An Enhanced Few-Shot Learning Method for Genomic Variant Detection

Genomic variant detection is essential for cancer research and treatment, enabling precise diagnosis and personalized therapies. Considering the scarcity of labeled data, recent studies adopt few-shot learning for the task of genomic variant detection. However, the existing methods face significant challenges, including sensitivity to label distribution variability and difficulties in predicting long-span entities. To address two issues, we propose an enhanced few-shot learning method that integrates adaptive memory module, supervised contrastive learning, and orthogonal transfer module for genomic variant detection. Experimental results on the tmVar dataset demonstrate that our proposed model outperforms the existing methods and strong baselines significantly.