jhuapl-bio/microbert

MicrobeRT模型训练使用的多个数据集，包括分类学数据集、抗微生物药物耐药性（AMR）数据集和致病性数据集。分类学数据集包含来自真菌、病毒、细菌和古菌的基因组序列。AMR数据集包含耐药和敏感序列，可用于二分类和多类分类任务。

Multiple datasets used for training the MicrobeRT models, including Taxonomy datasets, Anti-Microbial Resistance (AMR) datasets, and Pathogenicity datasets. The Taxonomy datasets contain genomic sequences from fungi, viruses, bacteria, and archaea. The AMR datasets include resistant and sensitive sequences, which can be used for binary and multi-class classification tasks.