持续学习中的基于信心的批次排序:单细胞RNA测序数据的课程学习方法
IEEE transactions on computational biology and bioinformatics
|January 16, 2026
概括
为像单细胞RNA测序 (scRNA-seq) 这样的大型数据集优化机器学习是具有挑战性的. 本研究介绍了一种基于信任的批量订单策略,用于持续学习 (CL),提高模型性能和对各种scRNA-seq数据的稳定性.
科学领域:
- 计算生物学 计算生物学
- 机器学习 机器学习
- 生物信息学是一种生物信息学.
背景情况:
- 在大型数据集上训练机器学习模型,特别是单细胞RNA测序 (scRNA-seq) 数据,面临着计算和记忆方面的挑战.
- 整合多样化的scRNA-seq数据集是复杂的,因为实验变化和技术差异.
- 持续学习 (CL) 提供增量培训,但对数据批次测序敏感,这是一个研究不足的因素.
研究的目的:
- 为持续学习 (CL) 算法引入和评估一种新的基于信任的批量订单策略.
- 提高在大型生物数据集上训练的机器学习模型的效率和性能.
- 针对异质单细胞RNA测序 (scRNA-seq) 数据的培训模型的挑战.
主要方法:
- 开发了一个基于信任的批量订单策略,用于CL算法.
- 通过估计他们的信心,优先训练样本.
- 结构化数据批次以信任度上升的顺序进行模型培训.
- 在多个scRNA-seq数据集上使用数据集内和数据集间实验评估性能.
主要成果:
- 基于信心的升级批次订单在scRNA-seq数据集中持续改善了分类性能.
- 这一策略在数据集内部实验中的F1中位数中优于随机和下降顺序.
- 基于信任的排序在训练来自不同测序协议的异质数据集时增强了模型的稳定性.
结论:
- 批次测序是优化CL工作流程的关键因素,用于诸如scRNA-seq分析等数据密集型应用程序.
- 提出的基于信任的订单策略提供了一种有希望的方法来提高机器学习模型的概括性和稳定性.
- 未来的工作可以将这一策略扩展到其他领域,并探索动态数据集的适应性信心指标.
相关概念视频
RNA-seq
11.8K
RNA sequencing, or RNA-Seq, is a high-throughput sequencing technology used to study the transcriptome of a cell. Transcriptomics helps to interpret the functional elements of a genome and identify the molecular constituents of an organism. Additionally, it also helps in understanding the development of an organism and the occurrence of diseases.
Before the discovery of RNA-seq, microarray-based methods and Sanger sequencing were used for transcriptome analysis. However, while...
Before the discovery of RNA-seq, microarray-based methods and Sanger sequencing were used for transcriptome analysis. However, while...
11.8K
Next-generation Sequencing
97.8K
The first human genome sequencing project cost $2.7 billion and was declared complete in 2003, after 15 years of international cooperation and collaboration between several research teams and funding agencies. Today, with the advent of next-generation sequencing technologies, the cost and time of sequencing a human genome have dropped over 100 fold.
Next-Generation Sequencing Methods
Although all next-generation methods use different technologies, they all share a set of standard features....
Next-Generation Sequencing Methods
Although all next-generation methods use different technologies, they all share a set of standard features....
97.8K


