Table 4. Performance comparison among various types of sequence features and methods for the across-germline prediction using 10-fold cross-validation.

Method	Sensitivity	Specificity	Accuracy (%)
Random Forests (AAC)	0.846	0.742	80.09
Random Forests (DPC)	0.862	0.823	84.49
Random Forests (PPs)	0.837	0.704	78.01
Random Forests (AAC+DPC)	0.870	0.801	84.03
Random Forests (AAC+PPs)	0.837	0.715	78.47
Random Forests (DPC+PPs)	0.862	0.780	82.64
Random Forests (AAC+DPC+PPs)	0.862	0.785	82.87