基于元学习的小样本癌症亚型分类算法
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

TP399,R730.49

基金项目:

国家自然科学基金项目(6192185, 62472202)


A Meta-Learning-Based Algorithm for Few-Shot Cancer Subtype Classification
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    癌症是一种与基因密切相关的疾病,具有多种亚型,各亚型在遗传、表型和治疗反应上存在显著差异。准确的癌症亚型分类对个性化治疗至关重要,有助于提高治疗效果。然而,基于患者基因表达数据的癌症亚型分类方法在样本不均衡的情况下,往往难以有效区分稀有亚型。为解决这一问题,本文提出一种基于元学习的癌症亚型分类方法MFP-VAE (meta-learning few-shot prototype learning VAE),专注于处理样本不均衡的数据集。该方法改进了样本抽取策略,以确保在元学习任务中不同亚型的样本得到平衡重视。该模型采用变分自编码器进行特征提取,并通过计算样本与癌症亚型对应原型之间的距离进行分类。实验结果表明,MFP-VAE在两个公开癌症数据集上的表现优于现有方法,特别是在样本不平衡的情况下,显著提高了分类效果。此外,生存率分析显示,不同的癌症亚型在临床特性上具有显著差异。

    Abstract:

    Cancer is a genetically related disease with multiple subtypes, each exhibiting significant differences in genetics, phenotype, and treatment response. Accurate classification of cancer subtypes is critical for personalized treatment, as it helps improve therapeutic outcomes. However, cancer subtype classification methods based on patient gene expression data often struggle to effectively distinguish rare subtypes in the presence of imbalanced samples. To address this issue, a cancer subtype classification method called MFP-VAE (meta-learning few-shot prototype learning VAE) is proposed, focusing on handling datasets with imbalanced samples. This method improves the sampling strategy to ensure balanced consideration of different subtypes in meta-learning tasks. The model employs a variational autoencoder for feature extraction and classifies samples by calculating the distance between the samples and their corresponding cancer subtype prototypes. Experimental results show that MFP-VAE outperforms existing methods on two public cancer datasets, significantly improving classification performance, especially under imbalanced sample conditions. Furthermore, survival analysis reveals that the distinguished cancer subtypes exhibit significant differences in clinical characteristics.

    参考文献
    相似文献
    引证文献
引用本文

引文格式
戴伟,张浩轩,陈方旭,等.基于元学习的小样本癌症亚型分类算法 [J].集成技术,2025,14(3):87-101

Citing format
DAI Wei, ZHANG Haoxuan, CHEN Fangxu, et al. A Meta-Learning-Based Algorithm for Few-Shot Cancer Subtype Classification[J]. Journal of Integration Technology,2025,14(3):87-101

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2024-10-12
  • 最后修改日期:2025-01-15
  • 录用日期:
  • 在线发布日期: 2025-05-09
  • 出版日期:
文章二维码