Network over-training was limited by using a test set of 40 pseudo-randomly distributed records.
Model was validated by predicting the IC50 values for a test set of 7 compounds.
A test set of 7 compounds was used for the external validation.
The predictive ability of the model was assessed using a test set of 7 compounds.
13321_2016_174_MOESM4_ESM.xlsx Additional file 3. ClassyFire's category assignments for a test set of 800 compounds.
Initially, a training set and a test set of examples with labels is required.
In other words, we cannot draw the same conclusions from a test set of 20 examples with respect to a test set of 100 examples and this should be represented in the scores.
The predictive abilities of the two models were further validated by a test set of 15 compounds.
The procedure was validated on a test set of 21 known protein protein complexes not used in the training set.
The predictive ability of the QSAR model was evaluated by using a test set of 10 compounds.
These models were validated by a test set of eight molecules that were not included in the training set.
