sdf import, csv files with id column

4 files changed, 163 insertions, 3 deletions

diff --git a/test/data/input_53.csv b/test/data/input_53.csv
new file mode 100644
index 0000000..b213027
--- /dev/null
+++ b/test/data/input_53.csv
@@ -0,0 +1,54 @@
+ID,SMILES

+123-30-8,Oc1ccc(N)cc1

+68391-25-3,OC(COc1ccccc1)CNc2ccc(cc2)Cc3ccc(N)cc3

+62-53-3,Nc1ccccc1

+123-98-8,O=C(CCCCCCCC(=O)Cl)Cl

+106-51-4,O=C1C=CC(=O)C=C1

+7144-65-2,O(c1ccccc1c2ccccc2)CC3OC3

+3130-19-6,O=C(OCC1CCC2OC2(C1))CCCCC(=O)OCC3CCC4OC4(C3)

+140-95-4,O=C(NCO)NCO

+2778-42-9,O=C=NC(c1cccc(c1)C(N=C=O)(C)C)(C)C

+593-60-2,C=CBr

+75-25-2,C(Br)(Br)Br

+1852-16-0,O=C(C=C)NCOCCCC

+107-58-4,O=C(C=C)NC(C)(C)C

+592-35-8,O=C(OCCCC)N

+2426-08-6,O(CCCC)CC1OC1

+79-07-2,O=C(N)CCl

+110-75-8,O(C=C)CCCl

+67-66-3,C(Cl)(Cl)Cl

+26172-55-4,O=C1C=C(Cl)SN1C

+598-09-4,O1CC1(C)CCl

+2556-36-7,O=C=NC1CCC(N=C=O)CC1

+3271-22-5,n1c(nc(nc1OC)c2ccc3ccc4cccc5ccc2c3c45)OC

+2680-03-7,O=C(C=C)N(C)C

+13036-41-4,O=C(C=C)NCOCC

+556-52-5,OCC1OC1

+2530-83-8,O(CCC[Si](OC)(OC)OC)CC1OC1

+106-90-1,O=C(OCC1OC1)C=C

+26761-45-5,O=C(OCC1OC1)C(C)(C)CCCCCC

+122-60-1,O(c1ccccc1)CC2OC2

+2210-79-9,O(c1ccccc1C)CC2OC2

+2461-15-6,O(CC1OC1)CC(CC)CCCC

+75-02-5,FC=C

+98-01-1,O=Cc1occc1

+111-30-8,O=CCCCC=O

+107-22-2,O=CC=O

+78-84-2,O=CC(C)C

+11087-88-0,O=C(OCCCCCC(C)C)CCCCCCCC1OC1(CCCCCCCC)

+3644-11-9,O=C(C=C)NCOC

+1187-59-3,O=C(C=C)NC

+54208-63-8,O(c1ccccc1Cc3ccccc3(OCC2OC2))CC4OC4

+110-26-9,O=C(C=C)NCNC(=O)C=C

+1208-52-2,Nc1ccc(cc1)Cc2ccccc2(N)

+71033-08-4,O(c1ccc(cc1)C(c3ccc(OCC(OCC2OC2)COCCCC)cc3)(C)C)CC(OCC4OC4)COCCCC

+5165-97-9,O=C(C=C)NC(C)(C)CS(=O)(=O)O

+34813-62-2,O=C=NCCCC(C)CN=C=O

+16669-59-3,O=C(C=C)NCOCC(C)C

+80-48-8,O=S(=O)(OC)c1ccc(cc1)C

+2386-87-0,O=C(OCC1CCC2OC2(C1))C3CCC4OC4(C3)

+104-49-4,O=C=Nc1ccc(N=C=O)cc1

+103-71-9,O=C=Nc1ccccc1

+111-19-3,O=C(CCCCCCCCC(=O)Cl)Cl

+7320-37-8,O1CC1CCCCCCCCCCCCCC

+2451-62-9,O=C1N(C(=O)N(C(=O)N1CC2OC2)CC3OC3)CC4OC4

diff --git a/test/data/input_53.tsv b/test/data/input_53.tsv
new file mode 100644
index 0000000..c46fdd4
--- /dev/null
+++ b/test/data/input_53.tsv
@@ -0,0 +1,54 @@
+Id	Smiles

+123-30-8	Oc1ccc(N)cc1

+68391-25-3	OC(COc1ccccc1)CNc2ccc(cc2)Cc3ccc(N)cc3

+62-53-3	Nc1ccccc1

+123-98-8	O=C(CCCCCCCC(=O)Cl)Cl

+106-51-4	O=C1C=CC(=O)C=C1

+7144-65-2	O(c1ccccc1c2ccccc2)CC3OC3

+3130-19-6	O=C(OCC1CCC2OC2(C1))CCCCC(=O)OCC3CCC4OC4(C3)

+140-95-4	O=C(NCO)NCO

+2778-42-9	O=C=NC(c1cccc(c1)C(N=C=O)(C)C)(C)C

+593-60-2	C=CBr

+75-25-2	C(Br)(Br)Br

+1852-16-0	O=C(C=C)NCOCCCC

+107-58-4	O=C(C=C)NC(C)(C)C

+592-35-8	O=C(OCCCC)N

+2426-08-6	O(CCCC)CC1OC1

+79-07-2	O=C(N)CCl

+110-75-8	O(C=C)CCCl

+67-66-3	C(Cl)(Cl)Cl

+26172-55-4	O=C1C=C(Cl)SN1C

+598-09-4	O1CC1(C)CCl

+2556-36-7	O=C=NC1CCC(N=C=O)CC1

+3271-22-5	n1c(nc(nc1OC)c2ccc3ccc4cccc5ccc2c3c45)OC

+2680-03-7	O=C(C=C)N(C)C

+13036-41-4	O=C(C=C)NCOCC

+556-52-5	OCC1OC1

+2530-83-8	O(CCC[Si](OC)(OC)OC)CC1OC1

+106-90-1	O=C(OCC1OC1)C=C

+26761-45-5	O=C(OCC1OC1)C(C)(C)CCCCCC

+122-60-1	O(c1ccccc1)CC2OC2

+2210-79-9	O(c1ccccc1C)CC2OC2

+2461-15-6	O(CC1OC1)CC(CC)CCCC

+75-02-5	FC=C

+98-01-1	O=Cc1occc1

+111-30-8	O=CCCCC=O

+107-22-2	O=CC=O

+78-84-2	O=CC(C)C

+11087-88-0	O=C(OCCCCCC(C)C)CCCCCCCC1OC1(CCCCCCCC)

+3644-11-9	O=C(C=C)NCOC

+1187-59-3	O=C(C=C)NC

+54208-63-8	O(c1ccccc1Cc3ccccc3(OCC2OC2))CC4OC4

+110-26-9	O=C(C=C)NCNC(=O)C=C

+1208-52-2	Nc1ccc(cc1)Cc2ccccc2(N)

+71033-08-4	O(c1ccc(cc1)C(c3ccc(OCC(OCC2OC2)COCCCC)cc3)(C)C)CC(OCC4OC4)COCCCC

+5165-97-9	O=C(C=C)NC(C)(C)CS(=O)(=O)O

+34813-62-2	O=C=NCCCC(C)CN=C=O

+16669-59-3	O=C(C=C)NCOCC(C)C

+80-48-8	O=S(=O)(OC)c1ccc(cc1)C

+2386-87-0	O=C(OCC1CCC2OC2(C1))C3CCC4OC4(C3)

+104-49-4	O=C=Nc1ccc(N=C=O)cc1

+103-71-9	O=C=Nc1ccccc1

+111-19-3	O=C(CCCCCCCCC(=O)Cl)Cl

+7320-37-8	O1CC1CCCCCCCCCCCCCC

+2451-62-9	O=C1N(C(=O)N(C(=O)N1CC2OC2)CC3OC3)CC4OC4

diff --git a/test/dataset.rb b/test/dataset.rb
index 055a029..11a4697 100644
--- a/test/dataset.rb
+++ b/test/dataset.rb
@@ -1,6 +1,21 @@
+# batch class
+
 require_relative "setup.rb"
 
 class DatasetTest < MiniTest::Test
+  
+  # TODO 
+  def test_from_pubchem
+    d = Dataset.from_pubchem 1190
+  end
+
+  def test_merge
+    skip "TODO"
+  end
+
+  def test_to_sdf
+    skip "TODO"
+  end
 
   # basics
 
@@ -21,6 +36,34 @@ class DatasetTest < MiniTest::Test
 
   # real datasets
 
+  def test_upload_csv_with_id
+    d = Dataset.from_csv_file "#{DATA_DIR}/input_53.csv"
+    assert_equal 53, d.compounds.size
+    assert_equal 1, d.features.size
+    f = d.features[0]
+    assert_equal "original_id", f.name
+    assert_equal ["123-30-8"], d.values(d.compounds.first,f)
+  end
+
+  def test_upload_tsv_with_id
+    d = Dataset.from_csv_file "#{DATA_DIR}/input_53.tsv"
+    assert_equal 53, d.compounds.size
+    assert_equal 1, d.features.size
+    assert_equal 1, d.features.size
+    f = d.features[0]
+    assert_equal "original_id", f.name
+    assert_equal ["123-30-8"], d.values(d.compounds.first,f)
+  end
+
+  def test_upload_sdf
+    #d = Dataset.from_sdf_file "#{DATA_DIR}/cas_4337.sdf"
+    d = Dataset.from_sdf_file "#{DATA_DIR}/PA.sdf"
+    assert_equal Compound.from_smiles("C[C@H]1C(=O)O[C@@H]2CCN3[C@@H]2C(=CC3)COC(=O)[C@]([C@]1(C)O)(C)O").smiles, d.compounds.first.smiles
+    f = Feature.find_by(:name => "original_id")
+    assert_equal 35, d.features.size
+    assert_equal ["9415"], d.values(d.compounds.first,f)
+  end
+
   def test_upload_hamster
     d = Dataset.from_csv_file "#{DATA_DIR}/hamster_carcinogenicity.csv"
     assert_equal Dataset, d.class
@@ -103,6 +146,15 @@ class DatasetTest < MiniTest::Test
     d.delete
   end
 
+  def test_multiple_uploads
+    datasets = []
+    2.times do
+      d = Dataset.from_csv_file("#{DATA_DIR}/hamster_carcinogenicity.csv")
+      datasets << d
+    end
+    assert_equal datasets[0],datasets[1]
+  end
+
   # batch predictions
 
   def test_create_without_features_smiles_and_inchi
diff --git a/test/setup.rb b/test/setup.rb
index 4a11aa0..c4c04cb 100644
--- a/test/setup.rb
+++ b/test/setup.rb
@@ -5,8 +5,8 @@ require_relative '../lib/lazar.rb'
 include OpenTox
 #$mongo.database.drop
 #$gridfs = $mongo.database.fs # recreate GridFS indexes
-PhysChem.descriptors
+#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
-Import::Enanomapper.import unless training_dataset
+#training_dataset = Dataset.where(:name => "Protein Corona Fingerprinting Predicts the Cellular Interaction of Gold and Silver Nanoparticles").first
+#Import::Enanomapper.import unless training_dataset