Microbiome functions are encoded within the genes of the community-wide metagenome. A natural question is whether properties of a microbial community can be predicted just from knowing the raw DNA sequences of its members. In this work, we employ set-aggregated genome embeddings (SAGE) to predict community-level abundance profiles, exploiting the few-shot learning capabilities of genomic language models (GLMs). We benchmark this approach to show improved generalization on novel genomes compared to classical bioinformatics approaches. Model ablation shows that community-level latent representations directly result in improved performance. Lastly, we demonstrate the benefits of intermediate transformations between latent representations and demonstrate the differences between GLM embedding choices.
@article{arxiv.2605.12286,
title = {Set-Aggregated Genome Embeddings for Microbiome Abundance Prediction},
author = {Younhun Kim and Georg K. Gerber and Travis E. Gibson},
journal= {arXiv preprint arXiv:2605.12286},
year = {2026}
}