GP-HTNLoc: 一个基于头尾网络模型的图形原型,用于对ncRNAs的多标签亚细胞局部化预测
Shuangkai Han1,2, Lin Liu1,2
1School of Information, Yunnan Normal University, Kunming, China.
Computational and structural biotechnology journal
|May 20, 2024
概括
GP-HTNLoc准确地预测了非编码RNA (ncRNA) 的亚细胞定位,即使它们位于多个位置. 这种新型模型解决了数据挑战,提高了各种ncRNA类型的预测准确性.
科学领域:
- 计算生物学是一种计算生物学.
- 分子生物学分子生物学
- 生物信息学是一种生物信息学.
背景情况:
- 了解非编码RNA (ncRNA) 亚细胞局部化对于破译它们的细胞功能和调节作用至关重要.
- 现有的计算模型往往专注于单标签预测,未能解释许多ncRNAs的多分区本地化.
- 当前的多标签预测方法与 ncRNA 数据集固有的稀疏训练数据和类不平衡作斗争.
研究的目的:
- 开发一种新的计算模型,GP-HTNLoc,用于准确的多标签ncRNAs亚细胞局部化预测.
- 克服现有模型的局限性,特别是关于ncRNA本地化预测中的数据稀缺性和类失衡.
- 为研究 ncRNA 功能和机制的研究人员提供一个强大的工具.
主要方法:
- 提出了GP-HTNLoc,这是一个新的ncRNA亚细胞局部化的多标签预测模型.
- 实施了针对头部和尾部位置标签的单独培训策略,以减轻阶级不平衡.
- 引入了一个图形原型模块,以提高小样本,多标签预测场景的性能.
主要成果:
- 通过十倍交叉验证,GP-HTNLoc证明了对基准数据集的竞争性预测性能.
- 在一个独立的数据集上,GP-HTNLoc显著超过了人类lncRNA,snoRNA和miRNA定位的现有模型.
- 获得的平均精度提高为31.5% (lncRNA),14.2% (snoRNA) 和5.6% (miRNA),分别达到0.685,0.632和0.704.
结论:
- GP-HTNLoc有效地解决了多标签ncRNA本地化预测的挑战,包括数据稀缺性和类不平衡.
- 该模型与预测ncRNA亚细胞局部化的现有方法相比,提供了更好的准确性和稳定性.
- 为GP-HTNLoc提供了一个可访问的在线服务器,以促进其在生物研究中的使用.
相关概念视频
01:46Nuclear Localization Signals and Import
5.7K
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...
5.7K
02:22Regulated mRNA Transport
6.3K
In eukaryotes, transcription and translation are compartmentalized; an mRNA is first synthesized in the nucleus and then selectively transported to the cytoplasm for protein synthesis. Before transport, a pre-mRNA undergoes several steps of post-transcriptional modifications including splicing, 5' capping, and the addition of a poly-adenine tail. Various proteins bind to the pre-mRNA during these modifications. The mRNA transport takes place with the help of multiple proteins playing...
6.3K
01:34Nuclear Protein Sorting
4.6K
Nuclear protein sorting is the selective trafficking of histones, polymerases, gene regulatory proteins into the nucleus and exporting RNAs and ribosomes to the cytosol. It is a tightly controlled process that regulates gene expression within a cell.
Proteins targeted to the nucleus carry nuclear localization signals or NLS recognized by import receptors in the cytosol. Similarly, proteins with nuclear export signals are recognized by export receptors. Import and export receptors are...
Proteins targeted to the nucleus carry nuclear localization signals or NLS recognized by import receptors in the cytosol. Similarly, proteins with nuclear export signals are recognized by export receptors. Import and export receptors are...
4.6K