Improving genomic language model reliability under distribution shift

Read full text Summarise with VIRAT
Authors: Gavin Hearne, Mohammad S. Refahi, Robi Polikar A, GAIL L. ROSEN
Cited by: 0
References: 42

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Abstract Transformer-based Genomic Language Models (GLMs) have achieved strong performance across diverse genomic prediction tasks. However, their tendency toward overconfident predictions—particularly on noisy or unfamiliar data—limits reliability. In genomics, where unknown species and novel variants are common, developing models robust to distribution shift is crucial for dependable predictions. Here, we analyze the impact of several common and novel uncertainty quantification (UQ) methods in the context of GLMs, evaluating their performance across diverse downstream genomic and metagenomic prediction tasks. Comparing model behavior on both in-distribution (ID) and out-of-distribution (OOD) data, we show that temperature scaling and epistemic neural networks are capable of improving classification reliability across multiple GLM architectures and domains. The software is available at: https://github.com/EESI/glm-epinet-pyt

Fields of Study & Subjects

Genomics and Phylogenetic Studies Machine Learning in Bioinformatics Adversarial Robustness in Machine Learning

Publication details

Journal / source
bioRxiv (Cold Spring Harbor Laboratory)
Publication date
20 March 2026
Language
EN
Document type
Preprint