seq-to-pheno/mapped_orthologs

该数据集包含来自Zoonomia项目的多种物种的直系同源蛋白映射信息，主要用于比较基因组学和进化研究。数据集的结构包括一个CSV文件，包含人类转录本ID、人类蛋白质名称、非人类生物转录本ID和查询物种名称等列。数据集仅包含训练集，数据来源于Zoonomia项目的蛋白质比对文件。使用该数据集时需要注意潜在的物种代表性和比对质量的偏差。

This dataset contains mapped orthologs for various species from the Zoonomia Project, primarily used for comparative genomics and evolutionary studies. The dataset structure includes a single CSV file with columns for human transcript ID, human protein name, non-human organism transcript ID, and the name of the query species. The dataset only contains a train split, and the data is sourced from protein alignment files of the Zoonomia Project. Users should be aware of potential biases in species representation and alignment quality when using this dataset.