[论文解读] AI-driven multi-omics integration for multi-scale predictive modeling of causal genotype-environment-phenotype relationships

You Wu, Lei Xie|arXiv (Cornell University)|Jul 8, 2024

Gene expression and cancer classification被引用 8

一句话总结

提出一个以人工智能驱动、受生物学启发的框架，用于在生物尺度和物种之间整合多组学数据，以在干预下预测因果的基因型-环境-表型关系。它回顾了扰动组学资源并评估了最先进的多组学整合方法。

ABSTRACT

Despite the wealth of single-cell multi-omics data, it remains challenging to predict the consequences of novel genetic and chemical perturbations in the human body. It requires knowledge of molecular interactions at all biological levels, encompassing disease models and humans. Current machine learning methods primarily establish statistical correlations between genotypes and phenotypes but struggle to identify physiologically significant causal factors, limiting their predictive power. Key challenges in predictive modeling include scarcity of labeled data, generalization across different domains, and disentangling causation from correlation. In light of recent advances in multi-omics data integration, we propose a new artificial intelligence (AI)-powered biology-inspired multi-scale modeling framework to tackle these issues. This framework will integrate multi-omics data across biological levels, organism hierarchies, and species to predict causal genotype-environment-phenotype relationships under various conditions. AI models inspired by biology may identify novel molecular targets, biomarkers, pharmaceutical agents, and personalized medicines for presently unmet medical needs.

研究动机与目标

• 动机：在环境扰动下利用中间表型作为连接纽带，推动从基因型预测表型的需求。
• 提出一个受生物学启发的AI框架，跨尺度和跨物种整合多组学数据，以推断因果的G-E-P关系。
• 调研扰动组学数据资源以及用于多组学整合的当代机器学习方法，以识别局限性与机遇。

提出的方法

• 回顾扰动组学数据资源（如 TCGA、LINCS、DepMap、scPerturb、PharmacoDB、ProteomicsDB）及其在G-E-P建模中的适用性。
• 总结并评估最先进的无监督、有监督和基于知识图谱的多组学整合方法（自编码器、 transformers、对比学习、图神经网络等）。
• 强调用于跨水平、跨尺度、跨物种数据整合的生物启发型AI建模原则，旨在预测对前所未有扰动的表型响应。

Figure 1: Illustration of cross-level, cross-scale, cross-species multi-omics data integration

实验结果

研究问题

• RQ1 现有的扰动组学数据资源有哪些，它们如何支持对G-E-P的预测建模？
• RQ2 当前无监督、有监督和基于图的多组学整合方法在跨水平基因型-环境-表型预测中的优缺点是什么？
• RQ3 受生物学启发的AI模型如何实现分子机制在跨物种到人类表型的翻译，适用于扰动情景？
• RQ4 在数据、泛化和因果关系方面存在哪些空缺，应由所提框架解决？

主要发现

• 在多模态和多物种中存在大量扰动组学数据，但用于扰动下表型预测的带标签数据仍然稀缺。
• 当前方法涵盖无监督、有监督和知识图谱方法，各自存在与数据配对要求、模态对齐和跨领域泛化相关的权衡。
• 受生物学启发的整合跨尺度和跨物种多组学的AI框架有望发现新靶点、生物标志物和个性化治疗方案。
• 基础模型（如 transformers）和跨物种分析（如 GeneCompass）展示了跨领域和跨物种G-E-P洞察的潜力，尽管存在依赖配对数据与领域对齐等局限性。

Figure 2: Illustration of multi-modal supervised learning. (a) A conventional strategy that requires paired data for all the modalities simultaneously. (b) An end-to-end deep neural network explicitly models asymmetric information flows from DNAs to RNAs to proteins to metabolites and ultimately to