scGImpute:一种混合双层多头图的基于注意力的归算框架,用于单细胞测序数据集的零失效
Kasmika Borah1, Himanish Shekhar Das1
1Department of Computer Science and Information Technology, Cotton University, Hem Baruah Rd, Panbazar, Kamrup Metropolitan, Guwahati, Assam 781001, India.
Computational biology and chemistry
|December 23, 2025
概括
单细胞测序 (SCS) 数据通常包含技术噪声,包括零读数. 一个新的神经网络框架scGImpute有效地将这些数据归因于多种omics类型,改进了下游分析.
科学领域:
- 基因组学和生物信息学
- 计算生物学 计算生物学
- 分子生物学分子生物学
背景情况:
- 单细胞测序 (SCS) 对于在各种生物体中进行多组体分析至关重要.
- 在SCS方面的进步有助于在分子水平上诊断和治疗疾病.
- 技术噪声,特别是零计数 (dropout),严重阻碍了SCS数据的实用性.
研究的目的:
- 为了解决SCS数据中的高频零计数.
- 开发一个新的对OMICS SCS数据集的归算方法.
- 为了保持生物零,同时恢复技术零.
主要方法:
- 提出了一种混合的两层多头图基于注意力的神经网络框架 (scGImpute).
- 设计的scGImpute对于scRNA-seq,scATAC-seq和CITE-seq数据都是通用的.
- 使用根平均平方误差 (RMSE) 和平均绝对误差 (MAE) 评估性能.
主要成果:
- scGImpute在原始与归算的scRNA-seq数据中获得了最低的RMSE (0.0039) 和MAE (0.0032).
- 在地面真相与归算scRNA-seq数据 (RMSE:0.3301,MAE:0.2924) 上表现出卓越的性能.
- 在评估中表现优于现有的归算技术和其他拟议的方法.
结论:
- scGImpute有效地减少了SCS数据集中的技术噪声.
- 该方法增强了生物发现的下游分析.
- 提供了一个强大的解决方案,用于跨多个omics类型的零赋值.
相关概念视频
Improving Translational Accuracy
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
Improving Translational Accuracy
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...


