Embedding Is (Almost) All You Need: Retrieval-Augmented Inference for Generalizable Genomic Prediction Tasks

TL;DR

This paper demonstrates that embedding-based methods using pre-trained DNA language models can achieve competitive or superior performance to fine-tuning in genomic prediction tasks, with significantly improved efficiency and generalizability.

Contribution

It introduces a simple embedding-based pipeline as a more efficient and generalizable alternative to fine-tuning for genomic prediction tasks.

Findings

Embedding methods outperform fine-tuning in diverse data distributions.

Embedding pipelines reduce inference time by 10x to 20x.

Embedding approaches lower carbon emissions significantly.

Abstract

Large pre-trained DNA language models such as DNABERT-2, Nucleotide Transformer, and HyenaDNA have demonstrated strong performance on various genomic benchmarks. However, most applications rely on expensive fine-tuning, which works best when the training and test data share a similar distribution. In this work, we investigate whether task-specific fine-tuning is always necessary. We show that simple embedding-based pipelines that extract fixed representations from these models and feed them into lightweight classifiers can achieve competitive performance. In evaluation settings with different data distributions, embedding-based methods often outperform fine-tuning while reducing inference time by 10x to 20x. Our results suggest that embedding extraction is not only a strong baseline but also a more generalizable and efficient alternative to fine-tuning, especially for deployment in diverse or unseen genomic contexts. For example, in enhancer classification, HyenaDNA embeddings combined with zCurve achieve 0.68 accuracy (vs. 0.58 for fine-tuning), with an 88% reduction in inference time and over 8x lower carbon emissions (0.02 kg vs. 0.17 kg CO2). In non-TATA promoter classification, DNABERT-2 embeddings with zCurve or GC content reach 0.85 accuracy (vs. 0.89 with fine-tuning) with a 22x lower carbon footprint (0.02 kg vs. 0.44 kg CO2). These results show that embedding-based pipelines offer over 10x better carbon efficiency while maintaining strong predictive performance. The code is available here: https://github.com/NIRJHOR-DATTA/EMBEDDING-IS-ALMOST-ALL-YOU-NEED.