Burkhart Joshua G, Wu Guanming, Song Xubo, Raimondi Francesco, McWeeney Shannon, Wong Melissa H, Deng Youping
Department of Quantitative Health Sciences, University of Hawaii John A. Burns School of Medicine, Honolulu, HI 96813, USA.
Division of Bioinformatics and Computational Biology, Department of Medical Informatics and Clinical Epidemiology, Oregon Health & Science University, Portland, OR 97239, USA.
Patterns (N Y). 2023 May 22;4(7):100758. doi: 10.1016/j.patter.2023.100758. eCollection 2023 Jul 14.
Functional heterogeneity of healthy human tissues complicates interpretation of molecular studies, impeding precision therapeutic target identification and treatment. Considering this, we generated a graph neural network with Reactome-based architecture and trained it using 9,115 samples from Genotype-Tissue Expression (GTEx). Our graph neural network (GNN) achieves adjusted Rand index (ARI) = 0.7909, while a Resnet18 control model achieves ARI = 0.7781, on 370 held-out healthy human tissue samples from The Cancer Genome Atlas (TCGA), despite the Resnet18 using over 600 times the parameters. Our GNN also succeeds in separating 83 healthy skin samples from 95 lesional psoriasis samples, revealing that upregulation of 26S- and NUB1-mediated degradation of NEDD8, UBD, and their conjugates is central to the largest perturbed reaction network component in psoriasis. We show that our results are not discoverable using traditional differential expression and hypergeometric pathway enrichment analyses yet are supported by separate human multi-omics and small-molecule mouse studies, suggesting future molecular disease studies may benefit from similar GNN analytical approaches.
健康人体组织的功能异质性使分子研究的解读变得复杂，阻碍了精准治疗靶点的识别和治疗。考虑到这一点，我们构建了一个基于Reactome架构的图神经网络，并使用来自基因型-组织表达（GTEx）的9115个样本对其进行训练。在来自癌症基因组图谱（TCGA）的370个保留的健康人体组织样本上，我们的图神经网络（GNN）实现了调整兰德指数（ARI）= 0.7909，而Resnet18对照模型实现了ARI = 0.7781，尽管Resnet18使用的参数是我们的GNN的600多倍。我们的GNN还成功地将83个健康皮肤样本与95个病变银屑病样本区分开来，揭示了26S和NUB1介导的NEDD8、UBD及其缀合物降解的上调是银屑病中最大扰动反应网络组件的核心。我们表明，使用传统的差异表达和超几何通路富集分析无法发现我们的结果，但这些结果得到了单独的人类多组学和小分子小鼠研究的支持，这表明未来的分子疾病研究可能会从类似的GNN分析方法中受益。
