RAPID IIBR Informatics Computational methods for utilizing SARS-Cov2 sequence and structure data in predicting host-pathogen protein-protein interactions

该奖项授予Hauptman-Woodward医学研究所，支持对机器学习方法的研究，以了解SARS-COV-2蛋白质的相互作用。研究人员将把来自病毒基因组的信息与其他有关蛋白质结构的数据结合起来，以预测蛋白质之间的相互作用。这项研究通过提供有关病毒生物学的重要信息，提供了显著的社会效益。这项研究还可能有助于识别潜在的治疗化合物。作为培训活动的一部分，一名早期研究人员将广泛参与该项目。这些研究的软件和数据将在公共储存库中共享，发表在同行评议的期刊上，并在科学会议上发表。该奖项支持的研究人员将开发基于机器学习的计算工具，用于预测涉及宿主蛋白质和病毒病原体蛋白质的传染病背景下的蛋白质-蛋白质相互作用(PPI)。能够利用立即出现的数据源推进病毒实验工作的计算工具可以对大流行的应对工作产生重大和直接的影响。支持向量机分类器和贝叶斯推理方法将被用于开发包含基因组和结构信息的机器学习模型，以更好地理解和预测蛋白质相互作用。创造计算机工具来了解宿主-病原体的界面的目的是提供关于蛋白质相互作用的基本信息，这些信息决定了病毒进入细胞的机制和病毒病原体的传播方式。在本提案中开发的方法在未来需要快速开发有关新出现病原体的信息时将是有价值的。这一快速奖项由生物基础设施部(DBI)利用冠状病毒援助、救济和经济安全(CARE)法案的资金做出。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

The award to Hauptman-Woodward Medical Research Institute supports research into machine learning approaches to understand the interactions of SARS-COV-2 proteins. The researchers will combine information from the viral genome with other data on protein structures to predict protein interactions. This research affords significant societal benefits by providing important information about the virus biology. The research may also contribute to the identification of potential therapeutic compounds. An early stage researcher will participate extensively in the project as part of training activities. Software and data from the studies will be shared in public repositories, published in peer-reviewed journals, and presented at scientific meetings.Researchers supported by this award will develop machine learning based computational tools for prediction of protein-protein interactions (PPI) in the infectious disease setting involving host proteins and viral pathogen proteins. Computational tools that can leverage immediately arising data sources to advance experimental work on the virus can make a major and immediate impact on pandemic response. Support vector machine classifiers and Bayesian inferential methods will be used to develop machine learning models that incorporate both genomic and structural information to better understand and predict protein interactions. The goal in creating computational tools to understand the host-pathogen interface is to contribute basic information on protein interactions that dictate the mechanisms of virus entry into cells and modes of transmission of viral pathogens. Methods developed in this proposal will be valuable in future situations where rapid information development about an emerging pathogen is required.This RAPID award is made by the Division of Biological Infrastructure (DBI) using funds from the Coronavirus Aid, Relief, and Economic Security (CARES) Act.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.