supports remote databases:
                                      e.g.   genevalidator -d "swissprot -remote" Input_File
-    -e, --extract_raw_seqs           Produces a fasta file of the raw sequences of all BLAST hits in the
-                                     supplied BLAST output file. This fasta file can then be provided to
-                                     GeneValidator with the "-r", "--raw_sequences" argument
-    -j, --json_file [JSON_FILE]      Generate HTML report from a JSON file (or a subset of a JSON file)
-                                     produced by GeneValidator
-    -x [BLAST_XML_FILE],             Provide GeneValidator with a pre-computed BLAST XML output
-        --blast_xml_file             file (BLAST -outfmt option 5).
-    -t [BLAST_TABULAR_FILE],         Provide GeneValidator with a pre-computed BLAST tabular output
-        --blast_tabular_file         file. (BLAST -outfmt option 6).
-    -o [BLAST_TABULAR_OPTIONS],      Custom format used in BLAST -outfmt argument
-        --blast_tabular_options      See BLAST+ manual pages for more details
-    -n, --num_threads num_of_threads Specify the number of processor threads to use when running
-                                     BLAST and Mafft within GeneValidator.
-    -r, --raw_sequences [raw_seq]    Supply a fasta file of the raw sequences of all BLAST hits present
+    -s, --select_single_best         Writes the fasta sequence of the best scoring gene to STDOUT.
+
+# OUTPUT ARGUMENTS
+
+    -o, --output_dir [PATH]          Path to the output folder.
+                                     By default the output folder is in the same directory as the input
+                                     file and is named as input filename, followed by the time of
+                                     analysis
+    -f, --force_rewrite              Rewrites over existing output.
+        --output_formats [STRING]    Output Formats to generate. This can be either: "all", "html",
+                                     "csv", "json", "summary" or "stdout". Multiple formats can be
+                                     separated by a semi-colon e.g. "csv:json".
+                                     By default, all output formats are generated.
+
+# BLAST ARGUMENTS
+
+        --min_blast_hits_required [NUM]
+                                     The minimum number of BLAST hits required by GeneValidator in order
+                                     to carry out validations. Note: certain validations have their own
+                                     set minimum (such as the multiple alignment validation, which
+                                      requires a minimum of 10 BLAST hits)
+    -b, --blast_options [STRING]     A string that is to passed to BLAST
+    -x, --blast_xml_file [PATH]      Provide GeneValidator with a pre-computed BLAST XML output
+                                     file (BLAST -outfmt option 5).
+    -t, --blast_tabular_file [PATH]  Provide GeneValidator with a pre-computed BLAST tabular output
+                                     file. (BLAST -outfmt option 6).
+        --blast_tabular_options [STRING]
+                                     Custom format used in BLAST -outfmt argument
+                                     See BLAST+ manual pages for more details
+        --raw_sequences [PATH]       Supply a fasta file of the raw sequences of all BLAST hits present
                                      in the supplied BLAST XML or BLAST tabular file.
-    -b, --binaries [binaries]        Path to BLAST and MAFFT bin folders (is added to $PATH variable)
-                                     To be provided as follows:
-                                     e.g.   genevalidator -b /blast/bin/path/ -b /mafft/bin/path/
-        --version                    The version of GeneValidator that you are running.
-    -h, --help                       Show this screen.
-```
 
+# EXTRACT RAW SEQUENCES ARGUMENTS
 
+    -e, --extract_raw_seqs           Extract a fasta file of the raw sequences of BLAST hits in the
+                                     supplied BLAST output file. This fasta file can then be provided to
+                                     GeneValidator with the "--raw_sequences" argument
 
+# REPROCESS JSON ARGUMENTS
 
+    -j, --json_file [JSON_FILE]      Path to json file. Re-generate the HTML report from a (filtered)
+                                     JSON file that was previously produced by GeneValidator
+
+# GENERAL ARGUMENTS
+
+    -n, --num_threads [THREADS]      Specify the number of processor threads to use when running
+                                     BLAST and GeneValidator.
+    -m, --mafft_threads [THREADS]    Specify the number of processor threads to use when running
+                                     Mafft. Note Mafft is run independently in each of the threads
+                                     specified in --num_threads.
+    -r, --resume [DIR]               Resume a previous analysis (creates a new output directory but
+                                      skips
+        --bin [DIR]                  Path to BLAST and MAFFT bin folders (is added to $PATH variable)
+                                     To be provided as follows:
+                                     e.g.   genevalidator --bin /blast/bin/ --bin /mafft/bin/
+    -h, --help                       Show this screen.
+    -v, --version                    The version of GeneValidator that you are running.```
 
 ## Example Usage Scenarios
 
-#### Simplest Usage (using NCBI remote BLAST servers)
-This runs BLAST on NCBI remote Swiss-Prot BLAST database. As such this is suitable for analyses on less than 10 sequences.
+#### Simplest Usage (using included SWISSPROT database)
+This runs BLAST on the included SwissProt BLAST database.
 
 ```bash
 genevalidator INPUT_FASTA_FILE
 ```
 
-#### Using a local BLAST database.
-GeneValidator would run BLAST (using an E-Value 1e-5) on each query against the provided BLAST database and then run the validation analyses.
+#### Using an alternative 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 of the makeblastdb script from BLAST+ (from Genevalidator Package, in the bin directory). See [this page](https://gist.github.com/IsmailM/3e3519de18c5b8b36d8aa0f223fb7948) for more information on how to set up BLAST databases.
 
 ```bash
 genevalidator -d DATABASE_PATH -n NUM_THREADS INPUT_FASTA_FILE
@@ -179,15 +183,7 @@ GeneValidator supports the XML and tabular BLAST output formats.
 # Run BLAST (XML output)
 blast(p/x) -db DATABASE_PATH -num_threads NUM_THREADS -outfmt 5 -out BLAST_XML_FILE -query INPUT_FASTA_FILE
 
-# Optional: Generate a fasta file for the BLAST hits.
-# Note: this works best if you use the same database used to create the BLAST OUTPUT file.
-genevalidator -d DATABASE_PATH -e -x BLAST_XML_FILE
-
 # Run GeneValidator
-## If you ran the previous command (i.e. if you produced fasta file for the BLAST hits)
-genevalidator -n NUM_THREADS -x BLAST_XML_FILE -r RAW_SEQUENCES_FILE INPUT_FASTA_FILE
-
-## If you did not run the previous command (this will run the previous command for you)
 genevalidator -d DATABASE_PATH -n NUM_THREADS -x BLAST_XML_FILE INPUT_FASTA_FILE
 ```
 
@@ -197,28 +193,24 @@ This is the same, but using the BLAST tabular output.
 # Run BLAST (tabular output)
 blast(p/x) -db DATABASE_PATH -num_threads NUM_THREADS -outfmt '7 qseqid sseqid sacc slen qstart qend sstart send length qframe pident nident evalue qseq sseq' -out BLAST_TAB_FILE -query INPUT_FASTA_FILE
 
-# Optional: Generate a fasta file for the BLAST hits.
-# Note: this works best if you use the same database used to create the BLAST OUTPUT file.
-genevalidator -d DATABASE_PATH -e -t BLAST_TAB_FILE -o 'qseqid sseqid sacc slen qstart qend sstart send length qframe pident nident evalue qseq sseq'
-
 # Run GeneValidator
-## If you ran the previous command (i.e. if you produced fasta file for the BLAST hits)
-genevalidator -n NUM_THREADS -t BLAST_TAB_FILE -o 'qseqid sseqid sacc slen qstart qend sstart send length qframe pident nident evalue qseq sseq' -r RAW_SEQUENCES_FILE INPUT_FASTA_FILE
-
-## If you did generate the BLAST hits fasta file (this will run the previous command for you)
-genevalidator -d DATABASE_PATH -n NUM_THREADS -t BLAST_TAB_FILE -o 'qseqid sseqid sacc slen qstart qend sstart send length qframe pident nident evalue qseq sseq' INPUT_FASTA_FILE
-
+genevalidator -n NUM_THREADS -t BLAST_TAB_FILE -o 'qseqid sseqid sacc slen qstart qend sstart send length qframe pident nident evalue qseq sseq' INPUT_FASTA_FILE
 ```
 
 
 
 
 ## Output
-The output produced by GeneValidator is presented in three manners.
+The output produced by GeneValidator is presented in four manners.
 
 #### HTML Output
 Firstly, the output is produced as a colourful, HTML file. This file is titled 'results.html' (found in the 'html' folder) and can be opened in a web browser (please use a supported browser - See [Installation Requirements](#installation-requirements)). This file contains all the results in an easy-to-view manner with graphical visualisations. See exemplar HTML output [here](http://wurmlab.github.io/tools/genevalidator/exemplar_data/protein_input/) (protein input data) and [here](http://wurmlab.github.io/tools/genevalidator/exemplar_data/genetic_input/) (DNA input data).
 
+
+#### CSV Output
+The output is also produced in JSON. GeneValidator is able to re-generate results for any JSON files (or derived JSON files) with that were previously generated by the program. This means that you are able to use the JSON file in your own analysis pipelines and then use GeneValidator to produce the HTML output for the analysed JSON file.
+
+
 #### JSON Output
 The output is also produced in JSON. GeneValidator is able to re-generate results for any JSON files (or derived JSON files) with that were previously generated by the program. This means that you are able to use the JSON file in your own analysis pipelines and then use GeneValidator to produce the HTML output for the analysed JSON file.
 
@@ -229,44 +221,34 @@ 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/) or [jq](https://stedolan.github.io/jq/). The below examples use the JSON tool.
-
-### Examplar JSON CLI Installation
-After installing node:
+## Using the JSON output
 
-```bash
-$ npm install -g json
-```
-
-### Filtering the results
+JSON output can be filtered or processed in a variety of ways using standard tools, such as the [streamable JSON command line program](http://trentm.com/json/), or [jq](https://stedolan.github.io/jq/). The examples below makes use of jq 1.5 which is bundled with GeneValidator.
 
 ```bash
+# Requires jq 1.5
 
 # Extract sequences that have an overall score of 100
-$ json -f INPUT_JSON_FILE -c 'this.overall_score == 100' > OUTPUT_JSON_FILE
+$ jq '.[] | select(.overall_score == 100)' INPUT_JSON_FILE > OUTPUT_JSON_FILE
 
 # Extract sequences that have an overall score of over 70
-$ json -f INPUT_JSON_FILE -c 'this.overall_score > 70' > OUTPUT_JSON_FILE
+$ jq '.[] | select(.overall_score == 70)' INPUT_JSON_FILE > OUTPUT_JSON_FILE
 
 # Extract sequences that have more than 50 hits
-$ json -f INPUT_JSON_FILE -c 'this.no_hits > 50' > OUTPUT_JSON_FILE
+$ jq '.[] | select(.no_hits > 50)' INPUT_JSON_FILE > OUTPUT_JSON_FILE
 
 # Sort the JSON based on the overall score (ascending - 0 to 100)
-$ 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
-
+$ jq 'sort_by(.overall_score)' INPUT_JSON_FILE > OUTPUT_JSON_FILE
 # Sort the JSON based on the overall score (decending - 100 to 0)
-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
+$ jq 'sort_by(- .overall_score)' INPUT_JSON_FILE > OUTPUT_JSON_FILE
+
+# Remove the large graphs objects (note these Graphs objects are required if you wish to pass the json back into GV using the `-j` option - see below)
+$ jq --raw-output '[ .[] | del(.validations[].graphs) ]' INPUT_JSON_FILE > 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
+genevalidator -j OUTPUT_JSON_FILE
 ```
 
-
-## Related projects
-[GeneValidatorApp](https://github.com/wurmlab/GeneValidatorApp) - A Web App wrapper for GeneValidator.<br>
-[GeneValidatorApp-API](https://github.com/wurmlab/GeneValidatorApp-API) - An easy to use API for GeneValidatorApp to allow you to use GeneValidator within your web applications.