Mahdi Baghbanzadeh

This study develops seqLens, a genomic language model family, and evaluates its performance on phenotypic predictions using diverse pretraining datasets and tokenization strategies.

The paper curates 16S rRNA databases to improve taxonomic accuracy and computational efficiency in microbial profiling by cleaning sequences and reducing redundancy.

The paper introduces a database of opsin genotypes and λmax phenotypes and demonstrates regression-based ML models can predict λmax and identify functionally critical sites.