一个基于图形神经网络的方法来识别 lncRNA 亚细胞局部
Lina Zhang1, Xiaorui Lin2, Runtao Yang1
1School of Airspace Science and Engineering, Shandong University, Weihai 264209, China; Shandong Key Laboratory of Intelligent Electronic Packaging Testing and Application, Shandong University, Weihai 264209, China; Preparation and Application of Aerospace High-Performance Composite Materials, Future Industry Laboratory of Higher Education Institutions in Shandong Province, Shandong University, Weihai 264209, China.
Computational biology and chemistry
|February 28, 2026
概括
一个新的图形神经网络模型, lncGATSagePre,通过整合序列结构和语义,准确地识别长非编码RNA (lncRNA) 亚细胞定位,改进了现有的疾病研究方法.
科学领域:
- 生物信息学是一种生物信息学.
- 计算生物学 计算生物学
- 基因组学就是基因组学.
背景情况:
- 长非编码RNAs (lncRNAs) 的细胞下定位对于它们的生物功能和参与疾病机制至关重要.
- 目前用于 lncRNA 定位识别的方法面临着数据不平衡和复杂的序列结构的挑战.
研究的目的:
- 提出一种基于图形神经网络 (GNN) 的新方法,IncGATSagePre,用于增强IncRNA亚细胞定位的识别.
- 为了解决数据不平衡,并有效地在lncRNA本地化预测中建模复杂的序列关系.
主要方法:
- lncRNA序列被转换成图形结构使用de Bruijn图形与k-mer节点由Word2vec初始化.
- 为了减轻数据不平衡,采用了合成少数群体过量采样技术 (SMOTE).
- 一个双层的图表注意力 (GAT) 网络和图表样本和聚合 (GraphSAGE) 网络架构被用于自适应性特征聚合.
主要成果:
- 在一个独立的测试组中,IncGATSagePre模型在四个类别的分类任务 (细胞质,核,核糖体,外体) 上获得了0.549的加权F1得分.
- lncGATSagePre显著超过了现有的方法,如IncLocator 2.0,DeepLncLoc和GraphLncLoc.
- 废除研究证实了GAT在局部特征提取和GraphSAGE在大规模图形处理中的协同效益.
结论:
- 拟议的 lncGATSagePre 模型通过通过 GNN 集成序列结构和语义信息,为 lncRNA 亚细胞定位研究提供了一种新有效的方法.
- 这种方法具有很大的潜力,可以促进我们对lncRNA功能机制的理解,并识别疾病点,尽管需要进一步优化少数样本的分类.
相关概念视频
02:39lncRNA - Long Non-coding RNAs
10.0K
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...
10.0K
02:39lncRNA - Long Non-coding RNAs
3.8K
3.8K
01:46Nuclear Localization Signals and Import
8.0K
Proteins targeted to the nucleus carry short stretches of amino acid sequences called the nuclear localization signal or NLS. Classical nuclear localization signals are of two types: monopartite and bipartite NLS. Monopartite classical NLS (cNLS) consists of a single cluster of 4-8 amino acids. Bipartite cNLS consists of two clusters of 2-3 amino acids and a 9-12 residue long proline-rich linker bridging the two clusters. Signal clusters are rich in positively charged amino acids such as...
8.0K