Supplemental data

Datasets for machine learning as described in "Genome-wide predictions of genetic redundancy in <em>Arabidopsis thaliana</em>" (https://doi.org/10.1101/2020.08.13.250225): Dataset_1.txt: Training set only, RD4 Dataset_2.txt: Training set only, RD9 Dataset_3.txt: Training set = RD4, testing set = whole genome and tandem duplicates (WG/TD set) + RD9 pairs not included in RD4 Dataset_4.txt: Training set = RD4, testing set = kinases (Kin set) + RD9 pairs not included in RD4本机器学习数据集源自《拟南芥（*Arabidopsis thaliana*）全基因组遗传冗余预测》（https://doi.org/10.1101/2020.08.13.250225）一文所描述的数据集： Dataset_1.txt：仅包含训练集RD4； Dataset_2.txt：仅包含训练集RD9； Dataset_3.txt：训练集为RD4，测试集为全基因组与串联重复基因集（WG/TD集）及未纳入RD4的RD9基因对； Dataset_4.txt：训练集为RD4，测试集为激酶基因集（Kin集）及未纳入RD4的RD9基因对。