Skip to main content
. 2021 May 10;11:9888. doi: 10.1038/s41598-021-89347-5

Table 4.

Comparison of SMNN 1–9 architectures (see Table 3).

SMNN TP FP FN TN Sensitivity Specificity Precision Acc. F1-Score
FM+ FM− FM+ FM− FM+ FM− FM+ FM−
1 209.00 46.60 28.20 158.40 0.88 0.77 0.77 0.88 0.83 0.86 0.83 0.85 0.80
(14.80) (39.48) (18.95) (41.75) (0.08) (0.20) (0.20) (0.08) (0.10) (0.06) (0.08) (0.06) (0.13)
2 215.00 48.20 22.20 156.80 0.91 0.76 0.76 0.91 0.83 0.88 0.84 0.86 0.81
(15.49) (36.57) (16.45) (37.49) (0.07) (0.18) (0.18) (0.07) (0.10) (0.07) (0.08) (0.06) (0.12)
3 214.20 47.00 23.00 158.00 0.90 0.77 0.77 0.90 0.83 0.88 0.84 0.86 0.81
(12.34) (32.44) (13.87) (33.14) (0.06) (0.16) (0.16) (0.06) (0.09) (0.06) (0.07) (0.06) (0.11)
4 209.40 40.80 27.80 164.20 0.88 0.80 0.80 0.88 0.84 0.86 0.84 0.86 0.82
(7.57) (19.46) (8.87) (20.19) (0.04) (0.10) (0.10) (0.04) (0.06) (0.03) (0.03) (0.02) (0.05)
5 214.00 29.60 23.20 175.40 0.90 0.86 0.86 0.90 0.88 0.89 0.88 0.89 0.87
(10.05) (12.20) (10.73) (13.26) (0.04) (0.06) (0.06) (0.04) (0.04) (0.04) (0.02) (0.02) (0.02)
6 212.80 47.00 24.40 158.00 0.90 0.77 0.77 0.90 0.83 0.87 0.84 0.86 0.81
(10.03) (34.18) (11.87) (36.15) (0.05) (0.17) (0.17) (0.05) (0.10) (0.04) (0.06) (0.04) (0.09)
7 205.20 45.20 23.20 168.60 0.90 0.78 0.78 0.90 0.83 0.88 0.85 0.86 0.82
(16.89) (29.35) (9.73) (41.88) (0.04) (0.15) (0.15) (0.04) (0.08) (0.04) (0.06) (0.04) (0.10)
8 209.00 46.00 28.20 159.00 0.88 0.77 0.77 0.88 0.83 0.85 0.83 0.85 0.80
(12.02) (36.59) (11.05) (37.99) (0.05) (0.18) (0.18) (0.05) (0.10) (0.03) (0.07) (0.04) (0.11)
9 205.20 39.60 25.40 172.00 0.89 0.81 0.81 0.89 0.85 0.87 0.85 0.86 0.84
(17.20) (25.68) (10.55) (34.89) (0.05) (0.13) (0.13) (0.05) (0.07) (0.03) (0.05) (0.04) (0.07)

Mean and standard deviation (in parenthesis) obtained on five cross-validation test sets (see Table 2) are shown for each model. Acc. - Accuracy. Best average values are shown in bold font.