Modified Solvated Protein Fragments Dataset

The "Solvated Protein Fragments" dataset[i],[ii]probes many-body intermolecular interactions between "protein fragments" and water molecules, which are important for the description of many biologically relevant condensed phase system. In total, the dataset provides reference energies, forces, and dipole moments for 2,731,180 structures.This sub-dataset was extracted from this original by only containing structures with all the C, N, H, O, S elements, molecules, hydroxide (OH) and methylidyne radical (CH), and carbon monoxide (CO) related structures that can be included in available molecules reaching 1gb in size and 721662 different molecules. [i] Unke, O. T. and Meuwly, M. "PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges" arxiv:1902.08408 (2019). [ii] Unke, O.T. and Meuwly, M. (2019). Solvated protein fragments dataset. Zenodo. http://doi.org/10.5281/zenodo.2605372