GUE
收藏arXiv2025-09-30 收录
下载链接:
https://github.com/zhihan1996/dnabert_2
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是一个包含28个不同数据集的全面多物种基因组分类基准,涵盖了7个分类任务。它评估了模型在处理长度从70到1000不等的序列时的能力。该基准测试涵盖了28个数据集,分布在7个任务中,旨在对基因组序列分类进行评估。
This dataset is a comprehensive multi-species genomic classification benchmark that includes 28 distinct datasets and covers 7 classification tasks. It evaluates the performance of models when handling sequences with lengths ranging from 70 to 1000. This benchmark encompasses 28 datasets distributed across 7 tasks, aiming to evaluate genomic sequence classification.



