Scholarlink

This study provides an innovative approach to the classification of Missense mutations in the CFTR gene, especially the convolutional neural networks (CNN). The primary aim of this paper is to predict the potential impact of these mutations on improved understanding and management of cystic fibrosis. The result obtained using the proposed CNN model outperformed machine learning approaches, including logistic regression, support vector machine, and random forest. The model achieved an accuracy of 91.34%, a sensitivity of 90.43%, and an F1 score of 90.21%, showing that deep learning techniques can be a powerful tool for genetic mutation classification problems. The obtained results have the potential to make significant contributions to developing personalized medicine approaches and to advance treatment strategies based on genetics.

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

Classification of the Missense Mutation in the CFTR Gene by Deep Learning

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Zahra Elmi,
  • Dilek Kodalak

摘要

This study provides an innovative approach to the classification of Missense mutations in the CFTR gene, especially the convolutional neural networks (CNN). The primary aim of this paper is to predict the potential impact of these mutations on improved understanding and management of cystic fibrosis. The result obtained using the proposed CNN model outperformed machine learning approaches, including logistic regression, support vector machine, and random forest. The model achieved an accuracy of 91.34%, a sensitivity of 90.43%, and an F1 score of 90.21%, showing that deep learning techniques can be a powerful tool for genetic mutation classification problems. The obtained results have the potential to make significant contributions to developing personalized medicine approaches and to advance treatment strategies based on genetics.