HCLAMCMI:基于超图对比学习和注意力机制的circRNA-miRNA相互作用的预测
Lei Chen1, Ying Chen1, Bo Zhou2
1College of Information Engineering, Shanghai Maritime University, Shanghai 201306, China.
Journal of chemical information and modeling
|October 18, 2025
概括
HCLAMCMI使用新型超图学习准确预测循环RNA-microRNA相互作用 (CMIs). 这种计算模型推进了用于疾病研究和治疗开发的CMI识别.
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:
- 循环RNA (circRNA) -microRNA相互作用 (CMIs) 是基因表达,细胞增殖和瘤发生的关键调节者.
- 准确的CMI识别对于理解疾病的发病和开发诊断/治疗策略至关重要.
- 现有的CMI预测计算方法在特征表示上存在局限性.
研究的目的:
- 提出HCLAMCMI,这是一个先进的计算模型,用于预测circRNA-miRNA相互作用 (CMIs).
- 与现有方法相比,提高CMI识别的准确性和效率.
- 为了利用超图的学习和注意力机制来增强特征表示.
主要方法:
- 从circRNA,miRNA和疾病的邻近性,相似性和异质网络中提取特征.
- 构建了互补的超图,以捕捉高阶的关系信息.
- 采用超图形卷积网络,对比学习,以及用于特征生成和改进的道注意力机制.
主要成果:
- 在训练数据上,HCLAMCMI实现了曲线下的面积 (AUC) 和精度回忆曲线下的面积 (AUPR) 值超过0.98.
- 该模型在独立测试集上表现出强的性能,AUC和AUPR值约为0.97.
- HCLAMCMI 持续优于现有的 CMI 预测模型.
结论:
- 拟议的HCLAMCMI模型在计算CMI预测方面取得了重大进展.
- 将基于超图的学习与注意力机制相结合,可以提高特征表示和预测准确度.
- HCLAMCMI为CMI识别提供了一个强大的工具,支持疾病研究和治疗策略.
相关概念视频
01:22MicroRNAs
3.8K
MicroRNA (miRNA) are short, regulatory RNA transcribed from introns (non-coding regions of a gene) or intergenic regions (stretches of DNA present between genes). Several processing steps are required to form biologically active, mature miRNA. The initial transcript, called primary miRNA (pri-mRNA), base-pairs with itself, forming a stem-loop structure. Within the nucleus, an endonuclease enzyme, called Drosha, shortens the stem-loop structure into hairpin-shaped pre-miRNA. After the pre-miRNA...
3.8K
01:22MicroRNAs
23.9K
MicroRNA (miRNA) are short, regulatory RNA transcribed from introns—non-coding regions of a gene—or intergenic regions—stretches of DNA present between genes. Several processing steps are required to form biologically active, mature miRNA. The initial transcript, called primary miRNA (pri-mRNA), base-pairs with itself forming a stem-loop structure. Within the nucleus, an endonuclease enzyme, called Drosha, shortens the stem-loop structure into hairpin-shaped pre-miRNA. After...
23.9K