Dreycey Albin

PhageScanner is a machine learning pipeline that annotates genomic and metagenomic data for bacteriophage features, including PVPs and toxins, using a BLAST-based classifier and LSTM model.

SeqScreen uses ensemble learning to accurately label pathogenic sequences with functional annotations, achieving high recall and precision for microbial pathogenesis.

This study analyzes over 7,000 SARS-CoV-2 datasets to reveal genomic diversity, showing iSNVs and small indels drive variation, and highlights implications for qRT-PCR and transmission tracking.