Skip to main content
. 2026 Feb 3;17:1739720. doi: 10.3389/fgene.2026.1739720

TABLE 10.

Comparison of the performance of different models on training dataset 2 using 5-fold cross-validation.

Predictor Sn SP Acc MCC AUC
iPromoter-5mC 0.895 0.920 0.931 0.786 0.981
BiLSTM-5mC 0.875 0.966 0.949 0.803 0.983
TCN-5mC 0.875 ± 0.0036 0.979 ± 0.0042 0.966 ± 0.0011 0.847 ± 0.0025 0.989 ± 0.0001

The highest value for each evaluation metric is highlighted in bold.