Measures for the assessment of fuzzy predictions of protein secondary structure

Many of the recent secondary structure prediction methods incorporate the idea of fuzzy set theory, where instead of assigning a definite secondary structure to a query residue, probability for the residue being in each of the conformational states is estimated. Moreover, continuous assignment of conformational states to the experimentally observed protein structures can be performed in order to reflect inherent flexibility. Although various measures have been developed for evaluating performances of secondary structure prediction methods, they depend only on the most probable secondary structures. They do not assess the accuracy of the probabilities produced by fuzzy prediction methods, and they cannot incorporate information contained in continuous assignments of conformational states to observed structures. Three important measures for evaluating performance of a secondary structure prediction algorithm, Q score, Segment OVerlap (SOV) measure, and the k-state correlation coefficient (Corr), are deformed into fuzzy measures F score, Fuzzy OVerlap (FOV) measure, and the fuzzy correlation coefficient (Forr), so that the new measures not only assess probabilistic outputs of fuzzy prediction methods, but also incorporate information from continuous assignments of secondary structure. As an example of application, prediction results of four fuzzy secondary structure prediction methods, PSIPRED, PROFking, SABLE, and PREDICT, are assessed using the new fuzzy measures.     

Combining evolutionary information and neural networks to predict protein secondary structure

Using evolutionary information contained in multiple sequence alignments as input to neural networks, secondary structure can be predicted at significantly increased accuracy. Here, we extend our previous three-level system of neural networks by using additional input information derived from multiple alignments. Using a position-specific conservation weight as part of the input increases performance. Using the number of insertions and deletions reduces the tendency for overprediction and increases overall accuracy. Addition of the global amino acid content yields a further improvement, mainly in predicting structural class. The final network system has a sustained overall accuracy of 71.6% in a multiple cross-validation test on 126 unique protein chains. A test on a new set of 124 recently solved protein structures that have no significant sequence similarity to the learning set confirms the high level of accuracy. The average cross-validated accuracy for all 250 sequence-unique chains is above 72%. Using various data sets, the method is compared to alternative prediction methods, some of which also use multiple alignments: the performance advantage of the network system is at least 6 percentage points in three-state accuracy. In addition, the network estimates secondary structure content from multiple sequence alignments about as well as circular dichroism spectroscopy on a single protein and classifies 75% of the 250 proteins correctly into one of four protein structural classes. Of particular practical importance is the definition of a position-specific reliability index. For 40% of all residues the method has a sustained three-state accuracy of 88%, as high as the overall average for homology modelling. A further strength of the method is greatly increased accuracy in predicting the placement of secondary structure segments. © 1994 Wiley-Liss, Inc.     

自动编码器方法的蛋白质二级结构预测

蛋白质二级结构预测是进行蛋白质三级结构研究的重要基础,氨基酸的编码方式对二级结构预测有一定的影响。本文应用了一种新的组合编码方式,即将基团编码与位置特异性打分矩阵(PSSM)进行组合的编码方式。本文中提出的基团编码是针对氨基酸的一种新的编码方式,基团编码是根据氨基酸内部组成来进行编码的,由42位属性组成。本文选取位置特异性打分矩阵(PSSM)中的Blosum62进化矩阵和新的基团编码进行组合,形成新的编码方式。然后对CB513和25pdb两组数据分别进行实验。本文中将采用贝叶斯分类器与自动编码器两种方法来对这种新的编码方式进行实验,然后比较这两种方法得到的两组数据的结果。可以很明显的发现采用自动编码器的实验结果要比使用贝叶斯分类器的结果要高出1.65%。在本文的实验中,可以提取特征的自动编码器的预测准确率更好。     

Analyzing the Interplay Between Secondary and Tertiary Structure Predictions in Folding Simulations with a Genetic Algorithm

Three different strategies to tackle mispredictions from incorrect secondary structure prediction are analysed using 21 small proteins (22-121 amino acids; 1-6 secondary structure elements) with known three dimensional structures: (1) Testing accuracy of different secondary structure predictions and improving them by combinations, (2) correcting mispredictions exploiting protein folding simulations with a genetic algorithm and (3) applying and combining experimental data to refine predictions both for secondary structure and tertiary fold. We demonstrate that predictions from secondary structure prediction programs can be efficiently combined to reduce prediction errors from missed secondary structure elements. Further, up to two secondary structure elements (helices, strands) missed by secondary structure prediction were corrected by the genetic algorithm simulation. Finally, we show how input from experimental data is exploited to refine the predictions obtained.Electronic Supplementary Material available.     

NetSurfP-2.0: Improved prediction of protein structural features by integrated deep learning

The ability to predict local structural features of a protein from the primary sequence is of paramount importance for unraveling its function in absence of experimental structural information. Two main factors affect the utility of potential prediction tools: their accuracy must enable extraction of reliable structural information on the proteins of interest, and their runtime must be low to keep pace with sequencing data being generated at a constantly increasing speed. Here, we present NetSurfP-2.0, a novel tool that can predict the most important local structural features with unprecedented accuracy and runtime. NetSurfP-2.0 is sequence-based and uses an architecture composed of convolutional and long short-term memory neural networks trained on solved protein structures. Using a single integrated model, NetSurfP-2.0 predicts solvent accessibility, secondary structure, structural disorder, and backbone dihedral angles for each residue of the input sequences. We assessed the accuracy of NetSurfP-2.0 on several independent test datasets and found it to consistently produce state-of-the-art predictions for each of its output features. We observe a correlation of 80% between predictions and experimental data for solvent accessibility, and a precision of 85% on secondary structure 3-class predictions. In addition to improved accuracy, the processing time has been optimized to allow predicting more than 1000 proteins in less than 2 hours, and complete proteomes in less than 1 day.     

PackHelix: a tool for helix-sheet packing during protein structure prediction

The three‐dimensional structure of a protein is organized around the packing of its secondary structure elements. Predicting the topology and constructing the geometry of structural motifs involving α‐helices and/or β‐strands are therefore key steps for accurate prediction of protein structure. While many efforts have focused on how to pack helices and on how to sample exhaustively the topologies and geometries of multiple strands forming a β‐sheet in a protein, there has been little progress on generating native‐like packings of helices on sheets. We describe a method that can generate the packing of multiple helices on a given β‐sheet for αβα sandwich type protein folds. This method mines the results of a statistical analysis of the conformations of αβ₂ motifs in protein structures to provide input values for the geometric attributes of the packing of a helix on a sheet. It then proceeds with a geometric builder that generates multiple arrangements of the helices on the sheet of interest by sampling through these values and performing consistency checks that guarantee proper loop geometry between the helices and the strands, minimal number of collisions between the helices, and proper formation of a hydrophobic core. The method is implemented as a module of ProteinShop. Our results show that it produces structures that are within 4–6 Å RMSD of the native one, regardless of the number of helices that need to be packed, though this number may increase if the protein has several helices between two consecutive strands in the sequence that pack on the sheet formed by these two strands. Proteins 2011; Published 2011 Wiley‐Liss, Inc.     

Secondary structure prediction and unrefined tertiary structure prediction for cyclin A,B, and D

We present heuristic-based predictions of the secondary and tertiary structures of the cyclins A, B, and D, representatives of the cyclin superfamily. The list of suggested constraints for tertiary structure assembly was left unrefined in order to submit this report before an announced crystal structure for cyclin A becomes available. To predict these constraints, a master sequence alignment over 270 positions of cyclin types A, B, and D was adjusted based on individual secondary structure predictions for each type. We used new heuristics for predicting aromatic residues at protein-protein interfaces and to identify sequentially distinct regions in the protein chain that cluster in the folded structure. The boundaries of two conjectured domains in the cyclin fold were predicted based on experimental data in the literature. The domain that is important for interaction of the cyclins with cyclin-dependent kinases (CDKs) is predicted to contain six helices; the second domain in the consensus model contains both helices and a β-sheet that is formed by sequentially distant regions in the protein chain. A plausible phosphorylation site is identified. This work represents a blinded test of the method for prediction of secondary and, to a lesser extent, tertiary structure from a set of homologous protein sequences. Evaluation of our predictions will become possible with the publication of the announced crystal structure.     

MUPRED: a tool for bridging the gap between template based methods and sequence profile based methods for protein secondary structure prediction

Predicting secondary structures from a protein sequence is an important step for characterizing the structural properties of a protein. Existing methods for protein secondary structure prediction can be broadly classified into template based or sequence profile based methods. We propose a novel framework that bridges the gap between the two fundamentally different approaches. Our framework integrates the information from the fuzzy k-nearest neighbor algorithm and position-specific scoring matrices using a neural network. It combines the strengths of the two methods and has a better potential to use the information in both the sequence and structure databases than existing methods. We implemented the framework into a software system MUPRED. MUPRED has achieved three-state prediction accuracy (Q3) ranging from 79.2 to 80.14%, depending on which benchmark dataset is used. A higher Q3 can be achieved if a query protein has a significant sequence identity (>25%) to a template in PDB. MUPRED also estimates the prediction accuracy at the individual residue level more quantitatively than existing methods. The MUPRED web server and executables are freely available at http://digbio.missouri.edu/mupred.     

基于CNN与LSTM模型的蛋白质二级结构预测

蛋白质结构的预测在理解蛋白质结构组成和蛋白质的生物学功能有重要意义,而蛋白质二级结构预测是蛋白质结构预测的重要环节。当PSSM位置特异性进化矩阵被广泛应用于将蛋白质初级结构序列编码作为输入样本后,每个残基可以被表示成二维空间的数据平面,由此文中尝试利用卷积神经网络对其进行训练。文中还设计了另一种卷积神经网络,利用长短记忆网络感知了CNN最后卷积特征面的横向特征和纵向特征后连同卷积神经网络的全连接共同完成分类,最后用ensemble方法对两类卷积神经网络模型进行了整合,最终ensemble方法中包含两类卷积神经网络的六个模型,在CB513蛋白质数据集测得的Q3结果为77.2。     

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.     

Benchmarking of TASSER in the ab initio limit

A significant number of protein sequences in a given proteome have no obvious evolutionarily related protein in the database of solved protein structures, the PDB. Under these conditions, ab initio or template-free modeling methods are the sole means of predicting protein structure. To assess its expected performance on proteomes, the TASSER structure prediction algorithm is benchmarked in the ab initio limit on a representative set of 1129 nonhomologous sequences ranging from 40 to 200 residues that cover the PDB at 30% sequence identity and which adopt alpha, alpha + beta, and beta secondary structures. For sequences in the 40-100 (100-200) residue range, as assessed by their root mean square deviation from native, RMSD, the best of the top five ranked models of TASSER has a global fold that is significantly close to the native structure for 25% (16%) of the sequences, and with a correct identification of the structure of the protein core for 59% (36%). In the absence of a native structure, the structural similarity among the top five ranked models is a moderately reliable predictor of folding accuracy. If we classify the sequences according to their secondary structure content, then 64% (36%) of alpha, 43% (24%) of alpha + beta, and 20% (12%) of beta sequences in the 40-100 (100-200) residue range have a significant TM-score (TM-score > or = 0.4). TASSER performs best on helical proteins because there are less secondary structural elements to arrange in a helical protein than in a beta protein of equal length, since the average length of a helix is longer than that of a strand. In addition, helical proteins have shorter loops and dangling tails. If we exclude these flexible fragments, then TASSER has similar accuracy for sequences containing the same number of secondary structural elements, irrespective of whether they are helices and/or strands. Thus, it is the effective configurational entropy of the protein that dictates the average likelihood of correctly arranging the secondary structure elements.     

A neural-network based method for prediction of gamma-turns in proteins from multiple sequence alignment

In the present study, an attempt has been made to develop a method for predicting gamma-turns in proteins. First, we have implemented the commonly used statistical and machine-learning techniques in the field of protein structure prediction, for the prediction of gamma-turns. All the methods have been trained and tested on a set of 320 nonhomologous protein chains by a fivefold cross-validation technique. It has been observed that the performance of all methods is very poor, having a Matthew's Correlation Coefficient (MCC) 相似文献   

Identification and application of the concepts important for accurate and reliable protein secondary structure prediction.

A protein secondary structure prediction method from multiply aligned homologous sequences is presented with an overall per residue three-state accuracy of 70.1%. There are two aims: to obtain high accuracy by identification of a set of concepts important for prediction followed by use of linear statistics; and to provide insight into the folding process. The important concepts in secondary structure prediction are identified as: residue conformational propensities, sequence edge effects, moments of hydrophobicity, position of insertions and deletions in aligned homologous sequence, moments of conservation, auto-correlation, residue ratios, secondary structure feedback effects, and filtering. Explicit use of edge effects, moments of conservation, and auto-correlation are new to this paper. The relative importance of the concepts used in prediction was analyzed by stepwise addition of information and examination of weights in the discrimination function. The simple and explicit structure of the prediction allows the method to be reimplemented easily. The accuracy of a prediction is predictable a priori. This permits evaluation of the utility of the prediction: 10% of the chains predicted were identified correctly as having a mean accuracy of > 80%. Existing high-accuracy prediction methods are "black-box" predictors based on complex nonlinear statistics (e.g., neural networks in PHD: Rost & Sander, 1993a). For medium- to short-length chains (> or = 90 residues and < 170 residues), the prediction method is significantly more accurate (P < 0.01) than the PHD algorithm (probably the most commonly used algorithm). In combination with the PHD, an algorithm is formed that is significantly more accurate than either method, with an estimated overall three-state accuracy of 72.4%, the highest accuracy reported for any prediction method.     

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…     

SPSSM8: An accurate approach for predicting eight-state secondary structures of proteins

Protein eight-state secondary structure prediction is challenging, but is necessary to determine protein structure and function. Here, we report the development of a novel approach, SPSSM8, to predict eight-state secondary structures of proteins accurately from sequences based on the structural position-specific scoring matrix (SPSSM). The SPSSM has been successfully utilized to predict three-state secondary structures. Now we employ an eight-state SPSSM as a feature that is obtained from sequence structure alignment against a large database of 9 million sequences with putative structural information. The SPSSM8 uses a low sequence identity dataset (9062 entries) as a training set and conditional random field for the classification algorithm. The SPSSM8 achieved an average eight-state secondary structure accuracy (Q8) of 71.7% (Q3, 81.6%) for an independent testing set (463 entries), which had an improved accuracy of 10.1% and 4.6% compared with SSPro8 and CNF, respectively, and significantly improved the accuracy of eight-state secondary structure prediction. For CASP 9 dataset (92 entries) the SPSSM8 achieved a Q8 accuracy of 80.1% (Q3, 83.0%). The SPSSM8 was confirmed as an outstanding predictor for eight-state secondary structures of proteins. SPSSM8 is freely available at http://cal.tongji.edu.cn/SPSSM8.     

Native secondary structure topology has near minimum contact energy among all possible geometrically constrained topologies

Secondary structure topology in this article refers to the order and the direction of the secondary structures, such as helices and strands, with respect to the protein sequence. Even when the locations of the secondary structure Cα atoms are known, there are still (N!2^N)(M!2^M) different possible topologies for a protein with N helices and M strands. This work explored the question if the native topology is likely to be identified among a large set of all possible geometrically constrained topologies through an evaluation of the residue contact energy formed by the secondary structures, instead of the entire chain. We developed a contact pair specific and distance specific multiwell function based on the statistical characterization of the side chain distances of 413 proteins in the Protein Data Bank. The multiwell function has specific parameters to each of the 210 pairs of residue contacts. We illustrated a general mathematical method to extend a single well function to a multiwell function to represent the statistical data. We have performed a mutation analysis using 50 proteins to generate all the possible geometrically constrained topologies of the secondary structures. The result shows that the native topology is within the top 25% of the list ranked by the effective contact energies of the secondary structures for all the 50 proteins, and is within the top 5% for 34 proteins. As an application, the method was used to derive the structure of the skeletons from a low resolution density map that can be obtained through electron cryomicroscopy. Proteins 2009. © 2009 Wiley‐Liss, Inc.     

Helix‐sheet packing in proteins

The three‐dimensional structure of a protein is organized around the packing of its secondary structure elements. Although much is known about the packing geometry observed between α‐helices and between β‐sheets, there has been little progress on characterizing helix–sheet interactions. We present an analysis of the conformation of αβ₂ motifs in proteins, corresponding to all occurrences of helices in contact with two strands that are hydrogen bonded. The geometry of the αβ₂ motif is characterized by the azimuthal angle θ between the helix axis and an average vector representing the two strands, the elevation angle ψ between the helix axis and the plane containing the two strands, and the distance D between the helix and the strands. We observe that the helix tends to align to the two strands, with a preference for an antiparallel orientation if the two strands are parallel; this preference is diminished for other topologies of the β‐sheet. Side‐chain packing at the interface between the helix and the strands is mostly hydrophobic, with a preference for aliphatic amino acids in the strand and aromatic amino acids in the helix. From the knowledge of the geometry and amino acid propensities of αβ₂ motifs in proteins, we have derived different statistical potentials that are shown to be efficient in picking native‐like conformations among a set of non‐native conformations in well‐known decoy datasets. The information on the geometry of αβ₂ motifs as well as the related statistical potentials have applications in the field of protein structure prediction. Proteins 2010. © 2010 Wiley‐Liss, Inc.     

Prediction of the location and type of beta-turns in proteins using neural networks.

A neural network has been used to predict both the location and the type of beta-turns in a set of 300 nonhomologous protein domains. A substantial improvement in prediction accuracy compared with previous methods has been achieved by incorporating secondary structure information in the input data. The total percentage of residues correctly classified as beta-turn or not-beta-turn is around 75% with predicted secondary structure information. More significantly, the method gives a Matthews correlation coefficient (MCC) of around 0.35, compared with a typical MCC of around 0.20 using other beta-turn prediction methods. Our method also distinguishes the two most numerous and well-defined types of beta-turn, types I and II, with a significant level of accuracy (MCCs 0.22 and 0.26, respectively).     

Improved sequence-based prediction of protein secondary structures by combining vacuum-ultraviolet circular dichroism spectroscopy with neural network

Synchrotron-radiation vacuum-ultraviolet circular dichroism (VUVCD) spectroscopy can significantly improve the predictive accuracy of the contents and segment numbers of protein secondary structures by extending the short-wavelength limit of the spectra. In the present study, we combined VUVCD spectra down to 160 nm with neural-network (NN) method to improve the sequence-based prediction of protein secondary structures. The secondary structures of 30 target proteins (test set) were assigned into alpha-helices, beta-strands, and others by the DSSP program based on their X-ray crystal structures. Combining the alpha-helix and beta-strand contents estimated from the VUVCD spectra of the target proteins improved the overall sequence-based predictive accuracy Q(3) for three secondary-structure components from 59.5 to 60.7%. Incorporating the position-specific scoring matrix in the NN method improved the predictive accuracy from 70.9 to 72.1% when combining the secondary-structure contents, to 72.5% when combining the numbers of segments, and finally to 74.9% when filtering the VUVCD data. Improvement in the sequence-based prediction of secondary structures was also apparent in two other indices of the overall performance: the correlation coefficient (C) and the segment overlap value (SOV). These results suggest that VUVCD data could enhance the predictive accuracy to over 80% when combined with the currently best sequence-prediction algorithms, greatly expanding the applicability of VUVCD spectroscopy to protein structural biology.     

An algorithm for predicting protein-protein interaction sites: Abnormally exposed amino acid residues and secondary structure elements

Multiprotein systems mediate most regulatory processes in living organisms. Although the structures of the individual proteins are often defined, less is known of the structures of multiprotein systems. Computational methods for predicting interfaces, using evolutionary conservation and/or physicochemical data, have been developed. Here we consider the use of solvent accessibility, residue propensity, and hydrophobicity, in conjunction with secondary structure data, as prediction parameters. We analyze the influence of residue type and secondary structure on solvent accessibility and define a measure of "relative exposedness." Clustering abnormally high scoring residues provides a basis for predicting interaction sites. The analysis is extended to investigate abnormally exposed secondary structure elements, particularly beta-sheet strands. We show that surface-exposed beta-strands lacking protective features are more likely to be found at protein-protein interfaces, allowing us to create an algorithm with approximately 68% and approximately 75% accuracy in differentiating between interacting and edge strands in isolated beta-strands and beta-sheet strands, respectively. These methods of identifying abnormally exposed surface regions are combined in an algorithm, which, on a data set of 77 unbound and disjoint (single chain extracted from complex) structures, predicts 79% of the protein-protein interfaces correctly. If enzyme-inhibitor complexes, where the inhibitor mimics a nonprotein substrate, are excluded, the accuracy increases to 85%.