Fig. 3From: Structure-primed embedding on the transcription factor manifold enables transparent model architectures for gene regulatory network and latent activity inferenceTranscription factor activity in single cell yeast. TFA estimated from hierarchical SupirFactor model. Violin plots are generated by scaling [0, 1] the underlying measurement. AÂ Cell cycle TFs regulate gene expression in specific cell cycle phases, with the phase the TF regulates annotated on the right y-axis [45]. Cell cycle phase of each cell is inferred from transcriptome and annotated on the x-axis. Panel (i) plots TFA, and panel (ii) plots the RNA expression of the TF. BÂ Same as A. Dot size represents the percentage of cells with a non-zero value. Color represents log fold-change (log FC) across the cell cycle phases. Panel (i) plots TFA, and panel (ii) plots the RNA expression of the TF. C: Interacting TF pair Pearson correlation for SupirFactor TFA, Inferelator TFA, and TF expression. DÂ Comparing TFA between rapamyacin (RAPA) treated and untreated (YPD) cells TFs known to be activated by treatment [46] or known to be more active in untreated cells are annotated on the right y-axis. EÂ UMAP projection of the scY dataset showing TFA estimate of co-regulator TFs and growth conditionsBack to article page