Using the Precision Lasso for gene selection in diffuse large B cell lymphoma cancer.

IF 2.1 Q3 ONCOLOGY Journal of the Egyptian National Cancer Institute Pub Date : 2023-06-26 DOI:10.1186/s43046-023-00172-5

Rashed Pourhamidi, Azam Moslemi

{"title":"Using the Precision Lasso for gene selection in diffuse large B cell lymphoma cancer.","authors":"Rashed Pourhamidi, Azam Moslemi","doi":"10.1186/s43046-023-00172-5","DOIUrl":null,"url":null,"abstract":"Background: Gene selection from gene expression profiles is the appropriate tool for diagnosing and predicting cancers. The aim of this study is to perform a Precision Lasso regression model on gene expression of diffuse large B cell lymphoma patients and to find marker genes related to DLBCL.Methods: In the present case-control study, the dataset included 180 gene expressions from 14 healthy individuals and 17 DLBCL patients. The marker genes were selected by fitting Ridge, Lasso, Elastic Net, and Precision Lasso regression models.Results: Based on our findings, the Precision Lasso, the Ridge, the Elastic Net, and the Lasso models choose the most marker genes, respectively. In addition, the top 20 genes are based on models compared with the results of clinical studies. The Precision Lasso and the Ridge models selected the most common genes with the clinical results, respectively.Conclusions: The performance of the Precision Lasso model in selecting related genes could be considered more acceptable rather than other models.","PeriodicalId":17301,"journal":{"name":"Journal of the Egyptian National Cancer Institute","volume":"35 1","pages":"19"},"PeriodicalIF":2.1000,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of the Egyptian National Cancer Institute","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1186/s43046-023-00172-5","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ONCOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Background: Gene selection from gene expression profiles is the appropriate tool for diagnosing and predicting cancers. The aim of this study is to perform a Precision Lasso regression model on gene expression of diffuse large B cell lymphoma patients and to find marker genes related to DLBCL.

Methods: In the present case-control study, the dataset included 180 gene expressions from 14 healthy individuals and 17 DLBCL patients. The marker genes were selected by fitting Ridge, Lasso, Elastic Net, and Precision Lasso regression models.

Results: Based on our findings, the Precision Lasso, the Ridge, the Elastic Net, and the Lasso models choose the most marker genes, respectively. In addition, the top 20 genes are based on models compared with the results of clinical studies. The Precision Lasso and the Ridge models selected the most common genes with the clinical results, respectively.

Conclusions: The performance of the Precision Lasso model in selecting related genes could be considered more acceptable rather than other models.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

应用精密套索进行弥漫大B细胞淋巴瘤的基因选择。

背景:从基因表达谱中选择基因是诊断和预测癌症的合适工具。本研究的目的是建立弥漫大B细胞淋巴瘤患者基因表达的Precision Lasso回归模型，寻找与弥漫大B细胞淋巴瘤相关的标记基因。方法:在本病例对照研究中，数据集包括来自14名健康个体和17名DLBCL患者的180个基因表达。通过Ridge、Lasso、Elastic Net和Precision Lasso回归模型选择标记基因。结果:基于我们的研究结果，Precision Lasso、Ridge、Elastic Net和Lasso模型分别选择了最多的标记基因。此外，排名前20位的基因是根据模型与临床研究结果进行比较的。Precision Lasso和Ridge模型分别选择了与临床结果最常见的基因。结论:Precision Lasso模型在相关基因选择上的表现优于其他模型。

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

Journal of the Egyptian National Cancer Institute ONCOLOGY-

CiteScore

3.50

自引率

0.00%

发文量

审稿时长

11 weeks

期刊介绍： As the official publication of the National Cancer Institute, Cairo University, the Journal of the Egyptian National Cancer Institute (JENCI) is an open access peer-reviewed journal that publishes on the latest innovations in oncology and thereby, providing academics and clinicians a leading research platform. JENCI welcomes submissions pertaining to all fields of basic, applied and clinical cancer research. Main topics of interest include: local and systemic anticancer therapy (with specific interest on applied cancer research from developing countries); experimental oncology; early cancer detection; randomized trials (including negatives ones); and key emerging fields of personalized medicine, such as molecular pathology, bioinformatics, and biotechnologies.