Machine learning-based analysis of cancer cell-derived vesicular proteins revealed significant tumor-specificity and predictive potential of extracellular vesicles for cell invasion and proliferation – A meta-analysis
Abstract Background Although interest in the role of extracellular vesicles (EV) in oncology is growing, not all potential aspects have been investigated. In this meta-analysis, data regarding (i) the EV proteome and (ii) the invasion and proliferation capacity of the NCI-60 tumor cell lines (60 cel...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-11-01
|
| Series: | Cell Communication and Signaling |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12964-023-01344-5 |
| _version_ | 1827633639433699328 |
|---|---|
| author | Matyas Bukva Gabriella Dobra Edina Gyukity-Sebestyen Timea Boroczky Marietta Margareta Korsos David G. Meckes Peter Horvath Krisztina Buzas Maria Harmati |
| author_facet | Matyas Bukva Gabriella Dobra Edina Gyukity-Sebestyen Timea Boroczky Marietta Margareta Korsos David G. Meckes Peter Horvath Krisztina Buzas Maria Harmati |
| author_sort | Matyas Bukva |
| collection | DOAJ |
| description | Abstract Background Although interest in the role of extracellular vesicles (EV) in oncology is growing, not all potential aspects have been investigated. In this meta-analysis, data regarding (i) the EV proteome and (ii) the invasion and proliferation capacity of the NCI-60 tumor cell lines (60 cell lines from nine different tumor types) were analyzed using machine learning methods. Methods On the basis of the entire proteome or the proteins shared by all EV samples, 60 cell lines were classified into the nine tumor types using multiple logistic regression. Then, utilizing the Least Absolute Shrinkage and Selection Operator, we constructed a discriminative protein panel, upon which the samples were reclassified and pathway analyses were performed. These panels were validated using clinical data (n = 4,665) from Human Protein Atlas. Results Classification models based on the entire proteome, shared proteins, and discriminative protein panel were able to distinguish the nine tumor types with 49.15%, 69.10%, and 91.68% accuracy, respectively. Invasion and proliferation capacity of the 60 cell lines were predicted with R 2 = 0.68 and R 2 = 0.62 (p < 0.0001). The results of the Reactome pathway analysis of the discriminative protein panel suggest that the molecular content of EVs might be indicative of tumor-specific biological processes. Conclusion Integrating in vitro EV proteomic data, cell physiological characteristics, and clinical data of various tumor types illuminates the diagnostic, prognostic, and therapeutic potential of EVs. Video Abstract |
| first_indexed | 2024-03-09T15:03:21Z |
| format | Article |
| id | doaj.art-c69c12b1de26431fa3df709d00263c33 |
| institution | Directory Open Access Journal |
| issn | 1478-811X |
| language | English |
| last_indexed | 2024-03-09T15:03:21Z |
| publishDate | 2023-11-01 |
| publisher | BMC |
| record_format | Article |
| series | Cell Communication and Signaling |
| spelling | doaj.art-c69c12b1de26431fa3df709d00263c332023-11-26T13:50:09ZengBMCCell Communication and Signaling1478-811X2023-11-0121111710.1186/s12964-023-01344-5Machine learning-based analysis of cancer cell-derived vesicular proteins revealed significant tumor-specificity and predictive potential of extracellular vesicles for cell invasion and proliferation – A meta-analysisMatyas Bukva0Gabriella Dobra1Edina Gyukity-Sebestyen2Timea Boroczky3Marietta Margareta Korsos4David G. Meckes5Peter Horvath6Krisztina Buzas7Maria Harmati8Department of Immunology, Albert Szent-Györgyi Medical School, Faculty of Science and Informatics, University of SzegedDepartment of Immunology, Albert Szent-Györgyi Medical School, Faculty of Science and Informatics, University of SzegedDepartment of Immunology, Albert Szent-Györgyi Medical School, Faculty of Science and Informatics, University of SzegedDepartment of Immunology, Albert Szent-Györgyi Medical School, Faculty of Science and Informatics, University of SzegedDepartment of Immunology, Albert Szent-Györgyi Medical School, Faculty of Science and Informatics, University of SzegedDepartment of Biomedical Sciences, Florida State University College of MedicineLaboratory of Microscopic Image Analysis and Machine Learning, Institute of Biochemistry, Biological Research Centre, Hungarian Research Network (HUN-REN)Department of Immunology, Albert Szent-Györgyi Medical School, Faculty of Science and Informatics, University of SzegedDepartment of Immunology, Albert Szent-Györgyi Medical School, Faculty of Science and Informatics, University of SzegedAbstract Background Although interest in the role of extracellular vesicles (EV) in oncology is growing, not all potential aspects have been investigated. In this meta-analysis, data regarding (i) the EV proteome and (ii) the invasion and proliferation capacity of the NCI-60 tumor cell lines (60 cell lines from nine different tumor types) were analyzed using machine learning methods. Methods On the basis of the entire proteome or the proteins shared by all EV samples, 60 cell lines were classified into the nine tumor types using multiple logistic regression. Then, utilizing the Least Absolute Shrinkage and Selection Operator, we constructed a discriminative protein panel, upon which the samples were reclassified and pathway analyses were performed. These panels were validated using clinical data (n = 4,665) from Human Protein Atlas. Results Classification models based on the entire proteome, shared proteins, and discriminative protein panel were able to distinguish the nine tumor types with 49.15%, 69.10%, and 91.68% accuracy, respectively. Invasion and proliferation capacity of the 60 cell lines were predicted with R 2 = 0.68 and R 2 = 0.62 (p < 0.0001). The results of the Reactome pathway analysis of the discriminative protein panel suggest that the molecular content of EVs might be indicative of tumor-specific biological processes. Conclusion Integrating in vitro EV proteomic data, cell physiological characteristics, and clinical data of various tumor types illuminates the diagnostic, prognostic, and therapeutic potential of EVs. Video Abstracthttps://doi.org/10.1186/s12964-023-01344-5Extracellular vesiclesNCI-60InvasionProliferationClassificationPrediction |
| spellingShingle | Matyas Bukva Gabriella Dobra Edina Gyukity-Sebestyen Timea Boroczky Marietta Margareta Korsos David G. Meckes Peter Horvath Krisztina Buzas Maria Harmati Machine learning-based analysis of cancer cell-derived vesicular proteins revealed significant tumor-specificity and predictive potential of extracellular vesicles for cell invasion and proliferation – A meta-analysis Cell Communication and Signaling Extracellular vesicles NCI-60 Invasion Proliferation Classification Prediction |
| title | Machine learning-based analysis of cancer cell-derived vesicular proteins revealed significant tumor-specificity and predictive potential of extracellular vesicles for cell invasion and proliferation – A meta-analysis |
| title_full | Machine learning-based analysis of cancer cell-derived vesicular proteins revealed significant tumor-specificity and predictive potential of extracellular vesicles for cell invasion and proliferation – A meta-analysis |
| title_fullStr | Machine learning-based analysis of cancer cell-derived vesicular proteins revealed significant tumor-specificity and predictive potential of extracellular vesicles for cell invasion and proliferation – A meta-analysis |
| title_full_unstemmed | Machine learning-based analysis of cancer cell-derived vesicular proteins revealed significant tumor-specificity and predictive potential of extracellular vesicles for cell invasion and proliferation – A meta-analysis |
| title_short | Machine learning-based analysis of cancer cell-derived vesicular proteins revealed significant tumor-specificity and predictive potential of extracellular vesicles for cell invasion and proliferation – A meta-analysis |
| title_sort | machine learning based analysis of cancer cell derived vesicular proteins revealed significant tumor specificity and predictive potential of extracellular vesicles for cell invasion and proliferation a meta analysis |
| topic | Extracellular vesicles NCI-60 Invasion Proliferation Classification Prediction |
| url | https://doi.org/10.1186/s12964-023-01344-5 |
| work_keys_str_mv | AT matyasbukva machinelearningbasedanalysisofcancercellderivedvesicularproteinsrevealedsignificanttumorspecificityandpredictivepotentialofextracellularvesiclesforcellinvasionandproliferationametaanalysis AT gabrielladobra machinelearningbasedanalysisofcancercellderivedvesicularproteinsrevealedsignificanttumorspecificityandpredictivepotentialofextracellularvesiclesforcellinvasionandproliferationametaanalysis AT edinagyukitysebestyen machinelearningbasedanalysisofcancercellderivedvesicularproteinsrevealedsignificanttumorspecificityandpredictivepotentialofextracellularvesiclesforcellinvasionandproliferationametaanalysis AT timeaboroczky machinelearningbasedanalysisofcancercellderivedvesicularproteinsrevealedsignificanttumorspecificityandpredictivepotentialofextracellularvesiclesforcellinvasionandproliferationametaanalysis AT mariettamargaretakorsos machinelearningbasedanalysisofcancercellderivedvesicularproteinsrevealedsignificanttumorspecificityandpredictivepotentialofextracellularvesiclesforcellinvasionandproliferationametaanalysis AT davidgmeckes machinelearningbasedanalysisofcancercellderivedvesicularproteinsrevealedsignificanttumorspecificityandpredictivepotentialofextracellularvesiclesforcellinvasionandproliferationametaanalysis AT peterhorvath machinelearningbasedanalysisofcancercellderivedvesicularproteinsrevealedsignificanttumorspecificityandpredictivepotentialofextracellularvesiclesforcellinvasionandproliferationametaanalysis AT krisztinabuzas machinelearningbasedanalysisofcancercellderivedvesicularproteinsrevealedsignificanttumorspecificityandpredictivepotentialofextracellularvesiclesforcellinvasionandproliferationametaanalysis AT mariaharmati machinelearningbasedanalysisofcancercellderivedvesicularproteinsrevealedsignificanttumorspecificityandpredictivepotentialofextracellularvesiclesforcellinvasionandproliferationametaanalysis |