TY - JOUR
T1 - SHREC2020 track
T2 - Multi-domain protein shape retrieval challenge
AU - Langenfeld, Florent
AU - Peng, Yuxu
AU - Lai, Yu Kun
AU - Rosin, Paul L.
AU - Aderinwale, Tunde
AU - Terashi, Genki
AU - Christoffer, Charles
AU - Kihara, Daisuke
AU - Benhabiles, Halim
AU - Hammoudi, Karim
AU - Cabani, Adnane
AU - Windal, Feryal
AU - Melkemi, Mahmoud
AU - Giachetti, Andrea
AU - Mylonas, Stelios
AU - Axenopoulos, Apostolos
AU - Daras, Petros
AU - Otu, Ekpo
AU - Zwiggelaar, Reyer
AU - Hunter, David
AU - Liu, Yonghuai
AU - Montès, Matthieu
N1 - Funding Information:
Stelios Mylonas, Apostolos Axenopoulos and Petros Daras were supported by the ATXN1-MED15 PPI project funded by the GSRT - Hellenic Foundation for Research and Innovation.
Funding Information:
Yuxu Peng was supported by the Young teachers growth plan project (2019QJCZ014) funded by Changsha University of Science & Technology. Stelios Mylonas, Apostolos Axenopoulos and Petros Daras were supported by the ATXN1-MED15 PPI project funded by the GSRT - Hellenic Foundation for Research and Innovation. Matthieu Montes and Florent Langenfeld were supported by the European Research Council Executive Agency under the research grant number 640283.
Funding Information:
Matthieu Montes and Florent Langenfeld were supported by the European Research Council Executive Agency under the research grant number 640283 .
Funding Information:
Yuxu Peng was supported by the Young teachers growth plan project ( 2019QJCZ014 ) funded by Changsha University of Science & Technology .
Publisher Copyright:
© 2020 The Author(s)
PY - 2020/10/1
Y1 - 2020/10/1
N2 - Proteins are natural modular objects usually composed of several domains, each domain bearing a specific function that is mediated through its surface, which is accessible to vicinal molecules. This draws attention to an understudied characteristic of protein structures: surface, that is mostly unexploited by protein structure comparison methods. In the present work, we evaluated the performance of six shape comparison methods, among which three are based on machine learning, to distinguish between 588 multi-domain proteins and to recreate the evolutionary relationships at the proteinand species levels of the SCOPe database. The six groups that participated in the challenge submitted a total of 15 sets of results. We observed that the performance of all the methods significantly decreases at the species level, suggesting that shape-only protein comparison is challenging for closely related proteins. Even if the dataset is limited in size (only 588 proteins are considered whereas more than 160,000 protein structures are experimentally solved), we think that this work provides useful insights into the current shape comparison methods performance, and highlights possible limitations to large-scale applications due to the computational cost.
AB - Proteins are natural modular objects usually composed of several domains, each domain bearing a specific function that is mediated through its surface, which is accessible to vicinal molecules. This draws attention to an understudied characteristic of protein structures: surface, that is mostly unexploited by protein structure comparison methods. In the present work, we evaluated the performance of six shape comparison methods, among which three are based on machine learning, to distinguish between 588 multi-domain proteins and to recreate the evolutionary relationships at the proteinand species levels of the SCOPe database. The six groups that participated in the challenge submitted a total of 15 sets of results. We observed that the performance of all the methods significantly decreases at the species level, suggesting that shape-only protein comparison is challenging for closely related proteins. Even if the dataset is limited in size (only 588 proteins are considered whereas more than 160,000 protein structures are experimentally solved), we think that this work provides useful insights into the current shape comparison methods performance, and highlights possible limitations to large-scale applications due to the computational cost.
KW - 3D shape analysis
KW - 3D shape descriptor
KW - 3D shape matching
KW - 3D shape retrieval
KW - Protein shape
KW - SHREC
UR - http://www.scopus.com/inward/record.url?scp=85089340492&partnerID=8YFLogxK
U2 - 10.1016/j.cag.2020.07.013
DO - 10.1016/j.cag.2020.07.013
M3 - Article
AN - SCOPUS:85089340492
SN - 0097-8493
VL - 91
SP - 189
EP - 198
JO - Computers & Graphics
JF - Computers & Graphics
ER -