Registration Dossier

Administrative data

Description of key information

Carcinogenicity in rat and mouse (male and female) was estimated by using two predictors: ACD/Percepta and Leadscope Model Applier. 

Key value for chemical safety assessment

Justification for classification or non-classification

Based on the weight of evidence assessments, the target was predicted with borderline reliability as negative for carcinogenicity on both mouse and rat, leading to an overall borderline reliable negative prediction of carcinogenicity.

Additional information

ACD/Percepta did not provide any predictions for carcinogenicity in rat and in mouse female since the target compound resulted out of the applicability domain of the two models

For carcinogenicity in mouse maleit provided a negative prediction, with positive prediction probability equal to 0.11. The prediction was assessed as borderline reliable being the reliability index equal to 0.40. ACD/Percepta displays up to 5 most structurally similar structures from the training set along with their experimental test results. The information on the structurally similar compounds in the training set was used to further assess the reliability of the prediction. Five compounds were identified as analogues of Pipamperone. These training compounds exhibit moderate similarity with respect to Pipamperone (similarity index ranging from 0.63 to 0.67), meaning that the target compound is moderately represented in the training set of the model, and experimental consistent negative test results. These considerations further supported the reliability of the negative prediction

Leadscope FDA Model Applier prediction for carcinogenicity in rat (both males and females) resulted to be negative, since the positive prediction probability was equal to 0.01 (male) and 0.23 (female). Since at least twenty-two features were found, it was concluded that Pipamperone is well represented by the models. Additionally, all the identified features are mainly represented in negative training compounds. The robustness of the prediction was further evaluated by examining compounds similar to the target from the training set. While this information does not take part to the prediction, it provides the complementary means to see how similar compounds were predicted and what the experimental values of similar compounds are. Two compounds from the training set ofCar Rat Malemodel andCar Rat Femalemodel were identified as analogues to Pipamperone (similarity > 30%), however they exhibit little similarity with respect to Pipamperone (similarity < 50%). Based on this consideration, the negative predictions were assessed as borderline reliable.

Leadscope FDA Model Applier prediction for carcinogenicity in mouse (both males and females)resulted to be negative, since the positive prediction probability was equal to 0.08 (male) and 0.14 (female). Since at least twenty-two features were found, it was concluded that Pipamperone is well represented by the models.Additionally, all the identified features are mainly represented in negative training compounds.The robustness of the prediction was further evaluated by examining compounds similar to the target from the training set.While this information does not take part to the prediction, it provides the complementary means to see how similar compounds were predicted and what the experimental values of similar compounds are.

Two compounds from the training set ofCar Mouse Malemodel andCar Mouse Femalemodel were identified as analogues to Pipamperone (similarity > 30%), however they exhibit little similarity with respect to Pipamperone (similarity < 50%).Based on this consideration, the negative predictions were assessed as borderline reliable.