Systematic analysis of non-structural protein features for the prediction of PTM function potential by artificial neural networks.

Direct comparison of the mean ROC AUC relative to the model input factor count for each of the 247 models revealed a clear trend showing that an increase in the number of input factors leads to an overall increase in the average mean and median ROC-AUC—indicating that the inclusion of a greater number of inputs generally improves prediction strength ( Fig 2A ).

also in 12,254 other papers