Fast and effective protein model refinement using deep graph neural networks

Abstract

Protein structure prediction has been greatly improved, but there are still a good portion of predicted models that do not have very high quality. Protein model refinement is one of the methods that may further improve model quality.Nevertheless, it is very challenging to refine a protein model towards better quality. Currently the most successful refinement methods rely on extensive conformation sampling and thus, take hours or days to refine even a single protein model. Here we propose a fast and effective method that may refine protein models with very limited conformation sampling. Our method applies GNN (graph neural networks) to predict refined inter-atom distance probability distribution from an initial model and then rebuilds the model using the predicted distance as restraints. On the CASP13 refinement targets our method may refine models with comparable quality as the two leading human groups (Feig and Baker) and greatly outperforms the others. On the CASP14 refinement targets our method is only second to Feig's method, comparable to Baker's method and much better than the others (who worsened instead of improved model quality). Our method achieves this result by generating only 5 refined models for an initial model, which can be done in ~15 minutes. Our study also shows that GNN performs much better than convolutional residual neural networks for protein model refinement when conformation sampling is limited.

An end-to-end deep learning method for rotamer-free protein side-chain packing

“…For our pair embedding, we follow a scheme similar to [17], but also incorporate residue pair information following the approach of AlphaFold2. Rather than embed each residue pair separately, the authors propose using two separate embeddings for residue types.…”

EGR: Equivariant Graph Refinement and Assessment of 3D Protein Complex Structures

“…Deep learning for protein structure refinement. DL models have also been used to guide the refinement of residue positions within tertiary protein structures [38] or predict refined residue positions using indirect target values such as inter-residue distances [39,40]. Unfortunately, such methods, following refinement, require all-atom restoration procedures as a post-processing step to recover the positions of backbone and side-chain atoms.…”

“…GalaxyRefineComplex [72] is another popular refinement protocol, one specifically designed for refining structural interfaces between chains in a protein complex. Similarly, we also include GNNRefine [40], which uses GNN-based distance predictions to drive tertiary structural refinement with PyRosetta [73]. We note that we are only able to include GalaxyRefineComplex and GNNRefine's results on our smaller Benchmark 2 test dataset, as their extraordinarily high refinement runtimes (e.g., 1,200 seconds per decoy with 16 CPU threads) prevent us from evaluating their performance in a reasonable amount of time on our full PSR test dataset consisting of over 5,000 complexes.…”

Protein sequence‐to‐structure learning: Is this the end(‐to‐end revolution)?

“…This allowed to effectively encode mutual angular dependence of neighboring graph nodes using spherical harmonics expansions 108 . In its turn, GNNRefine predicted distances between protein atoms using graph neural networks, and then converted these distances into interatomic potentials and employed them for protein structure refinement 113 . A more recent method, GVP‐GNN, 114 augments graph networks with the ability to reason about protein features expressed as geometric vectors in an equivariant manner.…”