Scholarlink

The availability of multi-omics data requires an ingenious analytical framework to maximise the information through optimal handling of high-dimensional observations. Machine learning (ML) approaches provide a promising analytical paradigm through efficient analytical procedures for high-dimensional multi-omics data. In this chapter, we discussed several ML schemes and their applications in precision oncology. Besides, several future ML strategies that efficiently harness the information obtained from the multi-omics data are also elucidated, with particular attention given to the Bayesian methodological framework and computational strategies and the integration between new ML strategies and emerging and innovative clinical trial designs. We believe the integrated ML approaches will facilitate new drug development and novel clinical trial designs, resulting in a more expeditious translation of novel therapeutic alternatives into apparent clinical benefits for cancer patients based on their specific cancer phenotypes.

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

Unveiling Cancer Complexity: Machine Learning Insights into Multi-omics Data

  • 章节

  • 发表日期：

    2024年

查看全文
  • Muhammad-Redha Abdullah-Zawawi,
  • Shing Cheng Tan,
  • M. Aiman Mohtar,
  • Saiful Effendi Syafruddin,
  • Teck Yew Low,
  • Muhammad Irfan Abdul Jalal

摘要

The availability of multi-omics data requires an ingenious analytical framework to maximise the information through optimal handling of high-dimensional observations. Machine learning (ML) approaches provide a promising analytical paradigm through efficient analytical procedures for high-dimensional multi-omics data. In this chapter, we discussed several ML schemes and their applications in precision oncology. Besides, several future ML strategies that efficiently harness the information obtained from the multi-omics data are also elucidated, with particular attention given to the Bayesian methodological framework and computational strategies and the integration between new ML strategies and emerging and innovative clinical trial designs. We believe the integrated ML approaches will facilitate new drug development and novel clinical trial designs, resulting in a more expeditious translation of novel therapeutic alternatives into apparent clinical benefits for cancer patients based on their specific cancer phenotypes.