PFI-RP: Precision diagnostics for personalized cancer care: development of new drugs and selection of treatment

这个创新研究伙伴关系（PFI-RP）项目的更广泛的影响/商业潜力是通过使用创新的人工智能（AI）技术来选择针对每个患者的最佳治疗方案，以延长患者的生命。尽管出现了新的治疗方法，但癌症仍然是美国第二大死亡原因。目前缺乏选择适合个体癌症患者的最佳治疗方案的临床工具。为了满足这些未满足的临床需求，该项目将采用成熟的尖端AI/大数据技术来确定个体患者的最佳治疗方法和治疗方案，以改善癌症预后。在成功完成这项技术的开发后，该解决方案将通过避免初始治疗失败来降低医疗成本。该项目还将促进跨学科的研究生研究，并培养未来的创新和创业领导者。这项工作如果成功，将导致阿巴拉契亚的工业投资和劳动力发展，减少西弗吉尼亚州的健康差距，该地区癌症发病率和死亡率高。拟议的项目基于领先的人工智能技术，在计算效率，可扩展性和准确性方面具有竞争优势，优于现有的其他方法，用于开发诊断基因测试和新药。使用所提出的技术，可以开发新的原型基因检测并申请专利，用于乳腺癌、卵巢癌、结肠癌和肺癌患者的诊断、预后和治疗益处的预测。这些基因检测将有能力识别肿瘤复发和转移的高风险个体，并选择最有利于患者的药物治疗。拟议的人工智能管道最初将专注于发现治疗肺癌的新药选择，但可以扩展到其他类型的癌症。该项目有三个目标：1）建立与多个创新网络/中心的联系，加强企业与行业的合作，2）加速原型产品的市场导向开发，3）开发跨计算机科学，肿瘤学，生物医学研究和创业精神的新型多学科研究生培训计划。为了克服商业化中的技术障碍，该项目将利用多模式患者数据，使用几家精密医疗公司的制造平台，以1）验证原型基因测定，以实现最佳治疗选择和更好的癌症结果，以及2）建立基于AI的技术，用于全面发现新药和/或重新定位食品和药物管理局（FDA）-该项目由创新伙伴计划和刺激竞争研究的既定计划（EPSCoR）共同资助。该奖项反映了NSF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进行评估，被认为值得支持审查标准。

The broader impact/commercial potential of this Partnerships for Innovation – Research Partnerships (PFI-RP) project is to benefit cancer patients by using AN innovative artificial intelligence (AI) technology to select optimal treatment options tailored to each individual patient with the goal of prolonging patient life. Despite emerging new therapies, cancer remains the second leading cause of death in the United States. Clinical tools to select optimal treatment options suitable for individual cancer patients are currently lacking. To meet these unmet clinical needs, this project will employ an established cutting-edge AI/big data technology to determine the best treatments and therapeutic options for individual patients to improve cancer outcomes. Upon successful completion of the development of this technology, the solution will reduce healthcare costs by avoiding initial treatment failures. This project will also foster transdisciplinary graduate research and educate future leaders in innovation and entrepreneurship. This work, if success, will result in industrial investments and workforce development in Appalachia, reducing health disparities in West Virginia, which has high cancer incidence and mortality rates.The proposed project is based on leading-edge AI technology with competitive advantages in computational efficiency, scalability, and accuracy over existing other methods for developing diagnostic gene tests and new drugs. Using the proposed technology, new prototype gene assays can be developed and patented for diagnosis, prognosis, and prediction of therapeutic benefits in breast, ovarian, colon, and lung cancer patients. These gene assays will have the ability to identify individuals who are at high-risk for tumor recurrence and metastasis and select the drug treatments that will benefit the patients the most. The proposed AI pipeline will initially focus on the discovery of new drug options for treating lung cancer but can be expanded to other types of cancers. This project has three goals: 1) to establish the connection with multiple innovation networks/hubs, enhancing academia-industry collaboration, 2) to accelerate market-oriented development of prototype products, and 3) to develop a novel multidisciplinary graduate training program across computer science, oncology, biomedical research, and entrepreneurship. To overcome the technical hurdles in commercialization, this project will leverage multi-modal patient data using several precision medicine companies' manufacturing platforms to 1) validate the prototype gene assays for optimal treatment selection and better cancer outcomes, and 2) establish an AI-based technology for comprehensively discovering new drugs and/or repositioning Food and Drug Administration (FDA)-approved drugs for cancer patients with failed prior therapy.This project is jointly funded by Partnerships for Innovation Program and the Established Program to Stimulate Competitive Research (EPSCoR).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.