Spectral Diffusion for Protein Dynamics

Hew Phipps, Matteo Cagiada, Santiago David Villalba, Charlotte Deane

Keywords: diffusion, fourier transform, spectral, spectral transform, stochastic interpolation, generative dynamics, protein dynamics, discrete cosine transform, molecular dynamics

TL;DR: We introduce the discrete cosine transform as a spectral representation of protein dynamics and train a diffusion model achieving strong results in capturing general protein dynamics

Abstract: Generative models present a promising alternative to expensive molecular dynamics for computationally querying protein dynamics, yet many existing approaches treat ensembles as unordered snapshots rather than temporally coherent trajectories. We present a new physics-informed representation using Fourier transforms as an inductive bias for the multiscale temporal nature of protein dynamics. Diffusion in the spectral domain allows for disentangling of dynamics into slow conformational modes and fast atomic jitter, enabling rapid, improved prediction of dynamics across a range of temperatures. This is facilitated by direct denoising of structure and temperature conditioned spectral volumes where the low frequencies encode per-residue flexibility. Trained on the mdCATH dataset, we evaluate our model, DynaMode, on a held-out test set achieving an RMSF pearson $r$ of $0.844$. However, we suffer from significantly more steric clashes than standard molecular dynamics, suggesting more explicit structural reasoning is necessary for state of the art dynamics emulation.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 76