Feature Engineering-Assisted Drug Repurposing on Disease-Drug Transcriptome Profiles in Gastric Cancer.

IF 1.6 4区医学 Q4 BIOCHEMICAL RESEARCH METHODS

Assay and drug development technologies Pub Date : 2024-04-04 DOI:10.1089/adt.2023.141

K. K. Kırboğa, M. Rudrapal

{"title":"Feature Engineering-Assisted Drug Repurposing on Disease-Drug Transcriptome Profiles in Gastric Cancer.","authors":"K. K. Kırboğa, M. Rudrapal","doi":"10.1089/adt.2023.141","DOIUrl":null,"url":null,"abstract":"Gastric cancer is one of the most common and deadly types of cancer in the world. To develop new biomarkers and drugs to diagnose and treat this cancer, it is necessary to identify the differences between the transcriptome profiles of gastric cancer and healthy individuals, identify critical genes associated with these differences, and make potential drug predictions based on these genes. In this study, using two gene expression datasets related to gastric cancer (GSE19826 and GSE79973), 200 genes that were ready for machine learning were selected, and their expression levels were analyzed. The best 100 genes for the model were chosen with the permutation feature importance method, and central genes, such as SCARB1, ETV3, SPATA17, FAM167A-AS1, and MTBP, which were shown to be associated with gastric cancer, were identified. Then, using the drug repurposing method with the Connectivity Map CLUE Query tools, potential drugs such as Forskolin, Gestrinone, Cediranib, Apicidine, and Everolimus, which showed a highly negative correlation with the expression levels of the selected genes, were identified. This study provides a method to develop new approaches to diagnosing and treating gastric cancer by comparing the transcriptome profiles of patients gastric cancer and performing a feature engineering-assisted drug repurposing analysis based on cancer data.","PeriodicalId":8586,"journal":{"name":"Assay and drug development technologies","volume":null,"pages":null},"PeriodicalIF":1.6000,"publicationDate":"2024-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Assay and drug development technologies","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1089/adt.2023.141","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"BIOCHEMICAL RESEARCH METHODS","Score":null,"Total":0}

引用次数: 0

Abstract

Gastric cancer is one of the most common and deadly types of cancer in the world. To develop new biomarkers and drugs to diagnose and treat this cancer, it is necessary to identify the differences between the transcriptome profiles of gastric cancer and healthy individuals, identify critical genes associated with these differences, and make potential drug predictions based on these genes. In this study, using two gene expression datasets related to gastric cancer (GSE19826 and GSE79973), 200 genes that were ready for machine learning were selected, and their expression levels were analyzed. The best 100 genes for the model were chosen with the permutation feature importance method, and central genes, such as SCARB1, ETV3, SPATA17, FAM167A-AS1, and MTBP, which were shown to be associated with gastric cancer, were identified. Then, using the drug repurposing method with the Connectivity Map CLUE Query tools, potential drugs such as Forskolin, Gestrinone, Cediranib, Apicidine, and Everolimus, which showed a highly negative correlation with the expression levels of the selected genes, were identified. This study provides a method to develop new approaches to diagnosing and treating gastric cancer by comparing the transcriptome profiles of patients gastric cancer and performing a feature engineering-assisted drug repurposing analysis based on cancer data.

查看原文本刊更多论文

胃癌疾病-药物转录组图谱的特征工程辅助药物再利用

胃癌是世界上最常见、最致命的癌症之一。为了开发诊断和治疗这种癌症的新生物标记物和药物，有必要确定胃癌与健康人转录组之间的差异，找出与这些差异相关的关键基因，并根据这些基因预测潜在的药物。本研究利用两个与胃癌相关的基因表达数据集（GSE19826 和 GSE79973），选择了 200 个可用于机器学习的基因，并对其表达水平进行了分析。利用置换特征重要性法选出了模型的最佳100个基因，并确定了与胃癌相关的中心基因，如SCARB1、ETV3、SPATA17、FAM167A-AS1和MTBP。然后，利用连接图CLUE查询工具的药物再利用方法，确定了与所选基因的表达水平呈高度负相关的潜在药物，如Forskolin、Gestrinone、Cediranib、Apicidine和Everolimus。这项研究通过比较胃癌患者的转录组图谱，并基于癌症数据进行特征工程辅助药物再利用分析，为开发诊断和治疗胃癌的新方法提供了一种方法。

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

Assay and drug development technologies 医学-生化研究方法

CiteScore

3.60

自引率

0.00%

发文量

审稿时长

>12 weeks

期刊介绍： ASSAY and Drug Development Technologies provides access to novel techniques and robust tools that enable critical advances in early-stage screening. This research published in the Journal leads to important therapeutics and platforms for drug discovery and development. This reputable peer-reviewed journal features original papers application-oriented technology reviews, topical issues on novel and burgeoning areas of research, and reports in methodology and technology application. ASSAY and Drug Development Technologies coverage includes: -Assay design, target development, and high-throughput technologies- Hit to Lead optimization and medicinal chemistry through preclinical candidate selection- Lab automation, sample management, bioinformatics, data mining, virtual screening, and data analysis- Approaches to assays configured for gene families, inherited, and infectious diseases- Assays and strategies for adapting model organisms to drug discovery- The use of stem cells as models of disease- Translation of phenotypic outputs to target identification- Exploration and mechanistic studies of the technical basis for assay and screening artifacts