AntigenLM: Structure-Aware DNA Language Modeling for Influenza
This work addresses the challenge of predicting influenza antigen evolution for public health and vaccine development, representing a novel method for a known bottleneck rather than an incremental improvement.
The paper tackled the problem of DNA language models lagging behind task-specific methods by introducing AntigenLM, a structure-aware generative model pretrained on influenza genomes with intact functional units, which accurately forecasts future antigenic variants across regions and subtypes, outperforming phylogenetic and evolution-based models, and achieves near-perfect subtype classification.
Language models have advanced sequence analysis, yet DNA foundation models often lag behind task-specific methods for unclear reasons. We present AntigenLM, a generative DNA language model pretrained on influenza genomes with intact, aligned functional units. This structure-aware pretraining enables AntigenLM to capture evolutionary constraints and generalize across tasks. Fine-tuned on time-series hemagglutinin (HA) and neuraminidase (NA) sequences, AntigenLM accurately forecasts future antigenic variants across regions and subtypes, including those unseen during training, outperforming phylogenetic and evolution-based models. It also achieves near-perfect subtype classification. Ablation studies show that disrupting genomic structure through fragmentation or shuffling severely degrades performance, revealing the importance of preserving functional-unit integrity in DNA language modeling. AntigenLM thus provides both a powerful framework for antigen evolution prediction and a general principle for building biologically grounded DNA foundation models.