Mohammad S. Refahi

Nevermore improves lead optimization by balancing binding affinity and developability constraints using a database-grounded framework with interpretable molecular edits.

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

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

Scorpio improves DNA sequence embeddings using contrastive learning, enhancing performance in taxonomic classification, AMR gene detection, and promoter identification across diverse datasets.

This study improves protein fold recognition accuracy by integrating evolutionary features with support vector machines, achieving over 6% accuracy improvement on benchmark datasets.