DeepTRACE: Flexible Machine Learning for Analysis and Discovery in Single Molecule Tracks

DeepTRACE is a machine learning tool for analysing long, complex single-molecule tracks in living cells; learning from sequences of molecular events using spatial, temporal, and photometric context. It traces how molecular processes unfold over time and space, incorporating past interactions, subcellular location, and photometric properties. DeepTRACE requires only a few hundred annotated tracks and minutes of CPU training, yet outperforms traditional methods and supports extensive downstream analysis, including the discovery of relationships absent from the training data.