Protein Shape Retrieval Contest

Florent Langenfeld, Απόστολος Αξενόπουλος, Halim Benhabiles, Petros Daras, Andrea Giachetti, Xusi Han, Karim Hammoudi, Daisuke Kihara, Tuan Lai, Haiguang Liu, Mahmoud Melkemi, Stelios Mylonas, Genki Terashi, Yufan Wang, Féryal Windal, Matthieu MontèsZenodo 2019 · DOI

Abstract

This track aimed at retrieving protein evolutionary classification based on their surfaces meshes only. Given that proteins are dynamic, non-rigid objects and that evolution tends to conserve patterns related to their activity and function, this track offers a challenging issue using biologically relevant molecules. We evaluated the performance of 5 different algorithms and analyzed their ability, over a dataset of 5,298 objects, to retrieve various conformations of identical proteins and various conformations of ortholog proteins (proteins from different organisms and showing the same activity). All methods were able to retrieve a member of the same class as the query in at least 94% of the cases when considering the first match, but show more divergent when more matches were considered. Last, similarity metrics trained on databases dedicated to proteins improved the results.
BibTeX
@inproceedings{langenfeld2019protein,
  author = {Florent Langenfeld and Απόστολος Αξενόπουλος and Halim Benhabiles and Petros Daras and Andrea Giachetti and Xusi Han and Karim Hammoudi and Daisuke Kihara and Tuan Lai and Haiguang Liu and Mahmoud Melkemi and Stelios Mylonas and Genki Terashi and Yufan Wang and Féryal Windal and Matthieu Montès},
  title = {{Protein Shape Retrieval Contest}},
  booktitle = {Zenodo},
  year = {2019},
  doi = {10.2312/3dor.20191058},
}

Loading related content...

Figure