Vaccine development through graph-based machine learning generated host-pathogen interactome

蛋白质-蛋白质相互作用（PPI）是大多数细胞功能的基础，其中病原体与宿主PPI网络的枢纽和瓶颈相互作用。将蛋白质建模为图形使我们能够将PPI作为不规则但结构几何学上的现象进行研究。基于图的机器学习允许对PPI预测的结构和利用进行推断。该项目将使用基于图形的机器学习生成宿主-病原体相互作用组图谱，用于球虫病，这是一种由艾美耳球虫引起的疾病，每年损失超过20亿美元。目前的疫苗是次优的，需要新的亚单位疫苗。生成的模型将显著提高我们识别疫苗靶点和利用宿主网络优化反应的能力。

Protein-protein interactions (PPIs) underlie most cellular functions, where pathogens interact with hubs and bottlenecks of the host PPI network. Modelling proteins as graphs allows us to study PPI as phenomena on irregular but structure geometry. Graph-based machine learning allows inference of structure and exploitation for PPI prediction. This project will generate a host-pathogen interactome map using graph-based machine learning for coccidiosis, a disease caused by Eimeria with annual losses exceeding USD 2 billion . Current vaccines are suboptimal and new subunit vaccines are required. The model generated will significantly advance our ability to identify vaccine targets and utilize host-networks to optimize responses.