用图神经网络生成可验证的神经疾病假说，跨多层级验证有效。
Graph AI generates neurological hypotheses validated in molecular, organoid, and clinical systems
- 基于异构图变压器构建假说生成模型，整合多源数据。
- 预测农药毒性和药物疗效，临床数据验证降低痴呆风险超37%。
- 适合神经疾病研究者、药物研发人员，推动AI驱动发现。
神经系统疾病是全球致残主因，但多数缺乏疾病修饰治疗。本文提出PROTON，一种异构图变压器，可在分子、类器官和临床系统中生成可检验假说。针对帕金森病（PD）、双相情感障碍（BD）和阿尔茨海默病（AD）进行评估：在PD中，模型将遗传风险位点与多巴胺能神经元存活相关基因关联，预测出对患者来源神经元有毒的农药，如杀虫剂硫丹，在预测排名中位于前1.29%；其在体外筛选中复现了六项全基因组α-突触核蛋白实验，包括分裂泛素酵母双杂交系统（归一化富集得分[NES]=2.30，FDR校正p<1×10⁻⁴）、抗坏血酸过氧化物酶邻近标记检测（NES=2.16，FDR<1×10⁻⁴），以及496例突触核蛋白病患者的高深度靶向外显子测序研究（NES=2.13，FDR<1×10⁻⁴）。在BD中，模型预测维生素D（钙三醇）可逆转双相障碍患者皮层类器官中的蛋白质组改变。在AD中，基于610,524名患者健康记录的分析证实，五种预测药物与七年痴呆风险下降显著相关（最低风险比=0.63，95%置信区间0.53–0.75，p<1×10⁻⁷）。PROTON生成的假说经分子、类器官和临床系统交叉验证，为神经疾病领域的AI驱动发现提供了路径。
原文摘要 · Abstract (English)
Neurological diseases are the leading global cause of disability, yet most lack disease-modifying treatments. We present PROTON, a heterogeneous graph transformer that generates testable hypotheses across molecular, organoid, and clinical systems. To evaluate PROTON, we apply it to Parkinson's disease (PD), bipolar disorder (BD), and Alzheimer's disease (AD). In PD, PROTON linked genetic risk loci to genes essential for dopaminergic neuron survival and predicted pesticides toxic to patient-derived neurons, including the insecticide endosulfan, which ranked within the top 1.29% of predictions. In silico screens performed by PROTON reproduced six genome-wide $α$-synuclein experiments, including a split-ubiquitin yeast two-hybrid system (normalized enrichment score [NES] = 2.30, FDR-adjusted $p < 1 \times 10^{-4}$), an ascorbate peroxidase proximity labeling assay (NES = 2.16, FDR $< 1 \times 10^{-4}$), and a high-depth targeted exome sequencing study in 496 synucleinopathy patients (NES = 2.13, FDR $< 1 \times 10^{-4}$). In BD, PROTON predicted calcitriol as a candidate drug that reversed proteomic alterations observed in cortical organoids derived from BD patients. In AD, we evaluated PROTON predictions in health records from $n = 610,524$ patients at Mass General Brigham, confirming that five PROTON-predicted drugs were associated with reduced seven-year dementia risk (minimum hazard ratio = 0.63, 95% CI: 0.53-0.75, $p < 1 \times 10^{-7}$). PROTON generated neurological hypotheses that were evaluated across molecular, organoid, and clinical systems, defining a path for AI-driven discovery in neurological disease.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。