Research and development of an adverse outcome pathway-focused mechanistic inference tool for 'omics data using semantic knowledge graphs

使用语义知识图研究和开发针对“组学数据”的以不良结果途径为中心的机械推理工具

• 批准号: 10761637
• 负责人: Ruchir Shah
• 金额: $ 24.99万
• 依托单位: SCIOME, LLC
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-09-01 至 2024-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10761637
• 关键词: 3-Dimensional; Address; Assessment tool; Biochemical; Biochemical Reaction; Biological; Cells; Chemicals; Collection; Controlled Vocabulary; Data; Data Set; Decision Making; Development; Disease; Disparate; Dose; Event; Exposure to; Gene Expression; Generations; Genes; Goals; Health; Individual; Intuition; Knowledge; Language; Link; Machine Learning; Maps; Measurable; Measurement; Methodology; Methods; Modeling; Molecular; Neighborhoods; Online Systems; Ontology; Organ; Organism; Pathway interactions; Population; Process; Proteins; Regulation; Regulatory Pathway; Reproducibility; Research; Research Personnel; Risk Assessment; Semantics; Series; Software Engineering; Source; System; Techniques; Testing; Time; Tissue-Specific Gene Expression; Tissues; Uncertainty; Validation; Visualization; adverse outcome; biomedical ontology; concept mapping; deep learning model; drug development; experience; experimental study; heuristics; improved; information organization; knowledge graph; light weight; novel; protein complex; public database; research and development; response; safety assessment; statistics; stressor; text searching; tool; web app; web interface; web-based tool

Project Summary 1 Adverse outcome pathways (AOPs) are risk assessment tools that provide a transparent, mechanistic description of a 2 stressor resulting in an adverse outcome. Each AOP describes a logical sequence of measurable, causally linked events at 3 varying levels of a biological hierarchy (e.g., molecular, cell, organ, and population). Starting with exposure to a stressor, 4 and proceeding through a series of key events, each AOP terminates with an adverse outcome for the health of an 5 organism or population as a whole. Despite the great popularity of AOPs in risk assessment, there are few tools that can 6 exploit the rich mechanistic information they provide, especially quantitatively and in an automated setting. The lack of a 7 systematic framework for representing AOPs in a way that is amenable to quantitative analysis is an important obstacle 8 that limits their regulatory applications. We have developed a unique system, TOXGRAPH, to address the aforementioned 9 limitations. TOXGRAPH integrates biological and biochemical knowledge across a heterogeneous collection of open 10 biomedical ontologies and public databases: a massive, tissue-specific semantic knowledge graph (KG) curated entirely in- 11 house. We have also developed a deep learning-based model that maps unstructured textual AOP descriptions to specific 12 concepts in this KG. To take advantage of these semantic AOP representations, we have developed a framework that 13 allows us to turn AOPs into hypothesis validation tools, by generating enrichment statistics of AOPs an their individual 14 events. This approach can significantly simplify downstream analysis by calculating enrichment statistics at varying levels 15 of granularity, using the results of experimental datasets, such as the results of differential gene expression experiments 16 to quantify AOP enrichment. 17 The research we propose encompasses three specific aims: (1) improve our AOP enrichment statistics; (2) enhance our 18 NLP mapping of AOP event descriptions to biomedical knowledge graph concepts; (3) software engineering for improved 19 user experience with interactive visualizations. In the first aim, we will improve our model to account for multiple 20 experimental doses and time points concurrently for the enrichment of AOP events. In our second aim, we will improve 21 our semantic similarity model to map arbitrary AOP event descriptions to a controlled vocabulary. For this research, we 22 will employ state-of-the-art machine learning, NLP and text mining methodologies. In our third aim, we will develop a 23 web interface to the current command line tool which besides producing the same enrichment results and mechanistic 24 hypotheses will allow users to navigate the results in a lightweight, interactive 3D space. We envision this as a powerful 25 exploratory tool to generate mechanistic hypotheses, with the added ability to show enriched relations across time 26 points in this 3D space. 27 Our overarching goal is to provide an easy, intuitive, and unbiased (data-driven) framework for querying AOPs and 28 researching mechanism of action. TOXGRAPH will directly contribute towards the development of novel non-animal 29 testing strategies and streamline regulatory decision making. Fundamentally, it will greatly facilitate the intended use of 30 AOPs for regulatory applications: to help minimize the uncertainty in decision making.

项目概要 1 不良结果路径 (AOP) 是风险评估工具，可对不良后果提供透明、机械的描述。 2 压力源导致不良结果。每个 AOP 描述了可测量的、因果关联的事件的逻辑序列 生物层次结构的 3 个不同级别（例如分子、细胞、器官和群体）。从暴露于压力源开始， 4 并进行一系列关键事件，每个 AOP 都会以对健康状况不利的结果终止 5 有机体或种群作为一个整体。尽管 AOP 在风险评估中非常受欢迎，但很少有工具可以 6 利用它们提供的丰富机械信息，尤其是定量信息和自动化设置。缺乏一个 7 以适合定量分析的方式表示 AOP 的系统框架是一个重要障碍 8 限制了它们的监管应用。我们开发了一个独特的系统 TOXGRAPH 来解决上述问题 9 限制。 TOXGRAPH 将生物和生化知识整合到异构的开放数据库中 10 个生物医学本体和公共数据库：一个大规模的、特定于组织的语义知识图（KG），完全由 11 房子。我们还开发了一种基于深度学习的模型，将非结构化文本 AOP 描述映射到特定的 本知识库中有 12 个概念。为了利用这些语义 AOP 表示，我们开发了一个框架 13 允许我们通过生成 AOP 及其个体的富集统计数据，将 AOP 转变为假设验证工具 14 个事件。这种方法可以通过计算不同级别的富集统计数据来显着简化下游分析 15的粒度，使用实验数据集的结果，例如差异基因表达实验的结果 16 量化 AOP 富集。 17 我们提出的研究包含三个具体目标：(1) 改进我们的 AOP 丰富统计数据； (2) 增强我们的 18 AOP事件描述到生物医学知识图概念的NLP映射； (3)软件工程改进 19 交互式可视化的用户体验。在第一个目标中，我们将改进我们的模型以考虑多个 同时进行 20 个实验剂量和时间点，以丰富 AOP 事件。在我们的第二个目标中，我们将改进 21 我们的语义相似性模型将任意 AOP 事件描述映射到受控词汇表。对于这项研究，我们 22 将采用最先进的机器学习、NLP 和文本挖掘方法。在我们的第三个目标中，我们将开发一个 23 当前命令行工具的 Web 界面，除了产生相同的富集结果和机制之外 24 种假设将允许用户在轻量级、交互式 3D 空间中导航结果。我们认为这是一个强大的 25 个探索性工具，用于生成机械假设，并具有显示丰富的跨时间关系的能力 这个 3D 空间中有 26 个点。 27 我们的首要目标是提供一个简单、直观且公正（数据驱动）的框架来查询 AOP 和 28 研究作用机制。 TOXGRAPH 将直接促进新型非动物的开发 29 种测试策略并简化监管决策。从根本上说，它将极大地促进预期用途 30 个适用于监管应用的 AOP：帮助最大限度地减少决策中的不确定性。