GCLink:基因调节网络推断的图形对比链接预测框架
Weiming Yu1, Zerun Lin1, Miaofang Lan1
1Guangdong Provincial Key Laboratory of Intelligent Information Processing and Shenzhen Key Laboratory of Media Security, College of Electronics and Information Engineering, Shenzhen University, Shenzhen 518060, China.
我们开发了GCLink,这是一种新的图形对比学习模型,用于从单细胞RNA测序数据中推断基因调节网络 (GRNs). GCLink 提高了预测准确度,特别是在已知相互作用有限的情况下,推进了系统生物学研究.
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) 对于理解细胞过程至关重要.
- 单细胞RNA测序 (scRNA-seq) 允许在单细胞分辨率下推断GRN.
- 现有的方法经常预测双向相互作用,限制了全面的网络分析和概括.
研究的目的:
- 提出一种新型模型,GCLink,用于从scRNA-seq数据中推断基因调节相互作用.
- 通过利用图形对比学习来增强对潜在的基因调节相互作用的预测.
- 提高GRN推理的概括性能,特别是在数据有限的场景中.
主要方法:
- 开发了一个图形对比链接预测 (GCLink) 模型.
- 利用图形对比学习策略来汇总基因特征和邻里信息.
- 在真实scRNA-seq数据集上训练和评估模型,包括预训练和微调方法.
主要成果:
- 从scRNA-seq数据中,GCLink有效地推断出潜在的基因调节相互作用.
- 该模型在真实数据集上展示了与最先进的方法相比更高的性能.
- 即使在已知相互作用有限的情况下,GCLink在GRN推理中也表现出强的表现,突出显示了其概括能力.
结论:
- GCLink提供了一种有效的方法,可以从scRNA-seq数据中推断基因调节网络.
- 图形对比学习策略提高了网络推断的准确性和稳定性.
- 该模型在有限的先前知识下表现良好的能力使其对各种生物应用具有价值.
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
09:58Mapping the Structure-Function Relationships of Disordered Oncogenic Transcription Factors Using Transcriptomic Analysis
Published on: June 27, 2020
相关概念视频
Covalently Linked Protein Regulators
Protein Networks
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
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...
Ligand Binding and Linkage
Cooperative Binding of Transcription Regulators
Cis-regulatory Sequences
