Pangenome-Informed Language Models for Synthetic Genome Sequence Generation
P.-S. Huang, François Charton, Jan-Niklas M. Schmelzle, Shelby S. Darnell, Pjotr Prins, Erik P. Garrison, G. Edward Suh · bioRxiv (Cold Spring Harbor Laboratory) · 2024
Language Models (LM) have been extensively utilized for learning DNA sequence patterns and generating synthetic sequences. In this paper, we present a novel approach for the generation of synthetic DNA data using pangenomes in combination with LM. We introduce three innovative pangenome-based tokenization schemes that enhance DNA sequence generation. Our experimental results demonstrate the superiority of pangenome-based tokenization over classical methods in generating high-utility synthetic DNA sequences, highlighting significant improvements in training efficiency and sequence quality.