The Janus kinase (JAK) family plays a pivotal role in most cytokine-mediated inflammatory and autoimmune responses via JAK/STAT signaling, and administration of JAK inhibitors is a promising therapeutic strategy for several diseases including COVID-19. However, to screen and design selective JAK inhibitors is a daunting task due to the extremely high homology among four JAK isoforms. In this study, we aimed to simultaneously predict pIC50 values of compounds for all JAK subtypes by constructing an interpretable GNN multitask regression model. The final model performance was positive, with R2 values of 0.96, 0.79 and 0.78 on the training, validation and test sets, respectively. Meanwhile, we calculated and visualized atom weights, followed by the rank sum tests and local mean comparisons to obtain key atoms and substructures that could be fine-tuned to design selective JAK inhibitors. Several successful case studies have demonstrated that our approach is feasible and our model could learn the interactions between proteins and small molecules well, which could provide practitioners with a novel way to discover and design JAK inhibitors with selectivity.

中文翻译：

---

基于多任务 GNN 的可解释模型，用于发现选择性 JAK 抑制剂

Janus 激酶 (JAK) 家族通过 JAK/STAT 信号传导在大多数细胞因子介导的炎症和自身免疫反应中发挥关键作用，而 JAK 抑制剂的施用是包括 COVID-19 在内的多种疾病的有希望的治疗策略。然而，由于四种 JAK 亚型之间的极高同源性，筛选和设计选择性 JAK 抑制剂是一项艰巨的任务。在这项研究中，我们旨在通过构建可解释的 GNN 多任务回归模型来同时预测所有 JAK 亚型的化合物的 pIC50 值。最终模型的性能是积极的，在训练集、验证集和测试集上的 R2 值分别为 0.96、0.79 和 0.78。同时，我们计算并可视化了原子重量，其次是秩和检验和局部平均值比较，以获得可以微调以设计选择性 JAK 抑制剂的关键原子和子结构。几个成功的案例研究表明，我们的方法是可行的，我们的模型可以很好地学习蛋白质和小分子之间的相互作用，这可以为从业者提供一种新的方法来发现和设计具有选择性的 JAK 抑制剂。