diff --git a/.dockerignore b/.dockerignore
index c712142f..96c8053c 100644
--- a/.dockerignore
+++ b/.dockerignore
@@ -1,5 +1,6 @@
 # Git
-#.git
+.git
+.github
 .gitignore
 # Logs
 log/*
@@ -8,3 +9,9 @@ tmp/*
 # Editor temp files
 *.swp
 *.swo
+coverage
+create_permissions.log
+# Ignore generated test data
+test/data/dictionary.txt
+test/data/ontology_files/repo/**/*
+test/data/tmp/*
diff --git a/.github/workflows/docker-image.yml b/.github/workflows/docker-image.yml
new file mode 100644
index 00000000..6105c1d8
--- /dev/null
+++ b/.github/workflows/docker-image.yml
@@ -0,0 +1,42 @@
+name: Docker Image CI
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  push_to_registry:
+    name: Push Docker image to Docker Hub
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out the repo
+        uses: actions/checkout@v3
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v2
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+
+      - name: Log in to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v4
+        with:
+          images: bioportal/ncbo_cron
+
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v4
+        with:
+          context: .
+          platforms: linux/amd64,linux/arm64
+          build-args: |
+            RUBY_VERSION=2.7
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
diff --git a/.github/workflows/ruby-unit-tests.yml b/.github/workflows/ruby-unit-tests.yml
index cde331e3..b61ce745 100644
--- a/.github/workflows/ruby-unit-tests.yml
+++ b/.github/workflows/ruby-unit-tests.yml
@@ -7,18 +7,17 @@ on:
 jobs:
   test:
     strategy:
+      fail-fast: false
       matrix:
-        backend: ['ruby', 'ruby-agraph'] # ruby runs tests with 4store backend and ruby-agraph runs with AllegroGraph backend
+        backend: ['ncbo_cron', 'ncbo_cron-agraph'] # ruby runs tests with 4store backend and ruby-agraph runs with AllegroGraph backend
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v3
     - name: copy config.rb file from template
       run:  cp config/config.test.rb config/config.rb
     - name: Build docker-compose
-      working-directory: ./test
       run: docker-compose build
     - name: Run unit tests
-      working-directory: ./test
       run: |
         ci_env=`bash <(curl -s https://codecov.io/env)`
         docker-compose run $ci_env -e CI --rm ${{ matrix.backend }} bundle exec rake test TESTOPTS='-v'
diff --git a/.gitignore b/.gitignore
index c98b8d52..3fdd0c6d 100644
--- a/.gitignore
+++ b/.gitignore
@@ -5,6 +5,8 @@ config/config.rb
 config/appliance.rb
 config/config_*.rb
 config/*.p12
+config/*.json
+data/
 projectFilesBackup/
 .ruby-version
 repo*
diff --git a/Dockerfile b/Dockerfile
index cd191621..dfc03492 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -20,4 +20,6 @@ ENV BUNDLE_PATH=/srv/ontoportal/bundle
 RUN bundle install
 
 COPY . /srv/ontoportal/ncbo_cron
+RUN cp /srv/ontoportal/ncbo_cron/config/config.rb.sample /srv/ontoportal/ncbo_cron/config/config.rb
+
 CMD ["/bin/bash"]
diff --git a/Gemfile b/Gemfile
index b771aaf8..c4fbe255 100644
--- a/Gemfile
+++ b/Gemfile
@@ -2,13 +2,11 @@ source 'https://rubygems.org'
 
 gemspec
 
-gem 'faraday', '~> 1.9'
 gem 'ffi'
-gem "google-apis-analytics_v3"
+gem 'google-analytics-data'
 gem 'mail', '2.6.6'
-gem 'minitest', '< 5.0'
 gem 'multi_json'
-gem 'oj', '~> 2.0'
+gem 'oj', '~> 3.0'
 gem 'parseconfig'
 gem 'pony'
 gem 'pry'
@@ -28,8 +26,8 @@ gem 'ncbo_annotator', github: 'ontoportal-lirmm/ncbo_annotator', branch: 'master
 # Testing
 group :test do
   gem 'email_spec'
+  gem 'minitest', '< 5.0'
   gem 'simplecov'
   gem 'simplecov-cobertura' # for codecov.io
   gem 'test-unit-minitest'
 end
-
diff --git a/Gemfile.lock b/Gemfile.lock
index 41535bd7..025d10f0 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -60,7 +60,7 @@ PATH
     ncbo_cron (0.0.1)
       dante
       goo
-      google-apis-analytics_v3
+      google-analytics-data
       mlanett-redis-lock
       multi_json
       ncbo_annotator
@@ -83,7 +83,6 @@ GEM
     connection_pool (2.4.1)
     cube-ruby (0.0.3)
     dante (0.2.0)
-    declarative (0.0.20)
     docile (1.4.0)
     domain_name (0.5.20190701)
       unf (>= 0.0.5, < 1.0.0)
@@ -103,17 +102,9 @@ GEM
       faraday-rack (~> 1.0)
       faraday-retry (~> 1.0)
       ruby2_keywords (>= 0.0.4)
-    faraday-em_http (1.0.0)
-    faraday-em_synchrony (1.0.0)
-    faraday-excon (1.1.0)
-    faraday-httpclient (1.0.1)
-    faraday-multipart (1.0.4)
-      multipart-post (~> 2)
-    faraday-net_http (1.0.1)
-    faraday-net_http_persistent (1.2.0)
-    faraday-patron (1.0.0)
-    faraday-rack (1.0.0)
-    faraday-retry (1.0.3)
+    faraday-net_http (3.0.2)
+    faraday-retry (2.2.0)
+      faraday (~> 2.0)
     ffi (1.15.5)
     google-apis-analytics_v3 (0.13.0)
       google-apis-core (>= 0.11.0, < 2.a)
@@ -129,15 +120,22 @@ GEM
     googleauth (1.7.0)
       faraday (>= 0.17.3, < 3.a)
       jwt (>= 1.4, < 3.0)
-      memoist (~> 0.16)
       multi_json (~> 1.11)
       os (>= 0.9, < 2.0)
       signet (>= 0.16, < 2.a)
+    grpc (1.58.0)
+      google-protobuf (~> 3.23)
+      googleapis-common-protos-types (~> 1.0)
+    grpc (1.58.0-x86_64-darwin)
+      google-protobuf (~> 3.23)
+      googleapis-common-protos-types (~> 1.0)
+    grpc (1.58.0-x86_64-linux)
+      google-protobuf (~> 3.23)
+      googleapis-common-protos-types (~> 1.0)
     htmlentities (4.3.4)
     http-accept (1.7.0)
     http-cookie (1.0.5)
       domain_name (~> 0.5)
-    httpclient (2.8.3)
     i18n (0.9.5)
       concurrent-ruby (~> 1.0)
     json (2.6.3)
@@ -151,9 +149,8 @@ GEM
       systemu (~> 2.6.5)
     mail (2.6.6)
       mime-types (>= 1.16, < 4)
-    memoist (0.16.2)
     method_source (1.0.0)
-    mime-types (3.4.1)
+    mime-types (3.5.1)
       mime-types-data (~> 3.2015)
     mime-types-data (3.2023.0218.1)
     mini_mime (1.1.2)
@@ -164,7 +161,7 @@ GEM
     multipart-post (2.3.0)
     net-http-persistent (2.9.4)
     netrc (0.11.0)
-    oj (2.18.5)
+    oj (3.16.1)
     omni_logger (0.1.4)
       logger
     os (1.1.4)
@@ -196,8 +193,7 @@ GEM
       http-cookie (>= 1.0.2, < 2.0)
       mime-types (>= 1.16, < 4.0)
       netrc (~> 0.8)
-    retriable (3.1.2)
-    rexml (3.2.5)
+    rexml (3.2.6)
     rsolr (2.5.0)
       builder (>= 2.1.2)
       faraday (>= 0.9, < 3, != 2.0.0)
@@ -206,7 +202,7 @@ GEM
     rubyzip (2.3.2)
     rufus-scheduler (2.0.24)
       tzinfo (>= 0.3.22)
-    signet (0.17.0)
+    signet (0.18.0)
       addressable (~> 2.8)
       faraday (>= 0.17.5, < 3.a)
       jwt (>= 1.5, < 3.0)
@@ -228,7 +224,6 @@ GEM
     trailblazer-option (0.1.2)
     tzinfo (2.0.6)
       concurrent-ruby (~> 1.0)
-    uber (0.1.0)
     unf (0.1.4)
       unf_ext
     unf_ext (0.0.8.2)
@@ -242,16 +237,15 @@ PLATFORMS
 DEPENDENCIES
   cube-ruby
   email_spec
-  faraday (~> 1.9)
   ffi
   goo!
-  google-apis-analytics_v3
+  google-analytics-data
   mail (= 2.6.6)
   minitest (< 5.0)
   multi_json
   ncbo_annotator!
   ncbo_cron!
-  oj (~> 2.0)
+  oj (~> 3.0)
   ontologies_linked_data!
   parseconfig
   pony
diff --git a/bin/ncbo_cron b/bin/ncbo_cron
index a7fbc686..397d726d 100755
--- a/bin/ncbo_cron
+++ b/bin/ncbo_cron
@@ -111,19 +111,9 @@ opt_parser = OptionParser.new do |opts|
   opts.on("--disable-update-check", "disable check for updated version of Ontoportal (for VMs)", "(default: #{options[:enable_update_check]})") do |v|
     options[:enable_update_check] = false
   end
-
-
-
-
-  opts.on("--disable-dictionary-generation", "disable mgrep dictionary generation job", "(default: #{options[:enable_dictionary_generation]})") do |v|
-    options[:enable_dictionary_generation] = false
+  opts.on("--enable-dictionary-generation-cron-job", "ENABLE mgrep dictionary generation JOB and DISABLE dictionary generation during ontology processing. If this is not passed in, dictionary is generated every time an ontology is processed.", "(default: Dictionary is generated on every ontology processing, CRON job is DISABLED)") do |v|
+    options[:enable_dictionary_generation_cron_job] = true
   end
-
-
-
-
-
-
   opts.on("--disable-obofoundry_sync", "disable OBO Foundry synchronization report", "(default: #{options[:enable_obofoundry_sync]})") do |v|
     options[:enable_obofoundry_sync] = false
   end
@@ -166,18 +156,10 @@ opt_parser = OptionParser.new do |opts|
   opts.on("--obofoundry_sync SCHED", String, "cron schedule to run OBO Foundry synchronization report", "(default: #{options[:cron_obofoundry_sync]})") do |c|
     options[:cron_obofoundry_sync] = c
   end
-
-
-
-
-  opts.on("--dictionary-generation SCHED", String, "cron schedule to run mgrep dictionary generation job", "(default: #{options[:cron_dictionary_generation]})") do |c|
-    options[:cron_dictionary_generation] = c
+  opts.on("--dictionary-generation-cron-job SCHED", String, "cron schedule to run mgrep dictionary generation job (if enabled)", "(default: #{options[:cron_dictionary_generation_cron_job]})") do |c|
+    options[:cron_dictionary_generation_cron_job] = c
   end
 
-
-
-
-
   # Display the help screen, all programs are assumed to have this option.
   opts.on_tail('--help', 'Display this screen') do
     puts opts
@@ -507,49 +489,27 @@ runner.execute do |opts|
     end
   end
 
-
-
-
-
-
-
-
-  # temporary job to generate mgrep dictionary file
+  # optional job to generate mgrep dictionary file
   # separate from ontology processing due to
   # https://github.com/ncbo/ncbo_cron/issues/45
-
-  if options[:enable_dictionary_generation]
+  if options[:enable_dictionary_generation_cron_job]
     dictionary_generation_thread = Thread.new do
       dictionary_generation_options = options.dup
-      dictionary_generation_options[:job_name] = "ncbo_cron_dictionary_generation"
+      dictionary_generation_options[:job_name] = "ncbo_cron_dictionary_generation_cron_job"
       dictionary_generation_options[:scheduler_type] = :cron
-      dictionary_generation_options[:cron_schedule] = dictionary_generation_options[:cron_dictionary_generation]
-      logger.info "Setting up mgrep dictionary generation job with #{dictionary_generation_options[:cron_dictionary_generation]}"; logger.flush
+      dictionary_generation_options[:cron_schedule] = dictionary_generation_options[:cron_dictionary_generation_cron_job]
+      logger.info "Setting up mgrep dictionary generation job with #{dictionary_generation_options[:cron_dictionary_generation_cron_job]}"; logger.flush
       NcboCron::Scheduler.scheduled_locking_job(dictionary_generation_options) do
-        logger.info "Starting mgrep dictionary generation..."; logger.flush
+        logger.info "Starting mgrep dictionary generation CRON job..."; logger.flush
         t0 = Time.now
         annotator = Annotator::Models::NcboAnnotator.new
         annotator.generate_dictionary_file()
-        logger.info "mgrep dictionary generation job completed in #{Time.now - t0} sec."; logger.flush
-        logger.info "Finished mgrep dictionary generation"; logger.flush
+        logger.info "mgrep dictionary generation CRON job completed in #{Time.now - t0} sec."; logger.flush
+        logger.info "Finished mgrep dictionary generation CRON job"; logger.flush
       end
     end
   end
 
-
-
-
-
-
-
-
-
-
-
-
-
-
-
   # Print running child processes
   require 'sys/proctable'
   at_exit do
@@ -573,12 +533,5 @@ runner.execute do |opts|
   mapping_counts_thread.join if mapping_counts_thread
   update_check_thread.join if update_check_thread
   obofoundry_sync_thread.join if obofoundry_sync_thread
-
-
-
-
   dictionary_generation_thread.join if dictionary_generation_thread
-
-
-
 end
diff --git a/bin/ncbo_ontology_annotate_generate_cache b/bin/ncbo_ontology_annotate_generate_cache
index b030bafb..b341e5af 100755
--- a/bin/ncbo_ontology_annotate_generate_cache
+++ b/bin/ncbo_ontology_annotate_generate_cache
@@ -49,7 +49,7 @@ opt_parser = OptionParser.new do |opts|
     options[:generate_dictionary] = true
   end
 
-  options[:logfile] = "logs/annotator_cache.log"
+  options[:logfile] = STDOUT
   opts.on('-l', '--logfile FILE', "Write log to FILE (default is 'logs/annotator_cache.log').") do |filename|
     options[:logfile] = filename
   end
diff --git a/bin/ncbo_ontology_archive_old_submissions b/bin/ncbo_ontology_archive_old_submissions
index 7a8e5950..535c129e 100755
--- a/bin/ncbo_ontology_archive_old_submissions
+++ b/bin/ncbo_ontology_archive_old_submissions
@@ -11,52 +11,121 @@ require_relative '../lib/ncbo_cron'
 config_exists = File.exist?(File.expand_path('../../config/config.rb', __FILE__))
 abort("Please create a config/config.rb file using the config/config.rb.sample as a template") unless config_exists
 require_relative '../config/config'
-
 require 'optparse'
-options = {}
-options[:force_archiving] = false
 
+options = { delete: false }
 opt_parser = OptionParser.new do |opts|
-  options[:ontology] = false
-  opts.on('-f', '--force-re-archiving', 'Force to re-archive already archived submissions.') do
-    options[:force_archiving] = true
+  # Set a banner, displayed at the top of the help screen.
+  opts.banner = "Usage: #{File.basename(__FILE__)} [options]"
+
+  options[:logfile] = STDOUT
+  opts.on( '-l', '--logfile FILE', "Write log to FILE (default is STDOUT)" ) do |filename|
+    options[:logfile] = filename
+  end
+
+  # Delete submission if it contains bad data
+  opts.on( '-d', '--delete', "Delete submissions that contain bad data" ) do
+    options[:delete] = true
   end
 
   # Display the help screen, all programs are assumed to have this option.
-  opts.on('-h', '--help', 'Display this screen') do
+  opts.on( '-h', '--help', 'Display this screen' ) do
     puts opts
     exit
   end
 end
 
 opt_parser.parse!
-
-logfile = 'archive_old_submissions.log'
-if File.file?(logfile);
-  File.delete(logfile);
-end
+logfile = options[:logfile]
+if File.file?(logfile); File.delete(logfile); end
 logger = Logger.new(logfile)
-options = { process_rdf: false, index_search: false, index_commit: false,
-            run_metrics: false, reasoning: false, archive: true }
+process_actions = { process_rdf: false, generate_labels: false, index_search: false, index_commit: false,
+            process_annotator: false, diff: false, run_metrics: false, archive: true }
 onts = LinkedData::Models::Ontology.all
 onts.each { |ont| ont.bring(:acronym, :submissions) }
 onts.sort! { |a, b| a.acronym <=> b.acronym }
-force_archiving = options[:force_archiving]
+bad_submissions = {}
+
 onts.each do |ont|
   latest_sub = ont.latest_submission
+
   unless latest_sub.nil?
     id = latest_sub.submissionId
     subs = ont.submissions
-    old_subs = subs.reject { |sub| sub.submissionId >= id }
+
+    old_subs = subs.reject { |sub|
+      begin
+        sub.submissionId >= id
+      rescue => e
+        msg = "Invalid submission ID detected (String instead of Integer): #{ont.acronym}/#{sub.submissionId} - #{e.class}:\n#{e.backtrace.join("\n")}"
+        puts msg
+        logger.error(msg)
+
+        if options[:delete]
+          sub.delete if options[:delete]
+          msg = "Deleted submission #{ont.acronym}/#{sub.submissionId} due to invalid Submission ID"
+          puts msg
+          logger.error(msg)
+        end
+        bad_submissions["#{ont.acronym}/#{sub.submissionId}"] = "Invalid Submission ID"
+        true
+      end
+    }
     old_subs.sort! { |a, b| a.submissionId <=> b.submissionId }
     old_subs.each do |sub|
-      if !sub.archived? || force_archiving
-        msg = "#{ont.acronym}: archive old submission with ID #{sub.submissionId}."
+      unless sub.archived?
+        msg = "#{ont.acronym}: found un-archived old submission with ID #{sub.submissionId}."
         puts msg
         logger.info msg
-        NcboCron::Models::OntologySubmissionParser.new.process_submission(logger, sub.id.to_s, options)
+
+        begin
+          NcboCron::Models::OntologySubmissionParser.new.process_submission(logger, sub.id.to_s, process_actions)
+        rescue => e
+          if e.class == Goo::Base::NotValidException
+            if sub.valid?
+              msg = "Error archiving submission #{ont.acronym}/#{sub.submissionId} - #{e.class}:\n#{e.backtrace.join("\n")}"
+              puts msg
+              logger.error(msg)
+              bad_submissions["#{ont.acronym}/#{sub.submissionId}"] = "Submission passes valid check but cannot be saved"
+            else
+              msg = "Error archiving submission #{ont.acronym}/#{sub.submissionId}:\n#{JSON.pretty_generate(sub.errors)}"
+              puts msg
+              logger.error(msg)
+
+              if options[:delete]
+                sub.delete if options[:delete]
+                msg = "Deleted submission #{ont.acronym}/#{sub.submissionId} due to invalid data"
+                puts msg
+                logger.error(msg)
+              end
+              bad_submissions["#{ont.acronym}/#{sub.submissionId}"] = "Submission is not valid to be saved"
+            end
+          else
+            msg = "Error archiving submission #{ont.acronym}/#{sub.submissionId} - #{e.class}:\n#{e.backtrace.join("\n")}"
+            puts msg
+            logger.error(msg)
+
+            if options[:delete] && (e.class == Net::HTTPBadResponse || e.class == Errno::ECONNREFUSED)
+              sub.delete
+              msg = "Deleted submission #{ont.acronym}/#{sub.submissionId} due to a non-working pull URL"
+              puts msg
+              logger.error(msg)
+            end
+            bad_submissions["#{ont.acronym}/#{sub.submissionId}"] = "#{e.class} - Runtime error"
+          end
+        end
       end
     end
   end
 end
 
+msg = JSON.pretty_generate(bad_submissions)
+puts
+puts msg
+logger.error(msg)
+
+msg = "Number of errored submissions: #{bad_submissions.length}"
+puts msg
+logger.error(msg)
+
+
diff --git a/bin/ncbo_ontology_import b/bin/ncbo_ontology_import
index db2e90c5..57d63aa1 100755
--- a/bin/ncbo_ontology_import
+++ b/bin/ncbo_ontology_import
@@ -20,27 +20,27 @@ require 'net/http'
 require 'optparse'
 ontologies_acronyms = ''
 ontology_source = ''
-source_api = ''
+source_apikey = ''
 username = ''
 opt_parser = OptionParser.new do |opts|
   opts.banner = 'Usage: ncbo_ontology_import [options]'
-  opts.on('-o', '--ontology ACRONYM', 'Ontologies acronyms which we want to import (separated by comma)') do |acronym|
+  opts.on('-o', '--ontologies ACRONYM1,ACRONYM2', 'Comma-separated list of ontologies to import') do |acronym|
     ontologies_acronyms = acronym
   end
 
-  opts.on('--from url', 'The ontoportal api url source of the ontology') do |url|
+  opts.on('--from URL', 'The ontoportal api url source of the ontology') do |url|
     ontology_source = url.to_s
   end
 
-  opts.on('--from-api api', 'An apikey to acces the ontoportal api') do |api|
-    source_api = api.to_s
+  opts.on('--from-apikey APIKEY', 'An apikey to acces the ontoportal api') do |apikey|
+    source_apikey = apikey.to_s
   end
 
-  opts.on('--admin-user username', 'The target admin user that will submit the ontology') do |user|
+  opts.on('--admin-user USERNAME', 'The target admin user that will submit the ontology') do |user|
     username = user.to_s
   end
   # Display the help screen, all programs are assumed to have this option.
-  opts.on( '-h', '--help', 'Display this screen') do
+  opts.on('-h', '--help', 'Display this screen') do
     puts opts
     exit
   end
@@ -48,9 +48,8 @@ end
 opt_parser.parse!
 
 # URL of the API and APIKEY of the Ontoportal  we want to import data FROM
-SOURCE_API =  ontology_source
-SOURCE_APIKEY =  source_api
-
+SOURCE_API = ontology_source
+SOURCE_APIKEY = source_apikey
 
 # The username of the user that will have the administration rights on the ontology on the target portal
 TARGETED_PORTAL_USER = username
@@ -58,17 +57,15 @@ TARGETED_PORTAL_USER = username
 # The list of acronyms of ontologies to import
 ONTOLOGIES_TO_IMPORT = ontologies_acronyms.split(',') || []
 
-
 def get_user(username)
   user = LinkedData::Models::User.find(username).first
   raise "The user #{username} does not exist" if user.nil?
+
   user.bring_remaining
 end
 
-
 # A function to create a new ontology (if already Acronym already existing on the portal it will return HTTPConflict)
 def create_ontology(ont_info)
-
   new_ontology = LinkedData::Models::Ontology.new
 
   new_ontology.acronym = ont_info['acronym']
@@ -97,23 +94,30 @@ def upload_submission(sub_info, ontology)
   # Build the json body
   # hasOntologyLanguage options: OWL, UMLS, SKOS, OBO
   # status: alpha, beta, production, retired
-  attr_to_reject = %w[id submissionStatus hasOntologyLanguage metrics ontology @id @type contact]
-  to_copy = sub_info.select do |k,v|
+  attr_to_reject = %w[id submissionStatus hasOntologyLanguage metrics ontology @id @type contact uploadFilePath diffFilePath]
+  to_copy = sub_info.select do |k, v|
     !v.nil? && !v.is_a?(Hash) && !v.to_s.empty? && !attr_to_reject.include?(k)
   end
   to_copy["ontology"] = ontology
-  to_copy["contact"] =  [LinkedData::Models::Contact.where(email: USER.email).first]
-  to_copy["hasOntologyLanguage"] =  LinkedData::Models::OntologyFormat.where(acronym: sub_info["hasOntologyLanguage"]).first
+
+  contact = LinkedData::Models::Contact.where(email: USER.email).first
+  unless contact
+    contact = LinkedData::Models::Contact.new(name: USER.username, email: USER.email).save
+    puts "created a new contact; name: #{USER.username}, email: #{USER.email}"
+  end
+
+  to_copy["contact"] = [contact]
+  to_copy["hasOntologyLanguage"] = LinkedData::Models::OntologyFormat.where(acronym: sub_info["hasOntologyLanguage"]).first
 
   to_copy.each do |key, value|
     attribute_settings = new_submission.class.attribute_settings(key.to_sym)
 
     if attribute_settings
-      if  attribute_settings[:enforce]&.include?(:date_time)
+      if attribute_settings[:enforce]&.include?(:date_time)
         value = DateTime.parse(value)
       elsif attribute_settings[:enforce]&.include?(:uri) && attribute_settings[:enforce]&.include?(:list)
         value = value.map { |v| RDF::IRI.new(v) }
-      elsif  attribute_settings[:enforce]&.include?(:uri)
+      elsif attribute_settings[:enforce]&.include?(:uri)
         value = RDF::IRI.new(value)
       end
     end
@@ -124,12 +128,11 @@ def upload_submission(sub_info, ontology)
   new_submission
 end
 
-
 USER = get_user username
-#get apikey for admin user
+# get apikey for admin user
 TARGET_APIKEY = USER.apikey
 
-SOURCE_APIKEY == '' && abort('--from-api has to be set')
+SOURCE_APIKEY == '' && abort('--from-apikey has to be set')
 SOURCE_API == '' && abort('--from has to be set')
 
 def result_log(ressource, errors)
@@ -143,10 +146,11 @@ end
 # Go through all ontologies acronym and get their latest_submission informations
 ONTOLOGIES_TO_IMPORT.each do |ont|
   sub_info = JSON.parse(Net::HTTP.get(URI.parse("#{SOURCE_API}/ontologies/#{ont}/latest_submission?apikey=#{SOURCE_APIKEY}&display=all")))
-  puts "Import #{ont} " ,
+  puts "Import #{ont} ",
        "From #{SOURCE_API}"
   # if the ontology is already created then it will return HTTPConflict, no consequences
   raise "The ontology #{ont} does not exist" if sub_info['ontology'].nil?
+
   new_ontology = create_ontology(sub_info['ontology'])
   errors = nil
   if new_ontology.valid?
@@ -159,6 +163,7 @@ ONTOLOGIES_TO_IMPORT.each do |ont|
 
   new_ontology ||= LinkedData::Models::Ontology.where(acronym: ont).first
   new_submission = upload_submission(sub_info, new_ontology)
+
   if new_submission.valid?
     new_submission.save
     errors = nil
@@ -167,6 +172,3 @@ ONTOLOGIES_TO_IMPORT.each do |ont|
   end
   result_log(sub_info["id"], errors)
 end
-
-
-
diff --git a/bin/ncbo_ontology_process b/bin/ncbo_ontology_process
index 05a1169b..e9b68182 100755
--- a/bin/ncbo_ontology_process
+++ b/bin/ncbo_ontology_process
@@ -31,9 +31,14 @@ opt_parser = OptionParser.new do |opts|
   end
 
   options[:tasks] = NcboCron::Models::OntologySubmissionParser::ACTIONS
-  opts.on('-t', '--tasks process_rdf,index_search,run_metrics', "Optional comma-separated list of processing tasks to perform. Default: #{NcboCron::Models::OntologySubmissionParser::ACTIONS.keys.join(',')}") do |tasks|
-    t = tasks.split(",").map {|t| t.strip.sub(/^:/, '').to_sym}
-    options[:tasks].each {|k, _| options[:tasks][k] = false unless t.include?(k)}
+  opts.on('-t', '--tasks process_rdf,generate_labels=false,index_search,run_metrics', "Optional comma-separated list of processing tasks to perform (or exclude). Default: #{NcboCron::Models::OntologySubmissionParser::ACTIONS.keys.join(',')}") do |tasks|
+    tasks_obj = {}
+    tasks.split(',').each { |t|
+      t_arr = t.gsub(/\s+/, '').gsub(/^:/, '').split('=')
+      tasks_obj[t_arr[0].to_sym] = (t_arr.length <= 1 || t_arr[1].downcase === 'true')
+    }
+    tasks_obj[:generate_labels] = true if tasks_obj[:process_rdf] && !tasks_obj.has_key?(:generate_labels)
+    options[:tasks].each {|k, _| options[:tasks][k] = false unless tasks_obj[k]}
   end
 
   options[:logfile] = STDOUT
diff --git a/config/config.rb.sample b/config/config.rb.sample
index b954b77d..ddd8d0d0 100644
--- a/config/config.rb.sample
+++ b/config/config.rb.sample
@@ -1,164 +1,100 @@
-# Sample for Bioportal (with the good subdomain created: sparql.bioportal.lirmm.fr, data.bioportal.lirmm.fr)
+# This file is designed to be used for unit testing with docker-compose
 
-$SITE_URL = "bioportal.lirmm.fr"
+GOO_BACKEND_NAME      = ENV.include?("GOO_BACKEND_NAME")      ? ENV["GOO_BACKEND_NAME"]      : "4store"
+GOO_HOST              = ENV.include?("GOO_HOST")              ? ENV["GOO_HOST"]              : "localhost"
+GOO_PATH_DATA         = ENV.include?("GOO_PATH_DATA")         ? ENV["GOO_PATH_DATA"]         : "/data/"
+GOO_PATH_QUERY        = ENV.include?("GOO_PATH_QUERY")        ? ENV["GOO_PATH_QUERY"]        : "/sparql/"
+GOO_PATH_UPDATE       = ENV.include?("GOO_PATH_UPDATE")       ? ENV["GOO_PATH_UPDATE"]       : "/update/"
+GOO_PORT              = ENV.include?("GOO_PORT")              ? ENV["GOO_PORT"]              : 9000
+MGREP_HOST            = ENV.include?("MGREP_HOST")            ? ENV["MGREP_HOST"]            : "localhost"
+MGREP_PORT            = ENV.include?("MGREP_PORT")            ? ENV["MGREP_PORT"]            : 55555
+MGREP_DICT_PATH       = ENV.include?("MGREP_DICT_PATH")       ? ENV["MGREP_DICT_PATH"]       : "./test/data/dictionary.txt"
+REDIS_GOO_CACHE_HOST  = ENV.include?("REDIS_GOO_CACHE_HOST")  ? ENV["REDIS_GOO_CACHE_HOST"]  : "localhost"
+REDIS_HTTP_CACHE_HOST = ENV.include?("REDIS_HTTP_CACHE_HOST") ? ENV["REDIS_HTTP_CACHE_HOST"] : "localhost"
+REDIS_PERSISTENT_HOST = ENV.include?("REDIS_PERSISTENT_HOST") ? ENV["REDIS_PERSISTENT_HOST"] : "localhost"
+REDIS_PORT            = ENV.include?("REDIS_PORT")            ? ENV["REDIS_PORT"]            : 6379
+REPORT_PATH           = ENV.include?("REPORT_PATH")           ? ENV["REPORT_PATH"]           : "./test/tmp/ontologies_report.json"
+REPOSITORY_FOLDER     = ENV.include?("REPOSITORY_FOLDER")     ? ENV["REPOSITORY_FOLDER"]     : "./test/data/ontology_files/repo"
+REST_URL_PREFIX       = ENV.include?("REST_URL_PREFIX")       ? ENV["REST_URL_PREFIX"]       : "http://localhost:9393"
+SOLR_PROP_SEARCH_URL  = ENV.include?("SOLR_PROP_SEARCH_URL")  ? ENV["SOLR_PROP_SEARCH_URL"]  : "http://localhost:8983/solr/prop_search_core1"
+SOLR_TERM_SEARCH_URL  = ENV.include?("SOLR_TERM_SEARCH_URL")  ? ENV["SOLR_TERM_SEARCH_URL"]  : "http://localhost:8983/solr/term_search_core1"
 
-begin
-  LinkedData.config do |config|
-    config.repository_folder  = "/srv/ncbo/repository"
-    config.goo_host           = "localhost"
-    config.goo_port           = 8081
-    config.search_server_url = "http://localhost:8082/solr/term_search_core1"
-    config.property_search_server_url = "http://localhost:8082/solr/prop_search_core1"
-    config.rest_url_prefix    = "http://data.#{$SITE_URL}/"
-    config.replace_url_prefix = true
-    config.id_url_prefix      = "http://data.bioontology.org/"
-    config.enable_security    = true    # enable private ontologies hiding
-    config.apikey             = ""
-    config.ui_host            = "#{$SITE_URL}"
-    config.sparql_endpoint_url = "http://sparql.#{$SITE_URL}/test"
-    config.enable_monitoring  = false
-    config.cube_host          = "localhost"
-    config.enable_slices      = true
-    config.enable_resource_index  = false
-
-    # Used to define other bioportal that can be mapped to
-    # Example to map to ncbo bioportal : {"ncbo" => {"api" => "http://data.bioontology.org", "ui" => "http://bioportal.bioontology.org", "apikey" => ""}
-    # Then create the mapping using the following class in JSON : "http://purl.bioontology.org/ontology/MESH/C585345": "ncbo:MESH"
-    # Where "ncbo" is the namespace used as key in the interportal_hash
-    config.interportal_hash   = {"ncbo" => {"api" => "http://data.bioontology.org", "ui" => "http://bioportal.bioontology.org", "apikey" => ""},
-                                 "agroportal" => {"api" => "http://data.agroportal.lirmm.fr", "ui" => "http://agroportal.lirmm.fr", "apikey" => ""}}
-
-    # Caches
-    config.http_redis_host    = "localhost"
-    config.http_redis_port    = 6380
-    config.enable_http_cache  = true
-    config.goo_redis_host     = "localhost"
-    config.goo_redis_port     = 6382
-
-    # Email notifications
-    config.enable_notifications   = true
-    config.email_sender           = "notifications@#{$SITE_URL}" # Default sender for emails
-    config.email_override         = "override@example.org" # all email gets sent here. Disable with email_override_disable.
-    config.email_disable_override = true
-    config.smtp_host              = "smtp.lirmm.fr"
-    config.smtp_port              = 25
-    config.smtp_auth_type         = :none # :none, :plain, :login, :cram_md5
-    config.smtp_domain            = "lirmm.fr"
-    # Emails of the instance administrators to get mail notifications when new user or new ontology
-    config.admin_emails           = ["my.mail@example.org"]
-
-    # PURL server config parameters
-    config.enable_purl            = false
-    config.purl_host              = "purl.example.org"
-    config.purl_port              = 80
-    config.purl_username          = "admin"
-    config.purl_password          = "password"
-    config.purl_maintainers       = "admin"
-    config.purl_target_url_prefix = "http://example.org"
-
-    # Ontology Google Analytics Redis
-    # disabled
-    config.ontology_analytics_redis_host = "localhost"
-    config.enable_ontology_analytics = true
-    config.ontology_analytics_redis_port = 6379
+LinkedData.config do |config|
+  config.goo_backend_name              = GOO_BACKEND_NAME.to_s
+  config.goo_host                      = GOO_HOST.to_s
+  config.goo_port                      = GOO_PORT.to_i
+  config.goo_path_query                = GOO_PATH_QUERY.to_s
+  config.goo_path_data                 = GOO_PATH_DATA.to_s
+  config.goo_path_update               = GOO_PATH_UPDATE.to_s
+  config.goo_redis_host                = REDIS_GOO_CACHE_HOST.to_s
+  config.goo_redis_port                = REDIS_PORT.to_i
+  config.http_redis_host               = REDIS_HTTP_CACHE_HOST.to_s
+  config.http_redis_port               = REDIS_PORT.to_i
+  config.ontology_analytics_redis_host = REDIS_PERSISTENT_HOST.to_s
+  config.ontology_analytics_redis_port = REDIS_PORT.to_i
+  config.repository_folder             = REPOSITORY_FOLDER.to_s
+  config.search_server_url             = SOLR_TERM_SEARCH_URL.to_s
+  config.property_search_server_url    = SOLR_PROP_SEARCH_URL.to_s
+#  config.replace_url_prefix            = false
+#  config.rest_url_prefix               = REST_URL_PREFIX.to_s
+   # Used to define other bioportal that can be mapped to
+   # Example to map to ncbo bioportal : {"ncbo" => {"api" => "http://data.bioontology.org", "ui" => "http://bioportal.bioontology.org", "apikey" => ""}
+   # Then create the mapping using the following class in JSON : "http://purl.bioontology.org/ontology/MESH/C585345": "ncbo:MESH"
+   # Where "ncbo" is the namespace used as key in the interportal_hash
+   config.interportal_hash   = {"ncbo" => {"api" => "http://data.bioontology.org", "ui" => "http://bioportal.bioontology.org", "apikey" => ""},
+                                   "agroportal" => {"api" => "http://data.agroportal.lirmm.fr", "ui" => "http://agroportal.lirmm.fr", "apikey" => ""}}
+  
+  # Email notifications.
+  config.enable_notifications    = true
+  config.email_sender            = "sender@domain.com" # Default sender for emails
+  config.email_override          = "test@domain.com" # By default, all email gets sent here.  Disable with email_override_disable.
+  config.smtp_host               = "smtp-unencrypted.stanford.edu"
+  config.smtp_user               = nil
+  config.smtp_password           = nil
+  config.smtp_auth_type          = :none
+  config.smtp_domain             = "localhost.localhost"
 end
 rescue NameError
   puts "(CNFG) >> LinkedData not available, cannot load config"
 end
 
-begin
-  Annotator.config do |config|
-    config.mgrep_dictionary_file   = "/srv/mgrep/dictionary/dictionary.txt"
-    config.stop_words_default_file = "/srv/ncbo/ncbo_cron/config/default_stop_words.txt"
-    config.mgrep_host              = "localhost"
-    config.mgrep_port              = 55555
-    config.mgrep_alt_host          = "localhost"
-    config.mgrep_alt_port          = 55555
-    config.annotator_redis_host    = "localhost"
-    config.annotator_redis_port    = 6379
-    config.annotator_redis_prefix  = ""
-    config.annotator_redis_alt_prefix  = "c2"
-    config.enable_recognizer_param = true
-    # This setting allows you to ask for other recognizer in URL params (if installed and class with "annotate_direct" created). Example: ?recognizer=alvis or mallet
+Annotator.config do |config|
+  config.mgrep_host              ||= "localhost"
+  config.annotator_redis_host  = REDIS_PERSISTENT_HOST.to_s
+  config.annotator_redis_port  = REDIS_PORT.to_i
+  config.mgrep_host            = MGREP_HOST.to_s
+  config.mgrep_port            = MGREP_PORT.to_i
+  config.mgrep_dictionary_file = MGREP_DICT_PATH.to_s
 end
 rescue NameError
   puts "(CNFG) >> Annotator not available, cannot load config"
 end
 
-begin
-  OntologyRecommender.config do |config|
-end
-rescue NameError
-  puts "(CNFG) >> OntologyRecommender not available, cannot load config"
-end
+NcboCron.config do |config|
+  config.redis_host = REDIS_PERSISTENT_HOST.to_s
+  config.redis_port = REDIS_PORT.to_i
+  # Ontologies Report config
+  config.ontology_report_path = REPORT_PATH
 
-begin
-  LinkedData::OntologiesAPI.config do |config|
-    config.enable_unicorn_workerkiller = true
-    config.enable_throttling           = false
-    config.enable_monitoring           = false
-    config.cube_host                   = "localhost"
-    config.http_redis_host             = "localhost"
-    config.http_redis_port             = 6380
-    config.ontology_rank               = ""
-end
-rescue NameError
-    puts "(CNFG) >> OntologiesAPI not available, cannot load config"
-end
+  # do not deaemonize in docker
+  config.daemonize  = false
 
-begin
-  NcboCron.config do |config|
-    config.redis_host                = Annotator.settings.annotator_redis_host
-    config.redis_port                = Annotator.settings.annotator_redis_port
-    # If no URL has been specified when reindexing ontologies, use the following
-    config.search_index_all_url      = "http://localhost:8082/solr/term_search_core2"
-    config.property_search_index_all_url = "http://localhost:8082/solr/prop_search_core2"
+  config.search_index_all_url = "http://localhost:8983/solr/term_search_core2"
+  config.property_search_index_all_url = "http://localhost:8983/solr/prop_search_core2"
 
-    # Minutes between every process new ontologies check
-    config.minutes_between    = 3
-    
-    # Schedules: run every 4 hours, starting at 00:30
-    config.cron_schedule                            = "30 */4 * * *"
-    # Pull schedule: run daily at 6 a.m. (18:00)
-    config.pull_schedule                            = "00 18 * * *"
-    # Pull long schedule for ontology that are pulled less frequently: run weekly on monday at 11 a.m. (23:00)
-    config.pull_schedule_long                       = "00 23 * * 1"
-    config.pull_long_ontologies                     = ["BIOREFINERY", "TRANSMAT", "GO"]
-    # Delete class graphs of archive submissions: run twice per week on tuesday and friday at 10 a.m. (22:00)
-    config.cron_flush                               = "00 22 * * 2,5"
-    # Remove graphs from deleted ontologies when flushing class graphs
-    config.remove_zombie_graphs                     = true
-    # Warmup long time running queries: run every 3 hours (beginning at 00:00)
-    config.cron_warmq                               = "00 */3 * * *"
-    # Create mapping counts schedule: run twice per week on Wednesday and Saturday at 12:30AM
-    config.cron_mapping_counts                      = "30 0 * * 3,6"
-    
-    config.enable_ontologies_report                 = true
-    # Ontologies report generation schedule: run daily at 1:30 a.m.
-    config.cron_ontologies_report                   = "30 1 * * *"
-    # Ontologies Report file location
-    config.ontology_report_path = "/srv/ncbo/reports/ontologies_report.json"
-    
-  # Ontology analytics refresh schedule: run daily at 4:30 a.m.
-    config.cron_ontology_analytics                  = "30 4 * * *"
-    config.enable_ontology_analytics                = true
-    config.analytics_service_account_email_address  = "account-1@bioportal.iam.gserviceaccount.com"
-    config.analytics_path_to_key_file               = "/srv/bioportal-ff92c5b03b63.p12" # you have to get this file from Google
-    config.analytics_profile_id                     = "ga:111823321" # replace with your ga view id
-    config.analytics_app_name                       = "bioportal"
-    config.analytics_app_version                    = "1.0.0"
-    config.analytics_start_date                     = "2015-11-13"
-    # To filter connexions coming from Stanford
-    config.analytics_filter_str                     = "ga:networkLocation!@stanford;ga:networkLocation!@amazon"
+  # Google Analytics GA4 config
+  config.analytics_path_to_key_file     = "config/your_analytics_key.json"
+  config.analytics_property_id          = "123456789"
+  # path to the Universal Analytics data, which stopped collecting on June 1st, 2023
+  config.analytics_path_to_ua_data_file = "data/your_ua_data.json"
+  # path to the file that will hold your Google Analytics data
+  # this is in addition to storing it in Redis
+  config.analytics_path_to_ga_data_file = "data/your_ga_data.json"
 
-    # this is a Base64.encode64 encoded personal access token
-    # you need to run Base64.decode64 on it before using it in your code
-    # this is a workaround because Github does not allow storing access tokens in a repo
-    config.git_repo_access_token = "YOUR GITHUB REPO PERSONAL ACCESS TOKEN, encoded using Base64"
-  end
-rescue NameError
-  #binding.pry
-  puts "(CNFG) >> NcboCron not available, cannot load config"
+  # this is a Base64.encode64 encoded personal access token
+  # you need to run Base64.decode64 on it before using it in your code
+  # this is a workaround because Github does not allow storing access tokens in a repo
+  config.git_repo_access_token = "YOUR GITHUB REPO PERSONAL ACCESS TOKEN, encoded using Base64"
 end
 
 Goo.use_cache = true
diff --git a/config/config.test.rb b/config/config.test.rb
index 0729a4b0..84a621ac 100644
--- a/config/config.test.rb
+++ b/config/config.test.rb
@@ -1,33 +1,42 @@
 # This file is designed to be used for unit testing with docker-compose
-#
-GOO_PATH_QUERY   = ENV.include?("GOO_PATH_QUERY")   ? ENV["GOO_PATH_QUERY"]   : "/sparql/"
-GOO_PATH_DATA    = ENV.include?("GOO_PATH_DATA")    ? ENV["GOO_PATH_DATA"]    : "/data/"
-GOO_PATH_UPDATE  = ENV.include?("GOO_PATH_UPDATE")  ? ENV["GOO_PATH_UPDATE"]  : "/update/"
-GOO_BACKEND_NAME = ENV.include?("GOO_BACKEND_NAME") ? ENV["GOO_BACKEND_NAME"] : "localhost"
-GOO_PORT         = ENV.include?("GOO_PORT")         ? ENV["GOO_PORT"]         : 9000
-GOO_HOST         = ENV.include?("GOO_HOST")         ? ENV["GOO_HOST"]         : "localhost"
-REDIS_HOST       = ENV.include?("REDIS_HOST")       ? ENV["REDIS_HOST"]       : "localhost"
-REDIS_PORT       = ENV.include?("REDIS_PORT")       ? ENV["REDIS_PORT"]       : 6379
-MGREP_HOST       = ENV.include?("MGREP_HOST")       ? ENV["MGREP_HOST"]       : "localhost"
-MGREP_PORT       = ENV.include?("MGREP_PORT")       ? ENV["MGREP_PORT"]       : 55555
-SOLR_TERM_SEARCH_URL = ENV.include?("SOLR_TERM_SEARCH_URL") ? ENV["SOLR_TERM_SEARCH_URL"] : "http://localhost:8983/solr/term_search_core1"
-SOLR_PROP_SEARCH_URL = ENV.include?("SOLR_PROP_SEARCH_URL") ? ENV["SOLR_PROP_SEARCH_URL"] : "http://localhost:8983/solr/prop_search_core1"
+
+GOO_BACKEND_NAME      = ENV.include?("GOO_BACKEND_NAME")      ? ENV["GOO_BACKEND_NAME"]      : "4store"
+GOO_HOST              = ENV.include?("GOO_HOST")              ? ENV["GOO_HOST"]              : "localhost"
+GOO_PATH_DATA         = ENV.include?("GOO_PATH_DATA")         ? ENV["GOO_PATH_DATA"]         : "/data/"
+GOO_PATH_QUERY        = ENV.include?("GOO_PATH_QUERY")        ? ENV["GOO_PATH_QUERY"]        : "/sparql/"
+GOO_PATH_UPDATE       = ENV.include?("GOO_PATH_UPDATE")       ? ENV["GOO_PATH_UPDATE"]       : "/update/"
+GOO_PORT              = ENV.include?("GOO_PORT")              ? ENV["GOO_PORT"]              : 9000
+MGREP_HOST            = ENV.include?("MGREP_HOST")            ? ENV["MGREP_HOST"]            : "localhost"
+MGREP_PORT            = ENV.include?("MGREP_PORT")            ? ENV["MGREP_PORT"]            : 55555
+MGREP_DICT_PATH       = ENV.include?("MGREP_DICT_PATH")       ? ENV["MGREP_DICT_PATH"]       : "./test/data/dictionary.txt"
+REDIS_GOO_CACHE_HOST  = ENV.include?("REDIS_GOO_CACHE_HOST")  ? ENV["REDIS_GOO_CACHE_HOST"]  : "localhost"
+REDIS_HTTP_CACHE_HOST = ENV.include?("REDIS_HTTP_CACHE_HOST") ? ENV["REDIS_HTTP_CACHE_HOST"] : "localhost"
+REDIS_PERSISTENT_HOST = ENV.include?("REDIS_PERSISTENT_HOST") ? ENV["REDIS_PERSISTENT_HOST"] : "localhost"
+REDIS_PORT            = ENV.include?("REDIS_PORT")            ? ENV["REDIS_PORT"]            : 6379
+REPORT_PATH           = ENV.include?("REPORT_PATH")           ? ENV["REPORT_PATH"]           : "./test/tmp/ontologies_report.json"
+REPOSITORY_FOLDER     = ENV.include?("REPOSITORY_FOLDER")     ? ENV["REPOSITORY_FOLDER"]     : "./test/data/ontology_files/repo"
+REST_URL_PREFIX       = ENV.include?("REST_URL_PREFIX")       ? ENV["REST_URL_PREFIX"]       : "http://localhost:9393"
+SOLR_PROP_SEARCH_URL  = ENV.include?("SOLR_PROP_SEARCH_URL")  ? ENV["SOLR_PROP_SEARCH_URL"]  : "http://localhost:8983/solr/prop_search_core1"
+SOLR_TERM_SEARCH_URL  = ENV.include?("SOLR_TERM_SEARCH_URL")  ? ENV["SOLR_TERM_SEARCH_URL"]  : "http://localhost:8983/solr/term_search_core1"
 
 LinkedData.config do |config|
+  config.goo_backend_name              = GOO_BACKEND_NAME.to_s
   config.goo_host                      = GOO_HOST.to_s
   config.goo_port                      = GOO_PORT.to_i
-  config.goo_backend_name              = GOO_BACKEND_NAME.to_s
   config.goo_path_query                = GOO_PATH_QUERY.to_s
   config.goo_path_data                 = GOO_PATH_DATA.to_s
   config.goo_path_update               = GOO_PATH_UPDATE.to_s
-  config.goo_redis_host                = REDIS_HOST.to_s
+  config.goo_redis_host                = REDIS_GOO_CACHE_HOST.to_s
   config.goo_redis_port                = REDIS_PORT.to_i
-  config.http_redis_host               = REDIS_HOST.to_s
+  config.http_redis_host               = REDIS_HTTP_CACHE_HOST.to_s
   config.http_redis_port               = REDIS_PORT.to_i
-  config.ontology_analytics_redis_host = REDIS_HOST.to_s
+  config.ontology_analytics_redis_host = REDIS_PERSISTENT_HOST.to_s
   config.ontology_analytics_redis_port = REDIS_PORT.to_i
+  config.repository_folder             = REPOSITORY_FOLDER.to_s
   config.search_server_url             = SOLR_TERM_SEARCH_URL.to_s
   config.property_search_server_url    = SOLR_PROP_SEARCH_URL.to_s
+#  config.replace_url_prefix            = false
+#  config.rest_url_prefix               = REST_URL_PREFIX.to_s
   # Email notifications.
   config.enable_notifications    = true
   config.email_sender            = "sender@domain.com" # Default sender for emails
@@ -40,15 +49,21 @@
 end
 
 Annotator.config do |config|
-  config.annotator_redis_host          = REDIS_HOST.to_s
-  config.annotator_redis_port          = REDIS_PORT.to_i
-  config.mgrep_host                    = MGREP_HOST.to_s
-  config.mgrep_port                    = MGREP_PORT.to_i
-  config.mgrep_dictionary_file         = "./test/data/dictionary.txt"
+  config.annotator_redis_host  = REDIS_PERSISTENT_HOST.to_s
+  config.annotator_redis_port  = REDIS_PORT.to_i
+  config.mgrep_host            = MGREP_HOST.to_s
+  config.mgrep_port            = MGREP_PORT.to_i
+  config.mgrep_dictionary_file = MGREP_DICT_PATH.to_s
 end
 
+# LinkedData::OntologiesAPI.config do |config|
+#   config.http_redis_host = REDIS_HTTP_CACHE_HOST.to_s
+#   config.http_redis_port = REDIS_PORT.to_i
+# end
+#
 NcboCron.config do |config|
-  config.redis_host = REDIS_HOST.to_s
+  config.daemonize  = false
+  config.redis_host = REDIS_PERSISTENT_HOST.to_s
   config.redis_port = REDIS_PORT.to_i
-  config.ontology_report_path = "./test/ontologies_report.json"
+  config.ontology_report_path = REPORT_PATH
 end
diff --git a/dip.yml b/dip.yml
new file mode 100644
index 00000000..3bbe4444
--- /dev/null
+++ b/dip.yml
@@ -0,0 +1,54 @@
+version: '7.1'
+
+# Define default environment variables to pass
+# to Docker Compose
+#environment:
+#  RAILS_ENV: development
+
+compose:
+  files:
+    - docker-compose.yml
+    #  project_name: ncbo_cron
+
+interaction:
+  # This command spins up a ncbo_cron container with the required dependencies (solr, 4store, etc),
+  # and opens a terminal within it.
+  runner:
+    description: Open a Bash shell within a ncbo_cron container (with dependencies up)
+    service: ncbo_cron
+    command: /bin/bash
+
+  # Run a container without any dependent services
+  bash:
+    description: Run an arbitrary script within a container (or open a shell without deps)
+    service: ncbo_cron
+    command: /bin/bash
+    compose_run_options: [ no-deps ]
+
+  # A shortcut to run Bundler commands
+  bundle:
+    description: Run Bundler commands within ncbo_cron container (with depencendies up)
+    service: ncbo_cron
+    command: bundle
+
+  # A shortcut to run unit tests
+  test:
+    description: Run unit tests with 4store triplestore
+    service: ncbo_cron
+    command: bundle exec rake test TESTOPTS='-v'
+
+  test-ag:
+    description: Run unit tests with AllegroGraph triplestore
+    service: ncbo_cron-agraph
+    command: bundle exec rake test TESTOPTS='-v'
+
+  'redis-cli':
+    description: Run Redis console
+    service: redis-ut
+    command: redis-cli -h redis-ut
+
+#provision:
+  #- dip compose down --volumes
+  #- dip compose up -d solr 4store
+  #- dip bundle install
+  #- dip bash -c bin/setup
diff --git a/test/docker-compose.yml b/docker-compose.yml
similarity index 50%
rename from test/docker-compose.yml
rename to docker-compose.yml
index db957907..0045ce12 100644
--- a/test/docker-compose.yml
+++ b/docker-compose.yml
@@ -1,43 +1,47 @@
 x-app: &app
-    build:
-      context: ../.
-      args:
-        RUBY_VERSION: '2.7'
-    # Increase the version number in the image tag every time Dockerfile or its arguments is changed
-    image: ncbo_cron-dev:0.0.1
-    environment: &env
-      # default bundle config resolves to /usr/local/bundle/config inside of the container
-      # we are setting it to local app directory if we need to use 'bundle config local'
-      BUNDLE_APP_CONFIG: /srv/ontoportal/ncbo_cron/.bundle
-      BUNDLE_PATH: /srv/ontoportal/bundle
-      COVERAGE: 'true' # enable simplecov code coverage
-      REDIS_HOST: redis-ut
-      REDIS_PORT: 6379
-      SOLR_TERM_SEARCH_URL: http://solr-ut:8983/solr/term_search_core1
-      SOLR_PROP_SEARCH_URL: http://solr-ut:8983/solr/prop_search_core1
-      MGREP_HOST: mgrep-ut
-      MGREP_PORT: 55555
-    stdin_open: true
-    tty: true
-    command: /bin/bash
-    volumes:
-      # bundle volume for hosting gems installed by bundle; it speeds up gem install in local development
-      - bundle:/srv/ontoportal/bundle
-      - ../.:/srv/ontoportal/ncbo_cron
-      # mount directory containing development version of the gems if you need to use 'bundle config local'
-      #- /Users/alexskr/ontoportal:/Users/alexskr/ontoportal
-    depends_on: &depends_on
-      solr-ut:
-        condition: service_healthy
-      redis-ut:
-        condition: service_healthy
-      mgrep-ut:
-        condition: service_healthy
-
+  build:
+    context: .
+    args:
+      RUBY_VERSION: '2.7'
+  # Increase the version number in the image tag every time Dockerfile or its arguments is changed
+  image: ncbo_cron:0.0.1
+  environment: &env
+    BUNDLE_PATH: /srv/ontoportal/bundle
+    # default bundle config resolves to /usr/local/bundle/config inside of the container
+    # we are setting it to local app directory if we need to use 'bundle config local'
+    BUNDLE_APP_CONFIG: /srv/ontoportal/ncbo_cron/.bundle
+    COVERAGE: 'true'
+    GOO_REDIS_HOST: redis-ut
+    REDIS_GOO_CACHE_HOST: redis-ut
+    REDIS_HTTP_CACHE_HOST: redis-ut
+    REDIS_PERSISTENT_HOST: redis-ut
+    REDIS_PORT: 6379
+    SOLR_TERM_SEARCH_URL: http://solr-ut:8983/solr/term_search_core1
+    SOLR_PROP_SEARCH_URL: http://solr-ut:8983/solr/prop_search_core1
+    MGREP_HOST: mgrep-ut
+    MGREP_PORT: 55555
+  stdin_open: true
+  tty: true
+  command: "bundle exec rackup -o 0.0.0.0 --port 9393"
+  ports:
+    - 9393:9393
+  volumes:
+    # bundle volume for hosting gems installed by bundle; it helps in local development with gem udpates
+    - bundle:/srv/ontoportal/bundle
+    # ncbo_cron code
+    - .:/srv/ontoportal/ncbo_cron
+    # mount directory containing development version of the gems if you need to use 'bundle config local'
+    #- /Users/alexskr/ontoportal:/Users/alexskr/ontoportal
+  depends_on: &depends_on
+    solr-ut:
+      condition: service_healthy
+    redis-ut:
+      condition: service_healthy
+    mgrep-ut:
+      condition: service_healthy
 
 services:
-  # environment wtih 4store backend
-  ruby:
+  ncbo_cron:
     <<: *app
     environment:
       <<: *env
@@ -54,8 +58,7 @@ services:
       4store-ut:
         condition: service_started
 
-  # environment with AllegroGraph backend
-  ruby-agraph:
+  ncbo_cron-agraph:
     <<: *app
     environment:
       <<: *env
@@ -65,16 +68,15 @@ services:
       GOO_PATH_QUERY: /repositories/bioportal_test
       GOO_PATH_DATA: /repositories/bioportal_test/statements
       GOO_PATH_UPDATE: /repositories/bioportal_test/statements
-      #    profiles:
-        #- agraph
+    profiles:
+      - agraph
     depends_on:
       <<: *depends_on
       agraph-ut:
-        condition: service_started
+        condition: service_healthy
 
   redis-ut:
     image: redis
-    command: ["redis-server", "--save", "", "--appendonly", "no"]
     healthcheck:
       test: redis-cli ping
       interval: 10s
@@ -83,6 +85,8 @@ services:
 
   4store-ut:
     image: bde2020/4store
+    platform: linux/amd64
+    #volume: fourstore:/var/lib/4store
     command: >
       bash -c "4s-backend-setup --segments 4 ontoportal_kb
       && 4s-backend ontoportal_kb
@@ -91,7 +95,7 @@ services:
       - 4store
 
   solr-ut:
-    image: ontoportal/solr-ut:0.1
+    image: ontoportal/solr-ut:0.0.2
     healthcheck:
       test: ["CMD-SHELL", "curl -sf http://localhost:8983/solr/term_search_core1/admin/ping?wt=json | grep -iq '\"status\":\"OK\"}' || exit 1"]
       start_period: 3s
@@ -100,7 +104,8 @@ services:
       retries: 5
 
   mgrep-ut:
-    image: ontoportal/mgrep-ncbo:0.1
+    image: ontoportal/mgrep:0.0.1
+    platform: linux/amd64
     healthcheck:
       test: ["CMD", "nc", "-z", "-v", "localhost", "55555"]
       start_period: 3s
@@ -109,7 +114,9 @@ services:
       retries: 5
 
   agraph-ut:
-    image: franzinc/agraph:v7.3.0
+    #image: franzinc/agraph:v7.3.1
+    image: ontoportal/agraph:v7.3.1-patch1
+    platform: linux/amd64
     environment:
       - AGRAPH_SUPER_USER=test
       - AGRAPH_SUPER_PASSWORD=xyzzy
@@ -122,8 +129,14 @@ services:
        ; agtool users add anonymous
        ; agtool users grant anonymous root:bioportal_test:rw
        ; tail -f /agraph/data/agraph.log"
-       #    profiles:
-         #- agraph
+    healthcheck:
+      test: ["CMD-SHELL", "agtool storage-report bioportal_test || exit 1"]
+      start_period: 10s
+      interval: 60s
+      timeout: 5s
+      retries: 3
+    profiles:
+      - agraph
 
 volumes:
   bundle:
diff --git a/lib/ncbo_cron/config.rb b/lib/ncbo_cron/config.rb
index 798768b2..f7e4acad 100644
--- a/lib/ncbo_cron/config.rb
+++ b/lib/ncbo_cron/config.rb
@@ -42,16 +42,8 @@ def config(&block)
     @settings.enable_spam_deletion ||= true
     # enable update check (vor VMs)
     @settings.enable_update_check ||= true
-
-
-
-
     # enable mgrep dictionary generation job
-    @settings.enable_dictionary_generation ||= true
-
-
-
-
+    @settings.enable_dictionary_generation_cron_job ||= false
 
     # UMLS auto-pull
     @settings.pull_umls_url ||= ""
@@ -94,17 +86,9 @@ def config(&block)
     @settings.cron_obofoundry_sync ||= "0 8 * * 1,2,3,4,5"
     # 00 3 * * * - run daily at 3:00AM
     @settings.cron_update_check ||= "00 3 * * *"
-
-
-
-
     # mgrep dictionary generation schedule
     # 30 3 * * * - run daily at 3:30AM
-    @settings.cron_dictionary_generation ||= "30 3 * * *"
-
-
-
-
+    @settings.cron_dictionary_generation_cron_job ||= "30 3 * * *"
 
     @settings.log_level ||= :info
     unless (@settings.log_path && File.exists?(@settings.log_path))
diff --git a/lib/ncbo_cron/ontology_analytics.rb b/lib/ncbo_cron/ontology_analytics.rb
index 097821fe..3a91b813 100644
--- a/lib/ncbo_cron/ontology_analytics.rb
+++ b/lib/ncbo_cron/ontology_analytics.rb
@@ -1,124 +1,214 @@
 require 'logger'
-require 'google/apis/analytics_v3'
-require 'google/api_client/auth/key_utils'
+require 'json'
+require 'benchmark'
+require 'google/analytics/data'
+
 
 module NcboCron
   module Models
 
     class OntologyAnalytics
-      ONTOLOGY_ANALYTICS_REDIS_FIELD = "ontology_analytics"
+      ONTOLOGY_ANALYTICS_REDIS_FIELD = 'ontology_analytics'
+      UA_START_DATE = '2013-10-01'
+      GA4_START_DATE = '2023-06-01'
 
       def initialize(logger)
         @logger = logger
       end
 
       def run
-        redis = Redis.new(:host => NcboCron.settings.redis_host, :port => NcboCron.settings.redis_port)
+        redis = Redis.new(:host => LinkedData.settings.ontology_analytics_redis_host, :port => LinkedData.settings.ontology_analytics_redis_port)
         ontology_analytics = fetch_ontology_analytics
+        File.open(NcboCron.settings.analytics_path_to_ga_data_file, 'w') do |f|
+          f.write(ontology_analytics.to_json)
+        end
         redis.set(ONTOLOGY_ANALYTICS_REDIS_FIELD, Marshal.dump(ontology_analytics))
       end
 
       def fetch_ontology_analytics
-        google_client = authenticate_google
-        aggregated_results = Hash.new
-        start_year = Date.parse(NcboCron.settings.analytics_start_date).year || 2013
-        ont_acronyms = LinkedData::Models::Ontology.where.include(:acronym).all.map {|o| o.acronym}
-        # ont_acronyms = ["NCIT", "ONTOMA", "CMPO", "AEO", "SNOMEDCT"]
-        filter_str = (NcboCron.settings.analytics_filter_str.nil? || NcboCron.settings.analytics_filter_str.empty?) ? "" : ";#{NcboCron.settings.analytics_filter_str}"
-
-        # If the user add filter through the configuration file
-        if !NcboCron.settings.analytics_filter_str.nil? && NcboCron.settings.analytics_filter_str != ""
-          analytics_filter = ";" + NcboCron.settings.analytics_filter_str
-        else
-          analytics_filter = ""
-        end
+        @logger.info "Starting Google Analytics refresh..."
+        @logger.flush
+        full_data = nil
 
-        ont_acronyms.each do |acronym|
+        time = Benchmark.realtime do
           max_results = 10000
-          num_results = 10000
-          start_index = 1
-          results = nil
-
-          loop do
-            results = google_client.get_ga_data(
-              ids          = NcboCron.settings.analytics_profile_id,
-              start_date   = NcboCron.settings.analytics_start_date,
-              end_date     = Date.today.to_s,
-              metrics      = 'ga:pageviews',
-              {
-                dimensions:  'ga:pagePath,ga:year,ga:month',
-                filters:     "ga:pagePath=~^(\\/ontologies\\/#{acronym})(\\/?\\?{0}|\\/?\\?{1}.*)$#{filter_str}",
-                start_index: start_index,
-                max_results: max_results
-              }
-            )
-            results.rows ||= []
-            start_index += max_results
-            num_results = results.rows.length
-            @logger.info "Acronym: #{acronym}, Results: #{num_results}, Start Index: #{start_index}"
-            @logger.flush
-
-            results.rows.each do |row|
-              if aggregated_results.has_key?(acronym)
-                # year
-                if aggregated_results[acronym].has_key?(row[1].to_i)
-                  # month
-                  if aggregated_results[acronym][row[1].to_i].has_key?(row[2].to_i)
-                    aggregated_results[acronym][row[1].to_i][row[2].to_i] += row[3].to_i
+          aggregated_results = Hash.new
+
+          @logger.info "Fetching all ontology acronyms from backend..."
+          @logger.flush
+          ont_acronyms = LinkedData::Models::Ontology.where.include(:acronym).all.map {|o| o.acronym}
+          # ont_acronyms = ["NCIT", "SNOMEDCT", "MEDDRA"]
+
+          @logger.info "Authenticating with the Google Analytics Endpoint..."
+          @logger.flush
+          google_client = authenticate_google
+
+          date_range = Google::Analytics::Data::V1beta::DateRange.new(
+            start_date: GA4_START_DATE,
+            end_date: Date.today.to_s
+          )
+          metrics_page_views = Google::Analytics::Data::V1beta::Metric.new(
+            name: "screenPageViews"
+          )
+          dimension_path = Google::Analytics::Data::V1beta::Dimension.new(
+            name: "pagePath"
+          )
+          dimension_year = Google::Analytics::Data::V1beta::Dimension.new(
+            name: "year"
+          )
+          dimension_month = Google::Analytics::Data::V1beta::Dimension.new(
+            name: "month"
+          )
+          string_filter = Google::Analytics::Data::V1beta::Filter::StringFilter.new(
+            match_type: Google::Analytics::Data::V1beta::Filter::StringFilter::MatchType::FULL_REGEXP
+          )
+          filter = Google::Analytics::Data::V1beta::Filter.new(
+            field_name: "pagePath",
+            string_filter: string_filter
+          )
+          filter_expression = Google::Analytics::Data::V1beta::FilterExpression.new(
+            filter: filter
+          )
+          order_year = Google::Analytics::Data::V1beta::OrderBy::DimensionOrderBy.new(
+            dimension_name: "year"
+          )
+          orderby_year = Google::Analytics::Data::V1beta::OrderBy.new(
+            desc: false,
+            dimension: order_year
+          )
+          order_month = Google::Analytics::Data::V1beta::OrderBy::DimensionOrderBy.new(
+            dimension_name: "month"
+          )
+          orderby_month = Google::Analytics::Data::V1beta::OrderBy.new(
+            desc: false,
+            dimension: order_month
+          )
+          @logger.info "Fetching GA4 analytics for all ontologies..."
+          @logger.flush
+
+          ont_acronyms.each do |acronym|
+            start_index = 0
+            string_filter.value = "^(\\/ontologies\\/#{acronym})(\\/?\\?{0}|\\/?\\?{1}.*)$"
+
+            loop do
+              request = Google::Analytics::Data::V1beta::RunReportRequest.new(
+                property: "properties/#{NcboCron.settings.analytics_property_id}",
+                metrics: [metrics_page_views],
+                dimension_filter: filter_expression,
+                dimensions: [dimension_path, dimension_year, dimension_month],
+                date_ranges: [date_range],
+                order_bys: [orderby_year, orderby_month],
+                offset: start_index,
+                limit: max_results
+              )
+              response = google_client.run_report request
+
+              response.rows ||= []
+              start_index += max_results
+              num_results = response.rows.length
+              @logger.info "Acronym: #{acronym}, Results: #{num_results}, Start Index: #{start_index}"
+              @logger.flush
+
+              response.rows.each do |row|
+                row_h = row.to_h
+                year_month_hits =  row_h[:dimension_values].map.with_index {
+                  |v, i| i > 0 ? v[:value].to_i.to_s : row_h[:metric_values][0][:value].to_i
+                }.rotate(1)
+
+                if aggregated_results.has_key?(acronym)
+                  # year
+                  if aggregated_results[acronym].has_key?(year_month_hits[0])
+                    # month
+                    if aggregated_results[acronym][year_month_hits[0]].has_key?(year_month_hits[1])
+                      aggregated_results[acronym][year_month_hits[0]][year_month_hits[1]] += year_month_hits[2]
+                    else
+                      aggregated_results[acronym][year_month_hits[0]][year_month_hits[1]] = year_month_hits[2]
+                    end
                   else
-                    aggregated_results[acronym][row[1].to_i][row[2].to_i] = row[3].to_i
+                    aggregated_results[acronym][year_month_hits[0]] = Hash.new
+                    aggregated_results[acronym][year_month_hits[0]][year_month_hits[1]] = year_month_hits[2]
                   end
                 else
-                  aggregated_results[acronym][row[1].to_i] = Hash.new
-                  aggregated_results[acronym][row[1].to_i][row[2].to_i] = row[3].to_i
+                  aggregated_results[acronym] = Hash.new
+                  aggregated_results[acronym][year_month_hits[0]] = Hash.new
+                  aggregated_results[acronym][year_month_hits[0]][year_month_hits[1]] = year_month_hits[2]
                 end
-              else
-                aggregated_results[acronym] = Hash.new
-                aggregated_results[acronym][row[1].to_i] = Hash.new
-                aggregated_results[acronym][row[1].to_i][row[2].to_i] = row[3].to_i
               end
-            end
+              break if num_results < max_results
+            end # loop
+          end # ont_acronyms
+          @logger.info "Refresh complete, merging GA4 and UA data..."
+          @logger.flush
+          full_data = merge_ga4_ua_data(aggregated_results)
+          @logger.info "Merged"
+          @logger.flush
+        end # Benchmark.realtime
+        @logger.info "Completed Google Analytics refresh in #{(time/60).round(1)} minutes."
+        @logger.flush
+        full_data
+      end
 
-            if num_results < max_results
-              # fill up non existent years
-              (start_year..Date.today.year).each do |y|
-                aggregated_results[acronym] = Hash.new if aggregated_results[acronym].nil?
-                aggregated_results[acronym][y] = Hash.new unless aggregated_results[acronym].has_key?(y)
-              end
-              # fill up non existent months with zeros
-              (1..12).each { |n| aggregated_results[acronym].values.each { |v| v[n] = 0 unless v.has_key?(n) } }
-              break
+      def merge_ga4_ua_data(ga4_data)
+        ua_data_file = File.read(NcboCron.settings.analytics_path_to_ua_data_file)
+        ua_data = JSON.parse(ua_data_file)
+        ua_ga4_intersecting_year = Date.parse(GA4_START_DATE).year.to_s
+        ua_ga4_intersecting_month = Date.parse(GA4_START_DATE).month.to_s
+
+        # add up hits for June of 2023 (the only intersecting month between UA and GA4)
+        ua_data.each do |acronym, _|
+          if ga4_data.has_key?(acronym)
+            if ga4_data[acronym][ua_ga4_intersecting_year].has_key?(ua_ga4_intersecting_month)
+              ua_data[acronym][ua_ga4_intersecting_year][ua_ga4_intersecting_month] +=
+                  ga4_data[acronym][ua_ga4_intersecting_year][ua_ga4_intersecting_month]
+              # delete data for June of 2023 from ga4_data to avoid overwriting when merging
+              ga4_data[acronym][ua_ga4_intersecting_year].delete(ua_ga4_intersecting_month)
             end
           end
         end
+        # merge ua and ga4 data
+        merged_data = ua_data.deep_merge(ga4_data)
+        # fill missing years and months
+        fill_missing_data(merged_data)
+        # sort acronyms, years and months
+        sort_ga_data(merged_data)
+      end
 
-        @logger.info "Completed ontology analytics refresh..."
-        @logger.flush
+      def fill_missing_data(ga_data)
+        # fill up non existent years
+        start_year = Date.parse(UA_START_DATE).year
+
+        ga_data.each do |acronym, _|
+          (start_year..Date.today.year).each do |y|
+            ga_data[acronym] = Hash.new if ga_data[acronym].nil?
+            ga_data[acronym][y.to_s] = Hash.new unless ga_data[acronym].has_key?(y.to_s)
+          end
+          # fill up non existent months with zeros
+          (1..12).each { |n| ga_data[acronym].values.each { |v| v[n.to_s] = 0 unless v.has_key?(n.to_s) } }
+        end
+      end
 
-        aggregated_results
+      def sort_ga_data(ga_data)
+        ga_data.transform_values { |value|
+          value.transform_values { |val|
+            val.sort_by { |key, _| key.to_i }.to_h
+          }.sort_by { |k, _| k.to_i }.to_h
+        }.sort.to_h
       end
 
       def authenticate_google
-        Google::Apis::ClientOptions.default.application_name = NcboCron.settings.analytics_app_name
-        Google::Apis::ClientOptions.default.application_version = NcboCron.settings.analytics_app_version
-        # enable google api call retries in order to
-        # minigate analytics processing failure due to ocasional google api timeouts and other outages
-        Google::Apis::RequestOptions.default.retries = 5
-        # uncoment to enable logging for debugging purposes
-        # Google::Apis.logger.level = Logger::DEBUG
-        # Google::Apis.logger = @logger
-        client = Google::Apis::AnalyticsV3::AnalyticsService.new
-        key = Google::APIClient::KeyUtils::load_from_pkcs12(NcboCron.settings.analytics_path_to_key_file, 'notasecret')
-        client.authorization = Signet::OAuth2::Client.new(
-            :token_credential_uri => 'https://accounts.google.com/o/oauth2/token',
-            :audience             => 'https://accounts.google.com/o/oauth2/token',
-            :scope                => 'https://www.googleapis.com/auth/analytics.readonly',
-            :issuer               => NcboCron.settings.analytics_service_account_email_address,
-            :signing_key          => key
-        ).tap { |auth| auth.fetch_access_token! }
-        client
+        Google::Analytics::Data.analytics_data do |config|
+          config.credentials = NcboCron.settings.analytics_path_to_key_file
+        end
       end
-    end
+    end # class
+
+  end
+end
+
+class ::Hash
+  def deep_merge(second)
+    merger = proc { |key, v1, v2| Hash === v1 && Hash === v2 ? v1.merge(v2, &merger) : v2 }
+    self.merge(second, &merger)
   end
 end
 
@@ -127,7 +217,8 @@ def authenticate_google
 # require 'ncbo_annotator'
 # require 'ncbo_cron/config'
 # require_relative '../../config/config'
-# ontology_analytics_log_path = File.join("logs", "ontology-analytics.log")
-# ontology_analytics_logger = Logger.new(ontology_analytics_log_path)
+# # ontology_analytics_log_path = File.join("logs", "ontology-analytics.log")
+# # ontology_analytics_logger = Logger.new(ontology_analytics_log_path)
+# ontology_analytics_logger = Logger.new(STDOUT)
 # NcboCron::Models::OntologyAnalytics.new(ontology_analytics_logger).run
-# ./bin/ncbo_cron --disable-processing true --disable-pull true --disable-flush true --disable-warmq true --disable-ontologies-report true --disable-mapping-counts true --disable-spam-deletion true --ontology-analytics '14 * * * *'
+# # ./bin/ncbo_cron --disable-processing true --disable-pull true --disable-flush true --disable-warmq true --disable-ontologies-report true --disable-mapping-counts true --disable-spam-deletion true --ontology-analytics '14 * * * *'
diff --git a/lib/ncbo_cron/ontology_submission_parser.rb b/lib/ncbo_cron/ontology_submission_parser.rb
index b0a3309c..3c908442 100644
--- a/lib/ncbo_cron/ontology_submission_parser.rb
+++ b/lib/ncbo_cron/ontology_submission_parser.rb
@@ -11,6 +11,7 @@ class OntologySubmissionParser
       ACTIONS = {
         :process_rdf => true,
         :extract_metadata => true,
+        :generate_labels => true,
         :index_search => true,
         :index_properties => true,
         :run_metrics => true,
@@ -182,7 +183,7 @@ def process_submission(logger, submission_id, actions=ACTIONS)
 
           # Check to make sure the file has been downloaded
           if sub.pullLocation && (!sub.uploadFilePath || !File.exist?(sub.uploadFilePath))
-            multi_logger.debug "Pull location found, but no file in the upload file path. Retrying download."
+            multi_logger.debug "Pull location found (#{sub.pullLocation}, but no file in the upload file path (#{sub.uploadFilePath}. Retrying download."
             file, filename = sub.download_ontology_file
             file_location = sub.class.copy_file_repository(sub.ontology.acronym, sub.submissionId, file, filename)
             file_location = "../" + file_location if file_location.start_with?(".") # relative path fix
@@ -237,10 +238,11 @@ def process_annotator(logger, sub)
           begin
             annotator = Annotator::Models::NcboAnnotator.new
             annotator.create_term_cache_for_submission(logger, sub)
-            # commenting this action out for now due to a problem with hgetall in redis
+            # this action only occurs if the CRON dictionary generation job is disabled
+            # if the CRON dictionary generation job is running,
+            # the dictionary will NOT be generated on each ontology parsing
             # see https://github.com/ncbo/ncbo_cron/issues/45 for details
-            # mgrep dictionary generation will occur as a separate CRON task
-            # annotator.generate_dictionary_file()
+            annotator.generate_dictionary_file() unless NcboCron.settings.enable_dictionary_generation_cron_job
           rescue Exception => e
             logger.error(e.message + "\n" + e.backtrace.join("\n\t"))
             logger.flush()
diff --git a/lib/ncbo_cron/spam_deletion.rb b/lib/ncbo_cron/spam_deletion.rb
index 8db5568b..e2ec64f8 100644
--- a/lib/ncbo_cron/spam_deletion.rb
+++ b/lib/ncbo_cron/spam_deletion.rb
@@ -25,8 +25,18 @@ def initialize(logger=nil)
       end
 
       def run
-        auth_token = Base64.decode64(NcboCron.settings.git_repo_access_token)
+        auth_token = NcboCron.settings.git_repo_access_token
         res = `curl --header 'Authorization: token #{auth_token}' --header 'Accept: application/vnd.github.v3.raw' --location #{FULL_FILE_PATH}`
+
+        begin
+          error_json = JSON.parse(res)
+          msg = "\nError while fetching the SPAM user list from #{FULL_FILE_PATH}: #{error_json}"
+          @logger.error(msg)
+          puts msg
+          exit
+        rescue JSON::ParserError
+          @logger.info("Successfully downloaded the SPAM user list from #{FULL_FILE_PATH}")
+        end
         usernames = res.split(",").map(&:strip)
         delete_spam(usernames)
       end
diff --git a/ncbo_cron.gemspec b/ncbo_cron.gemspec
index 821881d1..c8faa03d 100644
--- a/ncbo_cron.gemspec
+++ b/ncbo_cron.gemspec
@@ -8,7 +8,7 @@ Gem::Specification.new do |gem|
   gem.summary       = %q{}
   gem.homepage      = "https://github.com/ncbo/ncbo_cron"
 
-  gem.files         = `git ls-files`.split($\)
+  gem.files         = Dir['**/*']
   gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
   gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
   gem.name          = "ncbo_cron"
@@ -16,7 +16,7 @@ Gem::Specification.new do |gem|
 
   gem.add_dependency("dante")
   gem.add_dependency("goo")
-  gem.add_dependency("google-apis-analytics_v3")
+  gem.add_dependency("google-analytics-data")
   gem.add_dependency("mlanett-redis-lock")
   gem.add_dependency("multi_json")
   gem.add_dependency("ncbo_annotator")
diff --git a/rakelib/purl_management.rake b/rakelib/purl_management.rake
new file mode 100644
index 00000000..58cfadd7
--- /dev/null
+++ b/rakelib/purl_management.rake
@@ -0,0 +1,28 @@
+# Task for updating and adding missing purl for all ontologies
+#
+desc 'Purl Utilities'
+namespace :purl do
+  require 'bundler/setup'
+  # Configure the process for the current cron configuration.
+  require_relative '../lib/ncbo_cron'
+  config_exists = File.exist?(File.expand_path('../../config/config.rb', __FILE__))
+  abort('Please create a config/config.rb file using the config/config.rb.sample as a template') unless config_exists
+  require_relative '../config/config'
+
+  desc 'update purl for all ontologies'
+  task :update_all do
+    purl_client = LinkedData::Purl::Client.new
+    LinkedData::Models::Ontology.all.each do |ont|
+      ont.bring(:acronym)
+      acronym = ont.acronym
+
+      if purl_client.purl_exists(acronym)
+        puts "#{acronym} exists"
+        purl_client.fix_purl(acronym)
+      else
+        puts "#{acronym} DOES NOT exist"
+        purl_client.create_purl(acronym)
+      end
+    end
+  end
+end