Models

GPN comprises four genomic language model families with different biological inputs and modeling objectives.

Model	Paper	Notes
GPN	Benegas et al. 2023	Requires unaligned genomes
GPN-MSA	Benegas et al. 2025	Requires aligned genomes for training and inference; deprecated in favor of GPN-Star
PhyloGPN	Albors et al. 2025	Uses an alignment during training, but does not require it for inference or fine-tuning
GPN-Star	Ye et al. 2025	Requires aligned genomes for training and inference

Maintained support

GPN and GPN-Star support training on prepared data and inference. GPN-MSA is deprecated and supports inference only. PhyloGPN and the sorghum gene-expression model support inference only. Dataset and whole-genome-alignment construction are outside the maintained package.