QRB Discovery · 2022 · 16 citations · 62 references
Life SciencesBioinformaticsBiophysicsProtein Structure PredictionStructural BioinformaticsStructural BiologyCryo-electron MicroscopyProtein StructureProtein Structure ModelingStructural RefinementAtomic Model BuildingConvolutionCryo-electron Microscopy RefinementCryo-electron Microscopy-based Structure ModelingModel RefinementProtein TargetsReal-space RefinementRefinement
Recent breakthroughs in deep learning-based protein structure prediction show that it is possible to obtain highly accurate models for a wide range of difficult protein targets for which only the amino acid sequence is known. The availability of accurately predicted models from sequences can potentially revolutionise many modelling approaches in structural biology, including the interpretation of cryo-EM density maps. Although atomic structures can be readily solved from cryo-EM maps of better than 4 Å resolution, it is still challenging to determine accurate models from lower-resolution density maps. Here, we report on the benefits of models predicted by AlphaFold2 (the best-performing structure prediction method at CASP14) on cryo-EM refinement using the Phenix refinement suite for AlphaFold2 models. To study the robustness of model refinement at a lower resolution of interest, we introduced hybrid maps (i.e. experimental cryo-EM maps) filtered to lower resolutions by real-space convolution. The AlphaFold2 models were refined to attain good accuracies above 0.8 TM scores for 9 of the 13 cryo-EM maps. TM scores improved for AlphaFold2 models refined against all 13 cryo-EM maps of better than 4.5 Å resolution, 8 hybrid maps of 6 Å resolution, and 3 hybrid maps of 8 Å resolution. The results show that it is possible (at least with the Phenix protocol) to extend the refinement success below 4.5 Å resolution. We even found isolated cases in which resolution lowering was slightly beneficial for refinement, suggesting that high-resolution cryo-EM maps might sometimes trap AlphaFold2 models in local optima.
62
Highly accurate protein structure prediction with AlphaFold
John Jumper, Alexander Pritzel, Tim Green et al. · Nature · 2021 · 45.2K citations · Full text
ColabFold: making protein folding accessible to all
Milot Mirdita, Konstantin Schütze, Yoshitaka Moriwaki et al. · Nature Methods · 2022 · 9.7K citations · Full text
Accurate prediction of protein structures and interactions using a three-track neural network
Minkyung Baek, Frank DiMaio, Ivan Anishchenko et al. · Science · 2021 · 5.7K citations · Full text