TY - JOUR
T1 - Methods for estimation of model accuracy in CASP12
AU - Elofsson, Arne
AU - Joo, Keehyoung
AU - Keasar, Chen
AU - Lee, Jooyoung
AU - Maghrabi, Ali H.A.
AU - Manavalan, Balachandran
AU - McGuffin, Liam J.
AU - Ménendez Hurtado, David
AU - Mirabello, Claudio
AU - Pilstål, Robert
AU - Sidi, Tomer
AU - Uziela, Karolis
AU - Wallner, Björn
N1 - Publisher Copyright:
© 2017 Wiley Periodicals, Inc.
PY - 2018/3/1
Y1 - 2018/3/1
N2 - Methods to reliably estimate the quality of 3D models of proteins are essential drivers for the wide adoption and serious acceptance of protein structure predictions by life scientists. In this article, the most successful groups in CASP12 describe their latest methods for estimates of model accuracy (EMA). We show that pure single model accuracy estimation methods have shown clear progress since CASP11; the 3 top methods (MESHI, ProQ3, SVMQA) all perform better than the top method of CASP11 (ProQ2). Although the pure single model accuracy estimation methods outperform quasi-single (ModFOLD6 variations) and consensus methods (Pcons, ModFOLDclust2, Pcomb-domain, and Wallner) in model selection, they are still not as good as those methods in absolute model quality estimation and predictions of local quality. Finally, we show that when using contact-based model quality measures (CAD, lDDT) the single model quality methods perform relatively better.
AB - Methods to reliably estimate the quality of 3D models of proteins are essential drivers for the wide adoption and serious acceptance of protein structure predictions by life scientists. In this article, the most successful groups in CASP12 describe their latest methods for estimates of model accuracy (EMA). We show that pure single model accuracy estimation methods have shown clear progress since CASP11; the 3 top methods (MESHI, ProQ3, SVMQA) all perform better than the top method of CASP11 (ProQ2). Although the pure single model accuracy estimation methods outperform quasi-single (ModFOLD6 variations) and consensus methods (Pcons, ModFOLDclust2, Pcomb-domain, and Wallner) in model selection, they are still not as good as those methods in absolute model quality estimation and predictions of local quality. Finally, we show that when using contact-based model quality measures (CAD, lDDT) the single model quality methods perform relatively better.
KW - CASP
KW - consensus predictions
KW - estimates of model accuracy
KW - machine learning
KW - protein structure prediction
KW - quality assessment
UR - https://www.scopus.com/pages/publications/85042322601
U2 - 10.1002/prot.25395
DO - 10.1002/prot.25395
M3 - Article
C2 - 28975666
AN - SCOPUS:85042322601
SN - 0887-3585
VL - 86
SP - 361
EP - 373
JO - Proteins: Structure, Function and Bioinformatics
JF - Proteins: Structure, Function and Bioinformatics
ER -