HyenaCircle:一个基于HyenaDNA的预训练的大型语言模型,用于长时间的eccDNA预测
Fuyu Li1, Wenxiang Lu1, Yunfei Bai1
1State Key Laboratory of Digital Medical Engineering, School of Biological Science and Medical Engineering, Southeast University, Nanjing, China.
Frontiers in genetics
|July 11, 2025
概括
我们开发了HyenaCircle,这是一个使用大型语言模型和第三代测序的深度学习模型,用于预测长额外染色体圆形DNA (eccDNA). 这种新方法改善了检测这些与疾病相关的DNA结构.
科学领域:
- 基因组学就是基因组学.
- 生物信息学是一种生物信息学.
- 计算生物学 计算生物学
背景情况:
- 染色体外圆形DNA (eccDNA) 是来自染色体的圆形DNA分子,在各种疾病中起着重要作用.
- 检测长eccDNAs (1-5 kb) 由于其大小而具有挑战性,限制了功能研究.
- 现有的方法难以准确识别和预测长eccDNAs.
研究的目的:
- 介绍HyenaCircle,这是一个新的深度学习模型,用于预测长eccDNAs的形成.
- 利用第三代测序数据和大型语言模型来增强eccDNA检测.
- 克服目前识别大型eccDNA的方法的局限性.
主要方法:
- 通过将HyenaDNA模型与分类器头进行调整,利用纳米孔测序数据和侧面测序来开发HyenaCircle.
- 用数据增量,规范化和阶级不平衡权重来提高模型的稳定性.
- 该FLED算法识别了全长的eccDNAs,然后将其扩展并与负对照配对.
主要成果:
- 在AUROC中,HyenaCircle实现了0.715的验证AUROC和0.776的召回,在AUROC中表现比DNABERT优于5.9%.
- 废弃性研究证实了侧面序列对模型稳定性的重要性.
- 该模型与基线HyenaDNA架构相比,显示出更高的稳定性和融合性.
结论:
- HyenaCircle有效地整合了第三代测序和大型语言模型,用于准确的长eccDNA预测.
- DNA架构证明了长序基因组建的熟练性,为eccDNA识别提供了新的见解.
- 这项工作在预测和描述与疾病相关的eccDNA方面取得了重大进展.
相关概念视频
Euchromatin
7.6K
The extent of chromatin compaction can be studied by staining chromatin using specific DNA binding dyes. Under the microscope, the dense-compacted regions take up more dye, appearing darker, while the less-compact areas take up less dye and appear lighter. Based on the compaction level, chromatins are classified into two primary forms – euchromatin and heterochromatin.
Euchromatin is the less dense region of the chromatin and stains lighter. Euchromatin contains histone H3 extensively...
Euchromatin is the less dense region of the chromatin and stains lighter. Euchromatin contains histone H3 extensively...
7.6K
RACE - Rapid Amplification of cDNA Ends
6.6K
Rapid Amplification of cDNA Ends, or RACE, is one of the most effective methods to obtain a full-length cDNA from an mRNA sequence between a known internal region to the unknown sequence at the 5’ or 3’ end. The unknown region is cloned in the cDNA by a gene-specific primer that binds the known end, and a hybrid primer that attaches a predefined anchor sequence to the unknown end of the cDNA. The sequence in between is amplified by PCR with an anchor primer and a gene-specific...
6.6K
Histone Variants at the Centromere
4.5K
Histone variants are the histone proteins with structural and sequence variations. These variants may be regarded as “mutant” forms that replace their canonical histone counterparts in the nucleosomes. Specific post-translational modifications on the histone variants enable further chromatin complexity and regulate tissue-specific gene expression. The most common histone variants are from histone H2A, H2B, and linker histone H1 families. However, several variants of histone H3...
4.5K
lncRNA - Long Non-coding RNAs
9.0K
In humans, more than 80% of the genome gets transcribed. However, only around 2% of the genome codes for proteins. The remaining part produces non-coding RNAs which includes ribosomal RNAs, transfer RNAs, telomerase RNAs, and regulatory RNAs, among other types. A large number of regulatory non-coding RNAs have been classified into two groups depending upon their length – small non-coding RNAs, such as microRNA, which are less than 200 nucleotides in length, and long non-coding RNA...
9.0K
Nucleic Acid Structure
7.1K
The pentose sugar in DNA is deoxyribose, while in RNA the pentose sugar is ribose. The difference between the sugars is the presence of the hydroxyl group on the ribose's second carbon and a hydrogen on the deoxyribose's second carbon. The phosphate residue attaches to the hydroxyl group of the 5′ carbon of one sugar and the hydroxyl group of the 3′ carbon of the sugar of the next nucleotide, which forms a 5′ to 3′ phosphodiester linkage.
DNA Structure
DNA...
DNA Structure
DNA...
7.1K
The Nucleosome
2.5K
Human DNA is almost two meters long. However, it is compressed inside a tiny nucleus measuring only a few microns in diameter. To make this degree of compaction possible, DNA is organized into several sequential levels so that it can fit into such a tiny space. The most compact form of DNA is a chromosome that can be seen under a microscope in a dividing cell.
In a chromosome, DNA is wound twice around a protein complex called a histone octamer core, which consists of 8 histone proteins. This...
In a chromosome, DNA is wound twice around a protein complex called a histone octamer core, which consists of 8 histone proteins. This...
2.5K


