RAPID: Understanding the Transmission and Prevention of COVID-19 with Biomedical Knowledge Engineering

2019冠状病毒病已成为全球性大流行病，影响数百个国家的数百万人。本集团致力研究COVID-19的传播及预防。了解最新的研究对研究人员和从业人员至关重要。然而，相关文献数量的快速增长使得这是一项具有挑战性的任务。此项目建议建立COVID-19特定知识图谱，以促进获取COVID-19相关知识。知识图谱还将不断更新，其中包括利用自然语言处理技术从最新生物医学文献中提取的信息。一个软件管道，它集成了知识图，并使知识图作为一个Web服务公开提供，具有支持信息检索和问题回答的用户友好界面。将为用户提供交互式可视化，以探索知识图并导出推理路径以获得答案。用于构建知识图谱的所有相关数据和源代码都将公开提供。该项目通过以下方式构建COVID-19特定知识图谱：1）整合生物医学实体的现有知识库，包括生物学、临床和流行病学; 2）从最新的生物医学文献中提取新知识，并不断增强构建的知识图谱。虽然知识图谱针对COVID-19，但开发的管道和技术也可以轻松扩展到其他严重疾病。 拟议研究的技术内容将影响公共卫生、生物医学信息学、计算机科学和流行病学。拟议研究的结果将纳入课程。女性和代表性不足的研究人员，本科生和K-12学生，将积极参与本项目的研究工作。该奖项反映了NSF的法定使命，并已被认为是值得通过使用基金会的智力价值和更广泛的影响审查标准进行评估的支持。

COVID-19 has been a global pandemic affecting millions of people across hundreds of countries. Great efforts have been devoted to the research on the understanding of the transmission and prevention of COVID-19. Staying up-to-date with the latest research is crucial to the researchers and practitioners. However, the rapid growing of the number of the relevant literature makes this a challenging task. This project proposes to build a COVID 19 specific knowledge graph to facilitate the acquisition of COVID-19 related knowledge. The knowledge graph will also be continuously updated with the information extracted from latest biomedical literature with natural language processing techniques. A software pipeline that integrates and makes the knowledge graph publicly available as a web service with user friendly interface supporting information retrieval and question answering. Interactive visualization will be provided for the users to explore the knowledge graph and derive the inference paths to obtain the answers. All associated data and source codes for constructing the knowledge graph will be made publicly available. This project constructs a COVID-19 specific knowledge graph by 1) integrating the existing knowledge bases on biomedical entities from biological, clinical and epidemiological scales; 2) extracting new knowledge from latest biomedical literature and enhancing the constructed knowledge graph continuously. Although the knowledge graph targets COVID-19, the developed pipeline and techniques can be easily extended to other critical diseases as well. The technical content of the proposed research will impact public health, biomedical informatics, computer science and epidemiology. The results of the proposed research will be incorporated into the classes. Females and underrepresented researchers, undergraduates and K-12 students, will be actively engaged in the research effort of this project.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.