Protein Structure Prediction with Expectation Reflection
Cresswell-Clay, E. C.; Hoang, D.-T.; McKenna, J.; Yang, C.; Zhang, E.; Periwal, V.
Show abstract
Sequence covariation in multiple sequence alignments of homologous proteins has been used extensively to obtain insights into protein structure. However, global statistical inference is required in order to ascertain direct relationships between amino acid positions in these sequences that are not simply secondary correlations induced by interactions with a third residue. Methods for statistical inference of such covariation have been developed to exploit the growing availability of sequence data. These hints about the folded protein structure provide critical a priori information for more detailed 3D predictions by neural networks. We present a novel method for protein structure inference using an iterative parameter-free model estimator which uses the formalism of statistical physics. With no tunable learning rate, our method scales to large system sizes while providing improved performance in the regime of small sample sizes. We apply this method to 40974 PDB structures and compare its performance to that of other methods. Our method outperforms existing methods for 76% of analysed proteins.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Improving sequence-based modeling of protein families using secondary structure quality assessment 97%
- Fold recognition by scoring protein map similarities using the congruence coefficient 97%
- Patch-DCA: Improved Protein Interface Prediction by utilizing Structural Information and Clustering DCA scores 96%
Similar papers in this journal
Similar papers in this journal
Similar papers in this journal
- RFQAmodel: Random Forest Quality Assessment to identify a predicted protein structure in the correct fold 95%
- Assessing the Generalization Capabilities of TCR Binding Predictors via Peptide Distance Analysis 94%
- Classification of protein binding ligands using structural dispersion of binding site atoms from principal axes 94%
Similar papers in this journal
- WASCO: A Wasserstein-based statistical tool to compare conformational ensembles of intrinsically disordered proteins 95%
- Prediction of disordered regions in proteins with recurrent Neural Networks and protein dynamics 95%
- Optimising Elastic Network Models for Protein Dynamics and Allostery: Spatial and Modal Cut-offs and Backbone Stiffness 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.