PathoBERT: A Hybrid Attention-Based Genomic Language Model for Read-Level Bacterial Pathogenicity Prediction
Salem A. El-aarag, Mario Flores, Mohamed E. Hasan, Alaa E. Hemeida, Mahmoud ElHefnawi
PathoBERT improves bacterial pathogenicity prediction from short reads by combining a DNABERT encoder with attention-based feature extraction, achieving better performance than existing methods.
bioRxiv · Sep 29, 2026 · PreprintBioinformatics