Nicole L. Pershing

The paper introduces LAMBDA, a benchmark to evaluate genomic language models' ability to detect prophage sequences across four complexity levels.

This study evaluates the impact of tokenizer selection on genomic language models, finding that character tokenization outperforms sub-word methods for nucleotide-level tasks, but byte-pair encoding performs better for SARS-CoV-2 variant classification.

The paper identifies a prophage-encoded sRNA, svsR, that reduces lytic phage infection in AIEC by repressing maltodextrin transport genes, thereby limiting phage receptor expression.