Scholarlink

Cancer typically arises from failures in cell cycle regulation, leading to uncontrolled cell division and tumour formation. This study focuses on genes directly involved in the cell cycle and their interactions with nine key cell processes across different phases (G0, G1, S, G2, M), such as apoptosis, DNA replication, and chromosome segregation. By simulating gene mutations and analysing their impact on these processes, we used machine learning models, including Gradient Boosting Machines (GBM), Random Forests, Support Vector Machines (SVM), Neural Networks, and Logistic Regression, to predict mutation impact levels. Our findings demonstrate that GBM and Random Forests are highly effective for this purpose, achieving high accuracy and robustness, even with incomplete data. This research provides a valuable framework for understanding the molecular mechanisms of cancer progression and suggests potential therapeutic interventions based on gene mutation effects.

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

Predicting the Impact of Gene Mutations Using Supervised Learning Models

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Eneinta Veliai,
  • Sotiris Moschoyiannis

摘要

Cancer typically arises from failures in cell cycle regulation, leading to uncontrolled cell division and tumour formation. This study focuses on genes directly involved in the cell cycle and their interactions with nine key cell processes across different phases (G0, G1, S, G2, M), such as apoptosis, DNA replication, and chromosome segregation. By simulating gene mutations and analysing their impact on these processes, we used machine learning models, including Gradient Boosting Machines (GBM), Random Forests, Support Vector Machines (SVM), Neural Networks, and Logistic Regression, to predict mutation impact levels. Our findings demonstrate that GBM and Random Forests are highly effective for this purpose, achieving high accuracy and robustness, even with incomplete data. This research provides a valuable framework for understanding the molecular mechanisms of cancer progression and suggests potential therapeutic interventions based on gene mutation effects.