Mercurial > repos > bgruening > chembl

changeset 2:f56492688f43 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/chembl/chembl_webresource_client commit d7fca21744d3c87cf173c1539c069a5c720084f3"
author bgruening
date Fri, 06 Sep 2019 07:50:15 -0400
parents 6f8458d1cf46
children 8b6ba267714b
files chembl.py test-data/out1.smi test-data/out2.smi test-data/out3.smi test-data/out4.smi
diffstat 5 files changed, 127 insertions(+), 127 deletions(-) [+]
line wrap: on
line diff
--- a/chembl.py	Mon Aug 12 12:57:32 2019 -0400
+++ b/chembl.py	Fri Sep 06 07:50:15 2019 -0400
@@ -13,7 +13,7 @@
     """ 
     smiles = set()
     for smi in res: 
-        smiles.add(smi['molecule_structures']['canonical_smiles']) 
+        smiles.add('{}\t{}'.format(smi['molecule_structures']['canonical_smiles'], smi['molecule_chembl_id']))
     return smiles
 
 def sim_search(smiles, tanimoto):
@@ -21,14 +21,14 @@
     Return compounds which are within a Tanimoto range of the SMILES input
     """
     similarity = new_client.similarity
-    return similarity.filter(smiles=smiles, similarity=tanimoto).only(['molecule_structures'])
+    return similarity.filter(smiles=smiles, similarity=tanimoto).only(['molecule_structures', 'molecule_chembl_id'])
     
 def substr_search(smiles):
     """
     Return compounds which contain the SMILES substructure input
     """
     substructure = new_client.substructure
-    return substructure.filter(smiles=smiles).only(['molecule_structures'])
+    return substructure.filter(smiles=smiles).only(['molecule_structures', 'molecule_chembl_id'])
     
 def filter_drugs(mols):
     """
--- a/test-data/out1.smi	Mon Aug 12 12:57:32 2019 -0400
+++ b/test-data/out1.smi	Fri Sep 06 07:50:15 2019 -0400
@@ -1,47 +1,47 @@
-CN1CCCC1c2cccnc2
-CN1CCC[C@@H]1c2cccnc2
-CN1CCC[C@H]1c2cccnc2
-CCN1CCCC1c2cccnc2
-CN1CCCC1c2ccc(C)nc2
-CCc1ccc(cn1)C2CCCN2C
-CN1CCCC1c2cncc(C)c2
-CCCc1ccc(cn1)C2CCCN2C
-CCc1cncc(c1)C2CCCN2C
-CN1CCCC[C@H]1c2cccnc2
-CN1CCCCC1c2cccnc2
-CCCc1cncc(c1)C2CCCN2C
-CN1CCCC1c2cccnc2C
-CCCCc1ccc(cn1)C2CCCN2C
-CCCCCc1ccc(cn1)C2CCCN2C
-CC1CCN(C)[C@@H]1c2cccnc2
-CN1CCCC1c2ccc(CCCc3ccccc3)nc2
-CN1CCCC1c2cncc(Cl)c2
-CN1CCCC1c2ccc(CCc3ccccc3)nc2
-CN1CCC[C@H]1c2ccccc2
-CN1CCCC1c2ccccc2
-CN1CCC[C@H]1c2ccccn2
-CN1CCCC1c2cncc(F)c2
-COc1cncc(c1)C2CCCN2C
-CN1CCCC1c2cncc(Br)c2
-CN1CCCC1c2ccc(nc2)c3ccccc3
-CN1CCCC1c2ccc(\C=C\c3ccccc3)nc2
-COc1ccncc1C2CCCN2C
-CCCC[C@H]1CC[C@H](N1C)c2cccnc2
-CCCC[C@@H]1CC[C@H](N1C)c2cccnc2
-CN1CCCC1c2cnccc2N
-C[C@H]1C[C@H](N(C)C1)c2cccnc2
-CC[C@H]1C[C@H](N(C)C1)c2cccnc2
-CN1CCCC1c2ccc(CCc3ccc(Cl)cc3)nc2
-CN1CCCC1c2ccc(Cl)nc2
-CN1CCCC1c2ccc(C)cc2
-COCC1CCN(C)[C@@H]1c2cccnc2
-C(N1CCCC1c2cccnc2)c3ccccc3
-C[C@H]1CC[C@H](N1C)c2cccnc2
-C[C@@H]1CC[C@H](N1C)c2cccnc2
-CN1CCCC1c2ccc(Cl)cc2
-CN1CCCC1c2ccc(F)nc2
-CN1CCC(CF)[C@H]1c2cccnc2
-CN1CCCC1c2ccc(Br)nc2
-COc1ccc(CCc2ccc(cn2)C3CCCN3C)cc1
-CN1CCC(CO)[C@H]1c2cccnc2
-CN1CCCC1c2cnc3ccccc3c2
\ No newline at end of file
+CN1CCCC1c2ccc(Cl)cc2	CHEMBL279352
+CCCC[C@H]1CC[C@H](N1C)c2cccnc2	CHEMBL119581
+CN1CCCC1c2ccc(F)nc2	CHEMBL72470
+C[C@H]1CC[C@H](N1C)c2cccnc2	CHEMBL116645
+CCCC[C@@H]1CC[C@H](N1C)c2cccnc2	CHEMBL119574
+CN1CCCC1c2ccc(CCc3ccc(Cl)cc3)nc2	CHEMBL189470
+CN1CCC[C@H]1c2cccnc2	CHEMBL3
+CN1CCCC1c2cncc(Cl)c2	CHEMBL61013
+CCCCCc1ccc(cn1)C2CCCN2C	CHEMBL103566
+CN1CCCC1c2cccnc2	CHEMBL440464
+CN1CCCC1c2ccc(nc2)c3ccccc3	CHEMBL350748
+CN1CCCC1c2cnccc2N	CHEMBL193763
+C(N1CCCC1c2cccnc2)c3ccccc3	CHEMBL163552
+COCC1CCN(C)[C@@H]1c2cccnc2	CHEMBL119020
+CN1CCCC1c2ccc(C)nc2	CHEMBL294757
+CN1CCCC1c2ccc(C)cc2	CHEMBL180376
+CN1CCCC[C@H]1c2cccnc2	CHEMBL3640783
+C[C@@H]1CC[C@H](N1C)c2cccnc2	CHEMBL118038
+CN1CCC[C@H]1c2ccccn2	CHEMBL2068760
+CN1CCCC1c2cccnc2C	CHEMBL160034
+CCc1ccc(cn1)C2CCCN2C	CHEMBL103225
+C[C@H]1C[C@H](N(C)C1)c2cccnc2	CHEMBL432837
+CC[C@H]1C[C@H](N(C)C1)c2cccnc2	CHEMBL115793
+CN1CCCC1c2ccccc2	CHEMBL367126
+CN1CCCC1c2ccc(CCCc3ccccc3)nc2	CHEMBL361703
+CC1CCN(C)[C@@H]1c2cccnc2	CHEMBL119019
+CN1CCCC1c2ccc(Br)nc2	CHEMBL58231
+CN1CCCCC1c2cccnc2	CHEMBL102246
+CN1CCCC1c2ccc(CCc3ccccc3)nc2	CHEMBL190295
+CN1CCC[C@H]1c2ccccc2	CHEMBL1199383
+COc1cncc(c1)C2CCCN2C	CHEMBL303530
+COc1ccc(CCc2ccc(cn2)C3CCCN3C)cc1	CHEMBL190652
+CN1CCCC1c2cncc(F)c2	CHEMBL62128
+CN1CCCC1c2cncc(C)c2	CHEMBL364003
+CN1CCC(CO)[C@H]1c2cccnc2	CHEMBL325426
+CCN1CCCC1c2cccnc2	CHEMBL163042
+COc1ccncc1C2CCCN2C	CHEMBL370168
+CCc1cncc(c1)C2CCCN2C	CHEMBL111526
+CN1CCC[C@@H]1c2cccnc2	CHEMBL9732
+CN1CCC(CF)[C@H]1c2cccnc2	CHEMBL119016
+CN1CCCC1c2ccc(Cl)nc2	CHEMBL70050
+CN1CCCC1c2cncc(Br)c2	CHEMBL61772
+CN1CCCC1c2ccc(\C=C\c3ccccc3)nc2	CHEMBL190678
+CCCc1cncc(c1)C2CCCN2C	CHEMBL382287
+CN1CCCC1c2cnc3ccccc3c2	CHEMBL161944
+CCCc1ccc(cn1)C2CCCN2C	CHEMBL103537
+CCCCc1ccc(cn1)C2CCCN2C	CHEMBL320023
\ No newline at end of file
--- a/test-data/out2.smi	Mon Aug 12 12:57:32 2019 -0400
+++ b/test-data/out2.smi	Fri Sep 06 07:50:15 2019 -0400
@@ -1,1 +1,1 @@
-CN1CCC[C@H]1c2cccnc2
\ No newline at end of file
+CN1CCC[C@H]1c2cccnc2	CHEMBL3
\ No newline at end of file
--- a/test-data/out3.smi	Mon Aug 12 12:57:32 2019 -0400
+++ b/test-data/out3.smi	Fri Sep 06 07:50:15 2019 -0400
@@ -1,72 +1,72 @@
-CN1CCC[C@H]1c2cccnc2
-CN1CCC[C@H]1c2ccc[n+]([BH2-]C#N)c2
-CN1CC[C@H]2CCc3ncccc3[C@@H]12
-CN1CC[C@H]2CCc3c(ccc[n+]3[BH2-]C#N)[C@@H]12
-CN1[C@@H](CC[C@H]1c2cccnc2)C#N
-CN1[C@H](CC[C@H]1c2cccnc2)C#N
-CN1CCC[C@H]1c2cncc(c2)C#C
-CN1C[C@@H](Cc2ccccc2)C[C@H]1c3cccnc3
-C[C@@H]1CC[C@H](N1C)c2cccnc2
-C[C@H]1CC[C@H](N1C)c2cccnc2
-CC[C@H]1C[C@H](N(C)C1)c2cccnc2
-CN1C[C@@H](O)C[C@H]1c2cccnc2
-CN1CCC(CO)[C@H]1c2cccnc2
-CSC[C@H]1C[C@H](N(C)C1)c2cccnc2
-CN1C[C@H](CO)C[C@H]1c2cccnc2
-CN1C[C@@H](CC#N)C[C@H]1c2cccnc2
-CN1C[C@@H](CF)C[C@H]1c2cccnc2
-CO[C@H]1C[C@H](N(C)C1)c2cccnc2
-CN1CCC(CF)[C@H]1c2cccnc2
-CC1CCN(C)[C@@H]1c2cccnc2
-COCC1CCN(C)[C@@H]1c2cccnc2
-CN1C[C@@H](CO)C[C@H]1c2cccnc2
-CN1C[C@H](C[C@H]1c2cccnc2)OC(=O)C
-CN1C[C@@H](C[C@H]1c2cccnc2)C#N
-CC1CN(C)[C@@H](C1C)c2cccnc2
-C[C@H]1C[C@H](N(C)C1)c2cccnc2
-CN1C[C@H](C[C@H]1c2cccnc2)OS(=O)(=O)C
-COC[C@H]1C[C@H](N(C)C1)c2cccnc2
-CCCC[C@@H]1CC[C@H](N1C)c2cccnc2
-CCCC[C@H]1CC[C@H](N1C)c2cccnc2
-CN1[C@@H](CC[C@H]1c2cccnc2)c3ccccc3
-CN1[C@@H](CC[C@@H]1c2ccccc2)c3cccnc3
-Clc1ccc(OC[C@H]2CN3C(=O)CC[C@@]3(O2)c4cccnc4)cc1
-Clc1ccc(OC[C@@H]2CN3C(=O)CC[C@@]3(O2)c4cccnc4)cc1
-CN1[C@@H](CCC1=O)c2cccnc2
-CCCCCCCCC[n+]1cccc2[C@@H]3[C@@H](CCN3C)CCc12
-CN1CCC[C@H]1c2ccc[n+](CCCCCCCCCCCCCC[n+]3cccc(c3)[C@@H]4CCCN4C)c2
-CCCCCCCCCCCC[n+]1cccc2[C@@H]3[C@@H](CCN3C)CCc12
-CCCCCCCCCCCC[n+]1cccc(c1)[C@@H]2CCCN2C
-CCCCCCCCCC[n+]1cccc(c1)[C@@H]2CCCN2C
-CN1CCC[C@H]1c2ccc[n+](CCCCCC[n+]3cccc(c3)[C@@H]4CCCN4C)c2
-CN1CCC[C@H]1c2ccc[n+](CCCCCCCCCCC[n+]3cccc(c3)[C@@H]4CCCN4C)c2
-CN1CCC[C@H]1c2ccc[n+](CCCCCCCC[n+]3cccc(c3)[C@@H]4CCCN4C)c2
-CN1CCC[C@H]1c2ccc[n+](CCCCCCCCCC[n+]3cccc(c3)[C@@H]4CCCN4C)c2
-CN1CCC[C@H]1c2ccc[n+](CCCCc3ccc(CCCC[n+]4cccc(c4)[C@@H]5CCCN5C)cc3)c2
-CN1CCC[C@H]1c2ccc[n+](CCCCCc3ccccc3CCCCC[n+]4cccc(c4)[C@@H]5CCCN5C)c2
-CN1CCC[C@H]1c2ccc[n+](CCCC#Cc3ccccc3C#CCCC[n+]4cccc(c4)[C@@H]5CCCN5C)c2
-CN1CCC[C@H]1c2ccc[n+](CCCCCc3cc(CCCCC[n+]4cccc(c4)[C@@H]5CCCN5C)cc(CCCCC[n+]6cccc(c6)[C@@H]7CCCN7C)c3)c2
-CN1CCC[C@H]1c2ccc[n+](CCCCCCCCC[n+]3cccc(c3)[C@@H]4CCCN4C)c2
-CCCCCCCCCC[n+]1cccc2c1CC[C@]3(C)CCN(C)[C@]23C
-CN1CCC[C@H]1c2ccc[n+](CCCC#Cc3cccc(c3)C#CCCC[n+]4cccc(c4)[C@@H]5CCCN5C)c2
-CCCCCCCC[n+]1cccc2[C@@H]3[C@@H](CCN3C)CCc12
-CN1CCC[C@H]1c2ccc[n+](CCCC#Cc3cc(cc(c3)C#CCCC[n+]4cccc(c4)[C@@H]5CCCN5C)C#CCCC[n+]6cccc(c6)[C@@H]7CCCN7C)c2
-CCCCCCCCCCC[n+]1cccc2[C@@H]3[C@@H](CCN3C)CCc12
-CCCCCCCCCC[n+]1cccc2[C@@H]3[C@@H](CCN3C)CCc12
-C[N@+]1(CC[N@+]2(C)CCC[C@@H]2c3cccnc3)CCC[C@H]1c4cccnc4
-CN1[C@@H](C[C@@H](OC2O[C@@H]([C@@H](O)[C@H](O)[C@H]2O)C(=O)O)C1=O)c3cccnc3
-CN1C(=O)CC[C@@]1(O)c2cccnc2
-OCN1[C@@H](CCC1=O)c2cccnc2
-CN1CCC[C@H]1c2ccc[n+](c2)[C@@H]3O[C@@H]([C@@H](O)[C@H](O)[C@H]3O)C(=O)O
-C[N+]1([O-])CCC[C@H]1c2cccnc2
-CN1CCC[C@@]1(O)c2cccnc2
-CN1[C@@H](CCC1=O)c2ccc[n+](C)c2
-CN1[C@@H](CCC1=O)c2ccc[n+]([O-])c2
-CN1[C@@H](CCC1=O)c2ccc[n+](c2)C3O[C@@H]([C@@H](O)[C@H](O)[C@H]3O)C(=O)C
-Cc1cncc(c1)[C@@H]2CCC[N+]2(C)[O-]
-COc1ncc(cc1c2ncc(cc2[C@@H]3CC[C@H]4[C@H](OC(=O)N34)c5cc(cc(c5)C(F)(F)F)C(F)(F)F)C(F)(F)F)c6c(C)cc(cc6C)C(=O)O
-COc1ccc(cc1c2ncc(cc2[C@@H]3CC[C@H]4[C@H](OC(=O)N34)c5cc(cc(c5)C(F)(F)F)C(F)(F)F)C(F)(F)F)c6c(C)cc(cc6C)C(=O)O
-COc1ncc(cc1c2ncc(cc2[C@@H]3CC[C@H]4[C@H](OC(=O)N34)c5cc(cc(c5)C(F)(F)F)C(F)(F)F)C(F)(F)F)c6ccc(cc6C)C(=O)O
-COCCOc1ncccc1[C@@H]2C(C(=O)C(C)C)C(=O)C(=O)N2c3ccc(cc3)c4ccsc4
-COCCOc1ncccc1[C@@H]2C(C(=O)C(C)C)C(=O)C(=O)N2c3ccc(cc3)c4ccc(C)s4
-O=S(=O)(Nc1ncns1)c2ccc3c(cccc3c2)N4CCC[C@H]4c5cccnc5
\ No newline at end of file
+COc1ncc(cc1c2ncc(cc2[C@@H]3CC[C@H]4[C@H](OC(=O)N34)c5cc(cc(c5)C(F)(F)F)C(F)(F)F)C(F)(F)F)c6ccc(cc6C)C(=O)O	CHEMBL3657536
+CN1CCC[C@@]1(O)c2cccnc2	CHEMBL3544720
+CN1CCC[C@H]1c2ccc[n+](CCCC#Cc3cc(cc(c3)C#CCCC[n+]4cccc(c4)[C@@H]5CCCN5C)C#CCCC[n+]6cccc(c6)[C@@H]7CCCN7C)c2	CHEMBL1185865
+CN1CCC[C@H]1c2ccc[n+](CCCCCC[n+]3cccc(c3)[C@@H]4CCCN4C)c2	CHEMBL1179917
+CN1C[C@@H](Cc2ccccc2)C[C@H]1c3cccnc3	CHEMBL420694
+CC1CCN(C)[C@@H]1c2cccnc2	CHEMBL119019
+C[C@H]1C[C@H](N(C)C1)c2cccnc2	CHEMBL432837
+CN1C(=O)CC[C@@]1(O)c2cccnc2	CHEMBL3544599
+C[C@@H]1CC[C@H](N1C)c2cccnc2	CHEMBL118038
+CO[C@H]1C[C@H](N(C)C1)c2cccnc2	CHEMBL326597
+CCCC[C@@H]1CC[C@H](N1C)c2cccnc2	CHEMBL119574
+CN1[C@@H](CCC1=O)c2ccc[n+]([O-])c2	CHEMBL3544793
+CN1C[C@@H](CF)C[C@H]1c2cccnc2	CHEMBL116706
+CN1C[C@@H](CO)C[C@H]1c2cccnc2	CHEMBL118849
+CN1C[C@@H](O)C[C@H]1c2cccnc2	CHEMBL117339
+CC[C@H]1C[C@H](N(C)C1)c2cccnc2	CHEMBL115793
+CN1CCC[C@H]1c2cncc(c2)C#C	CHEMBL111659
+CN1CCC(CO)[C@H]1c2cccnc2	CHEMBL325426
+CN1CC[C@H]2CCc3ncccc3[C@@H]12	CHEMBL281410
+CN1[C@@H](CC[C@@H]1c2ccccc2)c3cccnc3	CHEMBL443018
+CN1CCC[C@H]1c2ccc[n+](CCCCc3ccc(CCCC[n+]4cccc(c4)[C@@H]5CCCN5C)cc3)c2	CHEMBL1182422
+CN1CCC[C@H]1c2ccc[n+](c2)[C@@H]3O[C@@H]([C@@H](O)[C@H](O)[C@H]3O)C(=O)O	CHEMBL3544704
+CN1[C@@H](CCC1=O)c2ccc[n+](c2)C3O[C@@H]([C@@H](O)[C@H](O)[C@H]3O)C(=O)C	CHEMBL3559662
+CN1CCC[C@H]1c2ccc[n+](CCCCCc3ccccc3CCCCC[n+]4cccc(c4)[C@@H]5CCCN5C)c2	CHEMBL1182431
+COC[C@H]1C[C@H](N(C)C1)c2cccnc2	CHEMBL119227
+CN1C[C@H](CO)C[C@H]1c2cccnc2	CHEMBL434607
+CCCCCCCCCC[n+]1cccc(c1)[C@@H]2CCCN2C	CHEMBL1179042
+CCCCCCCCCC[n+]1cccc2c1CC[C@]3(C)CCN(C)[C@]23C	CHEMBL1183842
+CN1[C@H](CC[C@H]1c2cccnc2)C#N	CHEMBL84210
+CN1C[C@@H](C[C@H]1c2cccnc2)C#N	CHEMBL119352
+COc1ccc(cc1c2ncc(cc2[C@@H]3CC[C@H]4[C@H](OC(=O)N34)c5cc(cc(c5)C(F)(F)F)C(F)(F)F)C(F)(F)F)c6c(C)cc(cc6C)C(=O)O	CHEMBL3657535
+CCCCCCCC[n+]1cccc2[C@@H]3[C@@H](CCN3C)CCc12	CHEMBL1185506
+CCCCCCCCCCCC[n+]1cccc2[C@@H]3[C@@H](CCN3C)CCc12	CHEMBL1179033
+CN1[C@@H](CCC1=O)c2ccc[n+](C)c2	CHEMBL3544791
+CN1CCC[C@H]1c2ccc[n+](CCCCCCCC[n+]3cccc(c3)[C@@H]4CCCN4C)c2	CHEMBL1179945
+CN1[C@@H](CCC1=O)c2cccnc2	CHEMBL578211
+CN1[C@@H](CC[C@H]1c2cccnc2)C#N	CHEMBL81899
+C[C@H]1CC[C@H](N1C)c2cccnc2	CHEMBL116645
+CC1CN(C)[C@@H](C1C)c2cccnc2	CHEMBL334222
+CSC[C@H]1C[C@H](N(C)C1)c2cccnc2	CHEMBL119144
+CN1CCC[C@H]1c2cccnc2	CHEMBL3
+CN1CCC[C@H]1c2ccc[n+](CCCCCCCCCCCCCC[n+]3cccc(c3)[C@@H]4CCCN4C)c2	CHEMBL1179025
+CN1CC[C@H]2CCc3c(ccc[n+]3[BH2-]C#N)[C@@H]12	CHEMBL277416
+CN1CCC[C@H]1c2ccc[n+](CCCC#Cc3cccc(c3)C#CCCC[n+]4cccc(c4)[C@@H]5CCCN5C)c2	CHEMBL1185135
+COCCOc1ncccc1[C@@H]2C(C(=O)C(C)C)C(=O)C(=O)N2c3ccc(cc3)c4ccsc4	CHEMBL3674905
+C[N+]1([O-])CCC[C@H]1c2cccnc2	CHEMBL3544718
+CN1C[C@H](C[C@H]1c2cccnc2)OS(=O)(=O)C	CHEMBL119186
+CN1CCC[C@H]1c2ccc[n+](CCCC#Cc3ccccc3C#CCCC[n+]4cccc(c4)[C@@H]5CCCN5C)c2	CHEMBL1182432
+CCCCCCCCCCC[n+]1cccc2[C@@H]3[C@@H](CCN3C)CCc12	CHEMBL1185915
+CN1CCC[C@H]1c2ccc[n+](CCCCCc3cc(CCCCC[n+]4cccc(c4)[C@@H]5CCCN5C)cc(CCCCC[n+]6cccc(c6)[C@@H]7CCCN7C)c3)c2	CHEMBL1182507
+CN1CCC[C@H]1c2ccc[n+](CCCCCCCCCCC[n+]3cccc(c3)[C@@H]4CCCN4C)c2	CHEMBL1179942
+Cc1cncc(c1)[C@@H]2CCC[N+]2(C)[O-]	CHEMBL3640778
+O=S(=O)(Nc1ncns1)c2ccc3c(cccc3c2)N4CCC[C@H]4c5cccnc5	CHEMBL3692144
+CCCC[C@H]1CC[C@H](N1C)c2cccnc2	CHEMBL119581
+CCCCCCCCCCCC[n+]1cccc(c1)[C@@H]2CCCN2C	CHEMBL1179038
+CN1CCC[C@H]1c2ccc[n+]([BH2-]C#N)c2	CHEMBL282473
+COCC1CCN(C)[C@@H]1c2cccnc2	CHEMBL119020
+CN1CCC[C@H]1c2ccc[n+](CCCCCCCCCC[n+]3cccc(c3)[C@@H]4CCCN4C)c2	CHEMBL1179963
+CCCCCCCCCC[n+]1cccc2[C@@H]3[C@@H](CCN3C)CCc12	CHEMBL1185930
+CN1CCC(CF)[C@H]1c2cccnc2	CHEMBL119016
+CN1[C@@H](CC[C@H]1c2cccnc2)c3ccccc3	CHEMBL116998
+C[N@+]1(CC[N@+]2(C)CCC[C@@H]2c3cccnc3)CCC[C@H]1c4cccnc4	CHEMBL1358826
+CN1[C@@H](C[C@@H](OC2O[C@@H]([C@@H](O)[C@H](O)[C@H]2O)C(=O)O)C1=O)c3cccnc3	CHEMBL3544598
+CN1C[C@@H](CC#N)C[C@H]1c2cccnc2	CHEMBL334001
+OCN1[C@@H](CCC1=O)c2cccnc2	CHEMBL3544621
+COCCOc1ncccc1[C@@H]2C(C(=O)C(C)C)C(=O)C(=O)N2c3ccc(cc3)c4ccc(C)s4	CHEMBL3679738
+Clc1ccc(OC[C@@H]2CN3C(=O)CC[C@@]3(O2)c4cccnc4)cc1	CHEMBL343159
+CN1CCC[C@H]1c2ccc[n+](CCCCCCCCC[n+]3cccc(c3)[C@@H]4CCCN4C)c2	CHEMBL1183837
+COc1ncc(cc1c2ncc(cc2[C@@H]3CC[C@H]4[C@H](OC(=O)N34)c5cc(cc(c5)C(F)(F)F)C(F)(F)F)C(F)(F)F)c6c(C)cc(cc6C)C(=O)O	CHEMBL3657533
+CN1C[C@H](C[C@H]1c2cccnc2)OC(=O)C	CHEMBL419230
+CCCCCCCCC[n+]1cccc2[C@@H]3[C@@H](CCN3C)CCc12	CHEMBL1179016
+Clc1ccc(OC[C@H]2CN3C(=O)CC[C@@]3(O2)c4cccnc4)cc1	CHEMBL442410
\ No newline at end of file
--- a/test-data/out4.smi	Mon Aug 12 12:57:32 2019 -0400
+++ b/test-data/out4.smi	Fri Sep 06 07:50:15 2019 -0400
@@ -1,4 +1,4 @@
-C1CCCCC1
-C1CCCCCCCCCCC1
-C1CCCCCCC1
-C1CCCC1
\ No newline at end of file
+C1CCCC1	CHEMBL1370850
+C1CCCCCCCCCCC1	CHEMBL3185808
+C1CCCCCCC1	CHEMBL452651
+C1CCCCC1	CHEMBL15980
\ No newline at end of file