Combining the GOR V algorithm with evolutionary information for protein secondary structure prediction from amino acid sequence

We have modified and improved the GOR algorithm for the protein secondary structure prediction by using the evolutionary information provided by multiple sequence alignments, adding triplet statistics, and optimizing various parameters. We have expanded the database used to include the 513 non-redundant domains collected recently by Cuff and Barton (Proteins 1999;34:508-519; Proteins 2000;40:502-511). We have introduced a variable size window that allowed us to include sequences as short as 20-30 residues. A significant improvement over the previous versions of GOR algorithm was obtained by combining the PSI-BLAST multiple sequence alignments with the GOR method. The new algorithm will form the basis for the future GOR V release on an online prediction server. The average accuracy of the prediction of secondary structure with multiple sequence alignment and full jack-knife procedure was 73.5%. The accuracy of the prediction increases to 74.2% by limiting the prediction to 375 (of 513) sequences having at least 50 PSI-BLAST alignments. The average accuracy of the prediction of the new improved program without using multiple sequence alignments was 67.5%. This is approximately a 3% improvement over the preceding GOR IV algorithm (Garnier J, Gibrat JF, Robson B. Methods Enzymol 1996;266:540-553; Kloczkowski A, Ting K-L, Jernigan RL, Garnier J. Polymer 2002;43:441-449). We have discussed alternatives to the segment overlap (Sov) coefficient proposed by Zemla et al. (Proteins 1999;34:220-223).     

Consensus Data Mining (CDM) Protein Secondary Structure Prediction Server: combining GOR V and Fragment Database Mining (FDM)

One of the challenges in protein secondary structure prediction is to overcome the cross-validated 80% prediction accuracy barrier. Here, we propose a novel approach to surpass this barrier. Instead of using a single algorithm that relies on a limited data set for training, we combine two complementary methods having different strengths: Fragment Database Mining (FDM) and GOR V. FDM harnesses the availability of the known protein structures in the Protein Data Bank and provides highly accurate secondary structure predictions when sequentially similar structural fragments are identified. In contrast, the GOR V algorithm is based on information theory, Bayesian statistics, and PSI-BLAST multiple sequence alignments to predict the secondary structure of residues inside a sliding window along a protein chain. A combination of these two different methods benefits from the large number of structures in the PDB and significantly improves the secondary structure prediction accuracy, resulting in Q3 ranging from 67.5 to 93.2%, depending on the availability of highly similar fragments in the Protein Data Bank.     

A Consensus Data Mining secondary structure prediction by combining GOR V and Fragment Database Mining

The major aim of tertiary structure prediction is to obtain protein models with the highest possible accuracy. Fold recognition, homology modeling, and de novo prediction methods typically use predicted secondary structures as input, and all of these methods may significantly benefit from more accurate secondary structure predictions. Although there are many different secondary structure prediction methods available in the literature, their cross-validated prediction accuracy is generally <80%. In order to increase the prediction accuracy, we developed a novel hybrid algorithm called Consensus Data Mining (CDM) that combines our two previous successful methods: (1) Fragment Database Mining (FDM), which exploits the Protein Data Bank structures, and (2) GOR V, which is based on information theory, Bayesian statistics, and multiple sequence alignments (MSA). In CDM, the target sequence is dissected into smaller fragments that are compared with fragments obtained from related sequences in the PDB. For fragments with a sequence identity above a certain sequence identity threshold, the FDM method is applied for the prediction. The remainder of the fragments are predicted by GOR V. The results of the CDM are provided as a function of the upper sequence identities of aligned fragments and the sequence identity threshold. We observe that the value 50% is the optimum sequence identity threshold, and that the accuracy of the CDM method measured by Q(3) ranges from 67.5% to 93.2%, depending on the availability of known structural fragments with sufficiently high sequence identity. As the Protein Data Bank grows, it is anticipated that this consensus method will improve because it will rely more upon the structural fragments.     

Improvement of protein secondary structure prediction using binary word encoding

We propose a binary word encoding to improve the protein secondary structure prediction. A binary word encoding encodes a local amino acid sequence to a binary word, which consists of 0 or 1. We use an encoding function to map an amino acid to 0 or 1. Using the binary word encoding, we can statistically extract the multiresidue information, which depends on more than one residue. We combine the binary word encoding with the GOR method, its modified version, which shows better accuracy, and the neural network method. The binary word encoding improves the accuracy of GOR by 2.8%. We obtain similar improvement when we combine this with the modified GOR method and the neural network method. When we use multiple sequence alignment data, the binary word encoding similarly improves the accuracy. The accuracy of our best combined method is 68.2%. In this paper, we only show improvement of the GOR and neural network method, we cannot say that the encoding improves the other methods. But the improvement by the encoding suggests that the multiresidue interaction affects the formation of secondary structure. In addition, we find that the optimal encoding function obtained by the simulated annealing method relates to non-polarity. This means that nonpolarity is important to the multiresidue interaction. Proteins 27:36–46 © 1997 Wiley-Liss, Inc.     

Further developments of protein secondary structure prediction using information theory. New parameters and consideration of residue pairs

We have re-evaluated the information used in the Garnier-Osguthorpe-Robson (GOR) method of secondary structure prediction with the currently available database. The framework of information theory provides a means to formulate the influence of local sequence upon the conformation of a given residue, in a rigorous manner. However, the existing database does not allow the evaluation of parameters required for an exact treatment of the problem. The validity of the approximations drawn from the theory is examined. It is shown that the first-level approximation, involving single-residue parameters, is only marginally improved by an increase in the database. The second-level approximation, involving pairs of residues, provides a better model. However, in this case the database is not big enough and this method might lead to parameters with deficiencies. Attention is therefore given to overcoming this lack of data. We have determined the significant pairs and the number of dummy observations necessary to obtain the best result for the prediction. This new version of the GOR method increases the accuracy of prediction by 7%, bringing the amount of residues correctly predicted to 63% for three states and 68 proteins, each protein to be predicted being removed from the database and the parameters derived from the other proteins. If the protein to be predicted is kept in the database the accuracy goes up to 69.7%.     

T-Epitope Designer: A HLA-peptide binding prediction server

The current challenge in synthetic vaccine design is the development of a methodology to identify and test short antigen peptides as potential T-cell epitopes. Recently, we described a HLA-peptide binding model (using structural properties) capable of predicting peptides binding to any HLA allele. Consequently, we have developed a web server named T-EPITOPE DESIGNER to facilitate HLA-peptide binding prediction. The prediction server is based on a model that defines peptide binding pockets using information gleaned from X-ray crystal structures of HLA-peptide complexes, followed by the estimation of peptide binding to binding pockets. Thus, the prediction server enables the calculation of peptide binding to HLA alleles. This model is superior to many existing methods because of its potential application to any given HLA allele whose sequence is clearly defined. The web server finds potential application in T cell epitope vaccine design. AVAILABILITY: http://www.bioinformation.net/ted/     

ToolShop: prerelease inspections for protein structure prediction servers.

The ToolShop server offers a possibility to compare a protein tertiary structure prediction server with other popular servers before releasing it to the public. The comparison is conducted on a set of 203 proteins and the collected models are compared with over 20 other programs using various assessment procedures. The evaluation lasts circa one week. AVAILABILITY: The ToolShop server is available at http://BioInfo.PL/ToolShop/. The administrator should be contacted to couple the tested server to the evaluation suite. CONTACT: leszek@bioinfo.pl SUPPLEMENTARY INFORMATION: The evaluation procedures are similar to those implemented in the continuous online server evaluation program, LiveBench. Additional information is available from its homepage (http://BioInfo.PL/LiveBench/).     

Role of evolutionary information in prediction of aromatic-backbone NH interactions in proteins

In this study, an attempt has been made to develop a neural network-based method for predicting segments in proteins containing aromatic-backbone NH (Ar-NH) interactions using multiple sequence alignment. We have analyzed 3121 segments seven residues long containing Ar-NH interactions, extracted from 2298 non-redundant protein structures where no two proteins have more than 25% sequence identity. Two consecutive feed-forward neural networks with a single hidden layer have been trained with standard back-propagation as learning algorithm. The performance of the method improves from 0.12 to 0.15 in terms of Matthews correlation coefficient (MCC) value when evolutionary information (multiple alignment obtained from PSI-BLAST) is used as input instead of a single sequence. The performance of the method further improves from MCC 0.15 to 0.20 when secondary structure information predicted by PSIPRED is incorporated in the prediction. The final network yields an overall prediction accuracy of 70.1% and an MCC of 0.20 when tested by five-fold cross-validation. Overall the performance is 15.2% higher than the random prediction. The method consists of two neural networks: (i) a sequence-to-structure network which predicts the aromatic residues involved in Ar-NH interaction from multiple alignment of protein sequences and (ii) a structure-to structure network where the input consists of the output obtained from the first network and predicted secondary structure. Further, the actual position of the donor residue within the 'potential' predicted fragment has been predicted using a separate sequence-to-structure neural network. Based on the present study, a server Ar_NHPred has been developed which predicts Ar-NH interaction in a given amino acid sequence. The web server Ar_NHPred is available at and (mirror site).     

Prediction of beta-turns in proteins from multiple alignment using neural network

A neural network-based method has been developed for the prediction of beta-turns in proteins by using multiple sequence alignment. Two feed-forward back-propagation networks with a single hidden layer are used where the first-sequence structure network is trained with the multiple sequence alignment in the form of PSI-BLAST-generated position-specific scoring matrices. The initial predictions from the first network and PSIPRED-predicted secondary structure are used as input to the second structure-structure network to refine the predictions obtained from the first net. A significant improvement in prediction accuracy has been achieved by using evolutionary information contained in the multiple sequence alignment. The final network yields an overall prediction accuracy of 75.5% when tested by sevenfold cross-validation on a set of 426 nonhomologous protein chains. The corresponding Q(pred), Q(obs), and Matthews correlation coefficient values are 49.8%, 72.3%, and 0.43, respectively, and are the best among all the previously published beta-turn prediction methods. The Web server BetaTPred2 (http://www.imtech.res.in/raghava/betatpred2/) has been developed based on this approach.     

SPOT-Disorder2: Improved Protein Intrinsic Disorder Prediction by Ensembled Deep Learning

Intrinsically disordered or unstructured proteins (or regions in proteins) have been found to be important in a wide range of biological functions and implicated in many diseases. Due to the high cost and low efficiency of experimental determination of intrinsic disorder and the exponential increase of unannotated protein sequences, developing complementary computational prediction methods has been an active area of research for several decades. Here, we employed an ensemble of deep Squeeze-and-Excitation residual inception and long short-term memory (LSTM) networks for predicting protein intrinsic disorder with input from evolutionary information and predicted one-dimensional structural properties. The method, called SPOT-Disorder2, offers substantial and consistent improvement not only over our previous technique based on LSTM networks alone, but also over other state-of-the-art techniques in three independent tests with different ratios of disordered to ordered amino acid residues, and for sequences with either rich or limited evolutionary information. More importantly, semi-disordered regions predicted in SPOT-Disorder2 are more accurate in identifying molecular recognition features (MoRFs) than methods directly designed for MoRFs prediction. SPOT-Disorder2 is available as a web server and as a standalone program at https://sparks-lab.org/server/spot-disorder2/.     

A top-down approach to enhance the power of predicting human protein subcellular localization: Hum-mPLoc 2.0

Predicting subcellular localization of human proteins is a challenging problem, particularly when query proteins may have a multiplex character, i.e., simultaneously exist at, or move between, two or more different subcellular location sites. In a previous study, we developed a predictor called “Hum-mPLoc” to deal with the multiplex problem for the human protein system. However, Hum-mPLoc has the following shortcomings. (1) The input of accession number for a query protein is required in order to obtain a higher expected success rate by selecting to use the higher-level prediction pathway; but many proteins, such as synthetic and hypothetical proteins as well as those newly discovered proteins without being deposited into databanks yet, do not have accession numbers. (2) Neither functional domain nor sequential evolution information were taken into account in Hum-mPLoc, and hence its power may be reduced accordingly. In view of this, a top-down strategy to address these shortcomings has been implemented. The new predictor thus obtained is called Hum-mPLoc 2.0, where the accession number for input is no longer needed whatsoever. Moreover, both the functional domain information and the sequential evolution information have been fused into the predictor by an ensemble classifier. As a consequence, the prediction power has been significantly enhanced. The web server of Hum-mPLoc2.0 is freely accessible at http://www.csbio.sjtu.edu.cn/bioinf/hum-multi-2/.     

A neural network method for prediction of beta-turn types in proteins using evolutionary information

MOTIVATION: The prediction of beta-turns is an important element of protein secondary structure prediction. Recently, a highly accurate neural network based method Betatpred2 has been developed for predicting beta-turns in proteins using position-specific scoring matrices (PSSM) generated by PSI-BLAST and secondary structure information predicted by PSIPRED. However, the major limitation of Betatpred2 is that it predicts only beta-turn and non-beta-turn residues and does not provide any information of different beta-turn types. Thus, there is a need to predict beta-turn types using an approach based on multiple sequence alignment, which will be useful in overall tertiary structure prediction. RESULTS: In the present work, a method has been developed for the prediction of beta-turn types I, II, IV and VIII. For each turn type, two consecutive feed-forward back-propagation networks with a single hidden layer have been used where the first sequence-to-structure network has been trained on single sequences as well as on PSI-BLAST PSSM. The output from the first network along with PSIPRED predicted secondary structure has been used as input for the second-level structure-to-structure network. The networks have been trained and tested on a non-homologous dataset of 426 proteins chains by 7-fold cross-validation. It has been observed that the prediction performance for each turn type is improved significantly by using multiple sequence alignment. The performance has been further improved by using a second level structure-to-structure network and PSIPRED predicted secondary structure information. It has been observed that Type I and II beta-turns have better prediction performance than Type IV and VIII beta-turns. The final network yields an overall accuracy of 74.5, 93.5, 67.9 and 96.5% with MCC values of 0.29, 0.29, 0.23 and 0.02 for Type I, II, IV and VIII beta-turns, respectively, and is better than random prediction. AVAILABILITY: A web server for prediction of beta-turn types I, II, IV and VIII based on above approach is available at http://www.imtech.res.in/raghava/betaturns/ and http://bioinformatics.uams.edu/mirror/betaturns/ (mirror site).     

Fully automated ab initio protein structure prediction using I-SITES,HMMSTR and ROSETTA

MOTIVATION: The Monte Carlo fragment insertion method for protein tertiary structure prediction (ROSETTA) of Baker and others, has been merged with the I-SITES library of sequence structure motifs and the HMMSTR model for local structure in proteins, to form a new public server for the ab initio prediction of protein structure. The server performs several tasks in addition to tertiary structure prediction, including a database search, amino acid profile generation, fragment structure prediction, and backbone angle and secondary structure prediction. Meeting reasonable service goals required improvements in the efficiency, in particular for the ROSETTA algorithm. RESULTS: The new server was used for blind predictions of 40 protein sequences as part of the CASP4 blind structure prediction experiment. The results for 31 of those predictions are presented here. 61% of the residues overall were found in topologically correct predictions, which are defined as fragments of 30 residues or more with a root-mean-square deviation in superimposed alpha carbons of less than 6A. HMMSTR 3-state secondary structure predictions were 73% correct overall. Tertiary structure predictions did not improve the accuracy of secondary structure prediction.     

The HMMTOP transmembrane topology prediction server

The HMMTOP transmembrane topology prediction server predicts both the localization of helical transmembrane segments and the topology of transmembrane proteins. Recently, several improvements have been introduced to the original method. Now, the user is allowed to submit additional information about segment localization to enhance the prediction power. This option improves the prediction accuracy as well as helps the interpretation of experimental results, i.e. in epitope insertion experiments. Availability: HMMTOP 2.0 is freely available to non-commercial users at http://www.enzim.hu/hmmtop. Source code is also available upon request to academic users.     

Arby: automatic protein structure prediction using profile-profile alignment and confidence measures

MOTIVATION: Arby is a new server for protein structure prediction that combines several homology-based methods for predicting the three-dimensional structure of a protein, given its sequence. The methods used include a threading approach, which makes use of structural information, and a profile-profile alignment approach that incorporates secondary structure predictions. The combination of the different methods with the help of empirically derived confidence measures affords reliable template selection. RESULTS: According to the recent CAFASP3 experiment, the server is one of the most sensitive methods for predicting the structure of single domain proteins. The quality of template selection is assessed using a fold-recognition experiment. AVAILABILITY: The Arby server is available through the portal of the Helmholtz Network for Bioinformatics at http://www.hnbioinfo.de under the protein structure category.     

Deep template-based protein structure prediction

MotivationProtein structure prediction has been greatly improved by deep learning, but most efforts are devoted to template-free modeling. But very few deep learning methods are developed for TBM (template-based modeling), a popular technique for protein structure prediction. TBM has been studied extensively in the past, but its accuracy is not satisfactory when highly similar templates are not available.ResultsThis paper presents a new method NDThreader (New Deep-learning Threader) to address the challenges of TBM. NDThreader first employs DRNF (deep convolutional residual neural fields), which is an integration of deep ResNet (convolutional residue neural networks) and CRF (conditional random fields), to align a query protein to templates without using any distance information. Then NDThreader uses ADMM (alternating direction method of multipliers) and DRNF to further improve sequence-template alignments by making use of predicted distance potential. Finally, NDThreader builds 3D models from a sequence-template alignment by feeding it and sequence coevolution information into a deep ResNet to predict inter-atom distance distribution, which is then fed into PyRosetta for 3D model construction. Our experimental results show that NDThreader greatly outperforms existing methods such as CNFpred, HHpred, DeepThreader and CEthreader. NDThreader was blindly tested in CASP14 as a part of RaptorX server, which obtained the best average GDT score among all CASP14 servers on the 58 TBM targets.