HybriDNA: A Hybrid Transformer-Mamba2 Long-Range DNA Language Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ma, Mingqian, Liu, Guoqing, Cao, Chuan, Deng, Pan, Dao, Tri, Gu, Albert, Jin, Peiran, Yang, Zhao, Xia, Yingce, Luo, Renqian, Hu, Pipi, Wang, Zun, Chen, Yuan-Jyue, Liu, Haiguang, Qin, Tao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929718710763520
author Ma, Mingqian
Liu, Guoqing
Cao, Chuan
Deng, Pan
Dao, Tri
Gu, Albert
Jin, Peiran
Yang, Zhao
Xia, Yingce
Luo, Renqian
Hu, Pipi
Wang, Zun
Chen, Yuan-Jyue
Liu, Haiguang
Qin, Tao
author_facet Ma, Mingqian
Liu, Guoqing
Cao, Chuan
Deng, Pan
Dao, Tri
Gu, Albert
Jin, Peiran
Yang, Zhao
Xia, Yingce
Luo, Renqian
Hu, Pipi
Wang, Zun
Chen, Yuan-Jyue
Liu, Haiguang
Qin, Tao
contents Advances in natural language processing and large language models have sparked growing interest in modeling DNA, often referred to as the "language of life". However, DNA modeling poses unique challenges. First, it requires the ability to process ultra-long DNA sequences while preserving single-nucleotide resolution, as individual nucleotides play a critical role in DNA function. Second, success in this domain requires excelling at both generative and understanding tasks: generative tasks hold potential for therapeutic and industrial applications, while understanding tasks provide crucial insights into biological mechanisms and diseases. To address these challenges, we propose HybriDNA, a decoder-only DNA language model that incorporates a hybrid Transformer-Mamba2 architecture, seamlessly integrating the strengths of attention mechanisms with selective state-space models. This hybrid design enables HybriDNA to efficiently process DNA sequences up to 131kb in length with single-nucleotide resolution. HybriDNA achieves state-of-the-art performance across 33 DNA understanding datasets curated from the BEND, GUE, and LRB benchmarks, and demonstrates exceptional capability in generating synthetic cis-regulatory elements (CREs) with desired properties. Furthermore, we show that HybriDNA adheres to expected scaling laws, with performance improving consistently as the model scales from 300M to 3B and 7B parameters. These findings underscore HybriDNA's versatility and its potential to advance DNA research and applications, paving the way for innovations in understanding and engineering the "language of life".
format Preprint
id arxiv_https___arxiv_org_abs_2502_10807
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HybriDNA: A Hybrid Transformer-Mamba2 Long-Range DNA Language Model
Ma, Mingqian
Liu, Guoqing
Cao, Chuan
Deng, Pan
Dao, Tri
Gu, Albert
Jin, Peiran
Yang, Zhao
Xia, Yingce
Luo, Renqian
Hu, Pipi
Wang, Zun
Chen, Yuan-Jyue
Liu, Haiguang
Qin, Tao
Machine Learning
Artificial Intelligence
Genomics
Advances in natural language processing and large language models have sparked growing interest in modeling DNA, often referred to as the "language of life". However, DNA modeling poses unique challenges. First, it requires the ability to process ultra-long DNA sequences while preserving single-nucleotide resolution, as individual nucleotides play a critical role in DNA function. Second, success in this domain requires excelling at both generative and understanding tasks: generative tasks hold potential for therapeutic and industrial applications, while understanding tasks provide crucial insights into biological mechanisms and diseases. To address these challenges, we propose HybriDNA, a decoder-only DNA language model that incorporates a hybrid Transformer-Mamba2 architecture, seamlessly integrating the strengths of attention mechanisms with selective state-space models. This hybrid design enables HybriDNA to efficiently process DNA sequences up to 131kb in length with single-nucleotide resolution. HybriDNA achieves state-of-the-art performance across 33 DNA understanding datasets curated from the BEND, GUE, and LRB benchmarks, and demonstrates exceptional capability in generating synthetic cis-regulatory elements (CREs) with desired properties. Furthermore, we show that HybriDNA adheres to expected scaling laws, with performance improving consistently as the model scales from 300M to 3B and 7B parameters. These findings underscore HybriDNA's versatility and its potential to advance DNA research and applications, paving the way for innovations in understanding and engineering the "language of life".
title HybriDNA: A Hybrid Transformer-Mamba2 Long-Range DNA Language Model
topic Machine Learning
Artificial Intelligence
Genomics
url https://arxiv.org/abs/2502.10807