Machine learning-driven approach combining single-cell RNA sequencing with virtual screening to identify siRNA candidates targeting intestinal fibrosis. Targets Crohn's disease by analyzing cellular mechanisms in the SAMP1/YitFc murine model, enabling faster and more cost-effective discovery of antifibrotic therapies compared to traditional high-throughput screening methods.
This research program leverages single-cell RNA sequencing (scRNA-seq) combined with machine learning and virtual screening to identify novel siRNA candidates for anti-fibrotic therapies, with a primary focus on Crohn's disease. By analyzing the cellular heterogeneity of intestinal fibrosis in the SAMP1/YitFc murine model, the project aims to uncover key mRNA targets involved in fibrosis genesis. The integration of structure-based and ligand-based virtual screening enables efficient sampling of chemical diversity while significantly reducing the time and costs associated with traditional wet high-throughput screening methods.
The approach addresses a critical unmet need in Crohn's disease treatment, where intestinal fibrosis remains a major complication lacking effective therapeutic options. By focusing on tissue-specific endpoints and clinically feasible siRNA applications, this research seeks to translate molecular insights into actionable therapeutic candidates.
Key methodological components:
The project is in an active research phase with a planned one-year timeline. The validation procedures draw upon established single-cell sequencing methodologies that have demonstrated utility in understanding Crohn's disease heterogeneity, including prior studies showing increased fibroblast heterogeneity in stricturing disease. The SAMP1/YitFc mouse model provides a well-characterized platform for studying spontaneous ileocolitis and fibrosis progression. The research team is seeking partnership support for scRNA-seq experiments and virtual screening analysis to advance candidate identification toward therapeutic development.