Deep learning for understanding gene regulation in diseases via 'omics' integration

通过“组学”整合了解疾病基因调控的深度学习

• 批准号: 10294097
• 负责人: Ritambhara Singh
• 金额: $ 37.95万
• 依托单位: BROWN UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-23 至 2026-06-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10294097
• 关键词: 3-Dimensional; Automobile Driving; Bayesian Analysis; Biological; Cell Line; Cells; Chromatin; DNA; DNA Methylation; Data; Data Set; Development; Disease; Effectiveness; Gene Expression; Gene Expression Regulation; Genes; Genomic Segment; Goals; Graph; Knowledge; Learning; Methods; Modeling; Molecular Conformation; Noise; Sampling; Signal Transduction; Structure; Up-Regulation; base; deep learning; design; experimental study; gene repression; genomic data; histone modification; improved; insight; interest; neural network; novel; repository; single cell technology; three-dimensional modeling; tool

PROJECT SUMMARY We propose to develop and refine neural networks gene expression to understand gene regulation in diseases. We will design deep learning frameworks to integrate various datasets (histone modifications, 3D conformation, sequences, and SNPs) and model their relationship with the gene expression. Our proposed models will explicitly capture the underlying structure and complexity of the biological data to learn meaningful connections. For example, we will use a graph-based neural network to model the 3D conformation of the DNA as a graph and learn from the connections between different genomic regions to predict gene expression. One of our critical goals for using these methods is to extract relevant signals that could be contributing to the up- and down-regulation of genes. We will accomplish this goal by applying interpretation methods for neural networks. These methods will allow us to assign importance scores to the input features that contribute the most towards a particular prediction of interest. Comparing these scores for genes across healthy and disease cell lines will provide insights into gene misregulation and serve as a hypothesis driving tool for biological experiments. We also propose a novel Bayesian inference-based interpretation method to improve explanations of graph-based neural networks that could be applied to various tasks. Finally, given the improvement of single-cell technologies and imputation methods, we will extend our deep learning frameworks to model relationships between signals like chromatin accessibility and DNA methylation with gene expression. This direction will allow us to explore the effectiveness of the imputation methods in removing noise and generating high-quality single-cell samples for usage in deep learning modeling of gene regulation. Looking at the modeled relationships across the cell's developmental stages could pinpoint timepoints for potential misregulation in diseases. Therefore, this proposal aims to develop unified approaches that utilize datasets spanning multiple repositories to leverage their collective knowledge and improve our understanding of diseases in a data-driven manner.

项目概要 我们建议开发和完善神经网络基因表达来理解基因 疾病中的调节。我们将设计深度学习框架来整合各种数据集 （组蛋白修饰、3D 构象、序列和 SNP）并模拟它们之间的关系 与基因表达。我们提出的模型将明确捕获底层结构 和生物数据的复杂性来学习有意义的联系。例如，我们将使用 基于图的神经网络，将 DNA 的 3D 构象建模为图并进行学习 根据不同基因组区域之间的连接来预测基因表达。我们的一员 使用这些方法的关键目标是提取可能有助于 基因的上调和下调。我们将通过应用解释来实现这一目标 神经网络方法。这些方法将使我们能够为 对特定感兴趣的预测贡献最大的输入特征。比较 这些健康细胞系和疾病细胞系的基因评分将提供对基因的深入了解 错误调节并作为生物实验的假设驱动工具。我们也 提出一种新的基于贝叶斯推理的解释方法来改进对 基于图的神经网络可应用于各种任务。最后，鉴于 单细胞技术和插补方法的改进，我们将深入研究 学习框架来模拟信号之间的关系，例如染色质可及性和 DNA 甲基化与基因表达。这个方向将使我们能够探索有效性 消除噪声和生成高质量单细胞样本的插补方法 在基因调控深度学习建模中的应用。查看建模的关系 跨越细胞的发育阶段可以查明潜在的错误调节的时间点 疾病。因此，该提案旨在开发利用数据集的统一方法 跨越多个存储库以利用他们的集体知识并改进我们的 以数据驱动的方式了解疾病。