Graph deep learning reveals multiple signal pathways activated in anti-citrullinated protein antibodies stimulated synoviocytes
Sun, M.; Chen, Y.; Brodin, P.; Catrina, A. I.
Show abstract
AO_SCPLOWBSTRACTC_SCPLOWWe present a study of anti-citrullinated protein antibodies stimulated fibroblast-like synoviocytes from patients with rheumatoid arthritis, which is powered by a novel graph deep learning framework applied to single-cell mRNA expression data. This new analytical framework discovered dominant pathways that suggest IL1-IL1R mediated signaling, a novel signal transduction response to ACPA-stimulation, and comfirmed our previous finding of PI3K/AKT activation in response of ACPA-stimulation as well. The study demonstrated the capability of graph deep learning framework on signaling pathway analysis. The findings suggest that ACPAs contribute to distinct pathogenic events through activating multiple signaling pathways.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Inference of an integrative, executable network for Rheumatoid Arthritis combining data-driven machine learning approaches and a state-of-the-art mechanistic disease map 95%
- Comprehensive profiling of genomic and transcriptomic differences between risk groups of lung adenocarcinoma and lung squamous cell carcinoma 89%
- The Autonomic Nervous System Differentiates Between Levels of Motor Intent and Hand Dominance 89%
Similar papers in this journal
- GraphMHC: neoantigen prediction model applying the graph neural network to molecular structure 93%
- Unsupervised tensor decomposition-based method to extract candidate transcription factors as histone modification bookmarks in post-mitotic transcriptional reactivation 92%
- Imbalanced Machine Learning Classification Models For Removal Biosimilar Drugs And Increased Activity In Patients With Rheumatic Diseases 92%
Similar papers in this journal
- Finding disease modules for cancer and COVID-19 in gene co-expression networks with the Core&Peel method 94%
- Naturally occurring combinations of receptors from single cell transcriptomics in endothelial cells 94%
- Single-cell transcriptome analysis of embryonic and adult endothelial cells allows to rank the hemogenic potential of post-natal endothelium 93%
Similar papers in this journal
- Wide and Deep Learning for Automatic Cell Type Identification 92%
- DeepNeuropePred: a robust and universal tool to predict cleavage sites from neuropeptide precursors by protein language model 91%
- iMDA-BN: Identification of miRNA-Disease Associations based on the Biological Network and Graph Embedding Algorithm 91%
Similar papers in this journal
- DIscBIO: a user-friendly pipeline for biomarker discovery in single-cell transcriptomics 92%
- Dissecting Response to Cancer Immunotherapy by Applying Bayesian Network Analysis to Flow Cytometry Data 92%
- Mast cells differentiated in synovial fluid and resident in osteophytes exalt the inflammatory pathology of osteoarthritis 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.