Free-energy landscape of the villin headpiece in an all-atom force field

We investigate the landscape of the internal free-energy of the 36 amino acid villin headpiece with a modified basin hopping method in the all-atom force field PFF01, which was previously used to predictively fold several helical proteins with atomic resolution. We identify near native conformations of the protein as the global optimum of the force field. More than half of the twenty best simulations started from random initial conditions converge to the folding funnel of the native conformation, but several competing low-energy metastable conformations were observed. From 76,000 independently generated conformations we derived a decoy tree which illustrates the topological structure of the entire low-energy part of the free-energy landscape and characterizes the ensemble of metastable conformations. These emerge as similar in secondary content, but differ in tertiary arrangement.     

Protein structure prediction by all-atom free-energy refinement

Background  

The reliable prediction of protein tertiary structure from the amino acid sequence remains challenging even for small proteins. We have developed an all-atom free-energy protein forcefield (PFF01) that we could use to fold several small proteins from completely extended conformations. Because the computational cost of de-novo folding studies rises steeply with system size, this approach is unsuitable for structure prediction purposes. We therefore investigate here a low-cost free-energy relaxation protocol for protein structure prediction that combines heuristic methods for model generation with all-atom free-energy relaxation in PFF01.     

An all-atom force field for tertiary structure prediction of helical proteins

We have developed an all-atom free-energy force field (PFF01) for protein tertiary structure prediction. PFF01 is based on physical interactions and was parameterized using experimental structures of a family of proteins believed to span a wide variety of possible folds. It contains empirical, although sequence-independent terms for hydrogen bonding. Its solvent-accessible surface area solvent model was first fit to transfer energies of small peptides. The parameters of the solvent model were then further optimized to stabilize the native structure of a single protein, the autonomously folding villin headpiece, against competing low-energy decoys. Here we validate the force field for five nonhomologous helical proteins with 20-60 amino acids. For each protein, decoys with 2-3 A backbone root mean-square deviation and correct experimental Cbeta-Cbeta distance constraints emerge as those with the lowest energy.     

GSAFold: a new application of GSA to protein structure prediction

The folding process defines three‐dimensional protein structures from their amino acid chains. A protein's structure determines its activity and properties; thus knowing such conformation on an atomic level is essential for both basic and applied studies of protein function and dynamics. However, the acquisition of such structures by experimental methods is slow and expensive, and current computational methods mostly depend on previously known structures to determine new ones. Here we present a new software called GSAFold that applies the generalized simulated annealing (GSA) algorithm on ab initio protein structure prediction. The GSA is a stochastic search algorithm employed in energy minimization and used in global optimization problems, especially those that depend on long‐range interactions, such as gravity models and conformation optimization of small molecules. This new implementation applies, for the first time in ab initio protein structure prediction, an analytical inverse for the Visitation function of GSA. It also employs the broadly used NAMD Molecular Dynamics package to carry out energy calculations, allowing the user to select different force fields and parameterizations. Moreover, the software also allows the execution of several simulations simultaneously. Applications that depend on protein structures include rational drug design and structure‐based protein function prediction. Applying GSAFold in a test peptide, it was possible to predict the structure of mastoparan‐X to a root mean square deviation of 3.00 Å. Proteins 2012; © 2012 Wiley Periodicals, Inc.     

A Free-Energy Approach for All-Atom Protein Simulation

All-atom free-energy methods offer a promising alternative to kinetic molecular mechanics simulations of protein folding and association. Here we report an accurate, transferable all-atom biophysical force field (PFF02) that stabilizes the native conformation of a wide range of proteins as the global optimum of the free-energy landscape. For 32 proteins of the ROSETTA decoy set and six proteins that we have previously folded with PFF01, we find near-native conformations with an average backbone RMSD of 2.14 Å to the native conformation and an average Z-score of −3.46 to the corresponding decoy set. We used nonequilibrium sampling techniques starting from completely extended conformations to exhaustively sample the energy surface of three nonhomologous hairpin-peptides, a three-stranded β-sheet, the all-helical 40 amino-acid HIV accessory protein, and a zinc-finger ββα motif, and find near-native conformations for the minimal energy for each protein. Using a massively parallel evolutionary algorithm, we also obtain a near-native low-energy conformation for the 54 amino-acid engrailed homeodomain. Our force field thus stabilized near-native conformations for a total of 20 proteins of all structure classes with an average RMSD of only 3.06 Å to their respective experimental conformations.     

Recapitulation of protein family divergence using flexible backbone protein design

We use flexible backbone protein design to explore the sequence and structure neighborhoods of naturally occurring proteins. The method samples sequence and structure space in the vicinity of a known sequence and structure by alternately optimizing the sequence for a fixed protein backbone using rotamer based sequence search, and optimizing the backbone for a fixed amino acid sequence using atomic-resolution structure prediction. We find that such a flexible backbone design method better recapitulates protein family sequence variation than sequence optimization on fixed backbones or randomly perturbed backbone ensembles for ten diverse protein structures. For the SH3 domain, the backbone structure variation in the family is also better recapitulated than in randomly perturbed backbones. The potential application of this method as a model of protein family evolution is highlighted by a concerted transition to the amino acid sequence in the structural core of one SH3 domain starting from the backbone coordinates of an homologous structure.     

Chaotic Artificial Bee Colony algorithm: A new approach to the problem of minimization of energy of the 3D protein structure

Prediction of the three-dimensional structure of a protein from its amino acid sequence can be considered as a global optimization problem. In this paper, the Chaotic Artificial Bee Colony (CABC) algorithm was introduced and applied to 3D protein structure prediction. Based on the 3D off-lattice AB model, the CABC algorithm combines global search and local search of the Artificial Bee Colony (ABC) algorithm with the chaotic search algorithm to avoid the problem of premature convergence and easily trapping the local optimum solution. The experiments carried out with the popular Fibonacci sequences demonstrate that the proposed algorithm provides an effective and high-performance method for protein structure prediction.     

Prediction of protein secondary structure content using amino acid composition and evolutionary information

Knowing protein structure and inferring its function from the structure are one of the main issues of computational structural biology, and often the first step is studying protein secondary structure. There have been many attempts to predict protein secondary structure contents. Previous attempts assumed that the content of protein secondary structure can be predicted successfully using the information on the amino acid composition of a protein. Recent methods achieved remarkable prediction accuracy by using the expanded composition information. The overall average error of the most successful method is 3.4%. Here, we demonstrate that even if we only use the simple amino acid composition information alone, it is possible to improve the prediction accuracy significantly if the evolutionary information is included. The idea is motivated by the observation that evolutionarily related proteins share the similar structure. After calculating the homolog-averaged amino acid composition of a protein, which can be easily obtained from the multiple sequence alignment by running PSI-BLAST, those 20 numbers are learned by a multiple linear regression, an artificial neural network and a support vector regression. The overall average error of method by a support vector regression is 3.3%. It is remarkable that we obtain the comparable accuracy without utilizing the expanded composition information such as pair-coupled amino acid composition. This work again demonstrates that the amino acid composition is a fundamental characteristic of a protein. It is anticipated that our novel idea can be applied to many areas of protein bioinformatics where the amino acid composition information is utilized, such as subcellular localization prediction, enzyme subclass prediction, domain boundary prediction, signal sequence prediction, and prediction of unfolded segment in a protein sequence, to name a few.     

Predicting peptide binding to MHC pockets via molecular modeling, implicit solvation, and global optimization

Development of a computational prediction method based on molecular modeling, global optimization, and implicit solvation has produced accurate structure and relative binding affinity predictions for peptide amino acids binding to five pockets of the MHC molecule HLA-DRB1*0101. Because peptide binding to MHC molecules is essential to many immune responses, development of such a method for understanding and predicting the forces that drive binding is crucial for pharmaceutical design and disease treatment. Underlying the development of this prediction method are two hypotheses. The first is that pockets formed by the peptide binding groove of MHC molecules are independent, separating the prediction of peptide amino acids that bind within individual pockets from those that bind between pockets. The second hypothesis is that the native state of a system composed of an amino acid bound to a protein pocket corresponds to the system's lowest free energy. The prediction method developed from these hypotheses uses atomistic-level modeling, deterministic global optimization, and three methods of implicit solvation: solvent-accessible area, solvent-accessible volume, and Poisson-Boltzmann electrostatics. The method predicts relative binding affinities of peptide amino acids for pockets of HLA-DRB1*0101 by determining computationally an amino acid's global minimum energy conformation. Prediction results from the method are in agreement with X-ray crystallography data and experimental binding assays.     

A seqlet-based maximum entropy Markov approach for protein secondary structure prediction

A novel method for predicting the secondary structures of proteins from amino acid sequence has been presented. The protein secondary structure seqlets that are analogous to the words in natural language have been extracted. These seqlets will capture the relationship between amino acid sequence and the secondary structures of proteins and further form the protein secondary structure dictionary. To be elaborate, the dictionary is organism-specific. Protein secondary structure prediction is formulated as an integrated word segmentation and part of speech tagging problem. The word-lattice is used to represent the results of the word segmentation and the maximum entropy model is used to calculate the probability of a seqlet tagged as a certain secondary structure type. The method is markovian in the seqlets, permitting efficient exact calculation of the posterior probability distribution over all possible word segmentations and their tags by viterbi algorithm. The optimal segmentations and their tags are computed as the results of protein secondary structure prediction. The method is applied to predict the secondary structures of proteins of four organisms respectively and compared with the PHD method. The results show that the performance of this method is higher than that of PHD by about 3.9% Q3 accuracy and 4.6% SOV accuracy. Combining with the local similarity protein sequences that are obtained by BLAST can give better prediction. The method is also tested on the 50 CASP5 target proteins with Q₃ accuracy 78.9% and SOV accuracy 77.1%. A web server for protein secondary structure prediction has been constructed which is available at http://www.insun.hit.edu.cn:81/demos/biology/index.html.     

A seqlet-based maximum entropy Markov approach for protein secondary structure prediction

1 Introduction The prediction of protein structure and function from amino acid sequences is one of the most impor-tant problems in molecular biology. This problem is becoming more pressing as the number of known pro-tein sequences is explored as a result of genome and other sequencing projects, and the protein sequence- structure gap is widening rapidly[1]. Therefore, com-putational tools to predict protein structures are needed to narrow the widening gap. Although the prediction of three dim…     

Prodepth: Predict Residue Depth by Support Vector Regression Approach from Protein Sequences Only

Residue depth (RD) is a solvent exposure measure that complements the information provided by conventional accessible surface area (ASA) and describes to what extent a residue is buried in the protein structure space. Previous studies have established that RD is correlated with several protein properties, such as protein stability, residue conservation and amino acid types. Accurate prediction of RD has many potentially important applications in the field of structural bioinformatics, for example, facilitating the identification of functionally important residues, or residues in the folding nucleus, or enzyme active sites from sequence information. In this work, we introduce an efficient approach that uses support vector regression to quantify the relationship between RD and protein sequence. We systematically investigated eight different sequence encoding schemes including both local and global sequence characteristics and examined their respective prediction performances. For the objective evaluation of our approach, we used 5-fold cross-validation to assess the prediction accuracies and showed that the overall best performance could be achieved with a correlation coefficient (CC) of 0.71 between the observed and predicted RD values and a root mean square error (RMSE) of 1.74, after incorporating the relevant multiple sequence features. The results suggest that residue depth could be reliably predicted solely from protein primary sequences: local sequence environments are the major determinants, while global sequence features could influence the prediction performance marginally. We highlight two examples as a comparison in order to illustrate the applicability of this approach. We also discuss the potential implications of this new structural parameter in the field of protein structure prediction and homology modeling. This method might prove to be a powerful tool for sequence analysis.     

MUFOLD‐SS: New deep inception‐inside‐inception networks for protein secondary structure prediction

Protein secondary structure prediction can provide important information for protein 3D structure prediction and protein functions. Deep learning offers a new opportunity to significantly improve prediction accuracy. In this article, a new deep neural network architecture, named the Deep inception‐inside‐inception (Deep3I) network, is proposed for protein secondary structure prediction and implemented as a software tool MUFOLD‐SS. The input to MUFOLD‐SS is a carefully designed feature matrix corresponding to the primary amino acid sequence of a protein, which consists of a rich set of information derived from individual amino acid, as well as the context of the protein sequence. Specifically, the feature matrix is a composition of physio‐chemical properties of amino acids, PSI‐BLAST profile, and HHBlits profile. MUFOLD‐SS is composed of a sequence of nested inception modules and maps the input matrix to either eight states or three states of secondary structures. The architecture of MUFOLD‐SS enables effective processing of local and global interactions between amino acids in making accurate prediction. In extensive experiments on multiple datasets, MUFOLD‐SS outperformed the best existing methods and other deep neural networks significantly. MUFold‐SS can be downloaded from http://dslsrv8.cs.missouri.edu/~cf797/MUFoldSS/download.html .     

基于遗传算法的蛋白质结构预测方法

遗传算法源于自然界的进化规律,是一种自适应启发式概率性迭代式全局搜索算法。本文主要介绍了GA的基本原理,算法及优点;总结GA在蛋白质结构预测中建立模型和执行策略,以及多种算法相互结合预测蛋白质结构的研究进展。     

Machine learning techniques for protein function prediction

Proteins play important roles in living organisms, and their function is directly linked with their structure. Due to the growing gap between the number of proteins being discovered and their functional characterization (in particular as a result of experimental limitations), reliable prediction of protein function through computational means has become crucial. This paper reviews the machine learning techniques used in the literature, following their evolution from simple algorithms such as logistic regression to more advanced methods like support vector machines and modern deep neural networks. Hyperparameter optimization methods adopted to boost prediction performance are presented. In parallel, the metamorphosis in the features used by these algorithms from classical physicochemical properties and amino acid composition, up to text-derived features from biomedical literature and learned feature representations using autoencoders, together with feature selection and dimensionality reduction techniques, are also reviewed. The success stories in the application of these techniques to both general and specific protein function prediction are discussed.     

Hybrid Global Optimization Algorithms for Protein Structure Prediction: Alternating Hybrids

Hybrid global optimization methods attempt to combine the beneficial features of two or more algorithms, and can be powerful methods for solving challenging nonconvex optimization problems. In this paper, novel classes of hybrid global optimization methods, termed alternating hybrids, are introduced for application as a tool in treating the peptide and protein structure prediction problems. In particular, these new optimization methods take the form of hybrids between a deterministic global optimization algorithm, the αBB, and a stochastically based method, conformational space annealing (CSA). The αBB method, as a theoretically proven global optimization approach, exhibits consistency, as it guarantees convergence to the global minimum for twice-continuously differentiable constrained nonlinear programming problems, but can benefit from computationally related enhancements. On the other hand, the independent CSA algorithm is highly efficient, though the method lacks theoretical guarantees of convergence. Furthermore, both the αBB method and the CSA method are found to identify ensembles of low-energy conformers, an important feature for determining the true free energy minimum of the system. The proposed hybrid methods combine the desirable features of efficiency and consistency, thus enabling the accurate prediction of the structures of larger peptides. Computational studies for met-enkephalin and melittin, employing sequential and parallel computing frameworks, demonstrate the promise for these proposed hybrid methods.     

Role of conformational sampling in computing mutation-induced changes in protein structure and stability

The prediction of changes in protein stability and structure resulting from single amino acid substitutions is both a fundamental test of macromolecular modeling methodology and an important current problem as high throughput sequencing reveals sequence polymorphisms at an increasing rate. In principle, given the structure of a wild-type protein and a point mutation whose effects are to be predicted, an accurate method should recapitulate both the structural changes and the change in the folding-free energy. Here, we explore the performance of protocols which sample an increasing diversity of conformations. We find that surprisingly similar performances in predicting changes in stability are achieved using protocols that involve very different amounts of conformational sampling, provided that the resolution of the force field is matched to the resolution of the sampling method. Methods involving backbone sampling can in some cases closely recapitulate the structural changes accompanying mutations but not surprisingly tend to do more harm than good in cases where structural changes are negligible. Analysis of the outliers in the stability change calculations suggests areas needing particular improvement; these include the balance between desolvation and the formation of favorable buried polar interactions, and unfolded state modeling.