English

Abundance-Aware Set Transformer for Microbiome Sample Embedding

Machine Learning 2025-08-18 v1

Abstract

Microbiome sample representation to input into LLMs is essential for downstream tasks such as phenotype prediction and environmental classification. While prior studies have explored embedding-based representations of each microbiome sample, most rely on simple averaging over sequence embeddings, often overlooking the biological importance of taxa abundance. In this work, we propose an abundance-aware variant of the Set Transformer to construct fixed-size sample-level embeddings by weighting sequence embeddings according to their relative abundance. Without modifying the model architecture, we replicate embedding vectors proportional to their abundance and apply self-attention-based aggregation. Our method outperforms average pooling and unweighted Set Transformers on real-world microbiome classification tasks, achieving perfect performance in some cases. These results demonstrate the utility of abundance-aware aggregation for robust and biologically informed microbiome representation. To the best of our knowledge, this is one of the first approaches to integrate sequence-level abundance into Transformer-based sample embeddings.

Keywords

Cite

@article{arxiv.2508.11075,
  title  = {Abundance-Aware Set Transformer for Microbiome Sample Embedding},
  author = {Hyunwoo Yoo and Gail Rosen},
  journal= {arXiv preprint arXiv:2508.11075},
  year   = {2025}
}
R2 v1 2026-07-01T04:50:47.366Z