longevity-genie/aging-expressions

此数据集提供了来自ARCHS4和GTEx数据库的年龄分层基因表达数据，专门为精细调整BulkFormer和其他批量RNA-seq深度学习模型而设计。数据集包含蛋白质编码基因的TPM归一化表达值，以及包括年龄、性别、组织类型和死亡情况在内的综合人口统计数据。数据集的描述包括其功能、来源、基因选择、样本特征、数据处理流程和使用示例。它还讨论了数据集的限制和伦理考虑。

This dataset provides age-stratified gene expression data derived from the ARCHS4 and GTEx databases, specifically curated for fine-tuning BulkFormer and other bulk RNA-seq deep learning models. It includes TPM-normalized expression values for protein-coding genes, along with demographic metadata such as age, sex, tissue type, and death circumstances. The dataset description covers its features, sources, gene selection, sample characteristics, data processing pipeline, and usage examples. It also discusses the datasets limitations and ethical considerations.