Skip to main content
. 2021 Jun 2;12:660303. doi: 10.3389/fpls.2021.660303

TABLE 3.

Important motifs in the gene expression pattern model.

Sequence Importance (weight in tree model) Motif Name and Annotation
CATGCATG 100.00 IDEF1 binding
ATCGATCG 56.83 Novel: Downstream core element in plant 2 (DCEp2)
ATAATGGC 54.71 Motif extracted from Zn regulated genes at downstream of TSS
GCAGCAGC 54.05 Novel: GCWGCWGC
CGACACGC 49.93 Novel: CGACACGC
EECCRCAH1 48.68 Myb- binding
CACCAACC 48.68 Novel: Myb-binding like
CRTDREHVCBF2 48.22 AP2/ERF binding
GCGCGCCA 46.23 GCGC box
CTACGTGC 44.20 bZIP/bHLH

Top 10 the most important motifs in Boruta-XGBoost model based on MAMA and PLACE model. Importance was calculated as xgboost feature importance to be between 0 (least important) and 100 (most important).