Fig. 4

Prioritizing drug combinations targeting transcriptionally-distinct subclones with CaDRReS-Sc. a Proportions of various transcriptionally distinct cell clusters (n=21) in head and neck cancer patient-derived cell lines. b Heatmap of predicted cell death percentages across cell clusters within each patient. c Comparison between predicted and observed drug response for five different drug combinations and patient-derived cells. Boxplots contrasting monotherapy (gray) and combinatorial therapy (orange) response based on d CaDRReS-Sc predictions and e experimental measurements. Error bars show 1 standard deviation (n=2–3), dashed lines indicate the best monotherapy, and asterisk symbols indicate drug combinations that show improvement. In general, relative response values for monotherapy and combinatorial therapy, as observed from experimental measurements, were also reflected in CaDRReS-Sc predictions. f Boxplots showing that drug combinations that were observed to improve over monotherapy (x-axis, no/low vs high determined based on median value in experiment) had significantly higher predicted improvements (combination over monotherapy) using CaDRReS-Sc as well (y-axis)