lazar 1.1.0 → 1.1.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 698fd96821077269f4c31fdfca6bead6beab36f0
-  data.tar.gz: 2fd49abf99e8f5367b83764735c5c2e49caad4d2
+  metadata.gz: 4e7ee9c1cb08576d2bb23d8e8e44986d2dba9f9b
+  data.tar.gz: a88d6469cf221fb10d159498d6c35620cfcd3fe8
 SHA512:
-  metadata.gz: ef5d243c765f5d1d6bb4c2dbd53bf2cdcca380df532cef8c48447b907ff01086f1b50c261e1f494827a30e52e7d8e62e2c077334cdbe30370546680ffd018886
-  data.tar.gz: d9bb905832388dcb44bb3211fb6976c4e0894d75eb02fdf60c17fe19f25dec73ba24b5585fea8cb85e77b6793b46518462cf1d9b2488c465332b9db3af132028
+  metadata.gz: b9dcd28f5b1ccbf93135a0aad1fef42e6dde4c765e5addb94f624a4e2e08d25c3dadf238c68b0e58d4ec36ad8700ad02fcc7fe66d54665c0316df36829b8f302
+  data.tar.gz: d91ea1ea8684ee5aecff7663081a424ec2ffea66a6149c102c9074a80d57c3aa22d71e4a71ab91d4958260175238bd984bacd71a28b406b815b25102f8c2469f

data/VERSION

@@ -1 +1 @@
-1.1.0
+1.1.3

data/lazar.gemspec

@@ -20,6 +20,7 @@ Gem::Specification.new do |s|
   # specify any dependencies here; for example:
   s.add_runtime_dependency 'bundler'
   s.add_runtime_dependency 'rest-client'
+  s.add_runtime_dependency 'addressable'
   s.add_runtime_dependency 'nokogiri'
   s.add_runtime_dependency 'rserve-client'
   s.add_runtime_dependency 'mongoid'

data/lib/import.rb

@@ -10,18 +10,17 @@ module OpenTox
       def self.import
         # time critical step: JSON parsing (>99%), Oj brings only minor speed gains (~1%)
         datasets = {}
-        bundles = JSON.parse(RestClientWrapper.get('https://data.enanomapper.net/bundle?media=application%2Fjson'))["dataset"]
+        bundles = JSON.parse(RestClientWrapper.get('https://data.enanomapper.net/bundle', {}, {accept: :json}))["dataset"]
         bundles.each do |bundle|
           datasets[bundle["URI"]] = Dataset.find_or_create_by(:source => bundle["URI"],:name => bundle["title"].strip)
           $logger.debug bundle["title"].strip
-          nanoparticles = JSON.parse(RestClientWrapper.get(bundle["dataset"]+"?media=application%2Fjson"))["dataEntry"]
+          nanoparticles = JSON.parse(RestClientWrapper.get(bundle["dataset"], {}, {accept: :json}))["dataEntry"]
           nanoparticles.each_with_index do |np,n|
             core_id = nil
             coating_ids = []
             np["composition"].each do |c|
               uri = c["component"]["compound"]["URI"]
-              uri = CGI.escape File.join(uri,"&media=application/json")
-              data = JSON.parse(RestClientWrapper.get "https://data.enanomapper.net/query/compound/url/all?media=application/json&search=#{uri}")
+              data = JSON.parse(RestClientWrapper.get("https://data.enanomapper.net/query/compound/url/all?search=#{uri}", {}, {accept: :json}))
               source = data["dataEntry"][0]["compound"]["URI"]
               smiles = data["dataEntry"][0]["values"]["https://data.enanomapper.net/feature/http%3A%2F%2Fwww.opentox.org%2Fapi%2F1.1%23SMILESDefault"]
               names = []
@@ -52,7 +51,7 @@ module OpenTox
               nanoparticle.dataset_ids << datasets[bundle_uri].id
             end
 
-            studies = JSON.parse(RestClientWrapper.get(File.join(np["compound"]["URI"],"study")))["study"]
+            studies = JSON.parse(RestClientWrapper.get(File.join(np["compound"]["URI"],"study"), {}, {accept: :json}))["study"]
             studies.each do |study|
               dataset = datasets[np["bundles"].keys.first]
               proteomics_features = {}

data/lib/lazar.rb

@@ -1,6 +1,7 @@
 require 'rubygems'
 require "bundler/setup"
 require "rest-client"
+require 'addressable'
 require 'yaml'
 require 'json'
 require 'logger'
@@ -49,6 +50,7 @@ rlib = File.expand_path(File.join(File.dirname(__FILE__),"..","R"))
 # http://stackoverflow.com/questions/19619582/number-of-processors-cores-in-command-line
 NR_CORES = `getconf _NPROCESSORS_ONLN`.to_i
 R = Rserve::Connection.new
+R.eval ".libPaths('#{rlib}')"
 R.eval "
 suppressPackageStartupMessages({
   library(labeling,lib=\"#{rlib}\")

data/lib/model.rb

@@ -46,15 +46,18 @@ module OpenTox
         model.prediction_feature_id = prediction_feature.id
         model.training_dataset_id = training_dataset.id
         model.name = "#{prediction_feature.name} (#{training_dataset.name})" 
-        # TODO: check if this works for gem version, add gem versioning?
+        # git or gem versioning
         dir = File.dirname(__FILE__)
-        commit = `cd #{dir}; git rev-parse HEAD`.chomp
-        branch = `cd #{dir}; git rev-parse --abbrev-ref HEAD`.chomp
-        url = `cd #{dir}; git config --get remote.origin.url`.chomp
-        if branch
+        path = File.expand_path("../", File.expand_path(dir))
+        if Dir.exists?(dir+"/.git")
+          commit = `git rev-parse HEAD`.chomp
+          branch = `git rev-parse --abbrev-ref HEAD`.chomp
+          url = `git config --get remote.origin.url`.chomp
           model.version = {:url => url, :branch => branch, :commit => commit}
         else
-          model.version = {:warning => "git is not installed"}
+          version = File.open(path+"/VERSION", &:gets).chomp
+          url = "https://rubygems.org/gems/lazar/versions/"+version
+          model.version = {:url => url, :branch => "gem", :commit => version}
         end
 
         # set defaults#
@@ -395,6 +398,7 @@ module OpenTox
       include Mongoid::Timestamps
 
       field :endpoint, type: String
+      field :qmrf, type: Hash
       field :species, type: String
       field :source, type: String
       field :unit, type: String

data/lib/overwrite.rb

@@ -197,7 +197,7 @@ module URI
   # @param [String]
   # @return [TrueClass,FalseClass]
   def self.valid? uri
-    u = URI.parse(uri)
+    u = Addressable::URI.parse(uri)
     u.scheme!=nil and u.host!=nil
   rescue URI::InvalidURIError
     false

data/lib/rest-client-wrapper.rb

@@ -26,6 +26,7 @@ module OpenTox
 
       define_singleton_method method do |uri,payload={},headers={},waiting_task=nil|
 
+        uri = Addressable::URI.encode(uri)
         # check input
         bad_request_error "Headers are not a hash: #{headers.inspect} for #{uri}." unless headers==nil or headers.is_a?(Hash) 
         headers[:subjectid] ||= @@subjectid

data/scripts/mol2mmol-log10.rb

@@ -0,0 +1,19 @@
+#!/usr/bin/env ruby
+require_relative '../lib/lazar.rb'
+include OpenTox
+newfile = ARGV[0].sub(/.csv/,"_mmol_log10.csv") 
+p newfile
+CSV.open(newfile, "wb") do |csv|
+  CSV.read(ARGV[0]).each do |line|
+    smi,mol = line
+    if mol.numeric?
+      c = Compound.from_smiles smi
+      #delog = 10**(-1*mol.to_f) #if values already -log10 but mol
+      mmol = mol.to_f*1000
+      log = -Math.log10(mmol)
+      csv << [smi, log]
+    else
+      csv << [smi, mol.gsub(/mol/,'mmol')]
+    end
+  end
+end

data/test/Rpackages.rb

@@ -0,0 +1,14 @@
+require_relative "setup.rb"
+
+class LazarRpackagesTest < MiniTest::Test
+
+  def test_user_packages_installed
+    packages = ["caret", "randomForest", "ggplot2", "pls", "doMC", "gridExtra", "foreach", "iterators", "stringi"]
+    packages.each do |p|
+      r = R.eval "require(#{p})"
+      assert_equal 1, r.payload[0]
+    end
+  end
+
+end
+

data/test/compound.rb

@@ -61,7 +61,9 @@ print c.sdf
 
   def test_chemblid
     c = OpenTox::Compound.from_inchi "InChI=1S/C6H6/c1-2-4-6-5-3-1/h1-6H"
-    assert_equal "CHEMBL277500", c.chemblid
+    assert_equal "CHEMBL1531487", c.chemblid
+    c = OpenTox::Compound.from_smiles "OC[C@](c1onc(n1)c1ncn2c1CN(C)C(=O)c1c2cccc1Cl)(O)C"
+    assert_equal "CHEMBL145418", c.chemblid
   end
 
   def test_sdf_storage
@@ -108,7 +110,7 @@ print c.sdf
 
   def test_molecular_weight
     c = OpenTox::Compound.from_smiles "CC(=O)CC(C)C"
-    assert_equal 100.15888, c.molecular_weight
+    assert_equal 100.15888, c.molecular_weight.round(5)
   end
 
   def test_physchem

data/test/setup.rb

@@ -5,6 +5,7 @@ require_relative '../lib/lazar.rb'
 include OpenTox
 #$mongo.database.drop
 #$gridfs = $mongo.database.fs # recreate GridFS indexes
+PhysChem.descriptors
 TEST_DIR ||= File.expand_path(File.dirname(__FILE__))
 DATA_DIR ||= File.join(TEST_DIR,"data")
 training_dataset = Dataset.where(:name => "Protein Corona Fingerprinting Predicts the Cellular Interaction of Gold and Silver Nanoparticles").first

data/test/validation-regression.rb

@@ -84,7 +84,7 @@ class ValidationRegressionTest < MiniTest::Test
     repeated_cv = RepeatedCrossValidation.create model
     repeated_cv.crossvalidations.each do |cv|
       assert cv.r_squared > 0.34, "R^2 (#{cv.r_squared}) should be larger than 0.034"
-      assert cv.rmse < 0.5, "RMSE (#{cv.rmse}) should be smaller than 0.5"
+      assert cv.rmse < 1.5, "RMSE (#{cv.rmse}) should be smaller than 0.5"
     end
   end
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: lazar
 version: !ruby/object:Gem::Version
-  version: 1.1.0
+  version: 1.1.3
 platform: ruby
 authors:
 - Christoph Helma, Martin Guetlein, Andreas Maunz, Micha Rautenberg, David Vorgrimmler,
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-05-26 00:00:00.000000000 Z
+date: 2018-04-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -39,6 +39,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: addressable
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: nokogiri
   requirement: !ruby/object:Gem::Requirement
@@ -155,6 +169,8 @@ files:
 - scripts/mg2mmol.rb
 - scripts/mirror-enm2test.rb
 - scripts/mmol2-log10.rb
+- scripts/mol2mmol-log10.rb
+- test/Rpackages.rb
 - test/all.rb
 - test/compound.rb
 - test/data/EPAFHM.csv
@@ -221,11 +237,12 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: lazar
-rubygems_version: 2.5.2
+rubygems_version: 2.6.8
 signing_key: 
 specification_version: 4
 summary: Lazar framework
 test_files:
+- test/Rpackages.rb
 - test/all.rb
 - test/compound.rb
 - test/data/EPAFHM.csv