Registration Dossier

Administrative data

skin sensitisation
other: in silico predictions
Type of information:
Adequacy of study:
supporting study
2 (reliable with restrictions)
Justification for type of information:
QSAR prediction: migrated from IUCLID 5.6

Data source

Reference Type:
study report
Report Date:

Materials and methods

Principles of method if other than guideline:
Estimated by employing Toxtree decision rule system and Vega QSAR.
GLP compliance:

Test material


Results and discussion

Any other information on results incl. tables

Toxtree predicts the skin sensitization according to decision rules based on the identification of Structural Alerts (SA) for skin sensitizationas defined by Enoch SJ et al. (Enoch SJ, Madden JC, Cronin MT, Identification of mechanisms of toxic action for skin sensitisation using a SMARTS pattern based approach, SAR QSAR Environ Res. 2008; 19(5-6):555-78).As one or more SAs embedded in a molecular structure are recognised, the system flags the potential skin sensitization activity of the chemical. The methodology used to capture this information is based on series of SMARTS (Smiles ARbitary Target Specification) patterns ( defining the rules. Thus, chemicals which contain a given reactive fragment are then assigned to the reactivity domain that the fragment belongs to. It is important to realize that a chemical may be assigned to one of the electrophilic reactivity domains even if it is a non-sensitizer. The SMARTS rules aim to identify potential electrophilic fragments and therefore identify a potential hazard associated with a compound. However, the best approach is to firstly classify the chemicals into potential reactivity domains and then perform further analysis within the domains in order to be able to predict skin sensitization. Toxtreepredicted the target 2-phenyl-2-piperidin-2-ylacetamide as not skin sensitizers, since it did not identify any skin sensitization reactivity domain alert. A detailed assessment of the reliability of the prediction is not provided.

Vega model predicts skin sensitization by an Adaptive Fuzzy Partition (AFP) model, which produces as output two values 1 (positive) and O (negative) that represent the belonging degree respectively to the sensitizer and non-sensitizer classes. The compound is assigned to the class having this degree value higher than 0.5.The applicability domain of the predictions is assessed using an Applicability Domain Index (ADI) that has values from 0 (worst case) to 1 (best case).An ADI value greater than 0.9 means that the predicted substance is into the applicability domain of the model; ADI value lower than 0.7 means that the predicted substance is out of the applicability domain of the model, while an ADI value between 0.7 and 0.9, means that the predicted substance could be out of the Applicability Domain of the model.Vega predicted the target 2-phenyl-2-piperidin-2-ylacetamide as skin sensitizers. However,the prediction is not reliable (ADI = 0.62) due to the following issues: only moderately similar compounds with known experimental value in the training set have been found and some atom centered fragments of the compound have not been found in the compounds of the training set or are rare fragments.

 Toxtree prediction  Vega prediction  Consensus



Not reliable


Applicant's summary and conclusion

Interpretation of results:
not sensitising
Migrated information
The skin sensitization of the target 2-phenyl-2-piperidin-2-ylacetamide was predicted employing two different in silico approaches: the QSAR statistical model as provided by Vega and the decision rule system provided by Toxtree. The two predictors were employed in order to apply a consensus approach to enhance the reliability of the prediction. In the consensus assessment only reliable predictions are to be taken into account. In the case of the target substance, Vega prediction resulted to be not reliable, while Toxtree did not identify any skin sensitization reactivity domain alert, concluding that the target 2-phenyl-2-piperidin-2-ylacetamide is NOT SKIN SENSITIZER.
A detailed assessment of the reliability of the consensus prediction is not provided.