Protein model quality assessment using rotation-equivariant transformations on point clouds.

Machine learning research concerning protein structure has seen a surge in popularity over the last years with promising advances for basic science and drug discovery. Working with macromolecular structure in a machine learning context requires an adequate numerical representation, and researchers have extensively studied representations such as graphs, discretized 3D grids, and distance maps. As part of CASP14, we explored a new and conceptually simple representation in a blind experiment: atoms as points in 3D, each with associated features.

Assessment of Patient Retention of Inpatient Care Information Post-Hospitalization.

Background: Patient understanding of medical care improves readmission rates and patient satisfaction, yet the literature suggests patients often have poor retention of care information post-hospitalization. Although multiple interventions have been implemented to facilitate this process, the cumulative durability of their benefit remains unclear. The authors conducted this study to more objectively understand how well patients retain care information after hospital discharge and to assess patient perspectives on facilitators of this process (for example, whiteboards and patient portals).