Scholarlink

<p>The financial and practical complexities of collecting a statistically significant number of tumour gene expression data can severely affect the reliability of differential expression analysis in cancer. Generally, studies are performed with an immense number of genes related to a minimal number of samples, leading to an underrepresentation of the disease heterogeneity. A potential solution lies in generating artificial tumour samples similar to real ones, thereby increasing the accuracy and robustness of biological experiments. In that sense, this work proposes a Wasserstein Generative Adversarial Network architecture for generating synthetic tumour samples. The primary objective is to ensure that the generated samples accurately preserve the shared behaviour of genes and the differential expression patterns observed in tumour samples. The study focuses on four cancer types: thyroid, breast, lung and prostate. The experimental results confirm that our proposal can reproduce the characteristics of the original samples, suggesting that the model is a reliable framework for increasing the number of tumour samples. In addition, the model proved able to exacerbate the distributions shown by each gene, allowing the discovery of possible hidden patterns.</p>

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

Massive Production of Cancer Synthetic RNA-Seq Gene Expression Samples

  • 期刊论文

  • 发表日期：

    2025年8月1日

查看全文
  • Matías Gabriel Rojas,
  • Ana Carolina Olivera,
  • Pablo Javier Vidal,
  • Jessica Andrea Carballido

摘要

The financial and practical complexities of collecting a statistically significant number of tumour gene expression data can severely affect the reliability of differential expression analysis in cancer. Generally, studies are performed with an immense number of genes related to a minimal number of samples, leading to an underrepresentation of the disease heterogeneity. A potential solution lies in generating artificial tumour samples similar to real ones, thereby increasing the accuracy and robustness of biological experiments. In that sense, this work proposes a Wasserstein Generative Adversarial Network architecture for generating synthetic tumour samples. The primary objective is to ensure that the generated samples accurately preserve the shared behaviour of genes and the differential expression patterns observed in tumour samples. The study focuses on four cancer types: thyroid, breast, lung and prostate. The experimental results confirm that our proposal can reproduce the characteristics of the original samples, suggesting that the model is a reliable framework for increasing the number of tumour samples. In addition, the model proved able to exacerbate the distributions shown by each gene, allowing the discovery of possible hidden patterns.