pub_soft/rdkit
3
0
Fork 0
mirror of https://github.com/rdkit/rdkit.git synced 2026-06-03 21:44:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

update a PAINS based on input from Simon Saubern

Browse Source
This commit is contained in:
Greg Landrum
2015-08-26 04:59:52 +02:00
parent 7b9a009619
commit e2487ffe79
3 changed files with 6 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
Data/Pains/test_data/run_tests.py
View File

@@ -14,12 +14,14 @@ class TestCase(unittest.TestCase):
def setUp(self):
self.basePath=os.path.join(RDConfig.RDDataDir,'Pains')
self.painsFile = os.path.join(self.basePath,'wehi_pains.csv')
self.painsDefs = [x for x in csv.reader(open(self.painsFile,'r'))]
with open(self.painsFile,'r') as inf:
self.painsDefs = [x for x in csv.reader(inf)]
self.matchers = [Chem.MolFromSmarts(x[0],mergeHs=True) for x in self.painsDefs]
def test1(self):
" molecules that we know should match "
testData = [x.strip().split() for x in open(os.path.join(self.basePath,'test_data','test_set3.txt'),'r') if x[0] != '#']
with open(os.path.join(self.basePath,'test_data','test_set3.txt'),'r') as inf:
testData = [x.strip().split() for x in inf if x[0] != '#']
for line in testData:
self.assertEqual(len(line),5)
id_ = int(line[0])

2
Data/Pains/test_data/test_set3.txt
View File

@@ -468,7 +468,7 @@
470 [#6]-[#6](=[!#6&!#1;!R])-[#6](=[!#6&!#1;!R])-[$([#6]),$([#16](=[#8])=[#8])] Cc1coc2c1C(=O)C(=O)c1c-2ccc2c1CC[C@@H](O)[C@]2(C)O CHEMBL3287734 ChEMBL
471 [#7]-[#6;X4]-c:1:c:c:c:c:c:1-[#8]-[#1] CN(C)c1ccc(C(Nc2nc3c(Cl)cccc3s2)c2c(O)ccc3ccccc23)cc1 CHEMBL3289923 ChEMBL
472 c:1:c:c(:c:c:c:1-[#7](-[#6;X4])-[#6;X4])-[#6]=[#6] CN(C)c1ccc(/C=C/C(=O)C2CCc3ccccc3C2=O)cc1 CHEMBL3289943 ChEMBL
473 c:1:c:c(:c:c:c:1-[#8]-[#6;X4])-[#7;!H0,$([#7]-[#6;X4])]-[#6;X4] C/N=C(\c1cccs1)N(C)c1ccc(OC)c(CSC2CCCC2)c1 CHEMBL3287822 ChEMBL
473 c:1:c:c(:c:c:c:1-[#8]-[#6;X4])-[#7;$([#7!H0]-[#6;X4]),$([#7](-[#6;X4])-[#6;X4])] S=C(N1CC(N(CC1)c2ccc(cc2)OC)C)Nc3c(cccc3)C(=O)OC WEHI-0023997 wehi
474 [#7]-1-[#6](=[#16])-[#16]-[#6](=[#6])-[#6]-1=[#8] O=C1Nc2ccc([N+](=O)[O-])cc2/C1=C1/SC(=S)N(NC(=O)c2cccnc2)C1=O CHEMBL3288597 ChEMBL
475 c:1(:c:c:c(:c:c:1)-[#6]=[#7]-[#7])-[#8]-[#1] O=C(N/N=C/c1ccc(O)cc1O)c1cc(-c2ccc(Cl)cc2)n[nH]1 CHEMBL3287091 ChEMBL
476 [#6]-1(=[#6])-[#6]=[#7]-[!#6&!#1]-[#6]-1=[#8] C=CCn1c(=O)/c(=C2/Sc3ccccc3N2CC)s/c1=C1/C(=O)NN=C1C CHEMBL3207742 ChEMBL

2
Data/Pains/wehi_pains.csv
View File

@@ -471,7 +471,7 @@
"[#6]-[#6](=[!#6&!#1;!R])-[#6](=[!#6&!#1;!R])-[$([#6]),$([#16](=[#8])=[#8])]","<regId=imine_one_A(321)>"
"[#7]-[#6;X4]-c:1:c:c:c:c:c:1-[#8]-[#1]","<regId=mannich_A(296)>"
"c:1:c:c(:c:c:c:1-[#7](-[#6;X4])-[#6;X4])-[#6]=[#6]","<regId=anil_di_alk_B(251)>"
"c:1:c:c(:c:c:c:1-[#8]-[#6;X4])-[#7;!H0,$([#7]-[#6;X4])]-[#6;X4]","<regId=anil_di_alk_C(246)>"
"c:1:c:c(:c:c:c:1-[#8]-[#6;X4])-[#7;$([#7!H0]-[#6;X4]),$([#7](-[#6;X4])-[#6;X4])]","<regId=anil_di_alk_C(246)>"
"[#7]-1-[#6](=[#16])-[#16]-[#6](=[#6])-[#6]-1=[#8]","<regId=ene_rhod_A(235)>"
"c:1(:c:c:c(:c:c:1)-[#6]=[#7]-[#7])-[#8]-[#1]","<regId=hzone_phenol_B(215)>"
"[#6]-1(=[#6])-[#6]=[#7]-[!#6&!#1]-[#6]-1=[#8]","<regId=ene_five_het_A(201)>"
1 c:1:c:c(:c:c:c:1-[#6;X4]-c:2:c:c:c(:c:c:2)-[#7&H2,$([#7;!H0]-[#6;X4]),$([#7](-[#6X4])-[#6X4])])-[#7&H2,$([#7;!H0]-[#6;X4]),$([#7](-[#6X4])-[#6X4])] <regId=anil_di_alk_F(14)>
471 [#6]-[#6](=[!#6&!#1;!R])-[#6](=[!#6&!#1;!R])-[$([#6]),$([#16](=[#8])=[#8])] <regId=imine_one_A(321)>
472 [#7]-[#6;X4]-c:1:c:c:c:c:c:1-[#8]-[#1] <regId=mannich_A(296)>
473 c:1:c:c(:c:c:c:1-[#7](-[#6;X4])-[#6;X4])-[#6]=[#6] <regId=anil_di_alk_B(251)>
474 c:1:c:c(:c:c:c:1-[#8]-[#6;X4])-[#7;!H0,$([#7]-[#6;X4])]-[#6;X4] c:1:c:c(:c:c:c:1-[#8]-[#6;X4])-[#7;$([#7!H0]-[#6;X4]),$([#7](-[#6;X4])-[#6;X4])] <regId=anil_di_alk_C(246)>
475 [#7]-1-[#6](=[#16])-[#16]-[#6](=[#6])-[#6]-1=[#8] <regId=ene_rhod_A(235)>
476 c:1(:c:c:c(:c:c:1)-[#6]=[#7]-[#7])-[#8]-[#1] <regId=hzone_phenol_B(215)>
477 [#6]-1(=[#6])-[#6]=[#7]-[!#6&!#1]-[#6]-1=[#8] <regId=ene_five_het_A(201)>