Treffer: TrackSegNet:A tool for trajectory segmentation into diffusive states using supervised deep learning

TrackSegNet is a command-line python program, which permits the classification and seg- mentation of trajectories into diffusive states. A deep neural network is trained for each particular case using synthetic data and trajectory features as inputs. After classification on the experimental data using the trained network, the trajectories are segmented and grouped per diffusive state. TrackSegNet further estimates the motion parameters (the diffusion constant and anomalous exponent ) for each segmented track using the mean squared displacement (MSD) analysis, and computes additional geometric measurements per tracklet state such as the angular distribution and velocity autocorrelation curve. The resulting segmentation and motion parameters are stored as CSV files. Originally developed for the quantification of protein dynamics using single-particle tracking imaging, its use can be extended to any type of trajectory dataset.