Proteomic profiling of extracellular vesicles allows for human breast cancer subtyping

Abstract

Extracellular vesicles (EVs) are a potential source of disease-associated biomarkers for diagnosis. In breast cancer, comprehensive analyses of EVs could yield robust and reliable subtype-specific biomarkers that are still critically needed to improve diagnostic routines and clinical outcome. Here, we show that proteome profiles of EVs secreted by different breast cancer cell lines are highly indicative of their respective molecular subtypes, even more so than the proteome changes within the cancer cells. Moreover, we detected molecular evidence for subtype-specific biological processes and molecular pathways, hyperphosphorylated receptors and kinases in connection with the disease, and compiled a set of protein signatures that closely reflect the associated clinical pathophysiology. These unique features revealed in our work, replicated in clinical material, collectively demonstrate the potential of secreted EVs to differentiate between breast cancer subtypes and show the prospect of their use as non-invasive liquid biopsies for diagnosis and management of breast cancer patients.

Keywords: Breast cancer; Mass spectrometry; Proteomic analysis.

Fig. 1

Extracellular vesicle isolation and characterization. a Cell lines used for EV isolation. b EV isolation and (phospho)proteomics workflow. c Cryo-EM images of purified MDAMB231 EVs and size distribution of the isolated vesicles determined using ImageJ software. d Comparative SDS-PAGE profile of a whole-cell lysate and an EV lysate. e Western blot of exosomal marker CD81 in the MDAMB231 EV lysate and whole-cell lysate (the full blot can be found in Supplementary Fig. 1)

Fig. 2

Mass spectrometry-based profiling of EV proteomes. EVs from 10 breast (cancer) cell lines (each n = 4 biologically independent samples) were analyzed by MS. a Bar plot of the total number of identified (black) and quantified (gray) proteins in EVs from each cell line. b Venn diagram of proteins identified in the EV samples compared with proteins annotated in the Exocarta and Vesiclepedia databases. c Gene ontology enrichment analysis of the EV proteins identified using the DAVID database. d Heatmap illustrating the enrichment of exosomal protein markers in the EVs compared with the whole-cell lysates based on their relative abundances

Fig. 3

EV proteomes stratify breast cancer by molecular subtype. a Principal component analysis (PCA). TNBC subtype cell line clusters distinctly from HER2-positive cell lines, MCF7, and MCF10A. Within each cell line, all biological replicates (n = 4 biologically independent samples) cluster close to each other. b Hierarchical clustering of Pearson correlations. Average correlations between biological replicates was >0.9, whereas average correlations between the same subtype cell lines was >0.7. c Heatmap of z-scored protein intensities of the differentially expressed EV-proteins (ANOVA, FDR<0.05) after unsupervised hierarchical clustering, and gene ontology analysis of proteins enriched in the TNBC- and HER2-positive EVs (see Supplementary Fig. 3). d Top gene sets enriched in EVs of the TNBC or HER2-positive BC subtype EVs, by GSEA. Proteins in each subset of EVs are ranked by GSEA based on their differential expression level. Whether a pre-specified pathway is significantly over-represented toward the top or bottom of the ranked gene list in each subtype is evaluated using the enrichment score (green line). Black vertical lines mark positions where members of a particular pathway appear in the ranked list of genes

Fig. 4

BC subtype-specific EV protein kinase networks. a Component of the Focal adhesion-PI3K-Akt-mTOR signaling pathway, and b components of the ErbB signaling pathway, visualized using PhosphoPath. Quantitative information for each EV subtype is featured in the accompanying boxes. Each box represents the median phosphosite intensity. The lines between nodes mark protein–protein interactions reported in Biogrid. Kinase-substrate interactions from PhosphositePlus are visualized by an arrow

Fig. 5

BC subtype-specific EV biomarker signatures. a Heatmap of subtype-specific EV protein markers (z-scored medians). b Functional enrichment analysis of the TNBC and HER2-positive EV subtype signatures using the ToppCluster tool (FDR correction, p-value < 0.05)

Fig. 6

Mapping of the EV subtype-specific signature proteins to human serum-derived EVs. Summed intensities of a subpanel of the TNBC- and HER2-signature proteins identified per patient-derived EVs (n = 5 biologically independent samples). Comparison of protein expression levels in each cancer type and healthy controls are given for four selected proteins per subtype-signature proteins (z-scored normalized Log₂ intensities). Light green triangles indicate low EV protein yield