基于癌症亚型识别的综合自我监督的深层次子空间融合
Min Li1,2, Mingzhuang Zhang1,2, Mingzh Lou1,2
1School of Information Engineering, Jiangxi University of Water Resources and Electric Power, No. 289 Tianxiang Road, Nanchang Jiangxi, P. R. China.
这项研究介绍了基于集成自我监督 (DSFIS) 的深度子空间融合,这是使用多omics数据识别癌症亚型的新框架. 通过发现更多的潜在信息来改善患者分层和治疗,DSFIS改进了现有的方法.
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:
- 高通量技术产生复杂的多学科数据,对癌症研究至关重要.
- 整合多学科数据存在挑战,原因是数据异质性和噪音.
- 现有的集成方法通常依赖于无监督学习,因为标记数据有限.
研究的目的:
- 引入一个新的框架,基于综合自我监督 (DSFIS) 的深次空间融合,用于癌症亚型识别.
- 加强从多omics数据中提取有价值的信息,以改善患者分层.
- 解决多omics数据集成中无监督方法的局限性.
主要方法:
- 开发了DSFIS,一个使用自动编码器和自我表示层的框架.
- 集成的自我监督指导自动编码器在生成代表性样本子空间结构.
- 将DSFIS与八种最先进的多omics数据集成方法进行了比较.
主要成果:
- 基于多个omics数据,DSFIS有效地识别了癌症亚型.
- 与其他算法相比,该框架在生存预后分析方面取得了卓越的表现.
- DSFIS展示了增强的临床相关性分析,表明其对个性化医学的潜力.
结论:
- DSFIS提供了一个强大的方法,用于整合多omics数据用于癌症亚型识别.
- 在DSFIS中的自我监督机制有效地捕捉了患者的相似性和差异性.
- 通过多omics数据分析,DSFIS显示了促进癌症研究和临床应用的巨大潜力.
更多相关视频
06:45Dissecting Multi-protein Signaling Complexes by Bimolecular Complementation Affinity Purification BiCAP
Published on: June 15, 2018
08:31Biosensor-based High Throughput Biopanning and Bioinformatics Analysis Strategy for the Global Validation of Drug-protein Interactions
Published on: December 1, 2020
相关概念视频
Light Acquisition
Detection of Black Holes
Their closest cousins are neutron stars, which are composed almost entirely of neutrons packed against each other, making them extremely dense. A neutron star has the same mass as the Sun but its diameter is only a few kilometers. Therefore, the escape velocity from their surface is close to the speed of light.
Not until the 1960s, when the first neutron...
Tagging and Fusion Proteins
Gas Chromatography: Types of Detectors-I
TCD is the earliest and most widely used detector that operates by measuring the changes in the thermal conductivity of the carrier gas. When a sample compound enters the detector,...
Gas Chromatography: Types of Detectors-II
High-Performance Liquid Chromatography: Types of Detectors
