基于知识引导多模态图学习从高内涵图谱解析基因型-表型机制
Deciphering Genotype-Phenotype Mechanisms from High-Content Profiling via Knowledge-Guided Multi-modal Graph Learning
把高内涵细胞形态学表型当作图上的关系信号而非节点特征，并学习逐边置信度与知识门控，这一思路可迁移到视觉中需要将图像特征嵌入结构化知识图谱的任务（如场景图推理、视觉-知识联合推理），也为细胞成像的表征学习提供了可解释的图建模范式。
原文依据 Prior approaches typically treat phenotypes as node features, overlooking that phenotypes primarily convey cellular-scale relational signals
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论理解基因型-表型关系对于推进生物医学研究、药物发现和精准医学至关重要。随着高通量细胞成像的兴起，必须将高内涵细胞形态与结构化生物学知识紧密结合，以提取细胞尺度的证据用于基因型到表型的映射。然而，将高维、异构且含噪的表型与结构化知识相整合仍然具有挑战性。已有方法通常将表型视为节点特征，忽略了表型主要传递的是关于扰动如何重塑相互作用的细胞尺度关系信号。我们提出 KERNEL，一个知识引导的多模态图学习框架，它将细胞成像表型整合进统一的知识图谱以预测基因型-表型相互作用，包括基因调控网络（GRN）推断、药物-靶点相互作用预测以及亚型特异性子网络发现。KERNEL 从含噪表型信号中动态增强任务相关的边，显式学习逐边置信度与边际效用，并利用知识门控使图拓扑与机制通路对齐。在大规模成像与单细胞数据集上，KERNEL 一致优于最优基线，例如 GRN 推断的 AUPR 提升最高达 38.1%，同时在药物-靶点相互作用与亚型子网络发现上给出更准确、更可解释的结果，展示了从更丰富、更难去噪的表型中进行稳健机制学习的能力。
英文原文摘要 1518 字符
Understanding genotype-phenotype relationships is pivotal for advancing biomedical research, drug discovery, and precision medicine. With the rise of high-throughput cellular imaging, it is essential to tightly integrate high-content cellular morphology with structured biological knowledge to extract cellular-scale evidence for genotype-to-phenotype mapping.However, integrating high-dimensional, heterogeneous, and noisy phenotypes with structured knowledge remains challenging. Prior approaches typically treat phenotypes as node features, overlooking that phenotypes primarily convey cellular-scale relational signals about how perturbations reshape interactions. We present KERNEL, a knowledge-guided multimodal graph learning framework that integrates cellular imaging phenotypes into a unified knowledge graph to predict genotype-phenotype interactions, including GRN inference, drug-target interaction prediction, and subtype-specific subnetwork discovery. KERNEL dynamically augments task-relevant edges from noisy phenotypic signals, explicitly learns per-edge confidence and marginal utility, and uses knowledge gating to align graph topology with mechanistic pathways. Across large-scale imaging and single-cell datasets, KERNEL consistently outperforms state-of-the-art baselines, e.g., up to 38.1% AUPR improvement for GRN inference, while delivering more accurate and interpretable DTI and subtype subnetwork discovery, demonstrating robust mechanism learning from richer, harder-to-denoise phenotypes.