Trained only with subject-level labels, NaroNet discovers phenotypes, neighborhoods, and areas with the highest influence when classifying subject types.
Could you please explain how the figures generated by the BioInsights component should be distinguished?
More specifically, in the "BioInsights/Cell type characterization/Phenotypes" folder, there are 9 figures on heatmap Marker Expression Colocalization with 3 different normalization methods and 3 different thresholds, I suppose. Which normalization method should be analyzed when predicting with NaroNet and which one was added in the base paper?
This is similar to the "heatmap Marker Expression" figures and the "heatmap_Phenotype_composition_of_neighborhoods" figures in the Neighbourhoods folder. Could you please explain how the thresholds were used?
Hello!
Could you please explain how the figures generated by the BioInsights component should be distinguished?
More specifically, in the "BioInsights/Cell type characterization/Phenotypes" folder, there are 9 figures on heatmap Marker Expression Colocalization with 3 different normalization methods and 3 different thresholds, I suppose. Which normalization method should be analyzed when predicting with NaroNet and which one was added in the base paper?
This is similar to the "heatmap Marker Expression" figures and the "heatmap_Phenotype_composition_of_neighborhoods" figures in the Neighbourhoods folder. Could you please explain how the thresholds were used?
Thanks in advance!