Fundamental limitations of genomic language models for realistic sequence generation.

ABSTRACT: Large language models (LLMs) have shown remarkable success in natural language processing, prompting interest in their application to genomic sequence analysis. Genomic Language Models based on similar architectures offer a promising avenue for synthetic genome generation and characterization. However, their effectiveness for biological sequence modeling remains poorly characterized. We present a comprehensive evaluation of a state-of-the-art genomic Language Model (gLM), Evo 2, on multiple genomic reconstruction tasks. We tested Evo 2 on diverse prokaryotic, eukaryotic and viral genomes and assessed performance across key biological features and organizational patterns. Our results reveal systematic failures in gLM-based genomic reconstruction. While the synthetic sequences captured local

SUBMITTER: Tzanakakis A 

PROVIDER: S-EPMC12871140 | biostudies-literature | 2026 Jan

REPOSITORIES: biostudies-literature