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

Basit Öğe Kaydı
dc.authoridKirboga, Kevser Kubra/0000-0002-2917-8860
dc.contributor.authorKirboga, Kevser Kubra
dc.contributor.authorRudrapal, Mithun
dc.date.accessioned2025-05-20T18:56:25Z
dc.date.issued2024
dc.departmentBilecik Şeyh Edebali Üniversitesi
dc.description.abstractGastric 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.
dc.description.sponsorshipStatistical Modeling Techniques and Applications in Natural Sciences [TUBITAK 2237]
dc.description.sponsorshipThis study was carried out thanks to first author's participation in the Statistical Modeling Techniques and Applications in Natural Sciences training event supported within the scope of TUBITAK 2237, a Support Program for Scientific Educational Activities (Statistical Modeling Techniques and Applications in Natural Sciences). This educational activity enabled the theoretical and practical learning and application of statistical modeling techniques in the field of natural sciences. Thanks to this educational activity, the authors have learned and applied the necessary methods and tools to analyze the datasets used in the research. For this reason, the authors would like to thank TUBITAK, trainers and organizers, for their efforts in organizing this training event.
dc.identifier.doi10.1089/adt.2023.141
dc.identifier.endpage191
dc.identifier.issn1540-658X
dc.identifier.issn1557-8127
dc.identifier.issue4
dc.identifier.pmid38572922
dc.identifier.scopus2-s2.0-85190415498
dc.identifier.scopusqualityQ3
dc.identifier.startpage181
dc.identifier.urihttps://doi.org/10.1089/adt.2023.141
dc.identifier.urihttps://hdl.handle.net/11552/7743
dc.identifier.volume22
dc.identifier.wosWOS:001196467700001
dc.identifier.wosqualityQ3
dc.indekslendigikaynakWoS
dc.indekslendigikaynakScopus
dc.indekslendigikaynakPubMed
dc.indekslendigikaynakWoS - Science Citation Index Expanded
dc.language.isoen
dc.publisherMary Ann Liebert, Inc
dc.relation.ispartofAssay and Drug Development Technologies
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_WOS_20250518
dc.subjectgastric cancer
dc.subjectdrug repurposing
dc.subjectfeature selection
dc.subjectgene expression
dc.subjectdisease-drug
dc.titleFeature Engineering-Assisted Drug Repurposing on Disease-Drug Transcriptome Profiles in Gastric Cancer
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar
PubMed İndeksli Yayınlar
Scopus İndeksli Yayınlar