{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Huang Z"],"funding":["the National Natural Science Fund of China Research Fund for International Scientists","the Key University Laboratory of Metabolism and Health of Guangdong, Southern University of Science and Technology, Shenzhen 518055, China","The National Natural Science Foundation of China","The Development Project of Jilin Province of China"],"pagination":["297"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC11942234"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["16(3)"],"pubmed_abstract":["This study introduces a novel framework that simultaneously addresses the challenges of performance accuracy and result interpretability in transcriptomic-data-based classification. <b>Background/objectives</b>: In biological data classification, it is challenging to achieve both high performance accuracy and interpretability at the same time. This study presents a framework to address both challenges in transcriptomic-data-based classification. The goal is to select features, models, and a meta-voting classifier that optimizes both classification performance and interpretability. <b>Methods</b>: The framework consists of a four-step feature selection process: (1) the identification of metabolic pathways whose enzyme-gene expressions discriminate samples with different labels, aiding inter"],"journal":["Genes"],"pubmed_title":["Optimizing Model Performance and Interpretability: Application to Biological Data Classification."],"pmcid":["PMC11942234"],"funding_grant_id":["W2431059","T2350010","2022KSYS007","No. 20220508125RC"],"pubmed_authors":["Chen Q","Mu X","Qiao S","Shi B","Huang Z","Cao Y","Xiao G","Wang Y","Xu Y"],"additional_accession":[]},"is_claimable":false,"name":"Optimizing Model Performance and Interpretability: Application to Biological Data Classification.","description":"This study introduces a novel framework that simultaneously addresses the challenges of performance accuracy and result interpretability in transcriptomic-data-based classification. <b>Background/objectives</b>: In biological data classification, it is challenging to achieve both high performance accuracy and interpretability at the same time. This study presents a framework to address both challenges in transcriptomic-data-based classification. The goal is to select features, models, and a meta-voting classifier that optimizes both classification performance and interpretability. <b>Methods</b>: The framework consists of a four-step feature selection process: (1) the identification of metabolic pathways whose enzyme-gene expressions discriminate samples with different labels, aiding inter","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025 Feb","modification":"2025-06-28T03:05:29.336Z","creation":"2025-06-28T03:05:29.336Z"},"accession":"S-EPMC11942234","cross_references":{"pubmed":["40149449"],"doi":["10.3390/genes16030297"]}}