DMS/NIGMS 2: A Stability Driven Recommendation System for Efficient Disease Mechanistic Discovery

DMS/NIGMS 2：用于高效疾病机制发现的稳定性驱动推荐系统

• 批准号: 10793779
• 负责人: Bin Yu
• 金额: $ 27.13万
• 依托单位: UNIVERSITY OF CALIFORNIA BERKELEY
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-09-25 至 2027-06-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10793779
• 关键词: Address; Algorithms; Awareness; Biological; Case Study; Clinical Trials; Complex; Data; Data Science; Decision Trees; Dependence; Disease; Effectiveness; Entropy; Etiology; Follow-Up Studies; Gene Silencing; Genes; Genetic; Genome; Hand; Head; Heart Diseases; Heart Hypertrophy; Heritability; Human; Investigation; Learning; Linkage Disequilibrium; Measures; Methodology; Methods; Modeling; National Institute of General Medical Sciences; Noise; Population; Problem Sets; Process; Proteins; Recommendation; Research Personnel; Risk Factors; Sampling; Signal Transduction; Small Interfering RNA; Source; Statistical Data Interpretation; Structure; Survival Analysis; System; Testing; Validation; Variant; Weight; Work; clinical practice; cohort; cost; disease heterogeneity; disease phenotype; effective therapy; experimental study; flexibility; follow-up; gene interaction; genome wide association study; improved; induced pluripotent stem cell derived cardiomyocytes; insight; multimodality; novel; random forest; simulation; success; trait

Overview. It is crucial to uncover the biological features underlying disease mechanisms to develop effective treatments and therapies. Typically, this is done via a two-step process: in stage 1, statistical analyses are used to recommend candidate variants/genes for follow-up investigation. In stage 2, researchers conduct costly experiments, clinical trials, or external studies via independent cohorts to validate or establish causality between candidate features and disease traits. To minimize costs, recommendations should lead to high-yield experiments and be replicable. These recommendations are often generated through GWAS methods, based on linear mixed models. Despite the successes of GWAS, there still exists a substantial heritability gap limiting the applicability of these associations in clinical practice. A number of key issues can contribute to missing heritability including: the need for more informative, multi-modal features; unidentified non-linear and epistatic effects; linkage disequilibrium among variants; and heterogeneous sources of variability. To confront these challenges, we propose a reality-checked stability-driven feature recommendation system based on decision trees that aims at efficient discoveries for high yields in experimentation. We build upon iterative random forests (iRF) and the veridical data science framework based on the principles of Predictability, Computability and Stability (PCS) developed by the PI to propose a number of novel advances for stage 1. We propose: (1) generalized MDI (gMDI) a stability-driven non-linear feature important measure for improving iRF recommendations; (2) dependence-aware feature and interaction discovery; (3) supervised local feature importance for heterogeneous mechanistic discoveries; and (4) validation through gene-silencing experiments. Importantly, we generate multi-modal features to extract information across the genome. Intellectual Merit. Our proposals: improve MDI-based methods by addressing drawbacks of MDI and tailoring to problem settings; incorporate gMDI and dependence structure in iRF; and detect heterogeneous sources of noise. Each aim will be vetted and follow the veridical data science framework. In the case study, we will recommend genes and interactions for gene-silencing experiments. These will supply valuable insights into genetic mechanisms underlying traits related to cardiac hypertrophy. Results of this work will impact mechanistic discovery for complex diseases and advance statistical methodology.

概述。揭示疾病机制背后的生物学特征对于发展至关重要 有效的治疗和疗法。通常，这是通过两步过程完成的：在第一阶段，统计 分析用于推荐候选变异/基因以进行后续调查。在第二阶段， 研究人员通过独立队列进行昂贵的实验、临床试验或外部研究 验证或建立候选特征和疾病特征之间的因果关系。为了最大限度地降低成本， 建议应带来高产实验并可复制。这些建议是 通常通过基于线性混合模型的 GWAS 方法生成。尽管取得了成功 GWAS，仍然存在很大的遗传力差距，限制了这些关联在 临床实践。许多关键问题可能导致遗传力缺失，包括： 信息丰富、多模式特征；未识别的非线性和上位效应；连锁不平衡 变体之间；以及变异性的异质来源。为了应对这些挑战，我们提出了 基于决策树的现实检验稳定性驱动特征推荐系统 实验中高产率的有效发现。我们建立在迭代随机森林（iRF）的基础上 基于可预测性、可计算性和稳定性原则的真实数据科学框架 (PCS) 由 PI 开发，为第一阶段提出一些新颖的进展。我们建议：(1) 广义MDI（gMDI）是稳定性驱动的非线性特征，是提高iRF的重要措施 建议； (2)依赖感知特征和交互发现； (3)有监督的局部特征 对于异质机制发现的重要性； (4) 通过基因沉默进行验证 实验。重要的是，我们生成多模式特征来提取整个基因组的信息。 智力优点。我们的建议：通过解决 MDI 的缺点来改进基于 MDI 的方法， 根据问题设置进行调整；将 gMDI 和依赖结构纳入 iRF 中；并检测 异质噪声源。每个目标都将经过审查并遵循真实的数据科学框架。 在案例研究中，我们将推荐用于基因沉默实验的基因和相互作用。这些将 为心脏肥大相关特征的遗传机制提供有价值的见解。结果 这项工作将影响复杂疾病的机制发现并推进统计方法。