IUCRC Planning Grant University of Michigan – Ann Arbor (UM): Center for Secured Computation for Drug Discovery and Repurposing (SCDDR)

医药发展对国家经济和公众健康有很大的影响。尽管每年在药物开发上投入大量资金，但许多药物在临床试验中失败，而大多数进入市场的药物未能产生利润。这些成本和低回报阻碍了进一步的开发。药物发现和再利用安全计算中心（SCDDR）通过追求其研究重点，有可能通过增加工程/科学劳动力的能力来极大地增强国家研究基础设施。特别是，SCDDR将为全行业合作药物发现提供新的方法和基础设施，以降低成本生产新药。该中心将专注于（生物）制药行业中未满足/服务不足的研究需求的三个主要领域，其目标是显著加快药物发现的步伐，同时降低研究成本：1)用于药物发现和再利用的机器学习方法的开发、测试和验证；2)为医药和患者数据提供具有第三方私有搜索功能的全行业且与供应商无关的安全数据中心；3)通过加密数据库实现药物重新定位的联合机器学习。有效的全同态加密以及耦合张量-矩阵和张量-张量补全方法在药物发现和再利用中的应用，为这些研究提供了新的发展。该项目汇集了数据科学家、数学家、生物医学研究人员和医疗保健提供者，以产生可重复的方法，这将对数据科学的药物发现和生物医学应用产生广泛的影响。SCCDR将建立一个世界级的数据科学社区，在学术管道的各个阶段都具有包容性和促进多样性。该中心将支持教育下一代数据科学工作人员、研究领导者和公民的项目。通过与工业界、政府和社区合作伙伴的合作，该项目将使研究成果得以传播并转化为有影响力的产品和服务，以改善社会。一个单一的中心范围内的项目存储库，包括已发表的结果、演示、开发的代码和教育材料，将通过中心网站（https://midas.umich.edu/scddr/.This）进行维护和传播，该奖项反映了国家科学基金会的法定使命，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。

Pharmaceutical development has a large impact on the nation’s economy and public health. Despite substantial annual outlays for pharmaceutical development, many drugs fail in clinical trial, while the majority of those making it to market fail to yield a profit. These costs and low returns hinder additional development. The Center for Secured Computation for Drug Discovery and Repurposing (SCDDR), through the pursuit of its research thrusts, has the potential to greatly enhance the national research infrastructure by increasing the capacity of the engineering/scientific workforce. In particular, SCDDR will produce new methodologies and infrastructure for industry-wide collaborative drug discovery, yielding new medicines at reduced cost.The Center will focus on three main areas of unmet/underserved research needs within the (bio)pharmaceutical sector, with the goal of significantly accelerating the pace of drug discovery while reducing research costs: 1) the development, testing, and validation of machine learning methods for drug discovery and repurposing; 2) providing an industry-wide and vendor-agnostic Secure Data Hub for pharmaceutical and patient data with third-party private search capabilities; and 3) enable federated machine learning for drug repositioning over encrypted databases. Enabling these research thrusts are new developments in efficient fully homomorphic encryption and applications of coupled tensor-matrix and tensor-tensor completion methods to drug discovery and repurposing.This project brings together data scientists, mathematicians, biomedical researchers, and healthcare providers to produce reproducible methodologies that will make a broad impact on drug discovery and biomedical applications of data science. SCCDR will build a world-class data science community that is inclusive and promotes diversity at all stages of the academic pipeline. The Center will support programs to educate the next generation of data science workforce members, research leaders, and citizens. By forming collaborations with industry, government, and community partners, the project will enable the dissemination and translation of research into impactful products and services for the betterment of society.A single Center-wide project repository, including published results, presentations, developed code, and educational materials, will be maintained and disseminated through the Center website – https://midas.umich.edu/scddr/.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.