OsterlundJBC_Figure S7

Figure S7 data Includes: -Panel C, 20000 single cell red channel images were randomly selected from the total dataset to show the distribution of landmarks in tSNE space. -Panel D, Confusion Matrix, plotting Predicted versus True(known localization of the red channel landmark) labels for the validation set of Red channel single cell images, which were not included in the initial training step. -Panel E, Example single cell images, randomly selected for each landmark.

PanelF-G, "RedCh" indicates Red channel. "PredictedLabel" indicates the label predicted by the classifier. "TrueLabel" indicates the ground truth label (known from the Platemap for each landmark in the Red Channel). The original image dataset was too large to upload here. Only classification results from combined 3 replicates are shown.