<ul><li>Recent breakthroughs in single-cell technology have led to the need for efficient annotation of long-tailed single-cell data pertaining to disease conditions.</li><li>To address this challenge, Celler, a generative pre-training model, has been introduced that incorporates the Gaussian Inflation (GInf) Loss function and Hard Data Mining (HDM) strategy.</li><li>The GInf Loss function dynamically adjusts sample weights, improving the model's ability to learn from rare categories and reducing the risk of overfitting for common categories.</li><li>The HDM strategy targets difficult-to-learn minority data samples, significantly improving the model's predictive accuracy.</li></ul>

Celler:A Genomic Language Model for Long-Tailed Single-Cell Annotation

Discover more