Identification of novel molecular subtypes and construction of a prognostic signature via multi-omics analysis and machine learning in lung adenocarcinoma
IntroductionThe development of high-throughput sequencing technologies and targeted therapeutic strategies has significantly improved the prognosis of lung adenocarcinoma (LUAD) patients with sensitive gene mutations. However, patients harboring rare or no actionable mutations were rarely benefit fr...
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-07-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2025.1590216/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839622848248807424 |
|---|---|
| author | Ke Ma Jie Xu Jie Xu Congyue Wang Congyue Wang Xu Cao Xu Cao Wenjie Yu Jingjing Xi Xuan Zhang Jiamin Zhan Yang Liu Aoyang Yu Aoyang Yu Shuhan Liu Yanhua Liu Yanhua Liu Chong Chen Chong Chen Xiaoli Mai Xiaoli Mai |
| author_facet | Ke Ma Jie Xu Jie Xu Congyue Wang Congyue Wang Xu Cao Xu Cao Wenjie Yu Jingjing Xi Xuan Zhang Jiamin Zhan Yang Liu Aoyang Yu Aoyang Yu Shuhan Liu Yanhua Liu Yanhua Liu Chong Chen Chong Chen Xiaoli Mai Xiaoli Mai |
| author_sort | Ke Ma |
| collection | DOAJ |
| description | IntroductionThe development of high-throughput sequencing technologies and targeted therapeutic strategies has significantly improved the prognosis of lung adenocarcinoma (LUAD) patients with sensitive gene mutations. However, patients harboring rare or no actionable mutations were rarely benefit from these targeted therapies. This study aimed to identify novel molecular subtypes and construct a prognostic signature to enhance the stratification of LUAD prognosis.Materials and methodsNovel molecular subtypes of LUAD patients were identified by applying 10 distinct clustering algorithms on multi-omics data. Single-cell RNA-sequencing (scRNA-seq) data were integrated to characterize subtype-specific immune microenvironments. A multi-omics and machine learning-driven prognostic signature (MO-MLPS) was constructed in The Cancer Genome Atlas (TCGA) LUAD dataset using ten machine learning algorithms and subsequently validated across six independent datasets from the Gene Expression Omnibus (GEO) database. The robustness of the model was assessed using the concordance index (C-index), Kaplan-Meier survival analyses, receiver operating characteristic (ROC) curves, and both univariate and multivariate Cox regression analyses. We further confirmed the effects of ANLN knockdown and the expression of a domain-negative anillin protein (dnANLN) via western blotting, cell proliferation assays, flow cytometry, and transwell migration assays in vitro.ResultsOur analysis revealed that the novel molecular subtypes exhibited differences in prognoses, biological functions, and immune infiltration profiles in LUAD. The MO-MLPS was successfully established and validated across TCGA-LUAD cohorts, six independent GEO datasets, and their composite meta-cohort. Higher risk scores from the MO-MLPS correlated with poorer prognosis in LUAD, with AUC values exceeding 0.5 at 1, 3, and 5 years across various cohorts. The signature outperformed 49 previously published prognostic signatures. Furthermore, patients classified as high risk exhibited significantly worse overall and progression-free survival than those classified as low risk. Notably, ANLN knockdown and dnANLN expression significantly inhibited cell proliferation and migration in vitro and enhanced the efficacy of docetaxel.ConclusionA comprehensive analysis of multi-omics data redefines the molecular subtype of LUAD patients. The MO-MLPS derived from subtype characteristics has the potential to serve as a clinically valuable prognostic tool. Furthermore, ANLN emerges as a promising novel therapeutic target in the treatment of LUAD. |
| format | Article |
| id | doaj-art-cd53d1c68f9f4c8fba8f8cf8545a66e9 |
| institution | Matheson Library |
| issn | 2234-943X |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj-art-cd53d1c68f9f4c8fba8f8cf8545a66e92025-07-21T14:32:00ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2025-07-011510.3389/fonc.2025.15902161590216Identification of novel molecular subtypes and construction of a prognostic signature via multi-omics analysis and machine learning in lung adenocarcinomaKe Ma0Jie Xu1Jie Xu2Congyue Wang3Congyue Wang4Xu Cao5Xu Cao6Wenjie Yu7Jingjing Xi8Xuan Zhang9Jiamin Zhan10Yang Liu11Aoyang Yu12Aoyang Yu13Shuhan Liu14Yanhua Liu15Yanhua Liu16Chong Chen17Chong Chen18Xiaoli Mai19Xiaoli Mai20Department of Radiology, Nanjing Drum Tower Hospital Clinical College of Xuzhou Medical University, Nanjing, Jiangsu, ChinaInstitute of Hematology, Xuzhou Medical University, Xuzhou, Jiangsu, ChinaDepartment of Oncology, The Second Affiliated Hospital of Shandong First Medical University, Taian, Shandong, ChinaInstitute of Hematology, Xuzhou Medical University, Xuzhou, Jiangsu, ChinaDepartment of Hematology, General Hospital of Xuzhou Mining Group, The Second Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, ChinaInstitute of Hematology, Xuzhou Medical University, Xuzhou, Jiangsu, ChinaDepartment of Oncology, The Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, ChinaInstitute of Hematology, Xuzhou Medical University, Xuzhou, Jiangsu, ChinaInstitute of Hematology, Xuzhou Medical University, Xuzhou, Jiangsu, ChinaInstitute of Hematology, Xuzhou Medical University, Xuzhou, Jiangsu, ChinaInstitute of Hematology, Xuzhou Medical University, Xuzhou, Jiangsu, ChinaInstitute of Hematology, Xuzhou Medical University, Xuzhou, Jiangsu, ChinaInstitute of Hematology, Xuzhou Medical University, Xuzhou, Jiangsu, ChinaDepartment of Oncology, The Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, ChinaDepartment of Radiology, Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, Jiangsu, ChinaInstitute of Hematology, Xuzhou Medical University, Xuzhou, Jiangsu, ChinaDepartment of Oncology, Xuzhou Central Hospital Affiliated to Xuzhou Medical University, Xuzhou, Jiangsu, ChinaInstitute of Hematology, Xuzhou Medical University, Xuzhou, Jiangsu, ChinaDepartment of Hematology, The Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, ChinaDepartment of Radiology, Nanjing Drum Tower Hospital Clinical College of Xuzhou Medical University, Nanjing, Jiangsu, ChinaDepartment of Radiology, Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, Jiangsu, ChinaIntroductionThe development of high-throughput sequencing technologies and targeted therapeutic strategies has significantly improved the prognosis of lung adenocarcinoma (LUAD) patients with sensitive gene mutations. However, patients harboring rare or no actionable mutations were rarely benefit from these targeted therapies. This study aimed to identify novel molecular subtypes and construct a prognostic signature to enhance the stratification of LUAD prognosis.Materials and methodsNovel molecular subtypes of LUAD patients were identified by applying 10 distinct clustering algorithms on multi-omics data. Single-cell RNA-sequencing (scRNA-seq) data were integrated to characterize subtype-specific immune microenvironments. A multi-omics and machine learning-driven prognostic signature (MO-MLPS) was constructed in The Cancer Genome Atlas (TCGA) LUAD dataset using ten machine learning algorithms and subsequently validated across six independent datasets from the Gene Expression Omnibus (GEO) database. The robustness of the model was assessed using the concordance index (C-index), Kaplan-Meier survival analyses, receiver operating characteristic (ROC) curves, and both univariate and multivariate Cox regression analyses. We further confirmed the effects of ANLN knockdown and the expression of a domain-negative anillin protein (dnANLN) via western blotting, cell proliferation assays, flow cytometry, and transwell migration assays in vitro.ResultsOur analysis revealed that the novel molecular subtypes exhibited differences in prognoses, biological functions, and immune infiltration profiles in LUAD. The MO-MLPS was successfully established and validated across TCGA-LUAD cohorts, six independent GEO datasets, and their composite meta-cohort. Higher risk scores from the MO-MLPS correlated with poorer prognosis in LUAD, with AUC values exceeding 0.5 at 1, 3, and 5 years across various cohorts. The signature outperformed 49 previously published prognostic signatures. Furthermore, patients classified as high risk exhibited significantly worse overall and progression-free survival than those classified as low risk. Notably, ANLN knockdown and dnANLN expression significantly inhibited cell proliferation and migration in vitro and enhanced the efficacy of docetaxel.ConclusionA comprehensive analysis of multi-omics data redefines the molecular subtype of LUAD patients. The MO-MLPS derived from subtype characteristics has the potential to serve as a clinically valuable prognostic tool. Furthermore, ANLN emerges as a promising novel therapeutic target in the treatment of LUAD.https://www.frontiersin.org/articles/10.3389/fonc.2025.1590216/fullsingle-cell RNA sequencinglung adenocarcinomamulti-omicsprognostic signaturemachine learning |
| spellingShingle | Ke Ma Jie Xu Jie Xu Congyue Wang Congyue Wang Xu Cao Xu Cao Wenjie Yu Jingjing Xi Xuan Zhang Jiamin Zhan Yang Liu Aoyang Yu Aoyang Yu Shuhan Liu Yanhua Liu Yanhua Liu Chong Chen Chong Chen Xiaoli Mai Xiaoli Mai Identification of novel molecular subtypes and construction of a prognostic signature via multi-omics analysis and machine learning in lung adenocarcinoma Frontiers in Oncology single-cell RNA sequencing lung adenocarcinoma multi-omics prognostic signature machine learning |
| title | Identification of novel molecular subtypes and construction of a prognostic signature via multi-omics analysis and machine learning in lung adenocarcinoma |
| title_full | Identification of novel molecular subtypes and construction of a prognostic signature via multi-omics analysis and machine learning in lung adenocarcinoma |
| title_fullStr | Identification of novel molecular subtypes and construction of a prognostic signature via multi-omics analysis and machine learning in lung adenocarcinoma |
| title_full_unstemmed | Identification of novel molecular subtypes and construction of a prognostic signature via multi-omics analysis and machine learning in lung adenocarcinoma |
| title_short | Identification of novel molecular subtypes and construction of a prognostic signature via multi-omics analysis and machine learning in lung adenocarcinoma |
| title_sort | identification of novel molecular subtypes and construction of a prognostic signature via multi omics analysis and machine learning in lung adenocarcinoma |
| topic | single-cell RNA sequencing lung adenocarcinoma multi-omics prognostic signature machine learning |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2025.1590216/full |
| work_keys_str_mv | AT kema identificationofnovelmolecularsubtypesandconstructionofaprognosticsignatureviamultiomicsanalysisandmachinelearninginlungadenocarcinoma AT jiexu identificationofnovelmolecularsubtypesandconstructionofaprognosticsignatureviamultiomicsanalysisandmachinelearninginlungadenocarcinoma AT jiexu identificationofnovelmolecularsubtypesandconstructionofaprognosticsignatureviamultiomicsanalysisandmachinelearninginlungadenocarcinoma AT congyuewang identificationofnovelmolecularsubtypesandconstructionofaprognosticsignatureviamultiomicsanalysisandmachinelearninginlungadenocarcinoma AT congyuewang identificationofnovelmolecularsubtypesandconstructionofaprognosticsignatureviamultiomicsanalysisandmachinelearninginlungadenocarcinoma AT xucao identificationofnovelmolecularsubtypesandconstructionofaprognosticsignatureviamultiomicsanalysisandmachinelearninginlungadenocarcinoma AT xucao identificationofnovelmolecularsubtypesandconstructionofaprognosticsignatureviamultiomicsanalysisandmachinelearninginlungadenocarcinoma AT wenjieyu identificationofnovelmolecularsubtypesandconstructionofaprognosticsignatureviamultiomicsanalysisandmachinelearninginlungadenocarcinoma AT jingjingxi identificationofnovelmolecularsubtypesandconstructionofaprognosticsignatureviamultiomicsanalysisandmachinelearninginlungadenocarcinoma AT xuanzhang identificationofnovelmolecularsubtypesandconstructionofaprognosticsignatureviamultiomicsanalysisandmachinelearninginlungadenocarcinoma AT jiaminzhan identificationofnovelmolecularsubtypesandconstructionofaprognosticsignatureviamultiomicsanalysisandmachinelearninginlungadenocarcinoma AT yangliu identificationofnovelmolecularsubtypesandconstructionofaprognosticsignatureviamultiomicsanalysisandmachinelearninginlungadenocarcinoma AT aoyangyu identificationofnovelmolecularsubtypesandconstructionofaprognosticsignatureviamultiomicsanalysisandmachinelearninginlungadenocarcinoma AT aoyangyu identificationofnovelmolecularsubtypesandconstructionofaprognosticsignatureviamultiomicsanalysisandmachinelearninginlungadenocarcinoma AT shuhanliu identificationofnovelmolecularsubtypesandconstructionofaprognosticsignatureviamultiomicsanalysisandmachinelearninginlungadenocarcinoma AT yanhualiu identificationofnovelmolecularsubtypesandconstructionofaprognosticsignatureviamultiomicsanalysisandmachinelearninginlungadenocarcinoma AT yanhualiu identificationofnovelmolecularsubtypesandconstructionofaprognosticsignatureviamultiomicsanalysisandmachinelearninginlungadenocarcinoma AT chongchen identificationofnovelmolecularsubtypesandconstructionofaprognosticsignatureviamultiomicsanalysisandmachinelearninginlungadenocarcinoma AT chongchen identificationofnovelmolecularsubtypesandconstructionofaprognosticsignatureviamultiomicsanalysisandmachinelearninginlungadenocarcinoma AT xiaolimai identificationofnovelmolecularsubtypesandconstructionofaprognosticsignatureviamultiomicsanalysisandmachinelearninginlungadenocarcinoma AT xiaolimai identificationofnovelmolecularsubtypesandconstructionofaprognosticsignatureviamultiomicsanalysisandmachinelearninginlungadenocarcinoma |