Inferring disease progression stages in single-cell transcriptomics using a weakly supervised deep learning approach

(Downloading may take up to 30 seconds. If the slide opens in your browser, select File -> Save As to save it.)

Click on image to view larger version.

Figure 4.
Figure 4.

Inference of response to DHT treatment in brain organoids by weakly supervised deep learning. (A) Histograms of DHT response score in DHT- and mock-treated organoids. Dashed line is a threshold to define DHT-responsive cells (DHT response score > 0.55). (B) UMAP plot of single cells colored by organoid type (left), DHT response (middle), and cluster (right): (N) neuron, (G) glia. (C) UMAP plot showing representative gene expression for each cell type. (D) Ratio of cells from DHT-treated and mock-treated organoids (left) and DHT- and nonresponded cells (right) in each cell type. (E) Representative differentially expressed genes in N3 and G5 cluster between DHT- and mock-treated cells (left) and between DHT- and nonresponded cells (right). Circle size represent log2(ratio).

This Article

  1. Genome Res. 35: 135-146

Preprint Server