jo-mengr/geo_70k_cellxgene_35k_multiplets
收藏Hugging Face2025-02-14 更新2025-02-15 收录
下载链接：
https://hf-mirror.com/datasets/jo-mengr/geo_70k_cellxgene_35k_multiplets
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测序数据和对应的文本描述，可用于训练多模态模型，以实现转录组数据与文本信息的对齐。数据集由CellWhisperer项目收集和注释，来源于CellxGene和GEO数据库。数据集可用于sentence-transformers框架，并提供了预计算的初始嵌入，用于下游模型的训练和推理。
This dataset contains RNA sequencing data and corresponding text descriptions, which can be used to train a multimodal model for aligning transcriptome and text modalities. The data is collected and annotated from the CellWhisperer project, sourced from CellxGene and GEO databases. It is compatible with the sentence-transformers framework and provides precomputed initial embeddings for downstream model training and inference.
提供机构：
jo-mengr
