Wisteria: A Unified Multi-Scale Feature Learning Framework for DNA Language Model
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917467048116224 |
|---|---|
| author | Wang, Weihua Li, Haoji Bao, Feilong Yang, Lei Gao, Guanglai |
| author_facet | Wang, Weihua Li, Haoji Bao, Feilong Yang, Lei Gao, Guanglai |
| contents | DNA language model aims to decipher the regulatory grammar and semantic of genomes by capturing long range dependencies in DNA sequences. Existing methods emphasize long range token interactions but often ignore the interplay between local motifs and global dependencies. In this paper, we propose Wisteria, a genomic language model that integrates multi scale feature learning within a unified framework for DNA sequence. Specifically, Wisteria augments the Mamba based architecture with gated dilated convolutions to capture local motifs and regulatory patterns, while gated multilayer perceptrons refine global dependencies. We further introduce a Fourier based attention mechanism to support frequency domain modeling, periodic extension and length generalization. Across four experimental settings with both short and long range dependencies, Wisteria demonstrates strong performance on downstream benchmarks against competitive DNA language model baselines. These results indicate that Wisteria effectively unifies local and global dependency modeling for multi scale genomic sequence analysis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_05913 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Wisteria: A Unified Multi-Scale Feature Learning Framework for DNA Language Model Wang, Weihua Li, Haoji Bao, Feilong Yang, Lei Gao, Guanglai Artificial Intelligence DNA language model aims to decipher the regulatory grammar and semantic of genomes by capturing long range dependencies in DNA sequences. Existing methods emphasize long range token interactions but often ignore the interplay between local motifs and global dependencies. In this paper, we propose Wisteria, a genomic language model that integrates multi scale feature learning within a unified framework for DNA sequence. Specifically, Wisteria augments the Mamba based architecture with gated dilated convolutions to capture local motifs and regulatory patterns, while gated multilayer perceptrons refine global dependencies. We further introduce a Fourier based attention mechanism to support frequency domain modeling, periodic extension and length generalization. Across four experimental settings with both short and long range dependencies, Wisteria demonstrates strong performance on downstream benchmarks against competitive DNA language model baselines. These results indicate that Wisteria effectively unifies local and global dependency modeling for multi scale genomic sequence analysis. |
| title | Wisteria: A Unified Multi-Scale Feature Learning Framework for DNA Language Model |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2605.05913 |