预测非编码RNA与疾病关联的多任务学习模型:结合本地和全球背景
Xiaohan Li1, Guohua Wang1, Dan Li1
1College of Computer and Control Engineering, Northeast Forestry University, Harbin, 150040, China.
Methods (San Diego, Calif.)
|March 20, 2025
概括
这项研究介绍了MTL-NRDA,这是一种用于预测长非编码RNA (lncRNA) 和microRNA (miRNA) 与疾病相互作用的新型计算模型. 它通过整合多个数据源和先进的网络分析来提高准确性,以便更好地预测疾病关联.
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) 和微RNAs (miRNAs) 是关键的非编码RNAs,涉及各种疾病.
- 当前的计算方法经常单独分析lncRNA-miRNA-疾病关联,导致预测能力和概括性有限.
- 在ncRNA-疾病关系中,高阶拓信息经常被现有的方法忽视.
研究的目的:
- 开发一个集成的计算模型,同时预测lncRNA与疾病的关联,miRNA与疾病的关联以及lncRNA与miRNA的相互作用.
- 解决孤立任务分析的局限性,并将高阶拓信息纳入ncRNA-疾病关系预测中.
- 提高预测非编码RNA (ncRNA) 参与疾病的准确性和通用性.
主要方法:
- 提出了非编码RNA-疾病协会 (MTL-NRDA) 模型的多任务学习,这是一个多任务学习框架.
- 综合多源信息,使用 lncRNAs,miRNAs 和疾病关联/相似性网络的异质网络.
- 采用高阶图形卷积网络 (HOGCN) 来进行本地特征聚合,以及用于全球特征提取的变压器编码器来优化节点嵌入.
主要成果:
- 与现有模型相比,MTL-NRDA在两个独立数据集上表现出更高的性能.
- 废弃性研究验证了单个模型组件和多任务学习策略的有效性.
- 关于乳腺癌和肝癌的案例研究强调了该模型在确定与疾病相关的ncRNA关联中的实际适用性.
结论:
- 通过利用多任务学习框架和整合多种数据源,MTL-NRDA模型有效地预测lncRNA疾病和miRNA疾病的相关性.
- 该模型捕获本地和全球拓特征的能力提高了ncRNA-疾病关系的预测.
- MTL-NRDA提供了一个有前途的计算工具,用于推进ncRNA相关疾病的诊断,预防和治疗策略.
更多相关视频
相关概念视频
02:39lncRNA - Long Non-coding RNAs
8.4K
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...
8.4K
01:11Genome-wide Association Studies-GWAS
12.3K
Genome-wide association studies or GWAS are used to identify whether common SNPs are associated with certain diseases. Suppose specific SNPs are more frequently observed in individuals with a particular disease than those without the disease. In that case, those SNPs are said to be associated with the disease. Chi-square analysis is performed to check the probability of the allele likely to be associated with the disease.
GWAS does not require the identification of the target gene involved in...
GWAS does not require the identification of the target gene involved in...
12.3K