Skip to main content
. 2021 Apr 12;12:2165. doi: 10.1038/s41467-021-22489-2

Fig. 8. Cis-regulatory features synergistically contribute to model prediction.

Fig. 8

a Percent contribution of individual feature to model prediction ranked by averaging normalized SHAP values. Error bars indicate the variability in feature contribution across the three substrates NEIL1 (orange dot), TTYH2 (purple dot), and AJUBA (green dot). The new features unique to this work is highlighted in red. Higher ranking with smaller standard errors indicates that these features are commonly among the highest contributors to model prediction in all three RNAs. b Contributions of different feature groups to the prediction of editing levels for each RNA library. NEIL1 (orange), TTYH2 (purple), and AJUBA (green). Black dots indicate the scale. The subgroups of individual features included in each feature group are listed in Supplementary Data 1.