inter dataset sd in mg units

3 files changed, 624 insertions, 0 deletions

diff --git a/data/all_mg_dup.csv b/data/all_mg_dup.csv
new file mode 100644
index 0000000..3e938ed
--- /dev/null
+++ b/data/all_mg_dup.csv
@@ -0,0 +1,215 @@
+SMILES,LOAEL
+OCC(C1OC(=O)C(=C1O)O)O,-3.4844
+OCC(C1OC(=O)C(=C1O)O)O,-3.1915
+CC(c1ccccc1)C,-2.6646
+CC(c1ccccc1)C,-2.5198
+CCc1ccccc1,-2.6107
+CCc1ccccc1,-2.4639
+OCCO,-2.3979
+OCCO,-2.6021
+OCCO,-3.301
+OCCO,-2.9638
+OCCO,-3.0
+C=Cc1ccccc1,-1.3222
+C=Cc1ccccc1,-2.4548
+C=Cc1ccccc1,-2.6021
+ClC(C(c1ccc(cc1)Cl)c1ccc(cc1)Cl)(Cl)Cl,-1.5051
+ClC(C(c1ccc(cc1)Cl)c1ccc(cc1)Cl)(Cl)Cl,0.60206
+COCN(c1c(CC)cccc1CC)C(=O)CCl,-1.1761
+COCN(c1c(CC)cccc1CC)C(=O)CCl,-1.1461
+COP(=S)(SCn1nnc2c(c1=O)cccc2)OC,0.4437
+COP(=S)(SCn1nnc2c(c1=O)cccc2)OC,-0.35218
+COP(=S)(SCn1nnc2c(c1=O)cccc2)OC,-0.41162
+O=C(C(C)(C)C)C(n1ncnc1)Oc1ccc(cc1)Cl,-1.3979
+O=C(C(C)(C)C)C(n1ncnc1)Oc1ccc(cc1)Cl,-2.0569
+ClC(C(SN1C(=O)C2C(C1=O)CC=CC2)(Cl)Cl)Cl,-1.0792
+ClC(C(SN1C(=O)C2C(C1=O)CC=CC2)(Cl)Cl)Cl,-1.1761
+CNC(=O)Oc1cccc2c1cccc2,-1.1931
+CNC(=O)Oc1cccc2c1cccc2,-1.7782
+ClC1CC2C(C1Cl)C1(C(C2(Cl)C(=C1Cl)Cl)(Cl)Cl)Cl,0.56864
+ClC1CC2C(C1Cl)C1(C(C2(Cl)C(=C1Cl)Cl)(Cl)Cl)Cl,0.30103
+ClC1CC2C(C1Cl)C1(C(C2(Cl)C(=C1Cl)Cl)(Cl)Cl)Cl,-0.77815
+ClC1CC2C(C1Cl)C1(C(C2(Cl)C(=C1Cl)Cl)(Cl)Cl)Cl,0.60206
+Nc1ccc(cc1)Cl,-0.77815
+Nc1ccc(cc1)Cl,-1.0969
+CCOP(=S)(Oc1ccc2c(c1)oc(=O)c(c2C)Cl)OCC,0.09691
+CCOP(=S)(Oc1ccc2c(c1)oc(=O)c(c2C)Cl)OCC,-0.23045
+COC(=O)c1c(Cl)c(Cl)c(c(c1Cl)Cl)C(=O)OC,-2.699
+COC(=O)c1c(Cl)c(Cl)c(c(c1Cl)Cl)C(=O)OC,-1.0
+OC(=O)C(Cl)(Cl)C,-1.4498
+OC(=O)C(Cl)(Cl)C,-1.699
+ClCCl,-1.699
+ClCCl,-1.7208
+COP(=O)(OC=C(Cl)Cl)OC,-0.36173
+COP(=O)(OC=C(Cl)Cl)OC,-0.33244
+OC(C(Cl)(Cl)Cl)(c1ccc(cc1)Cl)c1ccc(cc1)Cl,-1.301
+OC(C(Cl)(Cl)Cl)(c1ccc(cc1)Cl)c1ccc(cc1)Cl,-0.39794
+ClC1=C(Cl)C2(C(C1(Cl)C1C2C2CC1C1C2O1)(Cl)Cl)Cl,1.301
+ClC1=C(Cl)C2(C(C1(Cl)C1C2C2CC1C1C2O1)(Cl)Cl)Cl,0.90309
+ClC1=C(Cl)C2(C(C1(Cl)C1C2C2CC1C1C2O1)(Cl)Cl)Cl,1.0
+ClC1=C(Cl)C2(C(C1(Cl)C1C2C2CC1C1C2O1)(Cl)Cl)Cl,0.60206
+O=C(NC(=O)c1c(F)cccc1F)Nc1ccc(cc1)Cl,-0.90309
+O=C(NC(=O)c1c(F)cccc1F)Nc1ccc(cc1)Cl,-0.89209
+O=C(NC(=O)c1c(F)cccc1F)Nc1ccc(cc1)Cl,-0.8451
+CNC(=O)CSP(=S)(OC)OC,0.60206
+CNC(=O)CSP(=S)(OC)OC,-0.69897
+c1ccc(cc1)Nc1ccccc1,-1.4914
+c1ccc(cc1)Nc1ccccc1,-1.3979
+c1ccn2c(c1)c1ccccn1CC2,0.23657
+c1ccn2c(c1)c1ccccn1CC2,0.24413
+CCSCCSP(=S)(OCC)OCC,1.0
+CCSCCSP(=S)(OCC)OCC,1.3979
+CCSCCSP(=S)(OCC)OCC,0.65758
+O=C(N(C)C)Nc1ccc(c(c1)Cl)Cl,-0.77815
+O=C(N(C)C)Nc1ccc(c(c1)Cl)Cl,-0.79588
+ClCCP(=O)(O)O,-2.1761
+ClCCP(=O)(O)O,-2.6493
+ClCCP(=O)(O)O,-1.0792
+Cn1cc(c2cccc(c2)C(F)(F)F)c(=O)c(c1)c1ccccc1,-1.3979
+Cn1cc(c2cccc(c2)C(F)(F)F)c(=O)c(c1)c1ccccc1,-1.5119
+CCP(=S)(Sc1ccccc1)OCC,-0.19866
+CCP(=S)(Sc1ccccc1)OCC,-0.69897
+ClC1C(Cl)C(Cl)C(C(C1Cl)Cl)Cl,-0.69897
+ClC1C(Cl)C(Cl)C(C(C1Cl)Cl)Cl,-0.66276
+ClC1C(Cl)C(Cl)C(C(C1Cl)Cl)Cl,-0.6721
+ClC1C(Cl)C(Cl)C(C(C1Cl)Cl)Cl,-0.90309
+ClC1C(Cl)C(Cl)C(C(C1Cl)Cl)Cl,-0.60206
+C=CCOC(c1ccc(cc1Cl)Cl)Cn1cncc1,-1.6021
+C=CCOC(c1ccc(cc1Cl)Cl)Cn1cncc1,-1.1761
+CCOC(=O)CC(C(=O)OCC)SP(=S)(OC)OC,-1.699
+CCOC(=O)CC(C(=O)OCC)SP(=S)(OC)OC,-2.5563
+COc1sc(=O)n(n1)CSP(=S)(OC)OC,-0.30103
+COc1sc(=O)n(n1)CSP(=S)(OC)OC,0.09691
+COc1sc(=O)n(n1)CSP(=S)(OC)OC,-0.09691
+COc1sc(=O)n(n1)CSP(=S)(OC)OC,-0.20412
+CNC(=O)ON=C(SC)C,-1.0
+CNC(=O)ON=C(SC)C,-1.301
+CCOP(=S)(Oc1ccc(cc1)N(=O)=O)OCC,-0.54407
+CCOP(=S)(Oc1ccc(cc1)N(=O)=O)OCC,0.37675
+COP(=S)(SCN1C(=O)c2c(C1=O)cccc2)OC,-1.301
+COP(=S)(SCN1C(=O)c2c(C1=O)cccc2)OC,-0.95424
+CCN(C(=O)C(=C(OP(=O)(OC)OC)C)Cl)CC,-1.0899
+CCN(C(=O)C(=C(OP(=O)(OC)OC)C)Cl)CC,-0.17609
+CCN(c1nc(cc(n1)C)OP(=S)(OC)OC)CC,-0.39794
+CCN(c1nc(cc(n1)C)OP(=S)(OC)OC)CC,-1.1399
+CCC(=O)Nc1ccc(c(c1)Cl)Cl,-1.301
+CCC(=O)Nc1ccc(c(c1)Cl)Cl,-1.8808
+CCCC1COC(O1)(Cn1cncn1)c1ccc(cc1Cl)Cl,-1.3979
+CCCC1COC(O1)(Cn1cncn1)c1ccc(cc1Cl)Cl,-1.9823
+CCNc1nc(NCC)nc(n1)Cl,-0.69897
+CCNc1nc(NCC)nc(n1)Cl,-0.72428
+ClC=C(c1cc(Cl)c(cc1Cl)Cl)OP(=O)(OC)OC,-2.0
+ClC=C(c1cc(Cl)c(cc1Cl)Cl)OP(=O)(OC)OC,-1.699
+CN(C(=S)SSC(=S)N(C)C)C,-1.1761
+CN(C(=S)SSC(=S)N(C)C)C,-1.0607
+CN(C(=S)SSC(=S)N(C)C)C,-0.73799
+CN(C(=S)SSC(=S)N(C)C)C,-1.0792
+CC(N(c1c(cc(cc1N(=O)=O)C(F)(F)F)N(=O)=O)C(C)C)C,-1.6021
+CC(N(c1c(cc(cc1N(=O)=O)C(F)(F)F)N(=O)=O)C(C)C)C,-3.0
+COP(=O)(SC)N,0.045757
+COP(=O)(SC)N,1.0
+COP(=O)(SC)N,0.5376
+COP(=O)(NC(=O)C)SC,-1.5441
+COP(=O)(NC(=O)C)SC,-0.39794
+CCOP(=S)(Oc1cc(C)nc(n1)C(C)C)OCC,-0.17609
+CCOP(=S)(Oc1cc(C)nc(n1)C(C)C)OCC,-0.76343
+NC1CCCCC1,-1.7672
+NC1CCCCC1,-1.7782
+OC(=O)CNCP(=O)(O)O,-3.0
+OC(=O)CNCP(=O)(O)O,-2.4771
+S=C1NCCN1,0.63827
+S=C1NCCN1,0.60206
+S=C1NCCN1,-0.09691
+CON(C(=O)Nc1ccc(c(c1)Cl)Cl)C,-0.79588
+CON(C(=O)Nc1ccc(c(c1)Cl)Cl)C,-0.39794
+CCOP(=S)(Oc1nc(Cl)c(cc1Cl)Cl)OCC,-1.0
+CCOP(=S)(Oc1nc(Cl)c(cc1Cl)Cl)OCC,-1.2388e-09
+CC(OC(=O)Nc1cccc(c1)Cl)C,-2.699
+CC(OC(=O)Nc1cccc(c1)Cl)C,-3.0
+CCCCOCCOCCOCc1cc2OCOc2cc1CCC,-2.3979
+CCCCOCCOCCOCc1cc2OCOc2cc1CCC,-2.0
+N#CC(c1ccc(c(c1)Oc1ccccc1)F)OC(=O)C1C(C1(C)C)C=C(Cl)Cl,-1.0969
+N#CC(c1ccc(c(c1)Oc1ccccc1)F)OC(=O)C1C(C1(C)C)C=C(Cl)Cl,-0.87506
+N#CC(c1ccc(c(c1)Oc1ccccc1)F)OC(=O)C1C(C1(C)C)C=C(Cl)Cl,-0.77815
+N#CC(c1ccc(c(c1)Oc1ccccc1)F)OC(=O)C1C(C1(C)C)C=C(Cl)Cl,-1.0792
+ClC1C=CC2C1C1(Cl)C(=C(C2(C1(Cl)Cl)Cl)Cl)Cl,0.60206
+ClC1C=CC2C1C1(Cl)C(=C(C2(C1(Cl)Cl)Cl)Cl)Cl,0.42022
+CCOP(=S)(SCSC(C)(C)C)OCC,1.301
+CCOP(=S)(SCSC(C)(C)C)OCC,-0.30103
+CCOP(=S)(SCSC(C)(C)C)OCC,1.2218
+CN(C=Nc1ccc(cc1C)C)C=Nc1ccc(cc1C)C,-1.0086
+CN(C=Nc1ccc(cc1C)C)C=Nc1ccc(cc1C)C,-1.0
+CC(N1C(=O)c2ccccc2NS1(=O)=O)C,-1.6021
+CC(N1C(=O)c2ccccc2NS1(=O)=O)C,-1.5441
+CCSC(CC1CC(=O)C(=C(NOCC=CCl)CC)C(=O)C1)C,-2.0
+CCSC(CC1CC(=O)C(=C(NOCC=CCl)CC)C(=O)C1)C,-1.9345
+CCCN(C(=O)SCC)CCC,-0.95424
+CCCN(C(=O)SCC)CCC,-1.3979
+CSc1ccc(cc1C)OP(=S)(OC)OC,-0.57403
+CSc1ccc(cc1C)OP(=S)(OC)OC,0.14267
+CSc1ccc(cc1C)OP(=S)(OC)OC,0.34679
+c1scc(n1)c1nc2c([nH]1)cccc2,-0.30103
+c1scc(n1)c1nc2c([nH]1)cccc2,-1.6021
+c1scc(n1)c1nc2c([nH]1)cccc2,-1.4771
+Clc1c(Cl)c([N+](=O)[O-])c(c(c1Cl)Cl)Cl,-2.0969
+Clc1c(Cl)c([N+](=O)[O-])c(c(c1Cl)Cl)Cl,-2.1461
+Nc1ncn[nH]1,-0.39794
+Nc1ncn[nH]1,-0.69897
+O=C(NC(=O)c1c(F)cccc1F)Nc1cc(Cl)c(c(c1F)Cl)F,-1.415
+O=C(NC(=O)c1c(F)cccc1F)Nc1cc(Cl)c(c(c1F)Cl)F,-1.3979
+C=CCC1=C(C)C(CC1=O)OC(=O)C1C(C1(C)C)C=C(C)C,-1.8751
+C=CCC1=C(C)C(CC1=O)OC(=O)C1C(C1(C)C)C=C(C)C,-1.3892
+C=CCC1=C(C)C(CC1=O)OC(=O)C1C(C1(C)C)C=C(C)C,-1.1399
+CON=C(c1ccccc1COc1ccccc1C)C(=O)OC,-2.574
+CON=C(c1ccccc1COc1ccccc1C)C(=O)OC,-2.5682
+CC(N(c1c(cc(cc1N(=O)=O)S(=O)(=O)N)N(=O)=O)C(C)C)C,-1.5666
+CC(N(c1c(cc(cc1N(=O)=O)S(=O)(=O)N)N(=O)=O)C(C)C)C,-1.6532
+CCCN(C(=O)n1cncc1)CCOc1c(Cl)cc(cc1Cl)Cl,-0.87506
+CCCN(C(=O)n1cncc1)CCOc1c(Cl)cc(cc1Cl)Cl,-0.70757
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)(C)C,-1.2889
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)(C)C,-1.3979
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)C=C(Cl)Cl,-1.8751
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)C=C(Cl)Cl,-1.699
+ClC1C2OC2C2C1C1(Cl)C(=C(C2(C1(Cl)Cl)Cl)Cl)Cl,0.69897
+ClC1C2OC2C2C1C1(Cl)C(=C(C2(C1(Cl)Cl)Cl)Cl)Cl,1.6021
+N#CC(c1ccccc1)(Cn1cncn1)CCc1ccc(cc1)Cl,-1.6021
+N#CC(c1ccccc1)(Cn1cncn1)CCc1ccc(cc1)Cl,-1.4771
+O=C(C1C(C1(C)C)C=C(C(F)(F)F)Cl)OCc1cccc(c1C)c1ccccc1,-0.69897
+O=C(C1C(C1(C)C)C=C(C(F)(F)F)Cl)OCc1cccc(c1C)c1ccccc1,-0.90309
+[O-][N+](=O)c1cc(Cl)c(c(c1)Cl)N,-2.1761
+[O-][N+](=O)c1cc(Cl)c(c(c1)Cl)N,-2.3802
+CC(Oc1cccc(c1)NC(=O)c1ccccc1C(F)(F)F)C,-2.699
+CC(Oc1cccc(c1)NC(=O)c1ccccc1C(F)(F)F)C,-1.9395
+CCCCNC(=O)n1c(NC(=O)OC)nc2c1cccc2,-2.0607
+CCCCNC(=O)n1c(NC(=O)OC)nc2c1cccc2,-2.3979
+ClC(SN1C(=O)c2c(C1=O)cccc2)(Cl)Cl,-2.699
+ClC(SN1C(=O)c2c(C1=O)cccc2)(Cl)Cl,-1.6021
+ClC(SN1C(=O)c2c(C1=O)cccc2)(Cl)Cl,-1.699
+C#CCOS(=O)OC1CCCCC1Oc1ccc(cc1)C(C)(C)C,-2.0
+C#CCOS(=O)OC1CCCCC1Oc1ccc(cc1)C(C)(C)C,-1.2788
+N#Cc1sc2=c(sc1C#N)c(=O)c1c(c2=O)cccc1,-1.0
+N#Cc1sc2=c(sc1C#N)c(=O)c1c(c2=O)cccc1,-0.77815
+CN(C(=O)Oc1nc(nc(c1C)C)N(C)C)C,-1.0969
+CN(C(=O)Oc1nc(nc(c1C)C)N(C)C)C,-1.0899
+CNc1cnn(c(=O)c1Cl)c1cccc(c1)C(F)(F)F,-1.273
+CNc1cnn(c(=O)c1Cl)c1cccc(c1)C(F)(F)F,-1.7097
+Clc1ccccc1c1nnc(nn1)c1ccccc1Cl,-1.301
+Clc1ccccc1c1nnc(nn1)c1ccccc1Cl,-1.238
+CCCCCCCCc1cc(N(=O)=O)c(c(c1)N(=O)=O)OC(=O)C=CC,-1.699
+CCCCCCCCc1cc(N(=O)=O)c(c(c1)N(=O)=O)OC(=O)C=CC,-1.8062
+CCSC(=O)N1CCCCCC1,-1.1706
+CCSC(=O)N1CCCCCC1,-0.30103
+OC(C(C)(C)C)C(n1ncnc1)Oc1ccc(cc1)Cl,-1.3979
+OC(C(C)(C)C)C(n1ncnc1)Oc1ccc(cc1)Cl,-2.0212
+CCOP(=O)(Oc1ccc(c(c1)C)SC)NC(C)C,-0.17609
+CCOP(=O)(Oc1ccc(c(c1)C)SC)NC(C)C,-0.23045
+Cn1ccc(cc1)c1ccn(cc1)C,-0.57403
+Cn1ccc(cc1)c1ccn(cc1)C,-0.40654
+CCCCC(c1ccc(cc1)Cl)(Cn1cncn1)C#N,-0.993
+CCCCC(c1ccc(cc1)Cl)(Cn1cncn1)C#N,-0.99123
+Fc1ccc(cc1)C(=O)CCCN1CCN(CC1)c1ccccn1,-2.0607
+Fc1ccc(cc1)C(=O)CCCN1CCN(CC1)c1ccccn1,-1.4771
+N#CC(c1c(Cl)ccc(c1Cl)n1ncc(=O)[nH]c1=O)c1ccc(cc1)Cl,-1.1761
+N#CC(c1c(Cl)ccc(c1Cl)n1ncc(=O)[nH]c1=O)c1ccc(cc1)Cl,-1.3617
+COC1CC(OC2C(C)C=CC=C3COC4C3(O)C(C=C(C4O)C)C(=O)OC3CC(CC=C2C)OC2(C3)C=CC(C(O2)C(C)C)C)OC(C1OC1CC(OC)C(C(O1)C)NC(=O)C)C,-1.9287e-16
+COC1CC(OC2C(C)C=CC=C3COC4C3(O)C(C=C(C4O)C)C(=O)OC3CC(CC=C2C)OC2(C3)C=CC(C(O2)C(C)C)C)OC(C1OC1CC(OC)C(C(O1)C)NC(=O)C)C,-0.39794
diff --git a/data/mazzatorta_mg_dup.csv b/data/mazzatorta_mg_dup.csv
new file mode 100644
index 0000000..3e938ed
--- /dev/null
+++ b/data/mazzatorta_mg_dup.csv
@@ -0,0 +1,215 @@
+SMILES,LOAEL
+OCC(C1OC(=O)C(=C1O)O)O,-3.4844
+OCC(C1OC(=O)C(=C1O)O)O,-3.1915
+CC(c1ccccc1)C,-2.6646
+CC(c1ccccc1)C,-2.5198
+CCc1ccccc1,-2.6107
+CCc1ccccc1,-2.4639
+OCCO,-2.3979
+OCCO,-2.6021
+OCCO,-3.301
+OCCO,-2.9638
+OCCO,-3.0
+C=Cc1ccccc1,-1.3222
+C=Cc1ccccc1,-2.4548
+C=Cc1ccccc1,-2.6021
+ClC(C(c1ccc(cc1)Cl)c1ccc(cc1)Cl)(Cl)Cl,-1.5051
+ClC(C(c1ccc(cc1)Cl)c1ccc(cc1)Cl)(Cl)Cl,0.60206
+COCN(c1c(CC)cccc1CC)C(=O)CCl,-1.1761
+COCN(c1c(CC)cccc1CC)C(=O)CCl,-1.1461
+COP(=S)(SCn1nnc2c(c1=O)cccc2)OC,0.4437
+COP(=S)(SCn1nnc2c(c1=O)cccc2)OC,-0.35218
+COP(=S)(SCn1nnc2c(c1=O)cccc2)OC,-0.41162
+O=C(C(C)(C)C)C(n1ncnc1)Oc1ccc(cc1)Cl,-1.3979
+O=C(C(C)(C)C)C(n1ncnc1)Oc1ccc(cc1)Cl,-2.0569
+ClC(C(SN1C(=O)C2C(C1=O)CC=CC2)(Cl)Cl)Cl,-1.0792
+ClC(C(SN1C(=O)C2C(C1=O)CC=CC2)(Cl)Cl)Cl,-1.1761
+CNC(=O)Oc1cccc2c1cccc2,-1.1931
+CNC(=O)Oc1cccc2c1cccc2,-1.7782
+ClC1CC2C(C1Cl)C1(C(C2(Cl)C(=C1Cl)Cl)(Cl)Cl)Cl,0.56864
+ClC1CC2C(C1Cl)C1(C(C2(Cl)C(=C1Cl)Cl)(Cl)Cl)Cl,0.30103
+ClC1CC2C(C1Cl)C1(C(C2(Cl)C(=C1Cl)Cl)(Cl)Cl)Cl,-0.77815
+ClC1CC2C(C1Cl)C1(C(C2(Cl)C(=C1Cl)Cl)(Cl)Cl)Cl,0.60206
+Nc1ccc(cc1)Cl,-0.77815
+Nc1ccc(cc1)Cl,-1.0969
+CCOP(=S)(Oc1ccc2c(c1)oc(=O)c(c2C)Cl)OCC,0.09691
+CCOP(=S)(Oc1ccc2c(c1)oc(=O)c(c2C)Cl)OCC,-0.23045
+COC(=O)c1c(Cl)c(Cl)c(c(c1Cl)Cl)C(=O)OC,-2.699
+COC(=O)c1c(Cl)c(Cl)c(c(c1Cl)Cl)C(=O)OC,-1.0
+OC(=O)C(Cl)(Cl)C,-1.4498
+OC(=O)C(Cl)(Cl)C,-1.699
+ClCCl,-1.699
+ClCCl,-1.7208
+COP(=O)(OC=C(Cl)Cl)OC,-0.36173
+COP(=O)(OC=C(Cl)Cl)OC,-0.33244
+OC(C(Cl)(Cl)Cl)(c1ccc(cc1)Cl)c1ccc(cc1)Cl,-1.301
+OC(C(Cl)(Cl)Cl)(c1ccc(cc1)Cl)c1ccc(cc1)Cl,-0.39794
+ClC1=C(Cl)C2(C(C1(Cl)C1C2C2CC1C1C2O1)(Cl)Cl)Cl,1.301
+ClC1=C(Cl)C2(C(C1(Cl)C1C2C2CC1C1C2O1)(Cl)Cl)Cl,0.90309
+ClC1=C(Cl)C2(C(C1(Cl)C1C2C2CC1C1C2O1)(Cl)Cl)Cl,1.0
+ClC1=C(Cl)C2(C(C1(Cl)C1C2C2CC1C1C2O1)(Cl)Cl)Cl,0.60206
+O=C(NC(=O)c1c(F)cccc1F)Nc1ccc(cc1)Cl,-0.90309
+O=C(NC(=O)c1c(F)cccc1F)Nc1ccc(cc1)Cl,-0.89209
+O=C(NC(=O)c1c(F)cccc1F)Nc1ccc(cc1)Cl,-0.8451
+CNC(=O)CSP(=S)(OC)OC,0.60206
+CNC(=O)CSP(=S)(OC)OC,-0.69897
+c1ccc(cc1)Nc1ccccc1,-1.4914
+c1ccc(cc1)Nc1ccccc1,-1.3979
+c1ccn2c(c1)c1ccccn1CC2,0.23657
+c1ccn2c(c1)c1ccccn1CC2,0.24413
+CCSCCSP(=S)(OCC)OCC,1.0
+CCSCCSP(=S)(OCC)OCC,1.3979
+CCSCCSP(=S)(OCC)OCC,0.65758
+O=C(N(C)C)Nc1ccc(c(c1)Cl)Cl,-0.77815
+O=C(N(C)C)Nc1ccc(c(c1)Cl)Cl,-0.79588
+ClCCP(=O)(O)O,-2.1761
+ClCCP(=O)(O)O,-2.6493
+ClCCP(=O)(O)O,-1.0792
+Cn1cc(c2cccc(c2)C(F)(F)F)c(=O)c(c1)c1ccccc1,-1.3979
+Cn1cc(c2cccc(c2)C(F)(F)F)c(=O)c(c1)c1ccccc1,-1.5119
+CCP(=S)(Sc1ccccc1)OCC,-0.19866
+CCP(=S)(Sc1ccccc1)OCC,-0.69897
+ClC1C(Cl)C(Cl)C(C(C1Cl)Cl)Cl,-0.69897
+ClC1C(Cl)C(Cl)C(C(C1Cl)Cl)Cl,-0.66276
+ClC1C(Cl)C(Cl)C(C(C1Cl)Cl)Cl,-0.6721
+ClC1C(Cl)C(Cl)C(C(C1Cl)Cl)Cl,-0.90309
+ClC1C(Cl)C(Cl)C(C(C1Cl)Cl)Cl,-0.60206
+C=CCOC(c1ccc(cc1Cl)Cl)Cn1cncc1,-1.6021
+C=CCOC(c1ccc(cc1Cl)Cl)Cn1cncc1,-1.1761
+CCOC(=O)CC(C(=O)OCC)SP(=S)(OC)OC,-1.699
+CCOC(=O)CC(C(=O)OCC)SP(=S)(OC)OC,-2.5563
+COc1sc(=O)n(n1)CSP(=S)(OC)OC,-0.30103
+COc1sc(=O)n(n1)CSP(=S)(OC)OC,0.09691
+COc1sc(=O)n(n1)CSP(=S)(OC)OC,-0.09691
+COc1sc(=O)n(n1)CSP(=S)(OC)OC,-0.20412
+CNC(=O)ON=C(SC)C,-1.0
+CNC(=O)ON=C(SC)C,-1.301
+CCOP(=S)(Oc1ccc(cc1)N(=O)=O)OCC,-0.54407
+CCOP(=S)(Oc1ccc(cc1)N(=O)=O)OCC,0.37675
+COP(=S)(SCN1C(=O)c2c(C1=O)cccc2)OC,-1.301
+COP(=S)(SCN1C(=O)c2c(C1=O)cccc2)OC,-0.95424
+CCN(C(=O)C(=C(OP(=O)(OC)OC)C)Cl)CC,-1.0899
+CCN(C(=O)C(=C(OP(=O)(OC)OC)C)Cl)CC,-0.17609
+CCN(c1nc(cc(n1)C)OP(=S)(OC)OC)CC,-0.39794
+CCN(c1nc(cc(n1)C)OP(=S)(OC)OC)CC,-1.1399
+CCC(=O)Nc1ccc(c(c1)Cl)Cl,-1.301
+CCC(=O)Nc1ccc(c(c1)Cl)Cl,-1.8808
+CCCC1COC(O1)(Cn1cncn1)c1ccc(cc1Cl)Cl,-1.3979
+CCCC1COC(O1)(Cn1cncn1)c1ccc(cc1Cl)Cl,-1.9823
+CCNc1nc(NCC)nc(n1)Cl,-0.69897
+CCNc1nc(NCC)nc(n1)Cl,-0.72428
+ClC=C(c1cc(Cl)c(cc1Cl)Cl)OP(=O)(OC)OC,-2.0
+ClC=C(c1cc(Cl)c(cc1Cl)Cl)OP(=O)(OC)OC,-1.699
+CN(C(=S)SSC(=S)N(C)C)C,-1.1761
+CN(C(=S)SSC(=S)N(C)C)C,-1.0607
+CN(C(=S)SSC(=S)N(C)C)C,-0.73799
+CN(C(=S)SSC(=S)N(C)C)C,-1.0792
+CC(N(c1c(cc(cc1N(=O)=O)C(F)(F)F)N(=O)=O)C(C)C)C,-1.6021
+CC(N(c1c(cc(cc1N(=O)=O)C(F)(F)F)N(=O)=O)C(C)C)C,-3.0
+COP(=O)(SC)N,0.045757
+COP(=O)(SC)N,1.0
+COP(=O)(SC)N,0.5376
+COP(=O)(NC(=O)C)SC,-1.5441
+COP(=O)(NC(=O)C)SC,-0.39794
+CCOP(=S)(Oc1cc(C)nc(n1)C(C)C)OCC,-0.17609
+CCOP(=S)(Oc1cc(C)nc(n1)C(C)C)OCC,-0.76343
+NC1CCCCC1,-1.7672
+NC1CCCCC1,-1.7782
+OC(=O)CNCP(=O)(O)O,-3.0
+OC(=O)CNCP(=O)(O)O,-2.4771
+S=C1NCCN1,0.63827
+S=C1NCCN1,0.60206
+S=C1NCCN1,-0.09691
+CON(C(=O)Nc1ccc(c(c1)Cl)Cl)C,-0.79588
+CON(C(=O)Nc1ccc(c(c1)Cl)Cl)C,-0.39794
+CCOP(=S)(Oc1nc(Cl)c(cc1Cl)Cl)OCC,-1.0
+CCOP(=S)(Oc1nc(Cl)c(cc1Cl)Cl)OCC,-1.2388e-09
+CC(OC(=O)Nc1cccc(c1)Cl)C,-2.699
+CC(OC(=O)Nc1cccc(c1)Cl)C,-3.0
+CCCCOCCOCCOCc1cc2OCOc2cc1CCC,-2.3979
+CCCCOCCOCCOCc1cc2OCOc2cc1CCC,-2.0
+N#CC(c1ccc(c(c1)Oc1ccccc1)F)OC(=O)C1C(C1(C)C)C=C(Cl)Cl,-1.0969
+N#CC(c1ccc(c(c1)Oc1ccccc1)F)OC(=O)C1C(C1(C)C)C=C(Cl)Cl,-0.87506
+N#CC(c1ccc(c(c1)Oc1ccccc1)F)OC(=O)C1C(C1(C)C)C=C(Cl)Cl,-0.77815
+N#CC(c1ccc(c(c1)Oc1ccccc1)F)OC(=O)C1C(C1(C)C)C=C(Cl)Cl,-1.0792
+ClC1C=CC2C1C1(Cl)C(=C(C2(C1(Cl)Cl)Cl)Cl)Cl,0.60206
+ClC1C=CC2C1C1(Cl)C(=C(C2(C1(Cl)Cl)Cl)Cl)Cl,0.42022
+CCOP(=S)(SCSC(C)(C)C)OCC,1.301
+CCOP(=S)(SCSC(C)(C)C)OCC,-0.30103
+CCOP(=S)(SCSC(C)(C)C)OCC,1.2218
+CN(C=Nc1ccc(cc1C)C)C=Nc1ccc(cc1C)C,-1.0086
+CN(C=Nc1ccc(cc1C)C)C=Nc1ccc(cc1C)C,-1.0
+CC(N1C(=O)c2ccccc2NS1(=O)=O)C,-1.6021
+CC(N1C(=O)c2ccccc2NS1(=O)=O)C,-1.5441
+CCSC(CC1CC(=O)C(=C(NOCC=CCl)CC)C(=O)C1)C,-2.0
+CCSC(CC1CC(=O)C(=C(NOCC=CCl)CC)C(=O)C1)C,-1.9345
+CCCN(C(=O)SCC)CCC,-0.95424
+CCCN(C(=O)SCC)CCC,-1.3979
+CSc1ccc(cc1C)OP(=S)(OC)OC,-0.57403
+CSc1ccc(cc1C)OP(=S)(OC)OC,0.14267
+CSc1ccc(cc1C)OP(=S)(OC)OC,0.34679
+c1scc(n1)c1nc2c([nH]1)cccc2,-0.30103
+c1scc(n1)c1nc2c([nH]1)cccc2,-1.6021
+c1scc(n1)c1nc2c([nH]1)cccc2,-1.4771
+Clc1c(Cl)c([N+](=O)[O-])c(c(c1Cl)Cl)Cl,-2.0969
+Clc1c(Cl)c([N+](=O)[O-])c(c(c1Cl)Cl)Cl,-2.1461
+Nc1ncn[nH]1,-0.39794
+Nc1ncn[nH]1,-0.69897
+O=C(NC(=O)c1c(F)cccc1F)Nc1cc(Cl)c(c(c1F)Cl)F,-1.415
+O=C(NC(=O)c1c(F)cccc1F)Nc1cc(Cl)c(c(c1F)Cl)F,-1.3979
+C=CCC1=C(C)C(CC1=O)OC(=O)C1C(C1(C)C)C=C(C)C,-1.8751
+C=CCC1=C(C)C(CC1=O)OC(=O)C1C(C1(C)C)C=C(C)C,-1.3892
+C=CCC1=C(C)C(CC1=O)OC(=O)C1C(C1(C)C)C=C(C)C,-1.1399
+CON=C(c1ccccc1COc1ccccc1C)C(=O)OC,-2.574
+CON=C(c1ccccc1COc1ccccc1C)C(=O)OC,-2.5682
+CC(N(c1c(cc(cc1N(=O)=O)S(=O)(=O)N)N(=O)=O)C(C)C)C,-1.5666
+CC(N(c1c(cc(cc1N(=O)=O)S(=O)(=O)N)N(=O)=O)C(C)C)C,-1.6532
+CCCN(C(=O)n1cncc1)CCOc1c(Cl)cc(cc1Cl)Cl,-0.87506
+CCCN(C(=O)n1cncc1)CCOc1c(Cl)cc(cc1Cl)Cl,-0.70757
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)(C)C,-1.2889
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)(C)C,-1.3979
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)C=C(Cl)Cl,-1.8751
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)C=C(Cl)Cl,-1.699
+ClC1C2OC2C2C1C1(Cl)C(=C(C2(C1(Cl)Cl)Cl)Cl)Cl,0.69897
+ClC1C2OC2C2C1C1(Cl)C(=C(C2(C1(Cl)Cl)Cl)Cl)Cl,1.6021
+N#CC(c1ccccc1)(Cn1cncn1)CCc1ccc(cc1)Cl,-1.6021
+N#CC(c1ccccc1)(Cn1cncn1)CCc1ccc(cc1)Cl,-1.4771
+O=C(C1C(C1(C)C)C=C(C(F)(F)F)Cl)OCc1cccc(c1C)c1ccccc1,-0.69897
+O=C(C1C(C1(C)C)C=C(C(F)(F)F)Cl)OCc1cccc(c1C)c1ccccc1,-0.90309
+[O-][N+](=O)c1cc(Cl)c(c(c1)Cl)N,-2.1761
+[O-][N+](=O)c1cc(Cl)c(c(c1)Cl)N,-2.3802
+CC(Oc1cccc(c1)NC(=O)c1ccccc1C(F)(F)F)C,-2.699
+CC(Oc1cccc(c1)NC(=O)c1ccccc1C(F)(F)F)C,-1.9395
+CCCCNC(=O)n1c(NC(=O)OC)nc2c1cccc2,-2.0607
+CCCCNC(=O)n1c(NC(=O)OC)nc2c1cccc2,-2.3979
+ClC(SN1C(=O)c2c(C1=O)cccc2)(Cl)Cl,-2.699
+ClC(SN1C(=O)c2c(C1=O)cccc2)(Cl)Cl,-1.6021
+ClC(SN1C(=O)c2c(C1=O)cccc2)(Cl)Cl,-1.699
+C#CCOS(=O)OC1CCCCC1Oc1ccc(cc1)C(C)(C)C,-2.0
+C#CCOS(=O)OC1CCCCC1Oc1ccc(cc1)C(C)(C)C,-1.2788
+N#Cc1sc2=c(sc1C#N)c(=O)c1c(c2=O)cccc1,-1.0
+N#Cc1sc2=c(sc1C#N)c(=O)c1c(c2=O)cccc1,-0.77815
+CN(C(=O)Oc1nc(nc(c1C)C)N(C)C)C,-1.0969
+CN(C(=O)Oc1nc(nc(c1C)C)N(C)C)C,-1.0899
+CNc1cnn(c(=O)c1Cl)c1cccc(c1)C(F)(F)F,-1.273
+CNc1cnn(c(=O)c1Cl)c1cccc(c1)C(F)(F)F,-1.7097
+Clc1ccccc1c1nnc(nn1)c1ccccc1Cl,-1.301
+Clc1ccccc1c1nnc(nn1)c1ccccc1Cl,-1.238
+CCCCCCCCc1cc(N(=O)=O)c(c(c1)N(=O)=O)OC(=O)C=CC,-1.699
+CCCCCCCCc1cc(N(=O)=O)c(c(c1)N(=O)=O)OC(=O)C=CC,-1.8062
+CCSC(=O)N1CCCCCC1,-1.1706
+CCSC(=O)N1CCCCCC1,-0.30103
+OC(C(C)(C)C)C(n1ncnc1)Oc1ccc(cc1)Cl,-1.3979
+OC(C(C)(C)C)C(n1ncnc1)Oc1ccc(cc1)Cl,-2.0212
+CCOP(=O)(Oc1ccc(c(c1)C)SC)NC(C)C,-0.17609
+CCOP(=O)(Oc1ccc(c(c1)C)SC)NC(C)C,-0.23045
+Cn1ccc(cc1)c1ccn(cc1)C,-0.57403
+Cn1ccc(cc1)c1ccn(cc1)C,-0.40654
+CCCCC(c1ccc(cc1)Cl)(Cn1cncn1)C#N,-0.993
+CCCCC(c1ccc(cc1)Cl)(Cn1cncn1)C#N,-0.99123
+Fc1ccc(cc1)C(=O)CCCN1CCN(CC1)c1ccccn1,-2.0607
+Fc1ccc(cc1)C(=O)CCCN1CCN(CC1)c1ccccn1,-1.4771
+N#CC(c1c(Cl)ccc(c1Cl)n1ncc(=O)[nH]c1=O)c1ccc(cc1)Cl,-1.1761
+N#CC(c1c(Cl)ccc(c1Cl)n1ncc(=O)[nH]c1=O)c1ccc(cc1)Cl,-1.3617
+COC1CC(OC2C(C)C=CC=C3COC4C3(O)C(C=C(C4O)C)C(=O)OC3CC(CC=C2C)OC2(C3)C=CC(C(O2)C(C)C)C)OC(C1OC1CC(OC)C(C(O1)C)NC(=O)C)C,-1.9287e-16
+COC1CC(OC2C(C)C=CC=C3COC4C3(O)C(C=C(C4O)C)C(=O)OC3CC(CC=C2C)OC2(C3)C=CC(C(O2)C(C)C)C)OC(C1OC1CC(OC)C(C(O1)C)NC(=O)C)C,-0.39794
diff --git a/data/swiss_mg_dup.csv b/data/swiss_mg_dup.csv
new file mode 100644
index 0000000..3412c2e
--- /dev/null
+++ b/data/swiss_mg_dup.csv
@@ -0,0 +1,194 @@
+SMILES,LOAEL
+OC(=O)COc1ccc(cc1Cl)Cl,-1.7924
+OC(=O)COc1ccc(cc1Cl)Cl,-0.69897
+OC(=O)COc1ccc(cc1Cl)Cl,-1.8751
+CCOCN(c1c(C)cccc1CC)C(=O)CCl,-1.6767
+CCOCN(c1c(C)cccc1CC)C(=O)CCl,-1.8388
+CCOCN(c1c(C)cccc1CC)C(=O)CCl,-1.8254
+Clc1c(ccc(c1N)[N+](=O)[O-])Oc1ccccc1,-0.90309
+Clc1c(ccc(c1N)[N+](=O)[O-])Oc1ccccc1,-1.7924
+COCN(c1c(CC)cccc1CC)C(=O)CCl,-0.39794
+COCN(c1c(CC)cccc1CC)C(=O)CCl,-1.1461
+COCN(c1c(CC)cccc1CC)C(=O)CCl,-2.1004
+OCC(CCl)O,-1.4771
+OCC(CCl)O,-0.041393
+Nc1n[nH]cn1,-0.39794
+Nc1n[nH]cn1,-0.69897
+CCNc1nc(NC(C)C)nc(n1)Cl,-0.49136
+CCNc1nc(NC(C)C)nc(n1)Cl,-1.0
+CCNc1nc(NC(C)C)nc(n1)Cl,-1.3729
+CCOC(=O)CCN(C(C)C)SN(C(=O)Oc1cccc2c1OC(C2)(C)C)C,-1.0414
+CCOC(=O)CCN(C(C)C)SN(C(=O)Oc1cccc2c1OC(C2)(C)C)C,-1.3802
+Fc1ccc(c(c1)c1ccc(c(c1)Cl)Cl)NC(=O)c1cn(nc1C(F)F)C,-1.2405
+Fc1ccc(c(c1)c1ccc(c(c1)Cl)Cl)NC(=O)c1cn(nc1C(F)F)C,-1.0828
+ClC(SN1C(=O)C2C(C1=O)CC=CC2)(Cl)Cl,-2.0
+ClC(SN1C(=O)C2C(C1=O)CC=CC2)(Cl)Cl,-1.9912
+CNC(=O)Oc1cccc2c1OC(C2)(C)C,-0.068186
+CNC(=O)Oc1cccc2c1OC(C2)(C)C,-0.69897
+Nc1cnn(c(=O)c1Cl)c1ccccc1,-1.7782
+Nc1cnn(c(=O)c1Cl)c1ccccc1,-1.699
+ClCC[N+](C)(C)C.[Cl-],-2.1335
+ClCC[N+](C)(C)C.[Cl-],-2.0969
+ClCC[N+](C)(C)C.[Cl-],-1.8751
+N#Cc1c(Cl)c(C#N)c(c(c1Cl)Cl)Cl,-0.51851
+N#Cc1c(Cl)c(C#N)c(c(c1Cl)Cl)Cl,-1.6021
+CCOP(=S)(Oc1nc(Cl)c(cc1Cl)Cl)OCC,-1.0
+CCOP(=S)(Oc1nc(Cl)c(cc1Cl)Cl)OCC,-0.77815
+CCOP(=S)(Oc1nc(Cl)c(cc1Cl)Cl)OCC,-0.0
+CCO/N=C(\C1=C(O)CC(CC1=O)C1CCCSC1)/CCC,-1.4472
+CCO/N=C(\C1=C(O)CC(CC1=O)C1CCCSC1)/CCC,-0.80618
+N#CC(c1ccc(c(c1)Oc1ccccc1)F)OC(=O)C1C(C1(C)C)C=C(Cl)Cl,-1.2833
+N#CC(c1ccc(c(c1)Oc1ccccc1)F)OC(=O)C1C(C1(C)C)C=C(Cl)Cl,-1.3579
+O[Sn](C1CCCCC1)(C1CCCCC1)C1CCCCC1,-0.14301
+O[Sn](C1CCCCC1)(C1CCCCC1)C1CCCCC1,-0.77815
+O[Sn](C1CCCCC1)(C1CCCCC1)C1CCCCC1,-0.0
+CCNC(=O)NC(=O)/C(=N\OC)/C#N,-1.3711
+CCNC(=O)NC(=O)/C(=N\OC)/C#N,-1.4814
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)C=C(Cl)Cl,-1.699
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)C=C(Cl)Cl,-1.8751
+CN1CN(C)CSC1=S,-0.5563
+CN1CN(C)CSC1=S,-0.72428
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)C=C(Br)Br,-0.39794
+N#CC(c1cccc(c1)Oc1ccccc1)OC(=O)C1C(C1(C)C)C=C(Br)Br,-0.73239
+COc1cc(ccc1OC)/C(=C/C(=O)N1CCOCC1)/c1ccc(cc1)Cl,-1.5563
+COc1cc(ccc1OC)/C(=C/C(=O)N1CCOCC1)/c1ccc(cc1)Cl,-1.5315
+c1cc[n+]2c(c1)c1cccc[n+]1CC2,-0.46389
+c1cc[n+]2c(c1)c1cccc[n+]1CC2,-0.59106
+OC(=O)c1ccccc1.CCC(C1OC2(C=CC1C)OC1CC=C(C)C(OC3CC(OC)C(C(O3)C)OC3CC(OC)C(C(O3)C)NC)C(C)C=CC=C3C4(C(C(=O)OC(C2)C1)C=C(C)C(C4OC3)O)O)C,-0.39794
+OC(=O)c1ccccc1.CCC(C1OC2(C=CC1C)OC1CC=C(C)C(OC3CC(OC)C(C(O3)C)OC3CC(OC)C(C(O3)C)NC)C(C)C=CC=C3C4(C(C(=O)OC(C2)C1)C=C(C)C(C4OC3)O)O)C,-0.0
+O=S1OCC2C(CO1)C1(C(C2(Cl)C(=C1Cl)Cl)(Cl)Cl)Cl,-1.0414
+O=S1OCC2C(CO1)C1(C(C2(Cl)C(=C1Cl)Cl)(Cl)Cl)Cl,-0.4624
+O=S1OCC2C(CO1)C1(C(C2(Cl)C(=C1Cl)Cl)(Cl)Cl)Cl,-0.69897
+Fc1ccc(cc1)C1(Cn2cncn2)OC1c1ccccc1Cl,-0.69897
+Fc1ccc(cc1)C1(Cn2cncn2)OC1c1ccccc1Cl,-0.77815
+CCN(c1c(cc(cc1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-])CC(=C)C,-1.0294
+CCN(c1c(cc(cc1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-])CC(=C)C,-1.4624
+CCCSP(=O)(SCCC)OCC,0.30103
+CCCSP(=O)(SCCC)OCC,-0.38739
+CCOP(=O)(Oc1ccc(c(c1)C)SC)NC(C)C,-0.23045
+CCOP(=O)(Oc1ccc(c(c1)C)SC)NC(C)C,0.33724
+Clc1ccc(cc1)C(c1ccccc1Cl)(c1cncnc1)O,-0.5563
+Clc1ccc(cc1)C(c1ccccc1Cl)(c1cncnc1)O,-1.243
+Clc1ccc(cc1)C(c1ccccc1Cl)(c1cncnc1)O,-0.30103
+Clc1ccc(cc1)C(c1ccccc1Cl)(c1cncnc1)O,-0.39794
+CSc1ccc(cc1C)OP(=S)(OC)OC,0.69897
+CSc1ccc(cc1C)OP(=S)(OC)OC,0.14267
+Clc1cc(cnc1Nc1c(cc(c(c1[N+](=O)[O-])Cl)C(F)(F)F)[N+](=O)[O-])C(F)(F)F,-0.59106
+Clc1cc(cnc1Nc1c(cc(c(c1[N+](=O)[O-])Cl)C(F)(F)F)[N+](=O)[O-])C(F)(F)F,-0.58206
+O=C(c1cccc(c1C(=O)NC(CS(=O)(=O)C)(C)C)I)Nc1ccc(cc1C)C(C(F)(F)F)(C(F)(F)F)F,-1.8976
+O=C(c1cccc(c1C(=O)NC(CS(=O)(=O)C)(C)C)I)Nc1ccc(cc1C)C(C(F)(F)F)(C(F)(F)F)F,-1.5315
+O=C(NC(=O)c1c(F)cccc1F)Nc1ccc(cc1F)Oc1ccc(cc1Cl)C(F)(F)F,-2.3617
+O=C(NC(=O)c1c(F)cccc1F)Nc1ccc(cc1F)Oc1ccc(cc1Cl)C(F)(F)F,-2.3385
+O=C(N(C)C)Nc1cccc(c1)C(F)(F)F,-1.2348
+O=C(N(C)C)Nc1cccc(c1)C(F)(F)F,-1.4771
+CC(C(c1cncnc1)(c1ccc(cc1)OC(F)(F)F)O)C,-0.99123
+CC(C(c1cncnc1)(c1ccc(cc1)OC(F)(F)F)O)C,-1.6345
+Fc1ccc(cc1)[Si](c1ccc(cc1)F)(Cn1cncn1)C,-1.0
+Fc1ccc(cc1)[Si](c1ccc(cc1)F)(Cn1cncn1)C,-0.69897
+OC(=O)CNCP(=O)(O)O,-2.9731
+OC(=O)CNCP(=O)(O)O,-2.7482
+OC(=O)CNCP(=O)(O)O,-2.4771
+OC(=O)CNCP(=O)(O)O,-3.0842
+C=CCOC(c1ccc(cc1Cl)Cl)Cn1cncc1,-1.2014
+C=CCOC(c1ccc(cc1Cl)Cl)Cn1cncc1,-1.1761
+CCC(c1noc(c1)NC(=O)c1c(OC)cccc1OC)(CC)C,-2.7218
+CCC(c1noc(c1)NC(=O)c1c(OC)cccc1OC)(CC)C,-2.7782
+CO/N=C(\c1ccccc1COc1ccccc1C)/C(=O)OC,-2.8763
+CO/N=C(\c1ccccc1COc1ccccc1C)/C(=O)OC,-2.574
+CON(C(=O)Nc1ccc(c(c1)Cl)Cl)C,-0.79588
+CON(C(=O)Nc1ccc(c(c1)Cl)Cl)C,-1.4949
+CCOC(=O)CC(C(=O)OCC)SP(=S)(OC)OC,-1.4624
+CCOC(=O)CC(C(=O)OCC)SP(=S)(OC)OC,-2.1553
+C[N+]1(C)CCCCC1.[Cl-],-2.4281
+C[N+]1(C)CCCCC1.[Cl-],-2.8351
+CCCCCCC(c1cc(cc(c1OC(=O)/C=C\C)[N+](=O)[O-])[N+](=O)[O-])C,-2.0821
+CCCCCCC(c1cc(cc(c1OC(=O)/C=C\C)[N+](=O)[O-])[N+](=O)[O-])C,-1.8513
+Cc1nnc(c(=O)n1N)c1ccccc1,-1.29
+Cc1nnc(c(=O)n1N)c1ccccc1,-1.8727
+ClCC(=O)N(c1c(C)cccc1C)Cn1cccn1,-1.9395
+ClCC(=O)N(c1c(C)cccc1C)Cn1cccn1,-1.2455
+OC1(Cn2ncnc2)C(CCC1(C)C)Cc1ccc(cc1)Cl,-1.1173
+OC1(Cn2ncnc2)C(CCC1(C)C)Cc1ccc(cc1)Cl,-1.1399
+COc1sc(=O)n(n1)CSP(=S)(OC)OC,0.19382
+COc1sc(=O)n(n1)CSP(=S)(OC)OC,-0.23553
+CBr,-1.0414
+CBr,-1.2304
+CSc1nnc(c(=O)n1N)C(C)(C)C,-1.1139
+CSc1nnc(c(=O)n1N)C(C)(C)C,-1.1584
+CCCCC(c1ccc(cc1)Cl)(Cn1cncn1)C#N,-0.99564
+CCCCC(c1ccc(cc1)Cl)(Cn1cncn1)C#N,-2.0253
+CCN(C(=O)C(Oc1cccc2c1cccc2)C)CC,-1.6772
+CCN(C(=O)C(Oc1cccc2c1cccc2)C)CC,-2.0
+Oc1ccccc1c1ccccc1,-3.0
+Oc1ccccc1c1ccccc1,-2.301
+Oc1ccccc1c1ccccc1,-2.7251
+CCCN(c1c(cc(cc1[N+](=O)[O-])S(=O)(=O)N)[N+](=O)[O-])CCC,-1.1461
+CCCN(c1c(cc(cc1[N+](=O)[O-])S(=O)(=O)N)[N+](=O)[O-])CCC,-1.5563
+CNC(=O)ON=C(C(=O)N(C)C)SC,-0.62221
+CNC(=O)ON=C(C(=O)N(C)C)SC,-0.6902
+C[n+]1ccc(cc1)c1cc[n+](cc1)C,-0.40654
+C[n+]1ccc(cc1)c1cc[n+](cc1)C,-0.94792
+C[n+]1ccc(cc1)c1cc[n+](cc1)C,-0.57403
+CCOP(=S)(Oc1ccc(cc1)[N+](=O)[O-])OCC,-0.39794
+CCOP(=S)(Oc1ccc(cc1)[N+](=O)[O-])OCC,-0.20412
+COP(=S)(Oc1ccc(cc1)[N+](=O)[O-])OC,-0.39794
+COP(=S)(Oc1ccc(cc1)[N+](=O)[O-])OC,0.25964
+COP(=S)(Oc1ccc(cc1)[N+](=O)[O-])OC,0.30103
+CC(CC(c1sccc1NC(=O)c1cn(nc1C(F)(F)F)C)C)C,-1.9191
+CC(CC(c1sccc1NC(=O)c1cn(nc1C(F)(F)F)C)C)C,-2.0
+ClC(=CC1C(C1(C)C)C(=O)OCc1cccc(c1)Oc1ccccc1)Cl,-1.3979
+ClC(=CC1C(C1(C)C)C(=O)OCc1cccc(c1)Oc1ccccc1)Cl,-1.699
+COP(=S)(SCN1C(=O)c2c(C1=O)cccc2)OC,-0.60206
+COP(=S)(SCN1C(=O)c2c(C1=O)cccc2)OC,-0.25527
+OC(=O)c1nc(Cl)c(c(c1Cl)N)Cl,-2.301
+OC(=O)c1nc(Cl)c(c(c1Cl)N)Cl,-2.3979
+CO/C=C(\c1ccccc1COc1cccc(n1)C(F)(F)F)/C(=O)OC,-1.6628
+CO/C=C(\c1ccccc1COc1cccc(n1)C(F)(F)F)/C(=O)OC,-2.2095
+CCCOC(=O)NCCCN(C)C.Cl,-2.8338
+CCCOC(=O)NCCCN(C)C.Cl,-2.1761
+CCCOC(=O)NCCCN(C)C.Cl,-2.0569
+O=C(C(Oc1ccc(cc1)Oc1cnc2c(n1)ccc(c2)Cl)C)OCCON=C(C)C,-0.69897
+O=C(C(Oc1ccc(cc1)Oc1cnc2c(n1)ccc(c2)Cl)C)OCCON=C(C)C,-1.3979
+C#CCOS(=O)OC1CCCCC1Oc1ccc(cc1)C(C)(C)C,-1.1761
+C#CCOS(=O)OC1CCCCC1Oc1ccc(cc1)C(C)(C)C,-1.3838
+C#CCOS(=O)OC1CCCCC1Oc1ccc(cc1)C(C)(C)C,-1.4014
+ClCC(=O)N(c1c(C)cccc1CC)COC(C)C,-2.301
+ClCC(=O)N(c1c(C)cccc1CC)COC(C)C,-1.7993
+S=C1NCCCN1,-0.69897
+S=C1NCCCN1,-0.74819
+Clc1ccccc1CC(C1(Cl)CC1)(Cn1nc[nH]c1=S)O,-1.699
+Clc1ccccc1CC(C1(Cl)CC1)(Cn1nc[nH]c1=S)O,-2.8751
+CCOC(=O)c1cn2nc(cc2nc1C)OP(=S)(OCC)OCC,-1.0414
+CCOC(=O)c1cn2nc(cc2nc1C)OP(=S)(OCC)OCC,-0.60206
+COc1c(OC)cc(c(c1OC)C(=O)c1c(OC)ncc(c1C)Cl)C,-1.6325
+COc1c(OC)cc(c(c1OC)C(=O)c1c(OC)ncc(c1C)Cl)C,-1.5611
+O=C(CC(C)(C)C)OC1=C(C(=O)OC21CCCC2)c1c(C)cc(cc1C)C,-1.2014
+O=C(CC(C)(C)C)OC1=C(C(=O)OC21CCCC2)c1c(C)cc(cc1C)C,-1.1703
+O=C1CCCC(=O)C1C(=O)c1ccc(cc1Cl)S(=O)(=O)C,-1.8573
+O=C1CCCC(=O)C1C(=O)c1ccc(cc1Cl)S(=O)(=O)C,0.39794
+O=C(NC(=O)c1c(F)cccc1F)Nc1cc(Cl)c(c(c1F)Cl)F,-1.3945
+O=C(NC(=O)c1c(F)cccc1F)Nc1cc(Cl)c(c(c1F)Cl)F,-2.0881
+CCNc1nc(Cl)nc(n1)NC(C)(C)C,-0.093422
+CCNc1nc(Cl)nc(n1)NC(C)(C)C,-0.2014
+CCNc1nc(Cl)nc(n1)NC(C)(C)C,-0.23045
+CS/C(=N/OC(=O)N(SN(C(=O)O/N=C(/SC)\C)C)C)/C,-0.69897
+CS/C(=N/OC(=O)N(SN(C(=O)O/N=C(/SC)\C)C)C)/C,-1.0
+CS/C(=N/OC(=O)N(SN(C(=O)O/N=C(/SC)\C)C)C)/C,-1.0792
+COC(=O)NC(=S)Nc1ccccc1NC(=S)NC(=O)OC,-1.5051
+COC(=O)NC(=S)Nc1ccccc1NC(=S)NC(=O)OC,-1.7243
+CN(C(=S)SSC(=S)N(C)C)C,-1.0792
+CN(C(=S)SSC(=S)N(C)C)C,-0.86332
+Cc1ccc(cc1)N(S(=O)(=O)N(C)C)SC(Cl)(Cl)F,-2.0
+Cc1ccc(cc1)N(S(=O)(=O)N(C)C)SC(Cl)(Cl)F,-1.9542
+O=C(C(C)(C)C)C(n1ncnc1)Oc1ccc(cc1)Cl,-2.0569
+O=C(C(C)(C)C)C(n1ncnc1)Oc1ccc(cc1)Cl,-1.3856
+CC(N(C(=O)SCC(=C(Cl)Cl)Cl)C(C)C)C,-1.1139
+CC(N(C(=O)SCC(=C(Cl)Cl)Cl)C(C)C)C,-0.9345
+CCCN(c1c(cc(cc1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-])CCC,-1.4771
+CCCN(c1c(cc(cc1[N+](=O)[O-])C(F)(F)F)[N+](=O)[O-])CCC,-2.6812
+O=CNC(C(Cl)(Cl)Cl)N1CCN(CC1)C(C(Cl)(Cl)Cl)NC=O,-2.0
+O=CNC(C(Cl)(Cl)Cl)N1CCN(CC1)C(C(Cl)(Cl)Cl)NC=O,-2.2041
+C=CC1(C)OC(=O)N(C1=O)c1cc(Cl)cc(c1)Cl,-0.90309
+C=CC1(C)OC(=O)N(C1=O)c1cc(Cl)cc(c1)Cl,-0.43136
+CN(C(=S)S[Zn]SC(=S)N(C)C)C,-1.1139
+CN(C(=S)S[Zn]SC(=S)N(C)C)C,-0.39794