Set-Aggregated Genome Embeddings for Microbiome Abundance Prediction
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Few-Shot LearningSimilar Papers 제목 키워드 기반
MetagenBERT: a Transformer-based Architecture using Foundational genomic Large Language Models for novel Metagenome Representation
Metagenomic disease prediction commonly relies on species abundance tables derived from large, incomplete reference catalogs, constraining resolution and discarding valuable information contained in DNA reads. To overcom…
Abundance-Aware Set Transformer for Microbiome Sample Embedding
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 ea…
Group-wise normalization in differential abundance analysis of microbiome samples
A key challenge in differential abundance analysis of microbial samples is that the counts for each sample are compositional, resulting in biased comparisons of the absolute abundance across study groups. Normalization-b…
Enrichment of gut microbiome strains for cultivation-free genome sequencing using droplet microfluidics
We report a droplet microfluidic method to target and sort individual cells directly from complex microbiome samples, and to prepare these cells for bulk whole genome sequencing without cultivation. We characterize this …
Microbiome abundance patterns as attractors and the implications for the inference of microbial interaction networks
Inferring microbial interaction networks from abundance patterns is an important approach to advance our understanding of microbial communities in general and the human microbiome in particular. Here we suggest discrimin…