Skip to main content

Table 2 The performance summary for the devised network and the pure CNN model on the wild-type randomly split test sets

From: Identifying piRNA targets on mRNAs in C. elegans using a deep multi-head attention network

Algorithm model

F1

Precision

Recall

The devised network

0.891* ± 0.003

0.886* ± 0.006

0.899* ± 0.006

The pure CNN model

0.816 ± 0.003

0.805 ± 0.006

0.828 ± 0.005

  1. *indicates that the devised model outperformed the pure CNN model statistically significantly (\(\alpha\) = 0.05) using the one-tailed rank-sum test