Home > CPDBAS Rat

Carcinogenicity ─ CPDBAS Rat

Dataset sourcesEPA GOLD (1999)
Dataset warnings4 warnings 
  • Removed 39 compounds that could not be read by the CDK library.
  • Removed 310 compounds with missing/invalid enpoint values.
  • Removed 8 duplicate occurences of compounds (with equal endpoint values).
  • Removed 21 compounds that occured multiple times with different endpoint values.
Compounds604× 'inactive', 565× 'active'
ClassifierRandom Forest (trees: 100)
FeaturesFiltered ECFP4 fragments 
The service uses filtered (instead of folded) Extended-Connectivity Fingerprint (ECFP) fragments as features for the prediction algorithm. more..
Num features2048

 

Recent predictions

CompoundPrediction
Each prediction model provides a probability estimate for the prediction. The probability value indicates how confident the classifier is. more..
App-Domain
QSAR model predictions should not be trusted if the query compound is outside of the applicability domain of the model (i.e., if the query compound is dissimilar to the training dataset compounds). more..
O(c1ccc(cc1)CCCNC(Cc2ccccc2)C)C
  inactive (80%)
NC(=O)C(=C/N1CCOCC1)/C#N
  active (70%)
CC(C)CCCC(C)CCCC(C)CCCC1(C)CCC2=CC(=C(C)C(=C2O1)C)O
  inactive (76%)
COC1=C(C=CC(=C1)CC=C)O
  inactive (74%)
OC1=CC=C(Cl)C=C1
  active (67%)
C[C@@H]2COc3c(N1CCN(C)CC1)c(F)cc4c(=O)c(C(=O)O)cn2c34
  active (63%)
O(c1c(cccc1)CCN2CCC(CCc3c(OC)cccc3)CC2)C
  inactive (55%)
O(c1n(ccc1)CCCC2CCN(CCc3c(O)cccc3)CC2)C
  inactive (55%)
CN(C)CCCC(=O)O[C@H]2[C@@H]1[C@](C)([C@@H](O)CCC1(C)C)[C@@]3(O)C(=O)C[C@](C)(C=C)O[C@]3(C)[C@H]2OC(C)=O
  inactive (70%)
O=C1C(C(CC)=N)=C(O)CC(CC(C)=O)C1
  active (53%)