人类miRNA-疾病协会预测通过残余图形SAGE与非线性自适应特征融合和三重对比学习
Jianan Sui1, Weirong Cui1, Xiaoxiao Zhang2
1Centre in Artificial Intelligence Driven Drug Discovery, Faculty of Applied Sciences, Macao Polytechnic University, Macau.
Journal of molecular biology
|July 30, 2025
概括
研究人员开发了RGFMDA,这是一种用于预测微RNA (miRNA) -疾病关联的新计算工具. 这种方法提高了确定miRNA与疾病之间的联系的准确性,有助于治疗的发展.
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:
- 微RNAs (miRNAs) 是细胞过程的关键调节者.
- 失调的miRNA活性与许多人类疾病有关.
- 准确预测miRNA与疾病的关联对于疾病的理解和治疗至关重要.
研究的目的:
- 引入RGFMDA,这是预测miRNA疾病关联的先进框架.
- 提高该领域计算方法的准确性和可靠性.
主要方法:
- 利用剩余图谱采样和聚合网络来增强信息本地化.
- 包含非线性特征集成和用于协同特征分析的全球上下文模块.
- 采用三重对比学习来区分关联和非关联的miRNA-疾病对.
主要成果:
- 在HMDD v2.0数据集上获得了0.9524的AUC,优于现有方法.
- 在HMDD v3.2数据集上获得了0.9604的AUC,超过了最先进的性能.
- 通过对肺癌,食道癌,乳腺癌和结肠直肠癌的案例研究验证了疗效.
结论:
- RGFMDA是一个强大的计算工具,用于发现新的miRNA-疾病关联.
- 该框架促进生物研究,加速治疗开发.
- RGFMDA提高了微RNA与人类疾病之间的联系的预测.
相关概念视频
01:22MicroRNAs
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 ends...
01:22MicroRNAs
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...