Zhiquan He

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.

Transmembrane Protein Alignment and Fold Recognition Based on Predicted Topology

Background Although Transmembrane Proteins (TMPs) are highly important in various biological processes and pharmaceutical developments, general prediction of TMP structures is still far from satisfactory. Because TMPs have significantly different physicochemical properties from soluble proteins, current protein structure prediction tools for soluble proteins may not work well for TMPs. With the increasing number of experimental TMP structures available, template-based methods have the potential to become broadly applicable for TMP structure prediction. However, the current fold recognition methods for TMPs are not as well developed as they are for soluble proteins. Methodology We developed a novel TMP Fold Recognition method, TMFR, to recognize TMP folds based on sequence-to-structure pairwise alignment. The method utilizes topology-based features in alignment together with sequence profile and solvent accessibility. It also incorporates a gap penalty that depends on predicted topology structure segments. Given the difference between α-helical transmembrane protein (αTMP) and β-strands transmembrane protein (βTMP), parameters of scoring functions are trained respectively for these two protein categories using 58 αTMPs and 17 βTMPs in a non-redundant training dataset. Results We compared our method with HHalign, a leading alignment tool using a non-redundant testing dataset including 72 αTMPs and 30 βTMPs. Our method achieved 10% and 9% better accuracies than HHalign in αTMPs and βTMPs, respectively. The raw score generated by TMFR is negatively correlated with the structure similarity between the target and the template, which indicates its effectiveness for fold recognition. The result demonstrates TMFR provides an effective TMP-specific fold recognition and alignment method.

Protein Structural Model Selection by Combining Consensus and Single Scoring Methods

Quality assessment (QA) for predicted protein structural models is an important and challenging research problem in protein structure prediction. Consensus Global Distance Test (CGDT) methods assess each decoy (predicted structural model) based on its structural similarity to all others in a decoy set and has been proved to work well when good decoys are in a majority cluster. Scoring functions evaluate each single decoy based on its structural properties. Both methods have their merits and limitations. In this paper, we present a novel method called PWCom, which consists of two neural networks sequentially to combine CGDT and single model scoring methods such as RW, DDFire and OPUS-Ca. Specifically, for every pair of decoys, the difference of the corresponding feature vectors is input to the first neural network which enables one to predict whether the decoy-pair are significantly different in terms of their GDT scores to the native. If yes, the second neural network is used to decide which one of the two is closer to the native structure. The quality score for each decoy in the pool is based on the number of winning times during the pairwise comparisons. Test results on three benchmark datasets from different model generation methods showed that PWCom significantly improves over consensus GDT and single scoring methods. The QA server (MUFOLD-Server) applying this method in CASP 10 QA category was ranked the second place in terms of Pearson and Spearman correlation performance.

A multilayer evaluation approach for protein structure prediction and model quality assessment.

Protein tertiary structures are essential for studying functions of proteins at molecular level. An indispensable approach for protein structure solution is computational prediction. Most protein structure prediction methods generate candidate models first and select the best candidates by model quality assessment (QA). In many cases, good models can be produced, but the QA tools fail to select the best ones from the candidate model pool. Because of incomplete understanding of protein folding, each QA method only reflects partial facets of a structure model and thus has limited discerning power with no one consistently outperforming others. In this article, we developed a set of new QA methods, including two QA methods for evaluating target/template alignments, a molecular dynamics (MD)‐based QA method, and three consensus QA methods with selected references to reveal new facets of protein structures complementary to the existing methods. Moreover, the underlying relationship among different QA methods were analyzed and then integrated into a multilayer evaluation approach to guide the model generation and model selection in prediction. All methods are integrated and implemented into an innovative and improved prediction system hereafter referred to as MUFOLD. In CASP8 and CASP9, MUFOLD has demonstrated the proof of the principles in terms of both QA discerning power and structure prediction accuracy. Proteins 2011;

Prediction of protein tertiary structures using MUFOLD.

There have been steady improvements in protein structure prediction during the past two decades. However, current methods are still far from consistently predicting structural models accurately with computing power accessible to common users. To address this challenge, we developed MUFOLD, a hybrid method of using whole and partial template information along with new computational techniques for protein tertiary structure prediction. MUFOLD covers both template-based and ab initio predictions using the same framework and aims to achieve high accuracy and fast computing. Two major novel contributions of MUFOLD are graph-based model generation and molecular dynamics ranking (MDR). By formulating a prediction as a graph realization problem, we apply an efficient optimization approach of Multidimensional Scaling (MDS) to speed up the prediction dramatically. In addition, under this framework, we enhance the predictions consistently by iteratively using the information from generated models. MDR, in contrast to widely used static scoring functions, exploits dynamics properties of structures to evaluate their qualities, which can often identify best structures from a pool more effectively.

A sampling-based method for ranking protein structural models by integrating multiple scores and features.

One of the major challenges in protein tertiary structure prediction is structure quality assessment. In many cases, protein structure prediction tools generate good structural models, but fail to select the best models from a huge number of candidates as the final output. In this study, we developed a sampling-based machine-learning method to rank protein structural models by integrating multiple scores and features. First, features such as predicted secondary structure, solvent accessibility and residue-residue contact information are integrated by two Radial Basis Function (RBF) models trained from different datasets. Then, the two RBF scores and five selected scoring functions developed by others, i.e., Opus-CA, Opus-PSP, DFIRE, RAPDF, and Cheng Score are synthesized by a sampling method. At last, another integrated RBF model ranks the structural models according to the features of sampling distribution. We tested the proposed method by using two different datasets, including the CASP server prediction models of all CASP8 targets and a set of models generated by our in-house software MUFOLD. The test result shows that our method outperforms any individual scoring function on both best model selection, and overall correlation between the predicted ranking and the actual ranking of structural quality.

A Fast Projection-Based Algorithm for Clustering Big Data

With the fast development of various techniques, more and more data have been accumulated with the unique properties of large size (tall) and high dimension (wide). The era of big data is coming. How to understand and discover new knowledge from these data has attracted more and more scholars’ attention and has become the most important task in data mining. As one of the most important techniques in data mining, clustering analysis, a kind of unsupervised learning, could group a set data into objectives(clusters) that are meaningful, useful, or both. Thus, the technique has played very important role in knowledge discovery in big data. However, when facing the large-sized and high-dimensional data, most of the current clustering methods exhibited poor computational efficiency and high requirement of computational source, which will prevent us from clarifying the intrinsic properties and discovering the new knowledge behind the data. Based on this consideration, we developed a powerful clustering method, called MUFOLD-CL. The principle of the method is to project the data points to the centroid, and then to measure the similarity between any two points by calculating their projections on the centroid. The proposed method could achieve linear time complexity with respect to the sample size. Comparison with K-Means method on very large data showed that our method could produce better accuracy and require less computational time, demonstrating that the MUFOLD-CL can serve as a valuable tool, at least may play a complementary role to other existing methods, for big data clustering. Further comparisons with state-of-the-art clustering methods on smaller datasets showed that our method was fastest and achieved comparable accuracy. For the convenience of most scholars, a free soft package was constructed.

A New Hidden Markov Model for Protein Quality Assessment Using Compatibility Between Protein Sequence and Structure

Protein structure Quality Assessment (QA) is an essential component in protein structure prediction and analysis. The relationship between protein sequence and structure often serves as a basis for protein structure QA. In this work, we developed a new Hidden Markov Model (HMM) to assess the compatibility of protein sequence and structure for capturing their complex relationship. More specifically, the emission of the HMM consists of protein local structures in angular space, secondary structures, and sequence profiles. This model has two capabilities: (1) encoding local structure of each position by jointly considering sequence and structure information, and (2) assigning a global score to estimate the overall quality of a predicted structure, as well as local scores to assess the quality of specific regions of a structure, which provides useful guidance for targeted structure refinement. We compared the HMM model to state-of-art single structure quality assessment methods OPUSCA, DFIRE, GOAP, and RW in protein structure selection. Computational results showed our new score HMM.Z can achieve better overall selection performance on the benchmark datasets.

Selection of Near-Native Protein Structures by Means of Molecular Dynamics Simulations

In spite of recent advances, the problem of protein structure prediction from the amino acid sequence remains a challenging one. In general, once a large set of model protein structures is predicted one needs to define selection criteria for identifying the structure that is the closest to the native one. The most common way of discriminating between predicted structures of a given protein is to employ either knowledge or physics based energy functions. Here we present an alternative ranking method of the predicted structures of a protein by testing their stability during gradual heating achieved by all atom molecular dynamics (MD) simulations. In general, the smaller the RMSD of the structure of a protein is (with respect to its native one) the more stable this structure is. Thus, one can rank the quality of these structures by comparing the relative stability of the predicted structures against gradual heating. We refer to this approach as the MD-Ranking (MDR) method. We have successfully tested the MDR method on several sets of proteins. We have also tested the MDR method in the 2008 Critical Assessment of Techniques for Protein Structure Prediction (CASP8) competition as part of our MUFOLD-MD server, which worked as follows: i) it generated 10,000 structures using the ab initio method of the Rosetta software, ii) from these, 64 structures with the lowest Rosetta energy were selected, and iii) re-ranked with the MDR method. The top 5 models, with the best MDR score, were submitted to the CASP8 organizers. Based on the official CAP8 results, MUFOLD-MD was ranked as number one server in the Free Modeling category.Work supported by a grant from NIH [R21/R33-GM078601]. Major computer time was provided by the University of Missouri Bioinformatics Consortium.