PPRODO: prediction of protein domain boundaries using neural networks

Successful prediction of protein domain boundaries provides valuable information not only for the computational structure prediction of multidomain proteins but also for the experimental structure determination. Since protein sequences of multiple domains may contain much information regarding evolutionary processes such as gene-exon shuffling, this information can be detected by analyzing the position-specific scoring matrix (PSSM) generated by PSI-BLAST. We have presented a method, PPRODO (Prediction of PROtein DOmain boundaries) that predicts domain boundaries of proteins from sequence information by a neural network. The network is trained and tested using the values obtained from the PSSM generated by PSI-BLAST. A 10-fold cross-validation technique is performed to obtain the parameters of neural networks using a nonredundant set of 522 proteins containing 2 contiguous domains. PPRODO provides good and consistent results for the prediction of domain boundaries, with accuracy of about 66% using the +/-20 residue criterion. The PPRODO source code, as well as all data sets used in this work, are available from http://gene.kias.re.kr/ approximately jlee/pprodo/.     

A high-accuracy protein structural class prediction algorithm using predicted secondary structural information

One major problem with the existing algorithm for the prediction of protein structural classes is low accuracies for proteins from α/β and α+β classes. In this study, three novel features were rationally designed to model the differences between proteins from these two classes. In combination with other rational designed features, an 11-dimensional vector prediction method was proposed. By means of this method, the overall prediction accuracy based on 25PDB dataset was 1.5% higher than the previous best-performing method, MODAS. Furthermore, the prediction accuracy for proteins from α+β class based on 25PDB dataset was 5% higher than the previous best-performing method, SCPRED. The prediction accuracies obtained with the D675 and FC699 datasets were also improved.     

Neural networks for secondary structure and structural class predictions

A pair of neural network-based algorithms is presented for predicting the tertiary structural class and the secondary structure of proteins. Each algorithm realizes improvements in accuracy based on information provided by the other. Structural class prediction of proteins nonhomologous to any in the training set is improved significantly, from 62.3% to 73.9%, and secondary structure prediction accuracy improves slightly, from 62.26% to 62.64%. A number of aspects of neural network optimization and testing are examined. They include network overtraining and an output filter based on a rolling average. Secondary structure prediction results vary greatly depending on the particular proteins chosen for the training and test sets; consequently, an appropriate measure of accuracy reflects the more unbiased approach of “jackknife” cross-validation (testing each protein in the database individually).     

Some insights into protein structural class prediction

It has been quite clear that the success rate for predicting protein structural class can be improved significantly by using the algorithms that incorporate the coupling effect among different amino acid components of a protein. However, there is still a lot of confusion in understanding the relationship of these advanced algorithms, such as the least Mahalanobis distance algorithm, the component-coupled algorithm, and the Bayes decision rule. In this communication, a simple, rigorous derivation is provided to prove that the Bayes decision rule introduced recently for protein structural class prediction is completely the same as the earlier component-coupled algorithm. Meanwhile, it is also very clear from the derivative equations that the least Mahalanobis distance algorithm is an approximation of the component-coupled algorithm, also named as the covariant-discriminant algorithm introduced by Chou and Elrod in protein subcellular location prediction (Protein Engineering, 1999; 12:107-118). Clarification of the confusion will help use these powerful algorithms effectively and correctly interpret the results obtained by them, so as to conduce to the further development not only in the structural prediction area, but in some other relevant areas in protein science as well.     

基于蛋白质二级结构内容的域结构类预测

运用加入竞争层的BP网络,研究了基于蛋白质二级结构内容的域结构类预测问题.在BP网络中嵌入一竞争,层显著提高了网络预测性能.仅使用了一个小的训练集和简单的网络结构,获得了很高的预测精度自支持精度97.62%,jack-knife测试精度97.62%,及平均外推精度90.74%.在建立更完备的域结构类特征向量和更有代表性的训练集的基础上,所述方法将为蛋白质域结构分类领域提供新的分类基准.     

Prediction by a neural network of outer membrane beta-strand protein topology.

An artificial neural network (NN) was trained to predict the topology of bacterial outer membrane (OM) beta-strand proteins. Specifically, the NN predicts the z-coordinate of Calpha atoms in a coordinate frame with the outer membrane in the xy-plane, such that low z-values indicate periplasmic turns, medium z-values indicate transmembrane beta-strands, and high z-values indicate extracellular loops. To obtain a training set, seven OM proteins (porins) with structures known to high resolution were aligned with their pores along the z-axis. The relationship between Calpha z-values and topology was thereby established. To predict the topology of other OM proteins, all seven porins were used for the training set. Z-values (topologies) were predicted for two porins with hitherto unknown structure and for OM proteins not belonging to the porin family, all with insignificant sequence homology to the training set. The results of topology prediction compare favorably with experimental topology data.     

Customised fragments libraries for protein structure prediction based on structural class annotations

Background

Since experimental techniques are time and cost consuming, in silico protein structure prediction is essential to produce conformations of protein targets. When homologous structures are not available, fragment-based protein structure prediction has become the approach of choice. However, it still has many issues including poor performance when targets’ lengths are above 100 residues, excessive running times and sub-optimal energy functions. Taking advantage of the reliable performance of structural class prediction software, we propose to address some of the limitations of fragment-based methods by integrating structural constraints in their fragment selection process.

Results

Using Rosetta, a state-of-the-art fragment-based protein structure prediction package, we evaluated our proposed pipeline on 70 former CASP targets containing up to 150 amino acids. Using either CATH or SCOP-based structural class annotations, enhancement of structure prediction performance is highly significant in terms of both GDT_TS (at least +2.6, p-values < 0.0005) and RMSD (−0.4, p-values < 0.005). Although CATH and SCOP classifications are different, they perform similarly. Moreover, proteins from all structural classes benefit from the proposed methodology. Further analysis also shows that methods relying on class-based fragments produce conformations which are more relevant to user and converge quicker towards the best model as estimated by GDT_TS (up to 10% in average). This substantiates our hypothesis that usage of structurally relevant templates conducts to not only reducing the size of the conformation space to be explored, but also focusing on a more relevant area.

Conclusions

Since our methodology produces models the quality of which is up to 7% higher in average than those generated by a standard fragment-based predictor, we believe it should be considered before conducting any fragment-based protein structure prediction. Despite such progress, ab initio prediction remains a challenging task, especially for proteins of average and large sizes. Apart from improving search strategies and energy functions, integration of additional constraints seems a promising route, especially if they can be accurately predicted from sequence alone.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-015-0576-2) contains supplementary material, which is available to authorized users.     

神经网络在蛋白质二级结构预测中的应用

介绍了蛋白质二级结构预测的研究意义,讨论了用在蛋白质二级结构预测方面的神经网络设计问题,并且较详尽地评述了近些年来用神经网络方法在蛋白质二级结构预测中的主要工作进展情况,展望了蛋白质结构预测的前景。     

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.     

Accurate prediction of protein structural classes using functional domains and predicted secondary structure sequences

Protein structural class prediction is one of the challenging problems in bioinformatics. Previous methods directly based on the similarity of amino acid (AA) sequences have been shown to be insufficient for low-similarity protein data-sets. To improve the prediction accuracy for such low-similarity proteins, different methods have been recently proposed that explore the novel feature sets based on predicted secondary structure propensities. In this paper, we focus on protein structural class prediction using combinations of the novel features including secondary structure propensities as well as functional domain (FD) features extracted from the InterPro signature database. Our comprehensive experimental results based on several benchmark data-sets have shown that the integration of new FD features substantially improves the accuracy of structural class prediction for low-similarity proteins as they capture meaningful relationships among AA residues that are far away in protein sequence. The proposed prediction method has also been tested to predict structural classes for partially disordered proteins with the reasonable prediction accuracy, which is a more difficult problem comparing to structural class prediction for commonly used benchmark data-sets and has never been done before to the best of our knowledge. In addition, to avoid overfitting with a large number of features, feature selection is applied to select discriminating features that contribute to achieve high prediction accuracy. The selected features have been shown to achieve stable prediction performance across different benchmark data-sets.     

High-accuracy prediction of protein structural class for low-similarity sequences based on predicted secondary structure

Information on the structural classes of proteins has been proven to be important in many fields of bioinformatics. Prediction of protein structural class for low-similarity sequences is a challenge problem. In this study, 11 features (including 8 re-used features and 3 newly-designed features) are rationally utilized to reflect the general contents and spatial arrangements of the secondary structural elements of a given protein sequence. To evaluate the performance of the proposed method, jackknife cross-validation tests are performed on two widely used benchmark datasets, 1189 and 25PDB with sequence similarity lower than 40% and 25%, respectively. Comparison of our results with other methods shows that our proposed method is very promising and may provide a cost-effective alternative to predict protein structural class in particular for low-similarity datasets.     

Prediction of protein structural class for low-similarity sequences using support vector machine and PSI-BLAST profile

Knowledge of structural class plays an important role in understanding protein folding patterns. In this study, a simple and powerful computational method, which combines support vector machine with PSI-BLAST profile, is proposed to predict protein structural class for low-similarity sequences. The evolution information encoding in the PSI-BLAST profiles is converted into a series of fixed-length feature vectors by extracting amino acid composition and dipeptide composition from the profiles. The resulting vectors are then fed to a support vector machine classifier for the prediction of protein structural class. To evaluate the performance of the proposed method, jackknife cross-validation tests are performed on two widely used benchmark datasets, 1189 (containing 1092 proteins) and 25PDB (containing 1673 proteins) with sequence similarity lower than 40% and 25%, respectively. The overall accuracies attain 70.7% and 72.9% for 1189 and 25PDB datasets, respectively. Comparison of our results with other methods shows that our method is very promising to predict protein structural class particularly for low-similarity datasets and may at least play an important complementary role to existing methods.     

Reliable prediction of T-cell epitopes using neural networks with novel sequence representations

In this paper we describe an improved neural network method to predict T-cell class I epitopes. A novel input representation has been developed consisting of a combination of sparse encoding, Blosum encoding, and input derived from hidden Markov models. We demonstrate that the combination of several neural networks derived using different sequence-encoding schemes has a performance superior to neural networks derived using a single sequence-encoding scheme. The new method is shown to have a performance that is substantially higher than that of other methods. By use of mutual information calculations we show that peptides that bind to the HLA A*0204 complex display signal of higher order sequence correlations. Neural networks are ideally suited to integrate such higher order correlations when predicting the binding affinity. It is this feature combined with the use of several neural networks derived from different and novel sequence-encoding schemes and the ability of the neural network to be trained on data consisting of continuous binding affinities that gives the new method an improved performance. The difference in predictive performance between the neural network methods and that of the matrix-driven methods is found to be most significant for peptides that bind strongly to the HLA molecule, confirming that the signal of higher order sequence correlation is most strongly present in high-binding peptides. Finally, we use the method to predict T-cell epitopes for the genome of hepatitis C virus and discuss possible applications of the prediction method to guide the process of rational vaccine design.     

Protein structure prediction using multiple deep neural networks in the 13th Critical Assessment of Protein Structure Prediction (CASP13)

We describe AlphaFold, the protein structure prediction system that was entered by the group A7D in CASP13. Submissions were made by three free-modeling (FM) methods which combine the predictions of three neural networks. All three systems were guided by predictions of distances between pairs of residues produced by a neural network. Two systems assembled fragments produced by a generative neural network, one using scores from a network trained to regress GDT_TS. The third system shows that simple gradient descent on a properly constructed potential is able to perform on par with more expensive traditional search techniques and without requiring domain segmentation. In the CASP13 FM assessors' ranking by summed z-scores, this system scored highest with 68.3 vs 48.2 for the next closest group (an average GDT_TS of 61.4). The system produced high-accuracy structures (with GDT_TS scores of 70 or higher) for 11 out of 43 FM domains. Despite not explicitly using template information, the results in the template category were comparable to the best performing template-based methods.     

Evaluating the absolute quality of a single protein model using structural features and support vector machines

Knowing the quality of a protein structure model is important for its appropriate usage. We developed a model evaluation method to assess the absolute quality of a single protein model using only structural features with support vector machine regression. The method assigns an absolute quantitative score (i.e. GDT‐TS) to a model by comparing its secondary structure, relative solvent accessibility, contact map, and beta sheet structure with their counterparts predicted from its primary sequence. We trained and tested the method on the CASP6 dataset using cross‐validation. The correlation between predicted and true scores is 0.82. On the independent CASP7 dataset, the correlation averaged over 95 protein targets is 0.76; the average correlation for template‐based and ab initio targets is 0.82 and 0.50, respectively. Furthermore, the predicted absolute quality scores can be used to rank models effectively. The average difference (or loss) between the scores of the top‐ranked models and the best models is 5.70 on the CASP7 targets. This method performs favorably when compared with the other methods used on the same dataset. Moreover, the predicted absolute quality scores are comparable across models for different proteins. These features make the method a valuable tool for model quality assurance and ranking. Proteins 2009. © 2008 Wiley‐Liss, Inc.     

Using a neural network and spatial clustering to predict the location of active sites in enzymes

Structural genomics projects aim to provide a sharp increase in the number of structures of functionally unannotated, and largely unstudied, proteins. Algorithms and tools capable of deriving information about the nature, and location, of functional sites within a structure are increasingly useful therefore. Here, a neural network is trained to identify the catalytic residues found in enzymes, based on an analysis of the structure and sequence. The neural network output, and spatial clustering of the highly scoring residues are then used to predict the location of the active site.A comparison of the performance of differently trained neural networks is presented that shows how information from sequence and structure come together to improve the prediction accuracy of the network. Spatial clustering of the network results provides a reliable way of finding likely active sites. In over 69% of the test cases the active site is correctly predicted, and a further 25% are partially correctly predicted. The failures are generally due to the poor quality of the automatically generated sequence alignments.We also present predictions identifying the active site, and potential functional residues in five recently solved enzyme structures, not used in developing the method. The method correctly identifies the putative active site in each case. In most cases the likely functional residues are identified correctly, as well as some potentially novel functional groups.     

Using principal component analysis and support vector machine to predict protein structural class for low-similarity sequences via PSSM

The accurate identification of protein structure class solely using extracted information from protein sequence is a complicated task in the current computational biology. Prediction of protein structural class for low-similarity sequences remains a challenging problem. In this study, the new computational method has been developed to predict protein structural class by fusing the sequence information and evolution information to represent a protein sample. To evaluate the performance of the proposed method, jackknife cross-validation tests are performed on two widely used benchmark data-sets, 1189 and 25PDB with sequence similarity lower than 40 and 25%, respectively. Comparison of our results with other methods shows that the proposed method by us is very promising and may provide a cost-effective alternative to predict protein structural class in particular for low-similarity data-sets.