Integrative multi-omic and machine learning approach for prognostic stratification and therapeutic targeting in lung squamous cell carcinoma.

IF 5 3区 生物学 Q1 BIOCHEMISTRY & MOLECULAR BIOLOGY BioFactors Pub Date : 2024-10-11 DOI:10.1002/biof.2128
Xiao Zhang, Pengpeng Zhang, Qianhe Ren, Jun Li, Haoran Lin, Yuming Huang, Wei Wang
{"title":"Integrative multi-omic and machine learning approach for prognostic stratification and therapeutic targeting in lung squamous cell carcinoma.","authors":"Xiao Zhang, Pengpeng Zhang, Qianhe Ren, Jun Li, Haoran Lin, Yuming Huang, Wei Wang","doi":"10.1002/biof.2128","DOIUrl":null,"url":null,"abstract":"<p><p>The proliferation, metastasis, and drug resistance of cancer cells pose significant challenges to the treatment of lung squamous cell carcinoma (LUSC). However, there is a lack of optimal predictive models that can accurately forecast patient prognosis and guide the selection of targeted therapies. The extensive multi-omic data obtained from multi-level molecular biology provides a unique perspective for understanding the underlying biological characteristics of cancer, offering potential prognostic indicators and drug sensitivity biomarkers for LUSC patients. We integrated diverse datasets encompassing gene expression, DNA methylation, genomic mutations, and clinical data from LUSC patients to achieve consensus clustering using a suite of 10 multi-omics integration algorithms. Subsequently, we employed 10 commonly used machine learning algorithms, combining them into 101 unique configurations to design an optimal performing model. We then explored the characteristics of high- and low-risk LUSC patient groups in terms of the tumor microenvironment and response to immunotherapy, ultimately validating the functional roles of the model genes through in vitro experiments. Through the application of 10 clustering algorithms, we identified two prognostically relevant subtypes, with CS1 exhibiting a more favorable prognosis. We then constructed a subtype-specific machine learning model, LUSC multi-omics signature (LMS) based on seven key hub genes. Compared to previously published LUSC biomarkers, our LMS score demonstrated superior predictive performance. Patients with lower LMS scores had higher overall survival rates and better responses to immunotherapy. Notably, the high LMS group was more inclined toward \"cold\" tumors, characterized by immune suppression and exclusion, but drugs like dasatinib may represent promising therapeutic options for these patients. Notably, we also validated the model gene SERPINB13 through cell experiments, confirming its role as a potential oncogene influencing the progression of LUSC and as a promising therapeutic target. Our research provides new insights into refining the molecular classification of LUSC and further optimizing immunotherapy strategies.</p>","PeriodicalId":8923,"journal":{"name":"BioFactors","volume":" ","pages":""},"PeriodicalIF":5.0000,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"BioFactors","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.1002/biof.2128","RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"BIOCHEMISTRY & MOLECULAR BIOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

The proliferation, metastasis, and drug resistance of cancer cells pose significant challenges to the treatment of lung squamous cell carcinoma (LUSC). However, there is a lack of optimal predictive models that can accurately forecast patient prognosis and guide the selection of targeted therapies. The extensive multi-omic data obtained from multi-level molecular biology provides a unique perspective for understanding the underlying biological characteristics of cancer, offering potential prognostic indicators and drug sensitivity biomarkers for LUSC patients. We integrated diverse datasets encompassing gene expression, DNA methylation, genomic mutations, and clinical data from LUSC patients to achieve consensus clustering using a suite of 10 multi-omics integration algorithms. Subsequently, we employed 10 commonly used machine learning algorithms, combining them into 101 unique configurations to design an optimal performing model. We then explored the characteristics of high- and low-risk LUSC patient groups in terms of the tumor microenvironment and response to immunotherapy, ultimately validating the functional roles of the model genes through in vitro experiments. Through the application of 10 clustering algorithms, we identified two prognostically relevant subtypes, with CS1 exhibiting a more favorable prognosis. We then constructed a subtype-specific machine learning model, LUSC multi-omics signature (LMS) based on seven key hub genes. Compared to previously published LUSC biomarkers, our LMS score demonstrated superior predictive performance. Patients with lower LMS scores had higher overall survival rates and better responses to immunotherapy. Notably, the high LMS group was more inclined toward "cold" tumors, characterized by immune suppression and exclusion, but drugs like dasatinib may represent promising therapeutic options for these patients. Notably, we also validated the model gene SERPINB13 through cell experiments, confirming its role as a potential oncogene influencing the progression of LUSC and as a promising therapeutic target. Our research provides new insights into refining the molecular classification of LUSC and further optimizing immunotherapy strategies.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
肺鳞状细胞癌预后分层和靶向治疗的多组学和机器学习综合方法。
癌细胞的增殖、转移和耐药性给肺鳞癌(LUSC)的治疗带来了巨大挑战。然而,目前还缺乏能够准确预测患者预后并指导靶向疗法选择的最佳预测模型。从多层次分子生物学中获得的大量多组数据为了解癌症的基本生物学特征提供了一个独特的视角,为肺癌患者提供了潜在的预后指标和药物敏感性生物标志物。我们利用 10 种多组学整合算法套件,整合了包括 LUSC 患者的基因表达、DNA 甲基化、基因组突变和临床数据在内的各种数据集,以实现共识聚类。随后,我们采用了 10 种常用的机器学习算法,将它们组合成 101 种独特的配置,以设计出性能最佳的模型。然后,我们从肿瘤微环境和对免疫疗法的反应两方面探讨了高风险和低风险 LUSC 患者群体的特征,最终通过体外实验验证了模型基因的功能作用。通过应用 10 种聚类算法,我们确定了两种与预后相关的亚型,其中 CS1 的预后更佳。然后,我们基于七个关键枢纽基因构建了一个亚型特异性机器学习模型--LUSC 多组学特征(LMS)。与之前公布的LUSC生物标志物相比,我们的LMS评分显示出更优越的预测性能。LMS评分较低的患者总生存率更高,对免疫疗法的反应也更好。值得注意的是,高LMS组更倾向于 "冷 "肿瘤,其特点是免疫抑制和排斥,但达沙替尼等药物可能是这些患者有希望的治疗选择。值得注意的是,我们还通过细胞实验验证了模型基因SERPINB13,证实它是影响LUSC进展的潜在癌基因,也是有希望的治疗靶点。我们的研究为完善LUSC的分子分类和进一步优化免疫疗法策略提供了新的见解。
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 去求助
来源期刊
BioFactors
BioFactors 生物-内分泌学与代谢
CiteScore
11.50
自引率
3.30%
发文量
96
审稿时长
6-12 weeks
期刊介绍: BioFactors, a journal of the International Union of Biochemistry and Molecular Biology, is devoted to the rapid publication of highly significant original research articles and reviews in experimental biology in health and disease. The word “biofactors” refers to the many compounds that regulate biological functions. Biological factors comprise many molecules produced or modified by living organisms, and present in many essential systems like the blood, the nervous or immunological systems. A non-exhaustive list of biological factors includes neurotransmitters, cytokines, chemokines, hormones, coagulation factors, transcription factors, signaling molecules, receptor ligands and many more. In the group of biofactors we can accommodate several classical molecules not synthetized in the body such as vitamins, micronutrients or essential trace elements. In keeping with this unified view of biochemistry, BioFactors publishes research dealing with the identification of new substances and the elucidation of their functions at the biophysical, biochemical, cellular and human level as well as studies revealing novel functions of already known biofactors. The journal encourages the submission of studies that use biochemistry, biophysics, cell and molecular biology and/or cell signaling approaches.
期刊最新文献
Insights into an indolicidin-derived low-toxic anti-microbial peptide's efficacy against bacterial cells while preserving eukaryotic cell viability. Investigating the dysregulation of genes associated with glucose and lipid metabolism in gastric cancer and their influence on immunity and prognosis. Construction of lysosome-related prognostic signature to predict the survival outcomes and selecting suitable drugs for patients with HNSCC. Navigating the immune landscape with plasma cells: A pan-cancer signature for precision immunotherapy. Machine learning models reveal ARHGAP11A's impact on lymph node metastasis and stemness in NSCLC.
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1