Extended Data Fig. 3: MAGIK estimates local and global anomalous diffusion properties at the ensemble and single-object levels.
From: Geometric deep learning reveals the spatiotemporal features of microscopic motion
a, Simulated single-object tracking experiment. Fluorescence microscopy is used to follow the motion of single molecules characterized by a fractional Brownian motion (FBM) with varying anomalous diffusion exponent α. Scale bar = 20 px. b-c, Ground-truth and predicted graphs. Edges depict the network of associations used to directly infer dynamic properties without explicit linking. Nodes are colour-coded according to the value of the target feature α. The predicted node values agree with the ground truth also in crowded areas (for example, zoomed regions I and II). d, Probability distribution of the predicted vs. ground-truth anomalous diffusion exponent α. e-h, MAGIK estimates the relative fraction of objects following different diffusion modes, that is, sub- (0.2≤α≤0.6), normal (α = 1) and superdiffusion (1.4≤α≤1.8). e-g, Probability distribution of predicted vs. ground-truth fraction for subdiffusion, normal diffusion, and superdiffusion, respectively. h Confusion matrix demonstrating how the network classifies the underlying diffusion model exhibited by objects in 1199 validation videos. Column-based normalization is applied, such as the sum along the columns adds up to 1, with minor deviations due to rounding.
