jo-mengr/cellxgene_pseudo_bulk_full_lognorm-multiplets_natural_language_annotation
收藏Hugging Face2025-10-03 更新2025-11-15 收录
下载链接：
https://hf-mirror.com/datasets/jo-mengr/cellxgene_pseudo_bulk_full_lognorm-multiplets_natural_language_annotation
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含RNA测序数据和相关的文本描述。数据来源于CellWhisperer项目，并来自CellxGene和GEO数据库。数据集适合用于对比学习或推理任务，并包括多种与基因相关的信息以及文本注释。数据以.h5ad文件格式存储，可以使用sentence-transformers框架来训练多模态模型。
This dataset contains RNA sequencing data and associated text descriptions. It is derived from the CellWhisperer project and related to the CellxGene and GEO databases. The dataset is suitable for contrastive-learning or inference tasks and includes various gene-related information as well as text annotations. The data is stored in .h5ad file format and can be used with the sentence-transformers framework to train a multimodal model.
提供机构：
jo-mengr
