GMFGRN:基因调节网络推断的矩阵因子化和图形神经网络方法
Shuo Li1, Yan Liu2, Long-Chen Shen1
1School of Computer Science and Engineering, Nanjing University of Science and Technology, 200 Xiaolingwei, Nanjing, 210094, China.
一种新的方法,GMFGRN,使用图形神经网络 (GNN) 从单细胞RNA测序数据中准确推断基因调控网络 (GRNs). GMFGRN提高了准确性,并且在计算上高效,超过现有方法.
科学领域:
- 计算生物学是一种计算生物学.
- 基因组学就是基因组学.
- 生物信息学是一种生物信息学.
背景情况:
- 单细胞RNA测序 (scRNA-seq) 能够在单个细胞水平上进行基因表达分析.
- 从scRNA-seq数据中准确推断基因调节网络 (GRNs) 对于理解细胞机制至关重要.
- 现有的GRN推理方法经常与过渡性相互作用和高计算成本作斗争.
研究的目的:
- 从scRNA-seq数据开发一种新的,准确和高效的GRN推断方法.
- 解决现有方法的局限性,包括过渡性交互和计算资源需求.
主要方法:
- 介绍了GMFGRN,这是一种基于图形神经网络 (GNN) 的方法,用于GRN推断.
- 使用GNN进行矩阵因子化来学习基因嵌入.
- 利用学习嵌入来预测转录因子-基因相互作用.
主要成果:
- 在八个静态scRNA-seq数据集上,GMFGRN表现出优异的性能,比第二名的平均改善1.9% (AUROC) 和2.5% (AUPRC).
- 在四个时间序列数据集上,GMFGRN与亚军相比,实现了2.4% (AUROC) 和1.3% (AUPRC) 的最大增强.
- GMFGRN需要显著减少训练时间和记忆 (<10%的第二最佳方法).
结论:
- 在从scRNA-seq数据中推断GRN时,GMFGRN提供了实质性的进步.
- 该方法为现有方法提供了一个计算效率高,准确的替代方案.
- 对于推进系统生物学研究来说,GMFGRN具有显著的潜力.
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
08:51Author Spotlight: Integrated Multi-Omics Analysis for Unveiling Multicellular Immune Signatures in Clinical Heart Attack Cohorts
Published on: September 20, 2024
相关概念视频
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...
Regulation of Expression at Multiple Steps
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,...
Regulation of Expression Occurs at Multiple Steps
Transcription results in the generation of precursor (pre-mRNA) that consists of both exons and introns, which needs further processing before being translated to a...
Master Transcription Regulators
Co-activators and Co-repressors
