SIGRN:推断基因调控网络与软内观变异自编码器
Rongyuan Li1,2,3, Jingli Wu1,2,3, Gaoshi Li1,2,3
1Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin 541004, China.
这项研究介绍了SIGRN,这是一个新的计算模型,用于从单细胞RNA测序数据中推断基因调节网络 (GRNs). 与现有方法相比,SIGRN提高了数据质量和推断准确度.
科学领域:
- 计算生物学 计算生物学
- 基因组学就是基因组学.
- 系统生物学 系统生物学
背景情况:
- 基因调节网络 (GRNs) 对于理解生物过程至关重要.
- 从单细胞RNA测序 (scRNA-seq) 数据中推断GRNs在计算上具有挑战性.
- 像变量自编码器 (VAE) 这样的现有方法在数据质量方面存在局限性.
研究的目的:
- 开发一种改进的计算方法,从scRNA-seq数据中推断GRNs.
- 提高GRN推断和scRNA-seq数据生成的准确性和质量.
- 解决基于VAE的方法的数据质量缺陷.
主要方法:
- 拟议的SIGRN (软内观基因调节网络) 模型.
- 在VAE框架内引入了一个对抗机制.
- 采用"软"的内省对抗模式,以有效地优化模型参数.
主要成果:
- 与基准数据集上的九种主要方法相比,SIGRN显示出更高的推断准确度.
- 在细胞表示和scRNA-seq数据生成方面取得了更好的性能.
- 实验验证证了该方法的有效性.
结论:
- SIGRN为准确的GRN推断提供了一个有前途的方法.
- 该方法显示了改善scRNA-seq数据生成的潜力.
- SIGRN 推进了系统生物学研究的计算工具.
更多相关视频
10:44Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline
Published on: December 7, 2021
09:23Quantification of Information Encoded by Gene Expression Levels During Lifespan Modulation Under Broad-range Dietary Restriction in C. elegans
Published on: August 16, 2017
相关概念视频
Regulation of Expression at Multiple Steps
Variability: Analysis
The range is a simple measure of variability, indicating the difference between the highest and...
Multi-input and Multi-variable systems
In the absence...
Regulation of Expression Occurs at Multiple Steps
Constitutive and Regulated Gene Expression
Combinatorial Gene Control
The expression of more than 30,000 genes is controlled by approximately 2000-3000 transcription factors. This is possible because a single transcription factor can recognize more than one regulatory sequence. The specificity in gene...
