i3Drefine Software for Protein 3D Structure Refinement and Its Assessment in CASP10

Protein structure refinement refers to the process of improving the qualities of protein structures during structure modeling processes to bring them closer to their native states. Structure refinement has been drawing increasing attention in the community-wide Critical Assessment of techniques for Protein Structure prediction (CASP) experiments since its addition in 8^th CASP experiment. During the 9^th and recently concluded 10^th CASP experiments, a consistent growth in number of refinement targets and participating groups has been witnessed. Yet, protein structure refinement still remains a largely unsolved problem with majority of participating groups in CASP refinement category failed to consistently improve the quality of structures issued for refinement. In order to alleviate this need, we developed a completely automated and computationally efficient protein 3D structure refinement method, i3Drefine, based on an iterative and highly convergent energy minimization algorithm with a powerful all-atom composite physics and knowledge-based force fields and hydrogen bonding (HB) network optimization technique. In the recent community-wide blind experiment, CASP10, i3Drefine (as ‘MULTICOM-CONSTRUCT’) was ranked as the best method in the server section as per the official assessment of CASP10 experiment. Here we provide the community with free access to i3Drefine software and systematically analyse the performance of i3Drefine in strict blind mode on the refinement targets issued in CASP10 refinement category and compare with other state-of-the-art refinement methods participating in CASP10. Our analysis demonstrates that i3Drefine is only fully-automated server participating in CASP10 exhibiting consistent improvement over the initial structures in both global and local structural quality metrics. Executable version of i3Drefine is freely available at http://protein.rnet.missouri.edu/i3drefine/.     

Princeton_TIGRESS: Protein geometry refinement using simulations and support vector machines

Protein structure refinement aims to perform a set of operations given a predicted structure to improve model quality and accuracy with respect to the native in a blind fashion. Despite the numerous computational approaches to the protein refinement problem reported in the previous three CASPs, an overwhelming majority of methods degrade models rather than improve them. We initially developed a method tested using blind predictions during CASP10 which was officially ranked in 5th place among all methods in the refinement category. Here, we present Princeton_TIGRESS, which when benchmarked on all CASP 7,8,9, and 10 refinement targets, simultaneously increased GDT_TS 76% of the time with an average improvement of 0.83 GDT_TS points per structure. The method was additionally benchmarked on models produced by top performing three‐dimensional structure prediction servers during CASP10. The robustness of the Princeton_TIGRESS protocol was also tested for different random seeds. We make the Princeton_TIGRESS refinement protocol freely available as a web server at http://atlas.princeton.edu/refinement . Using this protocol, one can consistently refine a prediction to help bridge the gap between a predicted structure and the actual native structure. Proteins 2014; 82:794–814. © 2013 Wiley Periodicals, Inc.     

A novel method for predicting and using distance constraints of high accuracy for refining protein structure prediction

The principal bottleneck in protein structure prediction is the refinement of models from lower accuracies to the resolution observed by experiment. We developed a novel constraints‐based refinement method that identifies a high number of accurate input constraints from initial models and rebuilds them using restrained torsion angle dynamics (rTAD). We previously created a Bayesian statistics‐based residue‐specific all‐atom probability discriminatory function (RAPDF) to discriminate native‐like models by measuring the probability of accuracy for atom type distances within a given model. Here, we exploit RAPDF to score (i.e., filter) constraints from initial predictions that may or may not be close to a native‐like state, obtain consensus of top scoring constraints amongst five initial models, and compile sets with no redundant residue pair constraints. We find that this method consistently produces a large and highly accurate set of distance constraints from which to build refinement models. We further optimize the balance between accuracy and coverage of constraints by producing multiple structure sets using different constraint distance cutoffs, and note that the cutoff governs spatially near versus distant effects in model generation. This complete procedure of deriving distance constraints for rTAD simulations improves the quality of initial predictions significantly in all cases evaluated by us. Our procedure represents a significant step in solving the protein structure prediction and refinement problem, by enabling the use of consensus constraints, RAPDF, and rTAD for protein structure modeling and refinement. Proteins 2009. © 2009 Wiley‐Liss, Inc.     

REMO: A new protocol to refine full atomic protein models from C‐alpha traces by optimizing hydrogen‐bonding networks

Protein structure prediction approaches usually perform modeling simulations based on reduced representation of protein structures. For biological utilizations, it is an important step to construct full atomic models from the reduced structure decoys. Most of the current full atomic model reconstruction procedures have defects which either could not completely remove the steric clashes among backbone atoms or generate final atomic models with worse topology similarity relative to the native structures than the reduced models. In this work, we develop a new protocol, called REMO, to generate full atomic protein models by optimizing the hydrogen‐bonding network with basic fragments matched from a newly constructed backbone isomer library of solved protein structures. The algorithm is benchmarked on 230 nonhomologous proteins with reduced structure decoys generated by I‐TASSER simulations. The results show that REMO has a significant ability to remove steric clashes, and meanwhile retains good topology of the reduced model. The hydrogen‐bonding network of the final models is dramatically improved during the procedure. The REMO algorithm has been exploited in the recent CASP8 experiment which demonstrated significant improvements of the I‐TASSER models in both atomic‐level structural refinement and hydrogen‐bonding network construction. Proteins 2009. © 2009 Wiley‐Liss, Inc.     

Princeton_TIGRESS 2.0: High refinement consistency and net gains through support vector machines and molecular dynamics in double‐blind predictions during the CASP11 experiment

Protein structure refinement is the challenging problem of operating on any protein structure prediction to improve its accuracy with respect to the native structure in a blind fashion. Although many approaches have been developed and tested during the last four CASP experiments, a majority of the methods continue to degrade models rather than improve them. Princeton_TIGRESS (Khoury et al., Proteins 2014;82:794–814) was developed previously and utilizes separate sampling and selection stages involving Monte Carlo and molecular dynamics simulations and classification using an SVM predictor. The initial implementation was shown to consistently refine protein structures 76% of the time in our own internal benchmarking on CASP 7‐10 targets. In this work, we improved the sampling and selection stages and tested the method in blind predictions during CASP11. We added a decomposition of physics‐based and hybrid energy functions, as well as a coordinate‐free representation of the protein structure through distance‐binning distances to capture fine‐grained movements. We performed parameter estimation to optimize the adjustable SVM parameters to maximize precision while balancing sensitivity and specificity across all cross‐validated data sets, finding enrichment in our ability to select models from the populations of similar decoys generated for targets in CASPs 7‐10. The MD stage was enhanced such that larger structures could be further refined. Among refinement methods that are currently implemented as web‐servers, Princeton_TIGRESS 2.0 demonstrated the most consistent and most substantial net refinement in blind predictions during CASP11. The enhanced refinement protocol Princeton_TIGRESS 2.0 is freely available as a web server at http://atlas.engr.tamu.edu/refinement/ . Proteins 2017; 85:1078–1098. © 2017 Wiley Periodicals, Inc.     

Consistent refinement of submitted models at CASP using a knowledge‐based potential

Protein structure refinement is an important but unsolved problem; it must be solved if we are to predict biological function that is very sensitive to structural details. Specifically, critical assessment of techniques for protein structure prediction (CASP) shows that the accuracy of predictions in the comparative modeling category is often worse than that of the template on which the homology model is based. Here we describe a refinement protocol that is able to consistently refine submitted predictions for all categories at CASP7. The protocol uses direct energy minimization of the knowledge‐based potential of mean force that is based on the interaction statistics of 167 atom types (Summa and Levitt, Proc Natl Acad Sci USA 2007; 104:3177–3182). Our protocol is thus computationally very efficient; it only takes a few minutes of CPU time to run typical protein models (300 residues). We observe an average structural improvement of 1% in GDT_TS, for predictions that have low and medium homology to known PDB structures (Global Distance Test score or GDT_TS between 50 and 80%). We also observe a marked improvement in the stereochemistry of the models. The level of improvement varies amongst the various participants at CASP, but we see large improvements (>10% increase in GDT_TS) even for models predicted by the best performing groups at CASP7. In addition, our protocol consistently improved the best predicted models in the refinement category at CASP7 and CASP8. These improvements in structure and stereochemistry prove the usefulness of our computationally inexpensive, powerful and automatic refinement protocol. Proteins 2010. © 2010 Wiley‐Liss, Inc.     

CASP10–BCL::Fold efficiently samples topologies of large proteins

During CASP10 in summer 2012, we tested BCL::Fold for prediction of free modeling (FM) and template‐based modeling (TBM) targets. BCL::Fold assembles the tertiary structure of a protein from predicted secondary structure elements (SSEs) omitting more flexible loop regions early on. This approach enables the sampling of conformational space for larger proteins with more complex topologies. In preparation of CASP11, we analyzed the quality of CASP10 models throughout the prediction pipeline to understand BCL::Fold's ability to sample the native topology, identify native‐like models by scoring and/or clustering approaches, and our ability to add loop regions and side chains to initial SSE‐only models. The standout observation is that BCL::Fold sampled topologies with a GDT_TS score > 33% for 12 of 18 and with a topology score > 0.8 for 11 of 18 test cases de novo. Despite the sampling success of BCL::Fold, significant challenges still exist in clustering and loop generation stages of the pipeline. The clustering approach employed for model selection often failed to identify the most native‐like assembly of SSEs for further refinement and submission. It was also observed that for some β‐strand proteins model refinement failed as β‐strands were not properly aligned to form hydrogen bonds removing otherwise accurate models from the pool. Further, BCL::Fold samples frequently non‐natural topologies that require loop regions to pass through the center of the protein. Proteins 2015; 83:547–563. © 2015 Wiley Periodicals, Inc.     

Efficient identification of near‐native conformations in ab initio protein structure prediction using structural profiles

One of the major bottlenecks in many ab initio protein structure prediction methods is currently the selection of a small number of candidate structures for high‐resolution refinement from large sets of low‐resolution decoys. This step often includes a scoring by low‐resolution energy functions and a clustering of conformations by their pairwise root mean square deviations (RMSDs). As an efficient selection is crucial to reduce the overall computational cost of the predictions, any improvement in this direction can increase the overall performance of the predictions and the range of protein structures that can be predicted. We show here that the use of structural profiles, which can be predicted with good accuracy from the amino acid sequences of proteins, provides an efficient means to identify good candidate structures. Proteins 2010. © 2009 Wiley‐Liss, Inc.     

Predicted residue–residue contacts can help the scoring of 3D models

During the 7th Critical Assessment of Protein Structure Prediction (CASP7) experiment, it was suggested that the real value of predicted residue–residue contacts might lie in the scoring of 3D model structures. Here, we have carried out a detailed reassessment of the contact predictions made during the recent CASP8 experiment to determine whether predicted contacts might aid in the selection of close‐to‐native structures or be a useful tool for scoring 3D structural models. We used the contacts predicted by the CASP8 residue–residue contact prediction groups to select models for each target domain submitted to the experiment. We found that the information contained in the predicted residue–residue contacts would probably have helped in the selection of 3D models in the free modeling regime and over the harder comparative modeling targets. Indeed, in many cases, the models selected using just the predicted contacts had better GDT‐TS scores than all but the best 3D prediction groups. Despite the well‐known low accuracy of residue–residue contact predictions, it is clear that the predictive power of contacts can be useful in 3D model prediction strategies. Proteins 2010. © 2010 Wiley‐Liss, Inc.     

Refinement of protein structure homology models via long, all-atom molecular dynamics simulations

Accurate computational prediction of protein structure represents a longstanding challenge in molecular biology and structure-based drug design. Although homology modeling techniques are widely used to produce low-resolution models, refining these models to high resolution has proven difficult. With long enough simulations and sufficiently accurate force fields, molecular dynamics (MD) simulations should in principle allow such refinement, but efforts to refine homology models using MD have for the most part yielded disappointing results. It has thus far been unclear whether MD-based refinement is limited primarily by accessible simulation timescales, force field accuracy, or both. Here, we examine MD as a technique for homology model refinement using all-atom simulations, each at least 100 μs long-more than 100 times longer than previous refinement simulations-and a physics-based force field that was recently shown to successfully fold a structurally diverse set of fast-folding proteins. In MD simulations of 24 proteins chosen from the refinement category of recent Critical Assessment of Structure Prediction (CASP) experiments, we find that in most cases, simulations initiated from homology models drift away from the native structure. Comparison with simulations initiated from the native structure suggests that force field accuracy is the primary factor limiting MD-based refinement. This problem can be mitigated to some extent by restricting sampling to the neighborhood of the initial model, leading to structural improvement that, while limited, is roughly comparable to the leading alternative methods.     

A global machine learning based scoring function for protein structure prediction

We present a knowledge‐based function to score protein decoys based on their similarity to native structure. A set of features is constructed to describe the structure and sequence of the entire protein chain. Furthermore, a qualitative relationship is established between the calculated features and the underlying electromagnetic interaction that dominates this scale. The features we use are associated with residue–residue distances, residue–solvent distances, pairwise knowledge‐based potentials and a four‐body potential. In addition, we introduce a new target to be predicted, the fitness score, which measures the similarity of a model to the native structure. This new approach enables us to obtain information both from decoys and from native structures. It is also devoid of previous problems associated with knowledge‐based potentials. These features were obtained for a large set of native and decoy structures and a back‐propagating neural network was trained to predict the fitness score. Overall this new scoring potential proved to be superior to the knowledge‐based scoring functions used as its inputs. In particular, in the latest CASP (CASP10) experiment our method was ranked third for all targets, and second for freely modeled hard targets among about 200 groups for top model prediction. Ours was the only method ranked in the top three for all targets and for hard targets. This shows that initial results from the novel approach are able to capture details that were missed by a broad spectrum of protein structure prediction approaches. Source codes and executable from this work are freely available at http://mathmed.org /#Software and http://mamiris.com/ . Proteins 2014; 82:752–759. © 2013 Wiley Periodicals, Inc.     

Partial unfolding and refolding for structure refinement: A unified approach of geometric simulations and molecular dynamics

The most successful protein structure prediction methods to date have been template‐based modeling (TBM) or homology modeling, which predicts protein structure based on experimental structures. These high accuracy predictions sometimes retain structural errors due to incorrect templates or a lack of accurate templates in the case of low sequence similarity, making these structures inadequate in drug‐design studies or molecular dynamics simulations. We have developed a new physics based approach to the protein refinement problem by mimicking the mechanism of chaperons that rehabilitate misfolded proteins. The template structure is unfolded by selectively (targeted) pulling on different portions of the protein using the geometric based technique FRODA, and then refolded using hierarchically restrained replica exchange molecular dynamics simulations (hr‐REMD). FRODA unfolding is used to create a diverse set of topologies for surveying near native‐like structures from a template and to provide a set of persistent contacts to be employed during re‐folding. We have tested our approach on 13 previous CASP targets and observed that this method of folding an ensemble of partially unfolded structures, through the hierarchical addition of contact restraints (that is, first local and then nonlocal interactions), leads to a refolding of the structure along with refinement in most cases (12/13). Although this approach yields refined models through advancement in sampling, the task of blind selection of the best refined models still needs to be solved. Overall, the method can be useful for improved sampling for low resolution models where certain of the portions of the structure are incorrectly modeled. Proteins 2015; 83:2279–2292. © 2015 Wiley Periodicals, Inc.     

Selective refinement and selection of near‐native models in protein structure prediction

In recent years in silico protein structure prediction reached a level where fully automated servers can generate large pools of near‐native structures. However, the identification and further refinement of the best structures from the pool of models remain problematic. To address these issues, we have developed (i) a target‐specific selective refinement (SR) protocol; and (ii) molecular dynamics (MD) simulation based ranking (SMDR) method. In SR the all‐atom refinement of structures is accomplished via the Rosetta Relax protocol, subject to specific constraints determined by the size and complexity of the target. The best‐refined models are selected with SMDR by testing their relative stability against gradual heating through all‐atom MD simulations. Through extensive testing we have found that Mufold‐MD, our fully automated protein structure prediction server updated with the SR and SMDR modules consistently outperformed its previous versions. Proteins 2015; 83:1823–1835. © 2015 Wiley Periodicals, Inc.     

Progress and challenges in high-resolution refinement of protein structure models

Achieving atomic level accuracy in de novo structure prediction presents a formidable challenge even in the context of protein models with correct topologies. High-resolution refinement is a fundamental test of force field accuracy and sampling methodology, and its limited success in both comparative modeling and de novo prediction contexts highlights the limitations of current approaches. We constructed four tests to identify bottlenecks in our current approach and to guide progress in this challenging area. The first three tests showed that idealized native structures are stable under our refinement simulation conditions and that the refinement protocol can significantly decrease the root mean square deviation (RMSD) of perturbed native structures. In the fourth test we applied the refinement protocol to de novo models and showed that accurate models could be identified based on their energies, and in several cases many of the buried side chains adopted native-like conformations. We also showed that the differences in backbone and side-chain conformations between the refined de novo models and the native structures are largely localized to loop regions and regions where the native structure has unusual features such as rare rotamers or atypical hydrogen bonding between beta-strands. The refined de novo models typically have higher energies than refined idealized native structures, indicating that sampling of local backbone conformations and side-chain packing arrangements in a condensed state is a primary obstacle.     

Protein structure validation by generalized linear model root-mean-square deviation prediction

Large-scale initiatives for obtaining spatial protein structures by experimental or computational means have accentuated the need for the critical assessment of protein structure determination and prediction methods. These include blind test projects such as the critical assessment of protein structure prediction (CASP) and the critical assessment of protein structure determination by nuclear magnetic resonance (CASD-NMR). An important aim is to establish structure validation criteria that can reliably assess the accuracy of a new protein structure. Various quality measures derived from the coordinates have been proposed. A universal structural quality assessment method should combine multiple individual scores in a meaningful way, which is challenging because of their different measurement units. Here, we present a method based on a generalized linear model (GLM) that combines diverse protein structure quality scores into a single quantity with intuitive meaning, namely the predicted coordinate root-mean-square deviation (RMSD) value between the present structure and the (unavailable) "true" structure (GLM-RMSD). For two sets of structural models from the CASD-NMR and CASP projects, this GLM-RMSD value was compared with the actual accuracy given by the RMSD value to the corresponding, experimentally determined reference structure from the Protein Data Bank (PDB). The correlation coefficients between actual (model vs. reference from PDB) and predicted (model vs. "true") heavy-atom RMSDs were 0.69 and 0.76, for the two datasets from CASD-NMR and CASP, respectively, which is considerably higher than those for the individual scores (-0.24 to 0.68). The GLM-RMSD can thus predict the accuracy of protein structures more reliably than individual coordinate-based quality scores.     

Assessment of protein model structure accuracy estimation in CASP13: Challenges in the era of deep learning

Scoring model structure is an essential component of protein structure prediction that can affect the prediction accuracy tremendously. Users of protein structure prediction results also need to score models to select the best models for their application studies. In Critical Assessment of techniques for protein Structure Prediction (CASP), model accuracy estimation methods have been tested in a blind fashion by providing models submitted by the tertiary structure prediction servers for scoring. In CASP13, model accuracy estimation results were evaluated in terms of both global and local structure accuracy. Global structure accuracy estimation was evaluated by the quality of the models selected by the global structure scores and by the absolute estimates of the global scores. Residue-wise, local structure accuracy estimations were evaluated by three different measures. A new measure introduced in CASP13 evaluates the ability to predict inaccurately modeled regions that may be improved by refinement. An intensive comparative analysis on CASP13 and the previous CASPs revealed that the tertiary structure models generated by the CASP13 servers show very distinct features. Higher consensus toward models of higher global accuracy appeared even for free modeling targets, and many models of high global accuracy were not well optimized at the atomic level. This is related to the new technology in CASP13, deep learning for tertiary contact prediction. The tertiary model structures generated by deep learning pose a new challenge for EMA (estimation of model accuracy) method developers. Model accuracy estimation itself is also an area where deep learning can potentially have an impact, although current EMA methods have not fully explored that direction.     

Protein structure prediction using sparse NOE and RDC restraints with Rosetta in CASP13

Computational methods that produce accurate protein structure models from limited experimental data, for example, from nuclear magnetic resonance (NMR) spectroscopy, hold great potential for biomedical research. The NMR-assisted modeling challenge in CASP13 provided a blind test to explore the capabilities and limitations of current modeling techniques in leveraging NMR data which had high sparsity, ambiguity, and error rate for protein structure prediction. We describe our approach to predict the structure of these proteins leveraging the Rosetta software suite. Protein structure models were predicted de novo using a two-stage protocol. First, low-resolution models were generated with the Rosetta de novo method guided by nonambiguous nuclear Overhauser effect (NOE) contacts and residual dipolar coupling (RDC) restraints. Second, iterative model hybridization and fragment insertion with the Rosetta comparative modeling method was used to refine and regularize models guided by all ambiguous and nonambiguous NOE contacts and RDCs. Nine out of 16 of the Rosetta de novo models had the correct fold (global distance test total score > 45) and in three cases high-resolution models were achieved (root-mean-square deviation < 3.5 å). We also show that a meta-approach applying iterative Rosetta + NMR refinement on server-predicted models which employed non-NMR-contacts and structural templates leads to substantial improvement in model quality. Integrating these data-assisted refinement strategies with innovative non-data-assisted approaches which became possible in CASP13 such as high precision contact prediction will in the near future enable structure determination for large proteins that are outside of the realm of conventional NMR.     

Template‐free protein structure prediction and quality assessment with an all‐atom free‐energy model

Biophysical forcefields have contributed less than originally anticipated to recent progress in protein structure prediction. Here, we have investigated the selectivity of a recently developed all‐atom free‐energy forcefield for protein structure prediction and quality assessment (QA). Using a heuristic method, but excluding homology, we generated decoy‐sets for all targets of the CASP7 protein structure prediction assessment with <150 amino acids. The decoys in each set were then ranked by energy in short relaxation simulations and the best low‐energy cluster was submitted as a prediction. For four of nine template‐free targets, this approach generated high‐ranking predictions within the top 10 models submitted in CASP7 for the respective targets. For these targets, our de‐novo predictions had an average GDT_S score of 42.81, significantly above the average of all groups. The refinement protocol has difficulty for oligomeric targets and when no near‐native decoys are generated in the decoy library. For targets with high‐quality decoy sets the refinement approach was highly selective. Motivated by this observation, we rescored all server submissions up to 200 amino acids using a similar refinement protocol, but using no clustering, in a QA exercise. We found an excellent correlation between the best server models and those with the lowest energy in the forcefield. The free‐energy refinement protocol may thus be an efficient tool for relative QA and protein structure prediction. Proteins 2009. © 2009 Wiley‐Liss, Inc.     

Mimicking the action of folding chaperones by Hamiltonian replica-exchange molecular dynamics simulations: application in the refinement of de novo models

The efficiency of using a variant of Hamiltonian replica‐exchange molecular dynamics (Chaperone H‐replica‐exchange molecular dynamics [CH‐REMD]) for the refinement of protein structural models generated de novo is investigated. In CH‐REMD, the interaction between the protein and its environment, specifically, the electrostatic interaction between the protein and the solvating water, is varied leading to cycles of partial unfolding and refolding mimicking some aspects of folding chaperones. In 10 of the 15 cases examined, the CH‐REMD approach sampled structures in which the root‐mean‐square deviation (RMSD) of secondary structure elements (SSE‐RMSD) with respect to the experimental structure was more than 1.0 Å lower than the initial de novo model. In 14 of the 15 cases, the improvement was more than 0.5 Å. The ability of three different statistical potentials to identify near‐native conformations was also examined. Little correlation between the SSE‐RMSD of the sampled structures with respect to the experimental structure and any of the scoring functions tested was found. The most effective scoring function tested was the DFIRE potential. Using the DFIRE potential, the SSE‐RMSD of the best scoring structures was on average 0.3 Å lower than the initial model. Overall the work demonstrates that targeted enhanced‐sampling techniques such as CH‐REMD can lead to the systematic refinement of protein structural models generated de novo but that improved potentials for the identification of near‐native structures are still needed. Proteins 2012; © 2012 Wiley Periodicals, Inc.     

MUFOLD: A new solution for protein 3D structure prediction

There have been steady improvements in protein structure prediction during the past 2 decades. However, current methods are still far from consistently predicting structural models accurately with computing power accessible to common users. Toward achieving more accurate and efficient structure prediction, we developed a number of novel methods and integrated them into a software package, MUFOLD. First, a systematic protocol was developed to identify useful templates and fragments from Protein Data Bank for a given target protein. Then, an efficient process was applied for iterative coarse‐grain model generation and evaluation at the Cα or backbone level. In this process, we construct models using interresidue spatial restraints derived from alignments by multidimensional scaling, evaluate and select models through clustering and static scoring functions, and iteratively improve the selected models by integrating spatial restraints and previous models. Finally, the full‐atom models were evaluated using molecular dynamics simulations based on structural changes under simulated heating. We have continuously improved the performance of MUFOLD by using a benchmark of 200 proteins from the Astral database, where no template with >25% sequence identity to any target protein is included. The average root‐mean‐square deviation of the best models from the native structures is 4.28 Å, which shows significant and systematic improvement over our previous methods. The computing time of MUFOLD is much shorter than many other tools, such as Rosetta. MUFOLD demonstrated some success in the 2008 community‐wide experiment for protein structure prediction CASP8. Proteins 2010. © 2009 Wiley‐Liss, Inc.