Proteins and chemicals mentioned in COVID-19 clinical trials

A record of all COVID-19 related clinical trials is provided in the database hosted at https://ClinicalTrials.gov, thus tracking worldwide research efforts directed towards improvements in treating the pandemic. To help unlock insights buried in this database, we have created an automated text mining pipeline that dynamically tags chemical, protein, and gene names in all COVID-19 related database entries, as the database is updated. The output data from this tagging process are provided in this Zenodo entry. We plan to update these entries regularly. Interactive graphical views of these data can be accessed via https://yan073.github.io/visualtag/.托管于https://ClinicalTrials.gov的数据库中收录了所有与新型冠状病毒肺炎（COVID-19）相关的临床试验记录，该库旨在追踪全球范围内为优化该大流行病治疗方案所开展的科研工作。为挖掘该数据库中潜藏的科研洞见，我们开发了一套自动化文本挖掘流程，可在数据库更新时，对所有新冠相关的数据库条目动态标注化学物质、蛋白质与基因名称。本次标注流程生成的输出数据已收录于本Zenodo条目。我们将定期更新此类数据集条目。用户可通过https://yan073.github.io/visualtag/访问该数据集的交互式可视化视图。