Multiple machine learning-based integrations of multi-omics data to identify molecular subtypes and construct a prognostic model for HNSCC.

IF 2.7 3区 生物学
Xiaoqin Luo, Chao Li, Gang Qin
{"title":"Multiple machine learning-based integrations of multi-omics data to identify molecular subtypes and construct a prognostic model for HNSCC.","authors":"Xiaoqin Luo, Chao Li, Gang Qin","doi":"10.1186/s41065-025-00380-0","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Immunotherapy has introduced new breakthroughs in improving the survival of head and neck squamous cell carcinoma (HNSCC) patients, yet drug resistance remains a critical challenge. Developing personalized treatment strategies based on the molecular heterogeneity of HNSCC is essential to enhance therapeutic efficacy and prognosis.</p><p><strong>Methods: </strong>We integrated four HNSCC datasets (TCGA-HNSCC, GSE27020, GSE41613, and GSE65858) from TCGA and GEO databases. Using 10 multi-omics consensus clustering algorithms via the MOVICS package, we identified two molecular subtypes (CS1 and CS2) and validated their stability. A machine learning-driven prognostic signature was constructed by combining 101 algorithms, ultimately selecting 30 prognosis-related genes (PRGs) with the Elastic Net model. This signature was further linked to immune infiltration, functional pathways, and therapeutic sensitivity.</p><p><strong>Results: </strong>CS1 exhibited superior survival outcomes in both TCGA and META-HNSCC cohorts. The PRG-based signature stratified patients into low- and high-risk groups, with the low-risk group showing prolonged survival, enhanced immune cell infiltration (B cells, T cells, monocytes), and activated immune functions (cytolytic activity, T cell co-stimulation). High-risk patients were more sensitive to radiotherapy and chemotherapy (e.g., Cisplatin, 5-Fluorouracil), while low-risk patients responded better to immunotherapy and targeted therapies.</p><p><strong>Conclusion: </strong>Our study delineates two molecular subtypes of HNSCC and establishes a robust prognostic model using multi-omics data and machine learning. These findings provide a framework for personalized treatment selection, offering clinical insights to optimize therapeutic strategies for HNSCC patients.</p>","PeriodicalId":12862,"journal":{"name":"Hereditas","volume":"162 1","pages":"17"},"PeriodicalIF":2.7000,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11800565/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Hereditas","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.1186/s41065-025-00380-0","RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Background: Immunotherapy has introduced new breakthroughs in improving the survival of head and neck squamous cell carcinoma (HNSCC) patients, yet drug resistance remains a critical challenge. Developing personalized treatment strategies based on the molecular heterogeneity of HNSCC is essential to enhance therapeutic efficacy and prognosis.

Methods: We integrated four HNSCC datasets (TCGA-HNSCC, GSE27020, GSE41613, and GSE65858) from TCGA and GEO databases. Using 10 multi-omics consensus clustering algorithms via the MOVICS package, we identified two molecular subtypes (CS1 and CS2) and validated their stability. A machine learning-driven prognostic signature was constructed by combining 101 algorithms, ultimately selecting 30 prognosis-related genes (PRGs) with the Elastic Net model. This signature was further linked to immune infiltration, functional pathways, and therapeutic sensitivity.

Results: CS1 exhibited superior survival outcomes in both TCGA and META-HNSCC cohorts. The PRG-based signature stratified patients into low- and high-risk groups, with the low-risk group showing prolonged survival, enhanced immune cell infiltration (B cells, T cells, monocytes), and activated immune functions (cytolytic activity, T cell co-stimulation). High-risk patients were more sensitive to radiotherapy and chemotherapy (e.g., Cisplatin, 5-Fluorouracil), while low-risk patients responded better to immunotherapy and targeted therapies.

Conclusion: Our study delineates two molecular subtypes of HNSCC and establishes a robust prognostic model using multi-omics data and machine learning. These findings provide a framework for personalized treatment selection, offering clinical insights to optimize therapeutic strategies for HNSCC patients.

基于多个机器学习的多组学数据集成,以识别分子亚型并构建HNSCC的预后模型。
背景:免疫疗法在提高头颈部鳞状细胞癌(HNSCC)患者生存率方面取得了新的突破,但耐药性仍然是一个关键挑战。根据HNSCC的分子异质性制定个性化的治疗策略对于提高治疗效果和预后至关重要。方法:我们整合了TCGA和GEO数据库中的4个HNSCC数据集(TCGA-HNSCC、GSE27020、GSE41613和GSE65858)。通过MOVICS软件包使用10种多组学共识聚类算法,我们确定了两个分子亚型(CS1和CS2)并验证了它们的稳定性。结合101种算法构建了机器学习驱动的预后签名,最终选择了30个预后相关基因(prg)与Elastic Net模型。这一特征进一步与免疫浸润、功能途径和治疗敏感性有关。结果:CS1在TCGA和META-HNSCC队列中均表现出优越的生存结果。基于prg的标记将患者分为低风险组和高风险组,低风险组表现出延长的生存时间,增强的免疫细胞浸润(B细胞,T细胞,单核细胞)和激活的免疫功能(细胞溶解活性,T细胞共刺激)。高危患者对放疗和化疗(如顺铂、5-氟尿嘧啶)更敏感,低危患者对免疫治疗和靶向治疗反应更好。结论:我们的研究描述了HNSCC的两种分子亚型,并利用多组学数据和机器学习建立了一个强大的预后模型。这些发现为个性化治疗选择提供了框架,为优化HNSCC患者的治疗策略提供了临床见解。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Hereditas
Hereditas Biochemistry, Genetics and Molecular Biology-Genetics
CiteScore
3.80
自引率
3.70%
发文量
0
期刊介绍: For almost a century, Hereditas has published original cutting-edge research and reviews. As the Official journal of the Mendelian Society of Lund, the journal welcomes research from across all areas of genetics and genomics. Topics of interest include human and medical genetics, animal and plant genetics, microbial genetics, agriculture and bioinformatics.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信