Skip to main content
Fig. 5 | Genome Biology

Fig. 5

From: Explainable multiview framework for dissecting spatial relationships from highly multiplexed data

Fig. 5

Importance signature and contrasts of IMC data from 46 breast cancer samples. A First two principal components of the importance signature of the samples colored by grade and clinical subtype, and importance of the variables of the signature in the principal component analysis (10 variables with the highest square cosine shown). The naming of the variables is in the form View_Predictor_Target, representing the estimated importance of the interaction between the predictor and target markers for the specific spatial context (view). B Intragroup contrast of importances of marker expression as predictors of the expression of each target marker between the intraview and paraview for grade 1 samples and between the intraview and paraview for grade 3 samples. C Change of the total number of estimated important interactions per grade (Importance ≥ 0.5). D Intergroup contrast of importances of marker expression as predictors of the expression of each target maker for the intraview and for the paraview between grade 1 and grade 3 samples

Back to article page