The neural network relies on cell order in pseudotime and gene expression strength. A) Training new models of DELAY on increasing numbers of pseudotime-lagged matrices gives the largest performance increase when using up to a single lag. B) Reordering single cells in pseudotime sharply decreases performance, suggesting that DELAY relies on the specific ordering of adjacent cells in each trajectory. C and D) The network is sensitive to random down-sampling of cells across data sets (C) but relatively more robust to induced, additional gene dropouts in weakly expressing cells (D), suggesting that DELAY relies heavily on highly expressing cells. E and F) The network learns larger input weights for lagged matrices of the first pseudotime lag (E), which also contain more cells in the combined “ON” region (⁠$AON∪BON$⁠; dotted outline, F) on average across training data sets (dotted line, E). The combined “ON” region is comprised of the upper-left “ON–OFF” quadrant (⁠$AON∩BOFF$⁠), upper-right “ON–ON” quadrant (⁠$AON∩BON$⁠), and lower-right “OFF–ON” quadrant (⁠$AOFF∩BON$⁠). G) Masking different regions of the input matrices shows that the network relies heavily on the combined “ON” region. The lines and shaded regions in A–E) show the average and full range of values across five model replicates, and the markers in G) show the average values across model replicates. The statistical significance in G) was assessed with a Kruskal–Wallis test (***P ≤ 0.001).