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.
Graphical Abstract
In recent years, drug-induced nephrotoxicity has been one of the main reasons for the failure of drug development. Early prediction of the nephrotoxicity for drug candidates is critical to the success of clinical trials. Therefore, it is very important to construct an effective model that can predict the potential nephrotoxicity of compounds. Machine learning methods have been widely used to predict the physico-
Type 2 diabetes mellitus (T2DM) is a heterogeneous disorder, so achieving the desired therapeutic efficacy through monotherapy is tricky. Drug combinations play a vital role in treating multiple complex diseases by providing increased efficacy and reduced toxicity. Here, we adopted a computational framework to discover potential drugs and drug pairs for T2DM. Firstly, we collected T2DM‐associated genes and constructed the disease module for T2DM. Then, by quantifying the proximity between drugs and the disease module, we found out potential drugs. Based on the drug‐induced gene expression profiles, we further performed Gene Set Enrichment Analysis (GSEA) on these drugs and identified several potential candidates. In addition, through network‐based separation, potential drug combinations for T2DM were predicted. Results from this study could provide insights for anti‐T2DM drug discovery and rational drug use of existing agents. As a useful computational framework, our approach could also be applied in drug research for other complex diseases.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.