Skip to main content
. 2018 Oct 25;9:495. doi: 10.3389/fgene.2018.00495

FIGURE 1.

FIGURE 1

Framework of algorithms proposed in this study. There are two main steps. In the first step, the input RNA sequences are filtered by removing those irrelevant sequences. Then, the remaining sequences are fed into the proposed feature extraction algorithm for feature representation. In the second step, the resulting feature representations are optimized by feature selection, and then, the optimal feature representations are predicted by a XGBoost model.