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.

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 R2 = 0.68 and R2 = 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.

Impact of Experimental Conditions on Extracellular Vesicles' Proteome: A Comparative Study.

Extracellular vesicle (EV) research is a rapidly developing field, mainly due to the key role of EVs in intercellular communication and pathophysiological processes. However, the heterogeneity of EVs challenges their exploration and the establishment of gold-standard methods. Here, we aimed to reveal the influence of technical changes on EV biology and the reliability of experimental data. We used B16F1 melanoma cells as a model and applied nanoparticle tracking analysis, mass spectrometry (LC-MS/MS) and pathway enrichment analysis to analyze the quantity, size distribution, proteome and function of their small EVs (sEVs) produced in sEV-depleted fetal bovine serum (FBS)-containing medium or serum-free medium. Additionally, we investigated the effects of minor technical variances on the quality of sEV preparations. We found that storage of the isolates at -80 °C has no adverse effect on LC-MS/MS analysis, and an additional washing step after differential ultracentrifugation has a minor influence on the sEV proteome. In contrast, FBS starvation affects the production and proteome of sEVs; moreover, these vesicles may have a greater impact on protein metabolism, but a smaller impact on cell adhesion and membrane raft assembly, than the control sEVs. As we demonstrated that FBS starvation has a strong influence on sEV biology, applying serum-free conditions might be considered in in vitro sEV studies.

The role of the metabolite cargo of extracellular vesicles in tumor progression.

Metabolomic reprogramming in tumor and stroma cells is a hallmark of cancer but understanding its effects on the metabolite composition and function of tumor-derived extracellular vesicles (EVs) is still in its infancy. EVs are membrane-bound sacs with a complex molecular composition secreted by all living cells. They are key mediators of intercellular communication both in normal and pathological conditions and play a crucial role in tumor development. Although lipids are major components of EVs, most of the EV cargo studies have targeted proteins and nucleic acids. The potential of the EV metabolome as a source for biomarker discovery has gained recognition recently, but knowledge on the biological activity of tumor EV metabolites still remains limited. Therefore, we aimed (i) to compile the list of metabolites identified in tumor EVs isolated from either clinical specimens or in vitro samples and (ii) describe their role in tumor progression through literature search and pathway analysis.