Machine Learning-Driven Identification of Exosome-Related Genes in Head and Neck Squamous Cell Carcinoma for Prognostic Evaluation and Drug Response Prediction
<b>Background:</b> This study integrated four Gene Expression Omnibus (GEO) datasets to identify disease-specific feature genes in head and neck squamous cell carcinoma (HNSCC) through differential expression analysis with batch effect correction. <b>Methods</b>: The GeneCard...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Biomedicines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9059/13/4/780 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850183584680247296 |
|---|---|
| author | Hua Cai Liuqing Zhou Yao Hu Tao Zhou |
| author_facet | Hua Cai Liuqing Zhou Yao Hu Tao Zhou |
| author_sort | Hua Cai |
| collection | DOAJ |
| description | <b>Background:</b> This study integrated four Gene Expression Omnibus (GEO) datasets to identify disease-specific feature genes in head and neck squamous cell carcinoma (HNSCC) through differential expression analysis with batch effect correction. <b>Methods</b>: The GeneCards database was used to find genes related to exosomes, and samples were categorized into groups with high and low expression levels based on these feature genes. Functional and pathway enrichment analyses (GO, KEGG, and GSEA) were used to investigate the possible biological mechanisms underlying feature genes. A predictive model was produced by using machine learning algorithms (LASSO regression, SVM, and random forest) to find disease-specific feature genes. Receiver operating characteristic (ROC) curve analysis was used to assess the model’s effectiveness. The diagnostic model showed excellent predictive accuracy through external data GSE83519 validation. <b>Results</b>: This analysis highlighted 22 genes with significant differential expression. A predictive model based on five important genes (<i>AGRN</i>, <i>TSPAN6</i>, <i>MMP9</i>, <i>HBA1</i>, and <i>PFN2</i>) was produced by using machine learning algorithms. <i>MMP9</i> and <i>TSPAN6</i> showed relatively high predictive performance. Using the ssGSEA algorithm, three key genes (<i>MMP9</i>, <i>AGRN</i>, and <i>PFN2</i>) were identified as strongly linked to immune regulation, immune response suppression, and critical signaling pathways involved in HNSCC progression. Matching HNSCC feature gene expression profiles with DSigDB compound signatures uncovered potential therapeutic targets. Molecular docking simulations identified ligands with high binding affinity and stability, notably C5 and Hoechst 33258, which were prioritized for further validation and potential drug development. <b>Conclusions</b>: This study employs a novel diagnostic model for HNSCC constructed using machine learning technology, which can provide support for the early diagnosis of HNSCC and thus contribute to improving patient treatment plans and clinical management strategies. |
| format | Article |
| id | doaj-art-fb537f3dea10411eaa8746b8542d9efd |
| institution | OA Journals |
| issn | 2227-9059 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomedicines |
| spelling | doaj-art-fb537f3dea10411eaa8746b8542d9efd2025-08-20T02:17:19ZengMDPI AGBiomedicines2227-90592025-03-0113478010.3390/biomedicines13040780Machine Learning-Driven Identification of Exosome-Related Genes in Head and Neck Squamous Cell Carcinoma for Prognostic Evaluation and Drug Response PredictionHua Cai0Liuqing Zhou1Yao Hu2Tao Zhou3Department of Otorhinolaryngology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, ChinaDepartment of Otorhinolaryngology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, ChinaDepartment of Otorhinolaryngology, The Central Hospital of Wuhan, Wuhan 430021, ChinaDepartment of Otorhinolaryngology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China<b>Background:</b> This study integrated four Gene Expression Omnibus (GEO) datasets to identify disease-specific feature genes in head and neck squamous cell carcinoma (HNSCC) through differential expression analysis with batch effect correction. <b>Methods</b>: The GeneCards database was used to find genes related to exosomes, and samples were categorized into groups with high and low expression levels based on these feature genes. Functional and pathway enrichment analyses (GO, KEGG, and GSEA) were used to investigate the possible biological mechanisms underlying feature genes. A predictive model was produced by using machine learning algorithms (LASSO regression, SVM, and random forest) to find disease-specific feature genes. Receiver operating characteristic (ROC) curve analysis was used to assess the model’s effectiveness. The diagnostic model showed excellent predictive accuracy through external data GSE83519 validation. <b>Results</b>: This analysis highlighted 22 genes with significant differential expression. A predictive model based on five important genes (<i>AGRN</i>, <i>TSPAN6</i>, <i>MMP9</i>, <i>HBA1</i>, and <i>PFN2</i>) was produced by using machine learning algorithms. <i>MMP9</i> and <i>TSPAN6</i> showed relatively high predictive performance. Using the ssGSEA algorithm, three key genes (<i>MMP9</i>, <i>AGRN</i>, and <i>PFN2</i>) were identified as strongly linked to immune regulation, immune response suppression, and critical signaling pathways involved in HNSCC progression. Matching HNSCC feature gene expression profiles with DSigDB compound signatures uncovered potential therapeutic targets. Molecular docking simulations identified ligands with high binding affinity and stability, notably C5 and Hoechst 33258, which were prioritized for further validation and potential drug development. <b>Conclusions</b>: This study employs a novel diagnostic model for HNSCC constructed using machine learning technology, which can provide support for the early diagnosis of HNSCC and thus contribute to improving patient treatment plans and clinical management strategies.https://www.mdpi.com/2227-9059/13/4/780exosomehead and neck squamous cell carcinomaprognosisimmune infiltrationbioinformatics |
| spellingShingle | Hua Cai Liuqing Zhou Yao Hu Tao Zhou Machine Learning-Driven Identification of Exosome-Related Genes in Head and Neck Squamous Cell Carcinoma for Prognostic Evaluation and Drug Response Prediction Biomedicines exosome head and neck squamous cell carcinoma prognosis immune infiltration bioinformatics |
| title | Machine Learning-Driven Identification of Exosome-Related Genes in Head and Neck Squamous Cell Carcinoma for Prognostic Evaluation and Drug Response Prediction |
| title_full | Machine Learning-Driven Identification of Exosome-Related Genes in Head and Neck Squamous Cell Carcinoma for Prognostic Evaluation and Drug Response Prediction |
| title_fullStr | Machine Learning-Driven Identification of Exosome-Related Genes in Head and Neck Squamous Cell Carcinoma for Prognostic Evaluation and Drug Response Prediction |
| title_full_unstemmed | Machine Learning-Driven Identification of Exosome-Related Genes in Head and Neck Squamous Cell Carcinoma for Prognostic Evaluation and Drug Response Prediction |
| title_short | Machine Learning-Driven Identification of Exosome-Related Genes in Head and Neck Squamous Cell Carcinoma for Prognostic Evaluation and Drug Response Prediction |
| title_sort | machine learning driven identification of exosome related genes in head and neck squamous cell carcinoma for prognostic evaluation and drug response prediction |
| topic | exosome head and neck squamous cell carcinoma prognosis immune infiltration bioinformatics |
| url | https://www.mdpi.com/2227-9059/13/4/780 |
| work_keys_str_mv | AT huacai machinelearningdrivenidentificationofexosomerelatedgenesinheadandnecksquamouscellcarcinomaforprognosticevaluationanddrugresponseprediction AT liuqingzhou machinelearningdrivenidentificationofexosomerelatedgenesinheadandnecksquamouscellcarcinomaforprognosticevaluationanddrugresponseprediction AT yaohu machinelearningdrivenidentificationofexosomerelatedgenesinheadandnecksquamouscellcarcinomaforprognosticevaluationanddrugresponseprediction AT taozhou machinelearningdrivenidentificationofexosomerelatedgenesinheadandnecksquamouscellcarcinomaforprognosticevaluationanddrugresponseprediction |