A Modular Framework for Data-Driven Neurogenetics to Predict Complex and Multidimensional Autistic Phenotypes

数据驱动神经遗传学预测复杂和多维自闭症表型的模块化框架

• 批准号: 10826595
• 负责人: Archana Venkataraman
• 金额: $ 46.95万
• 依托单位: BOSTON UNIVERSITY (CHARLES RIVER CAMPUS)
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-06-01 至 2027-05-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10826595
• 关键词: Affect; Algorithms; Anxiety; Architecture; Attention; Attention deficit hyperactivity disorder; Awareness; Beds; Biological; Biological Markers; Biological Process; Brain; Brain region; Child; Clinical; Collection; Communities; Complex; Computational algorithm; Computer software; Copy Number Polymorphism; Data; Dependence; Diagnostic; Diffusion Magnetic Resonance Imaging; Dimensions; Disease; Etiology; Formulation; Functional Magnetic Resonance Imaging; Genes; Genetic; Genetic Markers; Genetic Risk; Genetic Variation; Genomics; Goals; Graph; Image; Impaired cognition; Impairment; Intervention; Learning; Linear Models; Link; Magnetic Resonance Imaging; Maps; Mental Depression; Methods; Modality; Modeling; Multimodal Imaging; Multiomic Data; Mutation; National Human Genome Research Institute; Neurologic; Ontology; Pathway interactions; Patients; Phenotype; Procedures; Process; Published Comment; Research; Research Personnel; Resources; Rest; Sex Differences; Single Nucleotide Polymorphism; Structure; Symptoms; Testing; United States; Universities; Validation; Variant; Virginia; Visualization; Work; analytical tool; autism spectrum disorder; autistic; autoencoder; base; behavioral impairment; biological systems; biomarker discovery; clinical heterogeneity; clinical phenotype; clinically relevant; comorbidity; cost; data framework; deep learning model; deep neural network; feature selection; flexibility; genetic architecture; genetic variant; genome-wide; graph neural network; imaging genetics; innovation; insight; instrument; lens; magnetic resonance imaging biomarker; model development; multidimensional data; multimodal data; multimodal neuroimaging; multimodality; neural; neural network architecture; neurogenetics; neuroimaging; neuroimaging marker; neuropsychiatric disorder; neuropsychiatry; next generation; novel; novel strategies; novel therapeutics; open source tool; operation; personalized intervention; personalized therapeutic; phenomenological models; social; synergism; tool; user-friendly

Project Summary/Abstract Autism Spectrum Disorder (ASD) can be viewed through three complementary lenses: neurologically, it is linked to distributed changes in brain structure, function, and connectivity; biologically, it is associated with genome-wide mutations across multiple pathways; and clinically, it manifests as a diverse spectrum of behavioral and cogni- tive impairments. Despite this richness, treatment options for ASD are based on coarse diagnostics and target a few specific symptoms, such as social awareness, irritability, and depression. As a result, they have varied, and often limited, efficacy across patients. Taken together, next-generation therapeutics for ASD will crucially depend on our ability to bridge its neurological, biological, and clinical viewpoints for personalized intervention. Imaging-genetics is an emerging field that attempts to link neuroimaging features with genetic variants. How- ever, most methods focus on a restricted set of biomarkers, and they do not account for clinical phenotype, both of which provide an incomplete picture of the impacted processes. Our long-term goal is to develop a modu- lar platform that fuses multimodal neuroimaging and multi-omics data to unravel the complex etiology of ASD. The overall objective of this proposal is to develop and validate interpretable deep learning models to combine genome-wide variants with whole-brain structural and functional MRI data. Our innovative strategy is to use biologically-informed neural network architectures to project each of the modalities to a shared latent space that is simultaneously predictive of patient-level clinical phenotype. This unique formulation can easily accommodate missing data modalities, thus maximally utilizing all of the available information. We will devise, implement, vali- date, and disseminate our model via four specific aims. In Aim 1 we will develop a graph neural network, whose connections mimic a well-known gene ontology. Hierarchical pooling operations will capture the information flow through the network, while an attention layer will learn the discriminative biological pathways associated with the phenotype. In Aim 2 we will develop and integrate a Bayesian feature selection procedure to identify ROI-based neuroimaging biomarkers and a matrix autoencoder to extract discriminative functional subnetworks from brain connectivity data. In Aim 3 we will use the fused imaging and genetic architectures to uncover the neural and biological bases underlying the observed clinical heterogeneity of ASD. Finally, in Aim 4 we will package and dis- seminate our model as a user-friendly tool for the broader research community. We anticipate the proposed work will have a transformative impact on ASD research by allowing us to develop refined diagnostic instruments and on the field of imaging-genetics by providing a new approach for multimodal biomarker discovery.

项目总结/摘要 自闭症谱系障碍（ASD）可以通过三个互补的镜头来看待：神经学上，它与 大脑结构、功能和连通性的分布变化;在生物学上，它与全基因组相关。 在临床上，它表现为行为和认知的多样性， 情感障碍尽管如此丰富，ASD的治疗选择仍基于粗略的诊断和目标 一些特定的症状，如社会意识，易怒和抑郁。因此，它们各不相同， 而且通常是有限的，对患者的有效性。总之，下一代ASD治疗方法将至关重要， 这取决于我们将神经学、生物学和临床观点联系起来进行个性化干预的能力。 成像遗传学是一个新兴的领域，试图将神经影像学特征与遗传变异联系起来。怎么-- 以往，大多数方法集中于一组有限的生物标志物，并且它们不考虑临床表型， 其中提供了受影响流程的不完整情况。我们的长期目标是发展现代化的... 更大的平台，融合多模态神经成像和多组学数据，以揭示ASD的复杂病因。 该提案的总体目标是开发和验证可解释的深度学习模型，以便将联合收割机 全基因组变异与全脑结构和功能MRI数据。我们的创新战略是利用 生物学上知情的神经网络架构，以将每种模态投射到共享的潜在空间， 同时预测患者水平的临床表型。这种独特的配方可以很容易地适应 缺失的数据模式，从而最大限度地利用所有可用信息。我们将设计，实施，价值- 日期，并通过四个具体目标传播我们的模型。在目标1中，我们将开发一个图神经网络，其 连接模仿一个众所周知的基因本体。分层池操作将捕获信息流 通过网络，而注意力层将学习与神经网络相关联的区别性生物途径。 表型在目标2中，我们将开发和集成贝叶斯特征选择程序，以识别基于ROI的 神经成像生物标志物和矩阵自动编码器，用于从大脑中提取区分性功能子网络 连接数据。在目标3中，我们将使用融合的成像和遗传架构来揭示神经和 ASD临床异质性的生物学基础。最后，在目标4中，我们将打包并显示- 将我们的模型作为更广泛的研究社区的用户友好工具。我们预计， 将通过允许我们开发改进的诊断仪器，对ASD研究产生变革性影响 以及通过提供用于多模态生物标志物发现的新方法而在成像遗传学领域上。