mdCATH: A Large-Scale MD Dataset for Data-Driven Computational Biophysics

Preprint from the De Fabritiis lab introducing a dataset of all-atom molecular dynamics simulations for 5,398 protein domains, modeled with a state-of-the-art classical force field, and simulated in five replicates each at five temperatures from 320 K to 413 K. They record coordinates and forces every 1 ns, for over 62 ms of accumulated simulation time.

https://arxiv.org/abs/2407.14794

2