eccDNAMamba: A Pre-Trained Model for Ultra-Long eccDNA Sequence Analysis

TL;DR

eccDNAMamba is a novel pre-trained model designed for efficient, full-length analysis of circular extrachromosomal DNA sequences, enabling better understanding of their regulatory roles in cancer.

Contribution

It introduces the first bidirectional state-space encoder for circular DNA, supporting sequences up to 200 Kbp with linear-time complexity.

Findings

Achieves strong classification performance on real datasets

Scales to sequences up to 200 Kbp in length

Provides a robust framework for circular genome modeling

Abstract

Extrachromosomal circular DNA (eccDNA) plays key regulatory roles and contributes to oncogene overexpression in cancer through high-copy amplification and long-range interactions. Despite advances in modeling, no pre-trained models currently support full-length circular eccDNA for downstream analysis. Existing genomic models are either limited to single-nucleotide resolution or hindered by the inefficiency of the quadratic attention mechanism. Here, we introduce eccDNAMamba, the first bidirectional state-space encoder tailored for circular DNA sequences. It combines forward and reverse passes for full-context representation learning with linear-time complexity, and preserves circular structure through a novel augmentation strategy. Tested on two real-world datasets, eccDNAMamba achieves strong classification performance and scales to sequences up to 200 Kbp, offering a robust and efficient framework for modeling circular genomes. Our codes are available at https://github.com/zzq1zh/GenAI-Lab.