Abstract Recent technological developments allow us to measure the status of dozens of proteins in individual cells. This opens the way to understand the heterogeneity of complex multi-signaling networks across cells and cell-types, with important implications to understand and treat diseases such as cancer. These technologies are however limited to proteins for which antibodies are available and are fairly costly, making predictions of new markers and of existing markers under new conditions a valuable alternative. To assess our capacity to make such predictions and boost further methodological development, we organised the Single Cell Signaling in Breast Cancer DREAM challenge. We used a mass cytometry data set, covering 36 markers in over 4,000 conditions totalling 80 million single cells across 67 breast cancer cell lines. Through four increasingly difficult subchallenges, the participants predicted missing markers, new conditions, and the time course response of single cells to stimuli in the presence and absence of kinase inhibitors. The challenge results show that despite the stochastic nature of signal transduction in single cells, the signaling events are tightly controlled and machine learning methods can accurately predict new experimental data. Graphical Abstract Key points Over 80 million single-cell multiplexed measurements across 67 cell lines, 54 conditions and 10 time points to benchmark predictive models of single cell signaling 73 approaches from 27 teams for predicting response to kinase inhibitors on single cell level, and dynamic response from unperturbed basal omics data Predictions of single marker models correlate with measurements with a correlation coefficient of 0.76 Top models of whole signaling response models perform almost as well as a biological replicate Cell-line specific variation in dynamics can be predicted from basal omics

Cell-to-cell and type-to-type heterogeneity of signaling networks: Insights from the crowd