Evaluating DNA function understanding in genomic language models using evolutionarily implausible sequences

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Shiyu, Liu, Xuyin, Wang, Zitong Jerry
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912554107797504
author Jiang, Shiyu
Liu, Xuyin
Wang, Zitong Jerry
author_facet Jiang, Shiyu
Liu, Xuyin
Wang, Zitong Jerry
contents Genomic language models (gLMs) hold promise for generating novel, functional DNA sequences for synthetic biology. However, realizing this potential requires models to go beyond evolutionary plausibility and understand how DNA sequence encodes gene expression and regulation. We introduce a benchmark called Nullsettes, which assesses how well models can predict in silico loss-of-function (LOF) mutations, in synthetic expression cassettes with little evolutionary precedent. Testing 12 state-of-the-art gLMs, we find that most fail to consistently detect these strong LOF mutations. All models show a sharp drop in predictive accuracy as the likelihood assigned to the original (nonmutant) sequence decreases, suggesting that gLMs rely heavily on pattern-matching to their evolutionary prior rather than on any mechanistic understanding of gene expression. Our findings highlight fundamental limitations in how gLMs generalize to engineered, non-natural sequences, and underscore the need for benchmarks and modeling strategies that prioritize functional understanding.
format Preprint
id arxiv_https___arxiv_org_abs_2506_10271
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Evaluating DNA function understanding in genomic language models using evolutionarily implausible sequences
Jiang, Shiyu
Liu, Xuyin
Wang, Zitong Jerry
Quantitative Methods
Machine Learning
Genomics
Genomic language models (gLMs) hold promise for generating novel, functional DNA sequences for synthetic biology. However, realizing this potential requires models to go beyond evolutionary plausibility and understand how DNA sequence encodes gene expression and regulation. We introduce a benchmark called Nullsettes, which assesses how well models can predict in silico loss-of-function (LOF) mutations, in synthetic expression cassettes with little evolutionary precedent. Testing 12 state-of-the-art gLMs, we find that most fail to consistently detect these strong LOF mutations. All models show a sharp drop in predictive accuracy as the likelihood assigned to the original (nonmutant) sequence decreases, suggesting that gLMs rely heavily on pattern-matching to their evolutionary prior rather than on any mechanistic understanding of gene expression. Our findings highlight fundamental limitations in how gLMs generalize to engineered, non-natural sequences, and underscore the need for benchmarks and modeling strategies that prioritize functional understanding.
title Evaluating DNA function understanding in genomic language models using evolutionarily implausible sequences
topic Quantitative Methods
Machine Learning
Genomics
url https://arxiv.org/abs/2506.10271