PathoLM: Identifying Pathogenicity from the DNA Sequence Through the Genome Foundation Model
Published in 19th Machine Learning in Computational Biology Meeting (MLCB 2024), 2024
PathoLM adapts pretrained DNA foundation models for pathogenicity identification from bacterial and viral sequences. It targets data-efficient detection of novel and divergent pathogens and evaluates zero-shot, few-shot, and species-classification settings.
Recommended citation: Dip, Sajib Acharjee. (2024). "PathoLM: Identifying Pathogenicity from the DNA Sequence Through the Genome Foundation Model." Proceedings of the 19th Machine Learning in Computational Biology Meeting, PMLR 261:153–161.
Download Paper