scPRAM精确地预测基于注意力机制的单细胞基因表达扰动反应
Qun Jiang1, Shengquan Chen2, Xiaoyang Chen1
1MOE Key Laboratory of Bioinformatics and Bioinformatics Division of BNRIST, Department of Automation, Tsinghua University, Beijing 100084, China.
Bioinformatics (Oxford, England)
|April 16, 2024
概括
我们介绍了scPRAM,这是一种用于预测单细胞基因表达对干扰反应的新方法. scPRAM准确地预测单个细胞中的基因表达变化,改进了现有的扰动分析方法.
科学领域:
- 单细胞基因组学 单细胞基因组学
- 计算生物学是一种计算生物学.
- 系统生物学 系统生物学
背景情况:
- 单细胞测序使得研究细胞对干扰的反应成为可能.
- 挑战包括样本采集成本和目前以平均响应为重点的方法的局限性.
研究的目的:
- 开发一种方法来预测单细胞水平的扰动反应.
- 解决现有方法在捕捉细胞特异性反应和反应分布方面的局限性.
主要方法:
- scPRAM利用了注意力机制,变化自动编码器和最佳传输.
- 它对干扰前后的细胞状态进行调整,以预测基因表达变化.
主要成果:
- scPRAM准确地预测了细胞类型,物种和个体的扰动反应.
- 它的性能优于药物治疗和细菌感染数据集的现有方法.
- 该方法在识别差异表达基因和捕捉响应异质性方面表现出色.
结论:
- scPRAM提供了一个强大的方法来预测单细胞基因表达对干扰的反应.
- 它增强了对细胞异质性和反应动态的理解.
- 该方法证明了对数据噪声和样本大小变化的稳定性.
相关概念视频
01:29Somatic to iPS Cell Reprogramming
2.2K
Reprogramming alters the gene expression in somatic cells, transforming them into induced pluripotent stem (iPS) cells over several generations. Scientists can reprogram cells by introducing genes for four transcription factors—Oct4, Sox2, Klf4, and c-Myc (OSKM) by viral or non-viral methods. These factors are also known as Yamanaka factors after Shinya Yamanaka, who first generated iPS cells using mouse skin cells. Yamanaka was awarded the Nobel Prize in Physiology or Medicine in 2012...
2.2K
01:22Diversity in Cell Signaling Responses
6.4K
The physiological function of a cell and cellular communication are outcomes of a range of extrinsic signals, intracellular signaling pathways, and cellular responses. No two cell types express the same repertoire of signaling components. Receptors are highly selective for their cognate ligands, but once activated, they can alter multiple cellular processes such as DNA transcription, protein synthesis, and metabolic activity.
Graded and Abrupt Responses
Some signaling systems generate...
Graded and Abrupt Responses
Some signaling systems generate...
6.4K