NMR as a Video-(Game): Constructing Super-Resolution Cross-Peak Trajectories in Protein Spectroscopy

Objective: High-resolution multidimensional NMR spectroscopy of proteins remains limited by long acquisition times, sensitivity constraints, and severe peak overlap, particularly for larger systems. Conventional 3D and higher-dimensional experiments trade experimental efficiency for resolution, while post-acquisition analysis often becomes the dominant bottleneck. Methods: Here, we present a new framework that redefines both how NMR experiments are constructed and how they are executed and analyzed, by treating an AI agent-controllable series of 2D spectra as a spatiotemporal dataset analogous to a video. Our approach is based on temperature-dependent series of reduced-dimensionality 2D HSQC and novel RDL-TROSY experiments, in which each 2D 1H,15N cross-peak is controllably shifted and split in proportion to the 13C chemical shift of the J-coupled carbons. We propose treating a variable-temperature (VT) series as a pseudo-temporal video sequence in which each cross-peak traces a physically motivated trajectory through frequency space. The proportionality coefficient (α) of this reduced-dimensionality encoding is systematically and programmatically varied together with the temperature providing full control for constructing optimal cross-peak trajectories. As a result, individual resonances follow predictable, spectral acquisition time-controllable trajectories in the 2D spectral plane across the series, which can be executed by an autonomous AI agent directly interacting with the NMR GUI layer. Each spectrum represents a single “frame,” while temperature and RD controls serve as the temporal dimension. We describe two complementary super-resolution strategies: a cross-peak model-independent approach based on deep-learning video super-resolution that leverages temporal redundancy to sharpen per-frame peak shapes, and a model-based approach that derives the exact mathematical form of the peak trajectories and uses it to design acquisition schedules that render individual peak paths maximally distinct and amenable for algorithmic deconvolution. Results and Discussion: As a result, we obtained full backbone resonance assignment in the wide temperature range (279–318 K) with one degree Kelvin resolution in a test protein in an automatic manner in the time frame typically required for collection of a single 3D NMR dataset. Conclusions: The VT-NMR experiment is reconceptualised as a video processing problem, with the temperature axis acting as a pseudo-temporal dimension that enables inter-frame pooling to resolve peaks not resolved in any single spectrum. The RD-HSQC provides simultaneous spectral, temporal, and topological discrimination. The agnostic super-resolution strategy improves per-frame quality without physical assumptions, while the model-based strategy uses spectral-width modulation to convert 13Cα diversity into engineered inter-trajectory separation. A formal scoring function, a selective intensity-control pulse sequence element, and an agentic design loop together enable fully automated acquisition optimisation. The framework is protein-independent and outputs an acquisition schedule calibrated to the specific assignment problem.