Low-input deep learning platform for citrullinated peptide identification, autoantigen discovery and rheumatoid arthritis treatment stratification - PubMed
4 hours ago
- #deep learning
- #autoantigen discovery
- #rheumatoid arthritis
- Development of Iseq-Cit, a low-input deep learning platform for citrullinated peptide identification.
- Iseq-Cit enables global citrullinome profiling with less than 1% of the sample input needed for conventional methods.
- Plasma citrullinome profiles correlate with rheumatoid arthritis (RA) development and severity.
- Integration of clinical indicators and citrullination data achieves high accuracy in predicting RA treatment response.
- A bidirectional gated recurrent unit model predicts RA-sera reactivity of citrullinated peptides with 84.2% accuracy.
- Identification of 19 promising candidates for RA diagnosis through external validation.