Prediction Of Side-chain Conformations Research Articles

All‐Atom Protein Sequence Design Based on Geometric Deep Learning

Designing sequences for specific protein backbones is a key step in creating new functional proteins. Here, we introduce GeoSeqBuilder, a deep learning framework that integrates protein sequence generation with side chain conformation prediction to produce the complete all‐atom structures for designed sequences. GeoSeqBuilder uses spatial geometric features from protein backbones and explicitly includes three‐body interactions of neighboring residues. GeoSeqBuilder achieves native residue type recovery rate of 51.6%, comparable to ProteinMPNN and other leading methods, while accurately predicting side chain conformations. We first used GeoSeqBuilder to design sequences for thioredoxin and a hallucinated three‐helical bundle protein. All the 15 tested sequences expressed as soluble monomeric proteins with high thermal stability, and the 2 high‐resolution crystal structures solved closely match the designed models. The generated protein sequences exhibit low similarity (minimum 23%) to the original sequences, with significantly altered hydrophobic cores. We further redesigned the hydrophobic core of glutathione peroxidase 4, and 3 of the 5 designs showed improved enzyme activity. Although further testing is needed, the high experimental success rate in our testing demonstrates that GeoSeqBuilder is a powerful tool for designing novel sequences for predefined protein structures with atomic details. GeoSeqBuilder is available at https://github.com/PKUliujl/GeoSeqBuilder

Simultaneous prediction of antibody backbone and side-chain conformations with deep learning.

Antibody engineering is becoming increasingly popular in medicine for the development of diagnostics and immunotherapies. Antibody function relies largely on the recognition and binding of antigenic epitopes via the loops in the complementarity determining regions. Hence, accurate high-resolution modeling of these loops is essential for effective antibody engineering and design. Deep learning methods have previously been shown to effectively predict antibody backbone structures described as a set of inter-residue distances and orientations. However, antigen binding is also dependent on the specific conformations of surface side-chains. To address this shortcoming, we created DeepSCAb: a deep learning method that predicts inter-residue geometries as well as side-chain dihedrals of the antibody variable fragment. The network requires only sequence as input, rendering it particularly useful for antibodies without any known backbone conformations. Rotamer predictions use an interpretable self-attention layer, which learns to identify structurally conserved anchor positions across several species. We evaluate the performance of the model for discriminating near-native structures from sets of decoys and find that DeepSCAb outperforms similar methods lacking side-chain context. When compared to alternative rotamer repacking methods, which require an input backbone structure, DeepSCAb predicts side-chain conformations competitively. Our findings suggest that DeepSCAb improves antibody structure prediction with accurate side-chain modeling and is adaptable to applications in docking of antibody-antigen complexes and design of new therapeutic antibody sequences.

DLPacker: Deep learning for prediction of amino acid side chain conformations in proteins.

Prediction of side chain conformations of amino acids in proteins (also termed "packing") is an important and challenging part of protein structure prediction with many interesting applications in protein design. A variety of methods for packing have been developed but more accurate ones are still needed. Machine learning (ML) methods have recently become a powerful tool for solving various problems in diverse areas of science, including structural biology. In this study, we evaluate the potential of deep neural networks (DNNs) for prediction of amino acid side chain conformations. We formulate the problem as image-to-image transformation and train a U-net style DNN to solve the problem. We show that our method outperforms other physics-based methods by a significant margin: reconstruction RMSDs for most amino acids are about 20% smaller compared to SCWRL4 and Rosetta Packer with RMSDs for bulky hydrophobic amino acids Phe, Tyr, and Trp being up to 50% smaller.

Toward the Accuracy and Speed of Protein Side-Chain Packing: ASystematic Study on Rotamer Libraries.

Protein rotamers refer to the conformational isomers taken by the side-chains of amino acids to accommodate specific structural folding environments. Since accurate modeling of atomic interactions is difficult, rotamer information collected from experimentally solved protein structures is often used to guide side-chain packing in protein folding and sequence design studies. Many rotamer libraries have been built in the literature but there is little quantitative guidance on which libraries should be chosen for different structural modeling studies. Here, we performed a comparative study of six widely used rotamer libraries and systematically examined their suitability for protein folding and sequence design in four aspects: (1) side-chain match accuracy, (2) side-chain conformation prediction, (3) de novo protein sequence design, and (4) computational time cost. We demonstrated that, compared to the backbone-dependent rotamer libraries (BBDRLs), the backbone-independent rotamer libraries (BBIRLs) generated conformations that more closely matched the native conformations due to the larger number of rotamers in the local rotamer search spaces. However, more practically, using an optimized physical energy function incorporated into a simulated annealing Monte Carlo searching scheme, we showed that utilization of the BBDRLs could result in higher accuracies in side-chain prediction and higher sequence recapitulation rates in protein design experiments. Detailed data analyses showed that the major advantage of BBDRLs lies in the energy term derived from the rotamer probabilities that are associated with the individual backbone torsion angle subspaces. This term is important for distinguishing between amino acid identities as well as the rotamer conformations of an amino acid. Meanwhile, the backbone torsion angle subspace-specific rotamer search drastically speeds up the searching time, despite the significantly larger number of total rotamers in the BBDRLs. These results should provide important guidance for the development and selection of rotamer libraries for practical protein design and structure prediction studies.

Prediction of protein mutation effects based on dehydration and hydrogen bonding - A large-scale study.

Reliable computational prediction of protein side chain conformations and the energetic impact of amino acid mutations are the key aspects for the optimization of biotechnologically relevant enzymatic reactions using structure-based design. By improving the protein stability, higher yields can be achieved. In addition, tuning the substrate selectivity of an enzymatic reaction by directed mutagenesis can lead to higher turnover rates. This work presents a novel approach to predict the conformation of a side chain mutation along with the energetic effect on the protein structure. The HYDE scoring concept applied here describes the molecular interactions primarily by evaluating the effect of dehydration and hydrogen bonding on molecular structures in aqueous solution. Here, we evaluate its capability of side-chain conformation prediction in classic remutation experiments. Furthermore, we present a new data set for evaluating "cross-mutations," a new experiment that resembles real-world application scenarios more closely. This data set consists of protein pairs with up to five point mutations. Thus, structural changes are attributed to point mutations only. In the cross-mutation experiment, the original protein structure is mutated with the aim to predict the structure of the side chain as in the paired mutated structure. The comparison of side chain conformation prediction ("remutation") showed that the performance of HYDEprotein is qualitatively comparable to state-of-the art methods. The ability of HYDEprotein to predict the energetic effect of a mutation is evaluated in the third experiment. Herein, the effect on protein stability is predicted correctly in 70% of the evaluated cases. Proteins 2017; 85:1550-1566. © 2017 Wiley Periodicals, Inc.

Modeling protein-protein and protein-peptide complexes: CAPRI 6th edition.

We present the sixth report evaluating the performance of methods for predicting the atomic resolution structures of protein complexes offered as targets to the community-wide initiative on the Critical Assessment of Predicted Interactions (CAPRI). The evaluation is based on a total of 20,670 predicted models for 8 protein-peptide complexes, a novel category of targets in CAPRI, and 12 protein-protein targets in CAPRI prediction Rounds held during the years 2013-2016. For two of the protein-protein targets, the focus was on the prediction of side-chain conformation and positions of interfacial water molecules. Seven of the protein-protein targets were particularly challenging owing to their multicomponent nature, to conformational changes at the binding site, or to a combination of both. Encouragingly, the very large multiprotein complex with the nucleosome was correctly predicted, and correct models were submitted for the protein-peptide targets, but not for some of the challenging protein-protein targets. Models of acceptable quality or better were obtained for 14 of the 20 targets, including medium quality models for 13 targets and high quality models for 8 targets, indicating tangible progress of present-day computational methods in modeling protein complexes with increased accuracy. Our evaluation suggests that the progress stems from better integration of different modeling tools with docking procedures, as well as the use of more sophisticated evolutionary information to score models. Nonetheless, adequate modeling of conformational flexibility in interacting proteins remains an important area with a crucial need for improvement. Proteins 2017; 85:359-377. © 2016 Wiley Periodicals, Inc.

Quantifying side-chain conformational variations in protein structure.

Protein side-chain conformation is closely related to their biological functions. The side-chain prediction is a key step in protein design, protein docking and structure optimization. However, side-chain polymorphism comprehensively exists in protein as various types and has been long overlooked by side-chain prediction. But such conformational variations have not been quantitatively studied and the correlations between these variations and residue features are vague. Here, we performed statistical analyses on large scale data sets and found that the side-chain conformational flexibility is closely related to the exposure to solvent, degree of freedom and hydrophilicity. These analyses allowed us to quantify different types of side-chain variabilities in PDB. The results underscore that protein side-chain conformation prediction is not a single-answer problem, leading us to reconsider the assessment approaches of side-chain prediction programs.

BetaSCPWeb: side-chain prediction for protein structures using Voronoi diagrams and geometry prioritization.

Many applications, such as protein design, homology modeling, flexible docking, etc. require the prediction of a protein's optimal side-chain conformations from just its amino acid sequence and backbone structure. Side-chain prediction (SCP) is an NP-hard energy minimization problem. Here, we present BetaSCPWeb which efficiently computes a conformation close to optimal using a geometry-prioritization method based on the Voronoi diagram of spherical atoms. Its outputs are visual, textual and PDB file format. The web server is free and open to all users at http://voronoi.hanyang.ac.kr/betascpweb with no login requirement.

Protein side chain conformation predictions with an MMGBSA energy function.

The prediction of protein side chain conformations from backbone coordinates is an important task in structural biology, with applications in structure prediction and protein design. It is a difficult problem due to its combinatorial nature. We study the performance of an "MMGBSA" energy function, implemented in our protein design program Proteus, which combines molecular mechanics terms, a Generalized Born and Surface Area (GBSA) solvent model, with approximations that make the model pairwise additive. Proteus is not a competitor to specialized side chain prediction programs due to its cost, but it allows protein design applications, where side chain prediction is an important step and MMGBSA an effective energy model. We predict the side chain conformations for 18 proteins. The side chains are first predicted individually, with the rest of the protein in its crystallographic conformation. Next, all side chains are predicted together. The contributions of individual energy terms are evaluated and various parameterizations are compared. We find that the GB and SA terms, with an appropriate choice of the dielectric constant and surface energy coefficients, are beneficial for single side chain predictions. For the prediction of all side chains, however, errors due to the pairwise additive approximation overcome the improvement brought by these terms. We also show the crucial contribution of side chain minimization to alleviate the rigid rotamer approximation. Even without GB and SA terms, we obtain accuracies comparable to SCWRL4, a specialized side chain prediction program. In particular, we obtain a better RMSD than SCWRL4 for core residues (at a higher cost), despite our simpler rotamer library. Proteins 2016; 84:803-819. © 2016 Wiley Periodicals, Inc.

Single-Point Mutation with a Rotamer Library Toolkit: Toward Protein Engineering.

Protein engineers have long been hard at work to harness biocatalysts as a natural source of regio-, stereo-, and chemoselectivity in order to carry out chemistry (reactions and/or substrates) not previously achieved with these enzymes. The extreme labor demands and exponential number of mutation combinations have induced computational advances in this domain. The first step in our virtual approach is to predict the correct conformations upon mutation of residues (i.e., rebuilding side chains). For this purpose, we opted for a combination of molecular mechanics and statistical data. In this work, we have developed automated computational tools to extract protein structural information and created conformational libraries for each amino acid dependent on a variable number of parameters (e.g., resolution, flexibility, secondary structure). We have also developed the necessary tool to apply the mutation and optimize the conformation accordingly. For side-chain conformation prediction, we obtained overall average root-mean-square deviations (RMSDs) of 0.91 and 1.01 Å for the 18 flexible natural amino acids within two distinct sets of over 3000 and 1500 side-chain residues, respectively. The commonly used dihedral angle differences were also evaluated and performed worse than the state of the art. These two metrics are also compared. Furthermore, we generated a family-specific library for kinases that produced an average 2% lower RMSD upon side-chain reconstruction and a residue-specific library that yielded a 17% improvement. Ultimately, since our protein engineering outlook involves using our docking software, Fitted/Impacts, we applied our mutation protocol to a benchmarked data set for self- and cross-docking. Our side-chain reconstruction does not hinder our docking software, demonstrating differences in pose prediction accuracy of approximately 2% (RMSD cutoff metric) for a set of over 200 protein/ligand structures. Similarly, when docking to a set of over 100 kinases, side-chain reconstruction (using both general and biased conformation libraries) had minimal detriment to the docking accuracy.

Improved packing of protein side chains with parallel ant colonies

IntroductionThe accurate packing of protein side chains is important for many computational biology problems, such as ab initio protein structure prediction, homology modelling, and protein design and ligand docking applications. Many of existing solutions are modelled as a computational optimisation problem. As well as the design of search algorithms, most solutions suffer from an inaccurate energy function for judging whether a prediction is good or bad. Even if the search has found the lowest energy, there is no certainty of obtaining the protein structures with correct side chains.MethodsWe present a side-chain modelling method, pacoPacker, which uses a parallel ant colony optimisation strategy based on sharing a single pheromone matrix. This parallel approach combines different sources of energy functions and generates protein side-chain conformations with the lowest energies jointly determined by the various energy functions. We further optimised the selected rotamers to construct subrotamer by rotamer minimisation, which reasonably improved the discreteness of the rotamer library.ResultsWe focused on improving the accuracy of side-chain conformation prediction. For a testing set of 442 proteins, 87.19% of and 77.11% of angles were predicted correctly within 40° of the X-ray positions. We compared the accuracy of pacoPacker with state-of-the-art methods, such as CIS-RR and SCWRL4. We analysed the results from different perspectives, in terms of protein chain and individual residues. In this comprehensive benchmark testing, 51.5% of proteins within a length of 400 amino acids predicted by pacoPacker were superior to the results of CIS-RR and SCWRL4 simultaneously. Finally, we also showed the advantage of using the subrotamers strategy. All results confirmed that our parallel approach is competitive to state-of-the-art solutions for packing side chains.ConclusionsThis parallel approach combines various sources of searching intelligence and energy functions to pack protein side chains. It provides a frame-work for combining different inaccuracy/usefulness objective functions by designing parallel heuristic search algorithms.

Assessment of protein side-chain conformation prediction methods in different residue environments.

Computational prediction of side-chain conformation is an important component of protein structure prediction. Accurate side-chain prediction is crucial for practical applications of protein structure models that need atomic-detailed resolution such as protein and ligand design. We evaluated the accuracy of eight side-chain prediction methods in reproducing the side-chain conformations of experimentally solved structures deposited to the Protein Data Bank. Prediction accuracy was evaluated for a total of four different structural environments (buried, surface, interface, and membrane-spanning) in three different protein types (monomeric, multimeric, and membrane). Overall, the highest accuracy was observed for buried residues in monomeric and multimeric proteins. Notably, side-chains at protein interfaces and membrane-spanning regions were better predicted than surface residues even though the methods did not all use multimeric and membrane proteins for training. Thus, we conclude that the current methods are as practically useful for modeling protein docking interfaces and membrane-spanning regions as for modeling monomers.

PRIME: Probabilistic Initial 3D Model Generation for Single-Particle Cryo-Electron Microscopy

Low-dose electron microscopy of cryo-preserved individual biomolecules (single-particle cryo-EM) is a powerful tool for obtaining information about the structure and dynamics of large macromolecular assemblies. Acquiring images with low dose reduces radiation damage, preserves atomic structural details, but results in low signal-to-noise ratio of the individual images. The projection directions of the two-dimensional images are random and unknown. The grand challenge is to achieve the precise three-dimensional (3D) alignment of many (tens of thousands to millions) noisy projection images, which may then be combined to obtain a faithful 3D map. An accurate initial 3D model is critical for obtaining the precise 3D alignment required for high-resolution (<10Å) map reconstruction. We report a method (PRIME) that, in a single step and without prior structural knowledge, can generate an accurate initial 3D map directly from the noisy images.

An energy‐based conformer library for side chain optimization: Improved prediction and adjustable sampling

Side chain optimization is a fundamental component of protein modeling applications such as docking, structural prediction, and design. In these applications side chain flexibility is often provided by rotamer or conformer libraries, which are collections of representative side chain conformations. Here we demonstrate that the sampling provided by the library can be substantially improved by adding an energetic criterion to its creation. The result of the new procedure is the Energy-Based library, a conformer library selected according to the propensity of its elements to fit energetically into natural protein environments. The new library performs outstandingly well in side chain optimization, producing structures with significantly lower energies and resulting in improved side chain conformation prediction. In addition, because the library was created as an ordered list, its size can be adjusted to any desired level. This feature provides unprecedented versatility in tuning sampling. It allows to precisely balance the number of conformers required by each amino acid type, equalizing their chances to fit into structural environments. It also allows to scale the amount of sampling to the specific requirement of any given side optimization problem. A rotameric version of the library was also produced with the same method to support applications that require a dihedral-only description of side chain conformation. The libraries are available at http://seneslab.org/EBL.

SIDEpro: A novel machine learning approach for the fast and accurate prediction of side‐chain conformations

Accurate protein side-chain conformation prediction is crucial for protein modeling and existing methods for the task are widely used; however, faster and more accurate methods are still required. Here we present a new machine learning approach to the problem where an energy function for each rotamer in a structure is computed additively over pairs of contacting atoms. A family of 156 neural networks indexed by amino acid and contacting atom types is used to compute these rotamer energies as a function of atomic contact distances. Although direct energy targets are not available for training, the neural networks can still be optimized by converting the energies to probabilities and optimizing these probabilities using Markov Chain Monte Carlo methods. The resulting predictor SIDEpro makes predictions by initially setting the rotamer probabilities for each residue from a backbone-dependent rotamer library, then iteratively updating these probabilities using the trained neural networks. After convergences of the probabilities, the side-chains are set to the highest probability rotamer. Finally, a post processing clash reduction step is applied to the models. SIDEpro represents a significant improvement in speed and a modest, but statistically significant, improvement in accuracy when compared with the state-of-the-art for rapid side-chain prediction method SCWRL4 on the following datasets: (1) 379 protein test set of SCWRL4; (2) 94 proteins from CASP9; (3) a set of seven large protein-only complexes; and (4) a ribosome with and without the RNA. Using the SCWRL4 test set, SIDEpro's accuracy (χ(1) 86.14%, χ(1+2) 74.15%) is slightly better than SCWRL4-FRM (χ(1) 85.43%, χ(1+2) 73.47%) and it is 7.0 times faster. On the same test set SIDEpro is clearly more accurate than SCWRL4-rigid rotamer model (RRM) (χ(1) 84.15%, χ(1+2) 71.24%) and 2.4 times faster. Evaluation on the additional test sets yield similar accuracy results with SIDEpro being slightly more accurate than SCWRL4-flexible rotamer model (FRM) and clearly more accurate than SCWRL4-RRM; however, the gap in CPU time is much more significant when the methods are applied to large protein complexes. SIDEpro is part of the SCRATCH suite of predictors and available from: http://scratch.proteomics.ics.uci.edu/.

RASP: rapid modeling of protein side chain conformations

Modeling of side chain conformations constitutes an indispensable effort in protein structure modeling, protein-protein docking and protein design. Thanks to an intensive attention to this field, many of the existing programs can achieve reasonably good and comparable prediction accuracy. Moreover, in our previous work on CIS-RR, we argued that the prediction with few atomic clashes can complement the current existing methods for subsequent analysis and refinement of protein structures. However, these recent efforts to enhance the quality of predicted side chains have been accompanied by a significant increase of computational cost. In this study, by mainly focusing on improving the speed of side chain conformation prediction, we present a RApid Side-chain Predictor, called RASP. To achieve a much faster speed with a comparable accuracy to the best existing methods, we not only employ the clash elimination strategy of CIS-RR, but also carefully optimize energy terms and integrate different search algorithms. In comprehensive benchmark testings, RASP is over one order of magnitude faster (~ 40 times over CIS-RR) than the recently developed methods, while achieving comparable or even better accuracy.

Fast and accurate prediction of protein side-chain conformations

Summary: We developed a fast and accurate side-chain modeling program [Optimized Side Chain Atomic eneRgy (OSCAR)-star] based on orientation-dependent energy functions and a rigid rotamer model. The average computing time was 18 s per protein for 218 test proteins with higher prediction accuracy (1.1% increase for χ1 and 0.8% increase for χ1+2) than the best performing program developed by other groups. We show that the energy functions, which were calibrated to tolerate the discrete errors of rigid rotamers, are appropriate for protein loop selection, especially for decoys without extensive structural refinement.Availability: OSCAR-star and the 218 test proteins are available for download at http://sysimm.ifrec.osaka-u.ac.jp/OSCARContact: standley@ifrec.osaka-u.ac.jpSupplementary information: Supplementary data are available at Bioinformatics online.

Genetic algorithm with alternating selection pressure for protein side-chain packing and p K(a) prediction

The prediction of protein side-chain conformation is central for understanding protein functions. Side-chain packing is a sub-problem of protein folding and its computational complexity has been shown to be NP-hard. We investigated the capabilities of a hybrid (genetic algorithm/simulated annealing) technique for side-chain packing and for the generation of an ensemble of low energy side-chain conformations. Our method first relies on obtaining a near-optimal low energy protein conformation by optimizing its amino-acid side-chains. Upon convergence, the genetic algorithm is allowed to undergo forward and “backward” evolution by alternating selection pressures between minimal and higher energy setpoints. We show that this technique is very efficient for obtaining distributions of solutions centered at any desired energy from the minimum. We outline the general concepts of our evolutionary sampling methodology using three different alternating selective pressure schemes. Quality of the method was assessed by using it for protein p K(a) prediction.

Computational design of ligand binding is not a solved problem

Computational design has been very successful in recent years: multiple novel ligand binding proteins as well as enzymes have been reported. We wanted to know in molecular detail how precise the predictions of the interactions of protein and ligands are. Therefore, we performed a structural analysis of a number of published receptors designed onto the periplasmic binding protein scaffold that were reported to bind to the new ligands with nano- to micromolar affinities. It turned out that most of these designed proteins are not suitable for structural studies due to instability and aggregation. However, we were able to solve the crystal structure of an arabinose binding protein designed to bind serotonin to 2.2 A resolution. While crystallized in the presence of an excess of serotonin, the protein is in an open conformation with no serotonin bound, although the side-chain conformations in the empty binding pocket are very similar to the conformations predicted. During subsequent characterization using isothermal titration calorimetry, CD, and NMR spectroscopy, no indication of binding could be detected for any of the tested designed receptors, whereas wild-type proteins bound their ligands as expected. We conclude that although the computational prediction of side-chain conformations appears to be working, it does not necessarily confer binding as expected. Hence, the computational design of ligand binding is not a solved problem and needs to be revisited.

SCWRL and MolIDE: computer programs for side-chain conformation prediction and homology modeling

SCWRL and MolIDE are software applications for prediction of protein structures. SCWRL is designed specifically for the task of prediction of side-chain conformations given a fixed backbone usually obtained from an experimental structure determined by X-ray crystallography or NMR. SCWRL is a command-line program that typically runs in a few seconds. MolIDE provides a graphical interface for basic comparative (homology) modeling using SCWRL and other programs. MolIDE takes an input target sequence and uses PSI-BLAST to identify and align templates for comparative modeling of the target. The sequence alignment to any template can be manually modified within a graphical window of the target-template alignment and visualization of the alignment on the template structure. MolIDE builds the model of the target structure on the basis of the template backbone, predicted side-chain conformations with SCWRL and a loop-modeling program for insertion-deletion regions with user-selected sequence segments. SCWRL and MolIDE can be obtained at (http://dunbrack.fccc.edu/Software.php).