Variable deep learning training horizons reveal the temporal complexity of biological systems

The increasing quantity of time-series images presents new opportunities for extracting biological insights from data. Here, we introduce a deep learning framework with a variable input sequence length to predict cell and colony morphologies. We apply this framework to <i>in silico</i> and <i>in vitro</i> microscopy datasets, evaluating the impact of temporal data on performance. We find that while performance increases monotonically with increasing <i>in silico</i> training data, performance is varied in the <i>in vitro</i> case studies. The varying results reflect the intrinsic challenges stochastic, complex biological systems pose to data-driven modeling, and offer a new method through which we can identify biological transition points using temporal dynamics.