Datasets for results reproduction of Machat et al. 2020

The aim of this webpage is to provide the data used to evaluate the shape retrieval algorithms and the structural methods, as well as the ground truth files and the output dissimilarity matrices.

Abstract

The investigation of the structure of biological systems at the molecular level gives insight about their functions and dynamics. Shape and surface of biomolecules are fundamental to molecular recognition events. Characterizing their geometry can lead to more adequate predictions of their interactions. In the present work, we assess the performance of reference shape retrieval methods from the computer vision community on different protein shapes datasets.

Dataset and Ground Truth

Set A has been taken from the community benchmark SHREC 2019. The off format is downloadable here. The pdb format is downloadable here. The pcd format is downloadable here.