Integrated Network Analysis and Therapeutic Target Exploration in Complex Diseases

复杂疾病的综合网络分析和治疗靶点探索

• 批准号: 2720655
• 金额: --
• 依托单位: University College London
• 依托单位国家: 英国
• 项目类别: Studentship
• 财政年份: 2022
• 资助国家: 英国
• 起止时间: 2022 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=studentship-2720655
• 关键词: Integrated; Network; Analysis; Therapeutic; Target

Complex diseases present a multifaceted interplay between genes, proteins, and other molecular entities, necessitating a multi-scale, integrated analysis for understanding their underlying mechanisms. This research project takes a novel approach to investigate complex disease pathways by leveraging the recent advancements in graph neural networks and geometric deep learning.The objectives include a comprehensive investigation of the pathways and fundamental mechanisms of complex diseases through a systems-biology approach, integration of disparate data sources including e.g. protein-protein interactions and differential gene expression, and application of advanced computational methods to elucidate the geometric and topological properties of these networks.The methodology encompasses the curation and amalgamation of large-scale biological datasets across different omics scales to establish a consolidated framework for analysis. State-of-the-art computational techniques, specifically graph neural networks and geometric deep learning, will be employed to decipher the complex structures of the curated integrated biological networks. The derived insights will be utilized to identify potential disease pathways, emphasizing those amenable for drug targeting.Expected outcomes encompass a nuanced understanding of complex disease mechanisms through comprehensive biological network analysis, identification of therapeutic targets, and discovery of drug intervention pathways. The alignment of advanced computational tools with omics data and biological network topology will present a pioneering approach to categorizing disease pathology.The significance of this research lies in its integration of cutting-edge computational techniques with vast biological data repositories. By focusing on intrinsic network structures and their associations with disease, this study hopes to uncover therapeutic targets and make substantial contributions to the field of biomedical research, particularly in the realms of drug development and therapeutic interventions for complex diseases.

复杂疾病呈现基因、蛋白质和其他分子实体之间的多方面相互作用，需要多尺度、综合分析以了解其潜在机制。该研究项目采用了一种新的方法来研究复杂疾病的途径，利用图神经网络和几何深度学习的最新进展。目标包括通过系统生物学方法全面研究复杂疾病的途径和基本机制，整合不同的数据源，例如蛋白质-蛋白质相互作用和差异基因表达，以及应用先进的计算方法来阐明这些网络的几何和拓扑特性。该方法包括跨不同组学尺度的大规模生物数据集的管理和合并，以建立一个统一的分析框架。最先进的计算技术，特别是图形神经网络和几何深度学习，将用于破译策划的综合生物网络的复杂结构。通过全面的生物网络分析、治疗靶点的确定和药物干预途径的发现，对复杂的疾病机制有细致入微的理解。将先进的计算工具与组学数据和生物网络拓扑结构相结合，将为疾病病理分类提供一种开创性的方法。这项研究的意义在于将尖端的计算技术与庞大的生物数据库相结合。通过关注内在网络结构及其与疾病的关联，本研究希望发现治疗靶点，并为生物医学研究领域做出实质性贡献，特别是在药物开发和复杂疾病的治疗干预领域。