Cross-validation strategy. The data-set is divided into three equal subsets, each with the same propotion of ASD and control subjects. Two of the tree subsets are used as the training set the model, whereas the other subset is used as the validation set for performance quantification; this is iterated three times, so that each subset is used twice for training and once for validation. The feature selection is performed only for GO and pathway-based features. The remaining set is used as test set to assess the performance of classification. The cross-validation procedure is repeated times to estimate the mean performance and its standard deviation.