PatchDNA: A Flexible and Biologically-Informed Alternative to Tokenization for DNA
Alice Del Vecchio, Chantriolnt-Andreas Kapourani, Abdullah M Athar, Agnieszka Dobrowolska, Andrew Anighoro, Benjamin Tenmann, Lindsay Edwards, Cristian Regep
PatchDNA introduces a flexible, biologically-informed patching method for DNA sequences that outperforms tokenization in DNA benchmarks with smaller models.
bioRxiv · Nov 28, 2025 · PreprintGenomics