SBIR Phase II: Machine Learning for Rapid Automated Viral Infectivity Assays (COVID-19)

SBIR 第二阶段：用于快速自动化病毒感染性检测的机器学习 (COVID-19)

• 批准号: 2136850
• 负责人: Ilya Goldberg
• 金额: $ 99.99万
• 依托单位: ViQi LLC
• 依托单位国家: 美国
• 项目类别: Cooperative Agreement
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-04-01 至 2025-03-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2136850&HistoricalAwards=false
• 关键词: SBIR; Phase; II; Machine; Learning

The broader impact of this Small Business Innovation Research (SBIR) Phase II project is to accelerate the development of antiviral drugs and vaccines for conditions such as COVID-19. The ability to accurately determine if cells are infected with virus is crucial for evaluating antiviral drugs and vaccine candidates. Currently, determining if a virus is infectious is done by infecting cells and waiting for them to die, which can take many days. The proposed technology uses artificial intelligence (AI) to analyze images of cells for signs of virus. This can be done within hours of infection instead of days, which can greatly accelerate the development of vaccines and antiviral drugs. In addition, it is simpler because the AI analysis is automated and does not need special probes or dyes to detect viruses.The proposed project will collect images of cells infected with various viruses imaged with automated microscopes. AIs will be trained to distinguish healthy and sick cells at various times after infection. The project will study many different viruses and the changes they induce in cells. The trained AIs will be used to process infectivity assays. The software will run on remote data centers and thus images will be uploaded for analysis and reporting. An AI can be trained using images from the common 96-well plate.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.

这项小企业创新研究（SBIR）第二阶段项目的更广泛影响是加速针对COVID-19等疾病的抗病毒药物和疫苗的开发。准确确定细胞是否被病毒感染的能力对于评估抗病毒药物和候选疫苗至关重要。目前，确定病毒是否具有传染性是通过感染细胞并等待它们死亡来完成的，这可能需要许多天的时间。该技术利用人工智能（AI）分析细胞图像，寻找病毒迹象。这可以在感染后几小时内完成，而不是几天，这可以大大加快疫苗和抗病毒药物的开发。此外，它更简单，因为人工智能分析是自动化的，不需要特殊的探针或染料来检测病毒。拟议的项目将收集用自动显微镜成像的感染各种病毒的细胞图像。人工智能将接受训练，在感染后的不同时间区分健康细胞和患病细胞。该项目将研究许多不同的病毒及其在细胞中引起的变化。经过训练的人工智能将用于处理感染性分析。该软件将在远程数据中心运行，因此图像将被上传以供分析和报告。人工智能可以使用普通96孔板的图像进行训练。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。