Robi Polikar A

This study evaluates uncertainty quantification methods to improve reliability of genomic language models under distribution shift in genomic and metagenomic tasks.

This study evaluates NBC++'s query performance across different parameters and shows its efficiency in training but longer query times, with challenges in classifying full diversity of life.

The paper introduces iMMseqs2 and iDiamond, incremental search tools for protein sequence databases, which maintain high accuracy while reducing computational resources.