Additional file 1 of Accurate prediction of metagenome-assembled genome completeness by MAGISTA, a random forest model built on alignment-free intra-bin statistics

Additional file 1. Supplementary Tables S1, S4, S5 and S6. Supplementary Table S1: Bacterial strains in the HC227 mock. Supplementary Table S4: Alignment-based statistics and distribution parameters for the training datasets. Supplementary Table S5: Alignment-based statistics and distribution parameters for the test datasets. Supplementary Table S6: Relative importance of input variables for the Random Forest classifiers used by MAGISTA and MAGISTIC, respectively.

附加文件1：补充表S1、S4、S5及S6。补充表S1：HC227模拟群落中的细菌菌株。补充表S4：训练数据集的基于序列比对的统计指标与分布参数。补充表S5：测试数据集的基于序列比对的统计指标与分布参数。补充表S6：分别为MAGISTA与MAGISTIC所用的随机森林分类器的输入变量相对重要性。