A structural biology community assessment of AlphaFold2 applications
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
A structural biology community assessment of AlphaFold2 applications. / Akdel, Mehmet; Pires, Douglas E.; Porta Pardo, Eduard; Jänes, Jürgen; Zalevsky, Arthur O.; Meszaros, Balint; Bryant, Patrick; Good, Lydia L.; Laskowski, Roman A.; Pozzati, Gabriele; Shenoy, Aditi; Zhu, Wensi; Kundrotas, Petras; Serra, Victoria Ruiz; Rodrigues, Carlos H. M.; Dunham, Alistair S.; Burke, David; Borkakoti, Neera; Velankar, Sameer; Frost, Adam; Basquin, Jérôme; Lindorff-Larsen, Kresten; Bateman, Alex; Kajava, Andrey; Valencia, Alfonso; Ovchinnikov, Sergey; Durairaj, Janani; Ascher, David B.; Thornton, Janet M.; Davey, Norman E.; Stein, Amelie; Elofsson, Arne; Croll, Tristan; Beltrao, Pedro.
In: Nature Structural & Molecular Biology, Vol. 29, No. 11, 2022.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - A structural biology community assessment of AlphaFold2 applications
AU - Akdel, Mehmet
AU - Pires, Douglas E.
AU - Porta Pardo, Eduard
AU - Jänes, Jürgen
AU - Zalevsky, Arthur O.
AU - Meszaros, Balint
AU - Bryant, Patrick
AU - Good, Lydia L.
AU - Laskowski, Roman A.
AU - Pozzati, Gabriele
AU - Shenoy, Aditi
AU - Zhu, Wensi
AU - Kundrotas, Petras
AU - Serra, Victoria Ruiz
AU - Rodrigues, Carlos H. M.
AU - Dunham, Alistair S.
AU - Burke, David
AU - Borkakoti, Neera
AU - Velankar, Sameer
AU - Frost, Adam
AU - Basquin, Jérôme
AU - Lindorff-Larsen, Kresten
AU - Bateman, Alex
AU - Kajava, Andrey
AU - Valencia, Alfonso
AU - Ovchinnikov, Sergey
AU - Durairaj, Janani
AU - Ascher, David B.
AU - Thornton, Janet M.
AU - Davey, Norman E.
AU - Stein, Amelie
AU - Elofsson, Arne
AU - Croll, Tristan
AU - Beltrao, Pedro
PY - 2022
Y1 - 2022
N2 - Here, the authors evaluate the performance of AlphaFold2 and its predicted structures on common structural biological applications, including missense variants, function and ligand binding site prediction, modeling of interactions and modeling of experimental structural data.Most proteins fold into 3D structures that determine how they function and orchestrate the biological processes of the cell. Recent developments in computational methods for protein structure predictions have reached the accuracy of experimentally determined models. Although this has been independently verified, the implementation of these methods across structural-biology applications remains to be tested. Here, we evaluate the use of AlphaFold2 (AF2) predictions in the study of characteristic structural elements; the impact of missense variants; function and ligand binding site predictions; modeling of interactions; and modeling of experimental structural data. For 11 proteomes, an average of 25% additional residues can be confidently modeled when compared with homology modeling, identifying structural features rarely seen in the Protein Data Bank. AF2-based predictions of protein disorder and complexes surpass dedicated tools, and AF2 models can be used across diverse applications equally well compared with experimentally determined structures, when the confidence metrics are critically considered. In summary, we find that these advances are likely to have a transformative impact in structural biology and broader life-science research.
AB - Here, the authors evaluate the performance of AlphaFold2 and its predicted structures on common structural biological applications, including missense variants, function and ligand binding site prediction, modeling of interactions and modeling of experimental structural data.Most proteins fold into 3D structures that determine how they function and orchestrate the biological processes of the cell. Recent developments in computational methods for protein structure predictions have reached the accuracy of experimentally determined models. Although this has been independently verified, the implementation of these methods across structural-biology applications remains to be tested. Here, we evaluate the use of AlphaFold2 (AF2) predictions in the study of characteristic structural elements; the impact of missense variants; function and ligand binding site predictions; modeling of interactions; and modeling of experimental structural data. For 11 proteomes, an average of 25% additional residues can be confidently modeled when compared with homology modeling, identifying structural features rarely seen in the Protein Data Bank. AF2-based predictions of protein disorder and complexes surpass dedicated tools, and AF2 models can be used across diverse applications equally well compared with experimentally determined structures, when the confidence metrics are critically considered. In summary, we find that these advances are likely to have a transformative impact in structural biology and broader life-science research.
KW - PROTEIN STABILITY
KW - MUTATIONS
KW - PREDICTION
KW - FEATURES
KW - SERVER
KW - IDENTIFICATION
KW - SEQUENCE
KW - DOCKING
KW - SPACE
KW - TOOL
U2 - 10.1038/s41594-022-00849-w
DO - 10.1038/s41594-022-00849-w
M3 - Journal article
C2 - 36344848
VL - 29
JO - Nature Structural and Molecular Biology
JF - Nature Structural and Molecular Biology
SN - 1545-9993
IS - 11
ER -
ID: 329743063