Scholarlink

This paper proposes an approach to missing value imputation in a transcriptomic dataset using a self-organizing map. The self-organizing map is trained on a complete subset of the data. Instances with missing values are presented to the trained map and the best matching unit is used to impute the missing values in the instance. The empirical results show promise in the application of self-organizing maps for missing value imputation in transcriptomic datasets.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Self-organizing Maps for Missing Value Imputation in Transcriptomic Datasets

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Louzanne Swart,
  • Andries Engelbrecht,
  • Lyn-Marié Birkholtz

摘要

This paper proposes an approach to missing value imputation in a transcriptomic dataset using a self-organizing map. The self-organizing map is trained on a complete subset of the data. Instances with missing values are presented to the trained map and the best matching unit is used to impute the missing values in the instance. The empirical results show promise in the application of self-organizing maps for missing value imputation in transcriptomic datasets.