Track genomics, neuroscience and molecular biology.
Search papers, labs, and topics across Lattice.
PepTIDE addresses the challenge of modeling peptide dynamics by introducing a multi-scale temporal framework that explicitly accounts for varying temporal resolutions within a single generative model. By training on windows with dynamically sampled strides and incorporating an Adaptive Physical-Time Embedding, the model learns an interval-aware velocity field, enabling it to capture sparse transition frames between metastable states. This approach achieves state-of-the-art distribution agreement and structural validity on benchmark datasets, demonstrating improved fidelity in reproducing inter-state fluxes.
Generative models can now accurately capture rare peptide conformational transitions by jointly modeling dynamics across multiple temporal scales.
Peptides occupy a particularly challenging regime of biomolecular dynamics. Short peptides lack a stable folded core and populate broad conformational ensembles, while cyclization adds ring closure, non-local residue coupling, and stereochemical diversity. Deep generative models have made remarkable progress in emulating molecular-dynamics trajectories directly, yet each is trained on windows cut at a fixed interval and therefore observes the process at a fixed temporal resolution. More fundamentally, none takes that interval as an input, so the physical time a window spans is never represented, leaving the sparse frames on which a peptide crosses between metastable states difficult to learn. Here, we introduce PepTIDE, a multi-scale temporal framework for peptide trajectory generation. The stride of each training window is drawn from a continuous range, so one model observes the same dynamics at many temporal resolutions, and an Adaptive Physical-Time Embedding encodes the relative interval of a window together with the absolute time of each frame, making the shared velocity field interval-aware. All frames are generated jointly through a stochastic-interpolant flow, and pair-aware invariant point attention captures the geometry and topology of both linear and cyclic peptides. On PepMD and a 50-system cyclic-peptide benchmark, PepTIDE reaches state-of-the-art distribution agreement and structural validity. Read in temporal order, its trajectories recover these sparse transition frames and reproduce inter-state fluxes more faithfully, confirming that modeling multiple temporal scales is what makes these rare events accessible.