InstaDeepAI/multi_omics_transcript_expression

该数据集基于GTEX项目数据描述了转录表达水平，包含人类转录本在31种组织（V1版本）和50种更具体组织（V2版本）中的转录水平。数据集中的基因表达水平是通过对多个患者测量的平均值进行对数转换得出的。每个数据集中的样本对应一个唯一的基因_转录本对，以及跨多个组织的量化表达水平、DNA序列、ATCG格式的RNA序列和蛋白质序列。数据集分为训练集、测试集和评估集。此外，该数据集目前仅包含编码基因（mRNA）。

This dataset describes transcript expression levels based on the GTEX project data, containing the transcription levels of human transcripts in 31 tissues (V1 version) and 50 more specific tissues (V2 version). The gene expression levels in the dataset are log-transformed averages from multiple patients measurements. Each entry in the dataset corresponds to a unique gene_transcript pair, along with expression levels across tissues, DNA sequence, RNA sequence in ATCG format, and protein sequence. The dataset is split into training, test, and evaluation sets. The dataset currently includes only coding genes (mRNA).