Hierarchy-aligned Language Modeling in Hyperbolic Space for mRNA Coding Sequences

TMLR Paper9132 Authors

Abstract: Language models are increasingly applied to biological sequences such as proteins and mRNA, yet their default Euclidean geometry may mismatch the hierarchical structures inherent to biological data. While hyperbolic geometry provides a better alternative for accommodating hierarchical data, it has yet to find a way into language modeling for mRNA sequences. In this work, we introduce HyperHELM, a novel framework that implements masked language model pre-training in hyperbolic space for coding (CDS) regions of mRNA sequences. Using a hybrid design with hyperbolic layers atop a Euclidean backbone, HyperHELM aligns learned representations with the biological hierarchy defined by the relationship between mRNA and amino acids. Across multiple multi-species datasets, it outperforms Euclidean baselines on 9 out of 10 tasks involving property prediction, with 10\% improvement on average, and excels in out-of-distribution generalization to long and low-GC content sequences; for antibody region annotation, it surpasses hierarchy-aware Euclidean models by 3\% in annotation accuracy. Our results highlight hyperbolic geometry as an effective inductive bias for hierarchical language modeling of the CDS regions of mRNA sequences.

Submission Type: Regular submission (no more than 12 pages of main content)

Assigned Action Editor: ~Lei_Wang13

Submission Number: 9132