CoGT: Ensemble Machine Learning Method and Its Application on JAK Inhibitor Discovery.

The discovery of new drug candidates to inhibit an intended target is a complex and resource-consuming process. A machine learning (ML) method for predicting drug-target interactions (DTI) is a potential solution to improve the efficiency. However, traditional ML approaches have limitations in accuracy. In this study, we developed a novel ensemble model CoGT for DTI prediction using multilayer perceptron (MLP), which integrated graph-based models to extract non-Euclidean molecular structures and large pretrained models, specifically chemBERTa, to process simplified molecular input line entry systems (SMILES). The performance of CoGT was evaluated using compounds inhibiting four Janus kinases (JAKs). Results showed that the large pretrained model, chemBERTa, was better than other conventional ML models in predicting DTI across multiple evaluation metrics, while the graph neural network (GNN) was effective for prediction on imbalanced data sets. To take full advantage of the strengths of these different models, we developed an ensemble model, CoGT, which outperformed other individual ML models in predicting compounds' inhibition on different isoforms of JAKs. Our data suggest that the ensemble model CoGT has the potential to accelerate the process of drug discovery.

Interleukin-35 inhibits angiogenesis through T helper17/ Interleukin-17 related signaling pathways in IL-1ß-stimulated SW1353 cells.

BACKGROUND: Angiogenesis associates with chondrocytes differentiation in inflammatory arthritis. Interleukin (IL)- 1ß stimulated SW1353 cells have a phenotype similar to this kind of chondrocytes. IL-17A, a target in T helper 17 (Th17)/IL-17 signaling pathways, was expressed by SW1353 cells. The study aimed to explore the role of IL-35 on angiogenesis in IL-1ß stimulated SW1353 cells and its related signaling pathways. METHODS: Microarray dataset was downloaded from the Gene Expression Omnibus database of arthritis cartilage. The protein-protein interaction (PPI) was analyzed for IL-35, pro-angiogenic factors and the differentially expressed genes (DEGs). We studied the effects of IL-35 on proliferation and apoptosis in IL-1ß stimulated SW1353 cells using cell counting kit-8 (CCK-8) assay and flow cytometry. The expression of pro-angiogenic factors and IL-17A were assessed by western blot and real-time PCR. Added plumbagin (inhibitor of IL-17A) to repeat the above experiment. The secretion of IL-17A was assessed by ELISA. RESULTS: IL-35, pro-angiogenic factors interacted with DEGs to affect the function of arthritis chondrocytes. IL-35 promoted IL-1ß-stimulated SW1353 cells proliferation, inhibited apoptosis, and decreased pro-angiogenic molecules and IL-17A expression in a concentration dependent manner. IL-35 inhibited IL-17A secretion in the supernatants of these cells. Blocking the Th17/IL-17 related pathways with plumbagin abolished the effects of IL-35 on IL-1ß-stimulated SW1353 cells. CONCLUSION: These results suggested that IL-35 regulated differentiation and pro-angiogenic molecules expression in IL-1ß stimulated SW1353 cells via Th17/IL-17 related signaling pathways. Our findings may reveal the mechanisms of novel angiogenesis molecules in inflammatory chondrocyte lesion.

Effects of fibromyalgia on the disease activity and treatment of patients with axial spondyloarthritis.

OBJECTIVES: To investigate whether patients with radiologically positive spondyloarthritis (SpA), suffer from comorbid fibromyalgia (FM), and to explore the impact of FM on the clinical manifestations and blood test results of patients with ankylosing spondylitis (AS). METHODS: 121 patients with spondyloarthritis (SpA) were enrolled in the study. The body function of the patients was evaluated using the Bath Ankylosing Spondylitis Functional Index (BASFI); the mental health was evaluated using the Hospital Anxiety and Depression Scale (HADS). RESULTS: Out of 121 patients with SpA, 111 patients were with axial spondyloarthritis (axSpA) and 11 patients with FM; 10 patients with peripheral SpA and 1 patient with FM. In axSpA, 107 were radiologically positive axSpA patients, 11 were complicated by FM, and 4 were radiologically negative axSpA (nr-axSpA). Among radiologically positive axSpA, the proportion of female patients in the FM group was higher (63.6%, P<0.05). The ASDAS-C-reactive protein (CRP), ASDAS-erythrocyte sedimentation rate (ESR), BASDAI, BASFI, and HADS-anxiety score, and HADS-depression score of the FM group were all significantly higher than those of the non-FM group. CONCLUSIONS: When determining the treatment plan for SpA, the possibility of coexistence of FM should be considered, and adjuvant treatment should be given when necessary.

Interleukin-35 Regulates Angiogenesis Through P38 Mitogen-Activated Protein Kinase Signaling Pathway in Interleukin-1ß-Stimulated SW1353 Cells and Cartilage Bioinformatics Analysis.

We aimed to investigate the effects of interleukin (IL)-35 on proangiogenic factors in IL-1ß-pretreated chondrocyte-like SW1353 cells and screen-related genes that participated in osteoarthritis (OA) cartilage with IL-35, proangiogenic factors, and P38 mitogen-activated protein kinase (MAPK) signaling pathway. Different concentrations of IL-35 incubated with IL-1ß stimulated SW1353 cells with or without SB203580 (inhibitor of P38 MAPK). Proangiogenic molecule expression was assessed by real-time polymerase chain reaction and enzyme-linked immunosorbent assay. Microarray datasets were downloaded from the Gene Expression Omnibus database of OA cartilage. Protein-protein interaction of genes was visualized by Search Tool for the Retrieval Interacting Genes and Cytoscape. Database for Annotation, Visualization, and Integrated Discovery was used to screen biological processes and pathways. IL-35 inhibited mRNA expression of proangiogenic factors in IL-1ß-stimulated SW1353 cells through the P38 MAPK signaling pathway. IL-35 inhibited angiopoietin-2 secretion. We found that 8 related genes, 18 biological processes, and 6 pathways may associate with IL-35, P38 MAPK signaling pathway, and cartilage angiogenesis. IL-35 regulated the expression of proangiogenic factors through P38 MAPK signaling pathway in IL-1ß-stimulated SW1353 cells. IL-35 and P38 MAPK pathway may participate in neovascularization of cartilage. Our findings may provide molecular mechanisms and possible genes target treatment for OA.