Registration Dossier

Administrative data

Description of key information

Carcinogenicity on 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

ACD/Percepta prediction for carcinogenicity on rat and mouse male and female resulted to be undefined, meaning that the target 2-phenyl-2-(pyridin-2-yl)acetamide could not be reliably classified on the basis of p and RI values.

Leadscope FDA Model Applier prediction for carcinogenicity on rat and mouse (both males and females) resulted to be NEGATIVE, since the positive prediction probability was equal to 0.44 (male) and 0.03 (female) for rat and equal to 0.08 (male) and 0.22 (female) for mouse.

Since at least eight features were found, it was concluded that 2-phenyl-2-(pyridin-2-yl)acetamide is 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. For rat two compounds from the training set of Car Rat Male model and Car Rat Female model were identified as analogues to 2-phenyl-2-(pyridin-2-yl)acetamide (similarity > 30%), and one of them with similarity greater than 0.5 and consistent negative test result. Based on this consideration, Leadscope predictions were assessed as moderate reliable.

For mouse, only one compound from the training set of Car Mouse Male model and Car Mouse Female model was identified as analogue (similarity > 30%), which however, exhibits little similarity (similarity < 50%) with respect to the target. Based on this consideration, Leadscope predictions were assessed as borderline reliable.

Based on described results, it was concluded that the target 2-phenyl-2-(pyridin-2-yl)acetamide is predicted NEGATIVE for carcinogenicity and the prediction was assessed as moderate reliable.

Additional information

ACD/Percepta models for carcinogenicity in rat and mouse estimate probability (“p-value”) that a compound will result positive in the carcinogenicity tests. The reliability of prediction is assessed in terms of reliability index (RI), which ranges from 0 to 1 and takes into account the similarity of the target with the training set compounds and the consistency of experimental values for similar compounds. A “positive” or “negative” call is provided if the compound can be reliably classified on the basis of p and RI values (“Undefined” otherwise).

Leadscope models estimate the probability that a compound will result positive in the two carcinogenicity tests. For each model, Leadscope results include the prediction call for carcinogenicity on rat and mouse (positive, negative or not in domain), a positive prediction probability and two parameters which assess the reliability of the prediction: 1) Model Features Count, i.e., containing structural model features that are present in the prediction model; 2) 30% Similarity Training Neighbours Count, i.e. number of training compounds with at least 30 % similarity.