Latent space mapping of interpretable structural coordinates from stochastic single-molecule signals
For nanopore sensing, this provides a paradigm shift from time-domain analysis to interpretable latent-space mapping, enabling robust molecule identification across devices.
Nanopore signals are distorted by stochastic translocation dynamics. The authors solve this by learning a latent-space mapping from simulated signals, enabling interpretable molecular coordinates and reducing computational cost by 1000x over alignment methods.
Nanopores are versatile single-molecular sensors, but their utility is fundamentally constrained by stochastic translocation dynamics warping any encoded information. We resolve it by shifting from time-domain analysis to a learned latent-space mapping via a contrastive encoder trained exclusively on simulated signals from a physics-informed model. This encoder maps solid-state nanopore signals of engineered DNA barcodes into an interpretable molecular coordinate system. The learned representation is responsive to structural barcode parameters while remaining invariant to acquisition conditions and translocation conformation, allowing data pooling across devices. Molecule identification requires a single pass through the encoder, reducing computational cost by three orders of magnitude relative to alignment-based methods. We experimentally validate through mixture quantification, rare-variant detection, consensus barcode reconstruction, and real-time signal acquisition. This shift from temporal analysis to mapping structural coordinates into a latent space changes the paradigm behind analyzing stochastic sensor signals by linking classification to interpretable encoded molecular information.