From: Collaborative development of predictive toxicology applications
Standard reports | |
---|---|
Report type | Specific information included in the report |
Prediction of a single (unseen) component | Activity, applicability domain, confidence |
Prediction of multiple (unseen) components | Ranking according to activity/confidence |
Validation of a model | Different performance criteria (on various datasets), based on cross-validation/external test set validation |
Making predictions on a particular dataset | Prediction results of various algorithms |
Comparison of different models/algorithms | Ranking according to different performance criteria |
Extended reports | |
Report type | Specific information included in the report |
Evaluation of a feature generation algorithm | Performance of various algorithms using the generated features compared to other features |
Evaluation of a feature selection algorithm | Performance of various algorithms using the selected features compared to no feature selection |