SBIR Phase I: Knowledge Graph-powered Information Retrieval and Causal Inference

SBIR 第一阶段：知识图谱驱动的信息检索和因果推理

• 批准号: 2335357
• 负责人: Jinfeng Zhang
• 金额: $ 27.5万
• 依托单位: INSILICOM LLC
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2024
• 资助国家: 美国
• 起止时间: 2024-02-15 至 2025-01-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2335357&HistoricalAwards=false
• 关键词: SBIR; Phase; Knowledge; Graph; powered

The broader/commercial impact of this Small Business Innovation Research (SBIR) Phase I project is as follows. The exponential growth of scientific literature poses two critical challenges: (1) missing important prior studies during research design can lead to resource and time wastage, incorrect conclusions, and missed discoveries, and (2) effectively utilizing the vast volume of scientific knowledge in raw text form has become increasingly difficult. This project aims to build disruptive, commercially valuable products that address these challenges, benefiting the pharmaceutical industry and academic research. In addition, the success of the project in developing advanced AI technologies will have a significant impact on the growth and development of the AI industry in Tallahassee, FL, and the broader southeast region of the United States.This Small Business Innovation Research (SBIR) Phase I project aims to develop AI-powered, commercially viable applications enabled by a large-scale biomedical knowledge graph (KG) constructed recently using an award-winning natural language processing (NLP) pipeline. The KG has been further transformed into a causal KG by integrating causal relations and enhanced by incorporating data from 40 public databases and analysis results of some commonly used genomics datasets. To facilitate seamless access to the KG, the project team has developed a versatile query interface named iExplore. This interface enables highly accurate information retrieval and supports causal inference, providing users with valuable insights. In the current project, Insilicom LLC will further increase the coverage of the KG and build a novel literature alert system called iPulse. By combining the advancements in AI, the richness of the knowledge graph, and the utility of the query interface and literature alert system, this project will result in practical and commercially viable applications that will revolutionize the way biomedical knowledge is accessed, interpreted, and utilized.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.

该小型企业创新研究 (SBIR) 第一阶段项目的更广泛/商业影响如下。科学文献的指数级增长带来了两个关键挑战：（1）在研究设计过程中缺少重要的先前研究可能会导致资源和时间浪费、错误的结论和错过的发现；（2）有效地利用原始数据中的大量科学知识。文本形式变得越来越困难。该项目旨在打造颠覆性的、具有商业价值的产品来应对这些挑战，使制药行业和学术研究受益。此外，该项目在开发先进人工智能技术方面的成功将对佛罗里达州塔拉哈西以及更广泛的美国东南部地区人工智能行业的增长和发展产生重大影响。这项小型企业创新研究（SBIR）第一阶段项目旨在开发由人工智能驱动的、商业上可行的应用程序，这些应用程序由最近使用屡获殊荣的自然语言处理（NLP）管道构建的大规模生物医学知识图（KG）支持。通过整合因果关系，知识图谱进一步转化为因果知识图谱，并通过合并来自40个公共数据库的数据和一些常用基因组数据集的分析结果来增强知识图谱。为了方便对KG的无缝访问，项目团队开发了一个名为iExplore的多功能查询接口。该界面可实现高度准确的信息检索并支持因果推理，为用户提供有价值的见解。在当前的项目中，Insilicom LLC将进一步扩大KG的覆盖范围，并建立一个名为iPulse的新颖文献警报系统。通过结合人工智能的进步、知识图谱的丰富性以及查询界面和文献警报系统的实用性，该项目将产生实用且商业上可行的应用程序，从而彻底改变生物医学知识的获取、解释和利用方式该奖项反映了 NSF 的法定使命，并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，被认为值得支持。