. 2021 Mar 29;17(3):e1008864. doi: 10.1371/journal.pcbi.1008864

Table 5. Classification of Abs recognizing two epitopes at either the base (ADI-15734) or the HR2/MPER region (ADI-15974) of the EBOV-GP trimer.

We colored the fingerprints for the DNN models according to the charge coloring code.

No. DNN models	Training and Validation			Testing Results
No. DNN models	‹N_training›^a	‹M_validation›^b	‹A_val›^c	‹N_test›^d	‹N_correct›^e	‹A_test›^f	‹κ›^g
30	1007 (SD 62)	282 (SD 28)	0.98 (SD 0.02)	501 (SD 85)	395 (SD 91)	0.79 (SD 0.13)	0.67 (SD 0.22)

^a ‹N_training›; average number of fingerprints selected for training.

^b ‹M_validation›; average number of fingerprints selected for validation.

^c ‹A_val›; average validation accuracy.

^d ‹N_test›; average number of images in the testing sets.

^e ‹N_correct›; average number of images in the testing sets predicted correctly.

^f ‹A_test›; average accuracy on the test sets.

^g ‹ κ ›; average value of the Cohen’s Kappa coefficient for predictions of the testing sets.