Skip to main content
Fig. 1 | Cell Communication and Signaling

Fig. 1

From: 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

Fig. 1

Classification efficiency based on the core and entire proteome. a t-SNE plot of the core proteome. b t-SNE plot of the entire proteome. The dots with different colors represent the 60 individual EV samples belonging to the nine tumor types. The color gradient in the plot indicates the dot density. c Confusion matrix of the classification results using the core proteome. d Confusion matrix of the classification results using the entire proteome. Each row of the matrices represents the instances in an actual class while each column represents the instances in a predicted class. Diagonally, the percentage of the correct classification is shown in blue. The percentage of errors is indicated in red

Back to article page

Cell Communication and Signaling

ISSN: 1478-811X