Scholarlink

<p>Colorectal Cancer (CRC) exhibits persistently high incidence and mortality rates worldwide, imposing a substantial socioeconomic burden. Early screening, early diagnosis, and early treatment can significantly improve patients’ survival rates while reducing mortality. However, there remains a lack of effective biomarkers to aid in early screening and diagnosis. As a branch of artificial intelligence, machine learning can automatically analyze large volumes of data, greatly saving human time and resources. The advancement of high-throughput sequencing technology has provided researchers with abundant gene expression data, offering rich data resources for the training and validation of machine learning models. With the development of artificial intelligence, integrating knowledge from bioinformatics, machine learning, molecular biology, and clinical medicine for analysis enables a more comprehensive understanding and exploration of the molecular biological mechanisms underlying CRC. In summary, this project aims to utilize machine learning techniques to screen five CRC signature genes (ABCG2, SCGN, USP2, CLDN1, and EPHX4) from GEO datasets, validate these signature genes using TCGA database, and perform RT-qPCR to detect the relative mRNA expression levels of these genes in CRC. Ultimately, this study seeks to provide novel biomolecular markers for the early diagnosis of CRC.</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

Screening and validation of potential molecular markers for colorectal cancer: based on bioinformatics analysis and machine learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月22日

查看全文
  • Yu Chang,
  • Mangmang Bai,
  • Yu Liu,
  • Kai Bai,
  • Yunfeng Hu

摘要

Colorectal Cancer (CRC) exhibits persistently high incidence and mortality rates worldwide, imposing a substantial socioeconomic burden. Early screening, early diagnosis, and early treatment can significantly improve patients’ survival rates while reducing mortality. However, there remains a lack of effective biomarkers to aid in early screening and diagnosis. As a branch of artificial intelligence, machine learning can automatically analyze large volumes of data, greatly saving human time and resources. The advancement of high-throughput sequencing technology has provided researchers with abundant gene expression data, offering rich data resources for the training and validation of machine learning models. With the development of artificial intelligence, integrating knowledge from bioinformatics, machine learning, molecular biology, and clinical medicine for analysis enables a more comprehensive understanding and exploration of the molecular biological mechanisms underlying CRC. In summary, this project aims to utilize machine learning techniques to screen five CRC signature genes (ABCG2, SCGN, USP2, CLDN1, and EPHX4) from GEO datasets, validate these signature genes using TCGA database, and perform RT-qPCR to detect the relative mRNA expression levels of these genes in CRC. Ultimately, this study seeks to provide novel biomolecular markers for the early diagnosis of CRC.