DeSide:一种统一的深度学习方法,用于瘤微环境的细胞解卷
Xin Xiong1, Yerong Liu2, Dandan Pu2
1Department of Physics, Hong Kong Baptist University, Hong Kong, China.
概括
深度学习方法DeSide使用大量RNA测序准确估计瘤中的细胞类型. 这种方法改善了对瘤微环境的理解,并有助于识别患者子组和治疗点.
科学领域:
- 在瘤学瘤学.
- 生物信息学是一种生物信息学.
- 计算生物学 计算生物学
背景情况:
- 大量RNA测序 (RNA-seq) 与流细胞计或单细胞RNA-seq (scRNA-seq) 相比,为分析瘤微环境提供了一种具有成本效益的方法.
- 瘤异质性对使用大量RNA-seq. 的精确细胞组成分析提出了重大挑战.
研究的目的:
- 开发一种基于深度学习的准确方法DeSide,用于从大量RNA-seq数据中解固体瘤中的细胞组成.
- 改善瘤微环境中16种不同的细胞类型和亚型的估计.
主要方法:
- DeSide集成了生物通路,并优先考虑非癌细胞类型评估,以解决癌细胞变异性基因表达特征.
- 使用独特的抽样和过技术在癌症基因组图谱 (TCGA) 批量RNA-seq数据上生成了一个高质量的培训套件,利用scRNA-seq引用.
- 深度学习模型是从6种癌症类型和22种癌症类型的185种癌症细胞系的数据中训练的.
主要成果:
- 德赛德在估计固体瘤中16种细胞类型和亚型的比例方面表现出极高的准确性.
- 该方法在确定19种TCGA癌症类型中的瘤纯度和非癌细胞比例方面优于现有的方法.
- 在多个外部数据集上验证了DeSide的有效性,显示了细胞组成的精确预测.
结论:
- DeSide 提供了一种强大而准确的解决方案,用于在固体瘤中使用大量RNA-seq.的细胞解.
- 该方法可以通过对组合细胞类型对进行分析来识别具有预后意义的患者群体.
- 这种方法可以更深入地了解瘤生物学,并根据细胞类型相互作用突出显示潜在的治疗点.
更多相关视频
相关概念视频
The Tumor Microenvironment
Every normal cell or tissue is embedded in a complex local environment called stroma, consisting of different cell types, a basal membrane, and blood vessels. As normal cells mutate and develop into cancer cells, their local environment also changes to allow cancer progression. The tumor microenvironment (TME) consists of a complex cellular matrix of stromal cells and the developing tumor. The cross-talk between cancer cells and surrounding stromal cells is critical to disrupt normal tissue...
The Tumor Microenvironment
Every normal cell or tissue is embedded in a complex local environment called stroma, consisting of different cell types, a basal membrane, and blood vessels. As normal cells mutate and develop into cancer cells, their local environment also changes to allow cancer progression. The tumor microenvironment (TME) consists of a complex cellular matrix of stromal cells and the developing tumor. The cross-talk between cancer cells and surrounding stromal cells is critical to disrupt normal tissue...


