starling-labs/PSL
收藏官方服务:
资源简介:
该数据集包含蛋白质亚细胞定位信息,每条记录包括PubMed ID、支持文本、UniProt ID、正样本定位位点、负样本定位位点、模型系统、蛋白质形式、实验条件、定位过程、证据基础、限定条件和额外细节。数据主要用于蛋白质定位研究,训练集包含1,798,418个样本。
This dataset contains protein subcellular localization information, with each record including PubMed ID, support text, UniProt ID, positive localization sites, negative localization sites, model system, protein form, experimental condition, localization process, evidence basis, qualifying conditions, and extra details. The data is primarily used for protein localization research, with a training set of 1,798,418 samples.
提供机构:
starling-labs


