I'm a bioinformatics PhD candidate at the University of Georgia, defending in Fall/Winter 2026. My dissertation is on where new genes in Populus come from . Lately much of my attention has turned to genomic foundation models , and this fall I'm also consulting part-time with the Computational Biology Consulting Group at IOB.
One question I keep returning to: these models post strong benchmark numbers, but what are they actually reading? You can rewrite a gene so the protein and the codon composition are both untouched and only the order changes. Whatever survives that is the part worth arguing about, and it is smaller than the benchmarks suggest.
Five peer-reviewed papers, mostly in plant genomics. I am looking for computational biology and ML research roles beginning Fall 2026, particularly the evaluation and interpretation of models over biological sequence data. My resume is here , and I am always glad to hear from you by email .