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

基本信息

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
项目类别：
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

项目摘要

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.

项目概要/摘要自闭症谱系障碍 (ASD) 可以通过三个互补的视角来看待：从神经学角度来看，它是相关的从生物学角度来说，它与大脑结构、功能和连接性的分布式变化有关；跨多种途径的突变；在临床上，它表现为多种行为和认知尽管存在丰富的障碍，但自闭症谱系障碍的治疗选择仍基于粗略的诊断和目标。一些具体的症状，如社交意识、易怒和抑郁，因此，它们各不相同，总的来说，下一代自闭症谱系障碍治疗方法的疗效往往有限。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。影像遗传学是一个新兴领域，试图将神经影像特征与遗传变异联系起来。迄今为止，大多数方法都专注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。我们的长期目标是开发一个模块化的解决方案。 lar 平台融合了多模式神经影像和多组学数据，以揭示 ASD 的复杂病因。该提案的总体目标是开发和解释可验证的深度学习模型，以结合我们的创新策略是使用全脑结构和功能 MRI 数据的全基因组变异。生物信息神经网络架构将每种模式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轻松适应。缺少数据模式，从而最大限度地利用所有可用信息，我们将设计、实施、验证。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，其特征是：连接模仿众所周知的基因本体，分层池化操作将捕获信息流。通过网络，而注意力层将学习与在目标 2 中，我们将开发并集成贝叶斯特征选择程序来识别基于 ROI 的特征。神经影像生物标志物和矩阵自动编码器从大脑中提取判别性功能子网络在目标 3 中，我们将使用融合成像和遗传架构来揭示神经和连接数据。最后，在目标 4 中，我们将打包和展示所观察到的 ASD 临床异质性的生物学基础。我们期望将我们的模型作为更广泛的研究界的用户友好工具。将使我们能够开发出精致的诊断仪器，从而对自闭症谱系障碍（ASD）研究产生变革性影响并在成像遗传学领域提供多模式生物标志物发现的新方法。