Neuro-fuzzy structural classification of proteins for improved protein secondary structure prediction

Fourier transform infrared (FTIR) spectroscopy is a very flexible technique for characterization of protein secondary structure. Measurements can be carried out rapidly in a number of different environments based on only small quantities of proteins. For this technique to become more widely used for protein secondary structure characterization, however, further developments in methods to accurately quantify protein secondary structure are necessary. Here we propose a structural classification of proteins (SCOP) class specialized neural networks architecture combining an adaptive neuro-fuzzy inference system (ANFIS) with SCOP class specialized backpropagation neural networks for improved protein secondary structure prediction. Our study shows that proteins can be accurately classified into two main classes "all alpha proteins" and "all beta proteins" merely based on the amide I band maximum position of their FTIR spectra. ANFIS is employed to perform the classification task to demonstrate the potential of this architecture with moderately complex problems. Based on studies using a reference set of 17 proteins and an evaluation set of 4 proteins, improved predictions were achieved compared to a conventional neural network approach, where structure specialized neural networks are trained based on protein spectra of both "all alpha" and "all beta" proteins. The standard errors of prediction (SEPs) in % structure were improved by 4.05% for helix structure, by 5.91% for sheet structure, by 2.68% for turn structure, and by 2.15% for bend structure. For other structure, an increase of SEP by 2.43% was observed. Those results were confirmed by a "leave-one-out" run with the combined set of 21 FTIR spectra of proteins.     

Prediction of the disulfide bonding state of cysteines in proteins with hidden neural networks

A hybrid system (hidden neural network) based on a hidden Markov model (HMM) and neural networks (NN) was trained to predict the bonding states of cysteines in proteins starting from the residue chains. Training was performed using 4136 cysteine-containing segments extracted from 969 non-homologous proteins of well-resolved 3D structure and without chain-breaks. After a 20-fold cross-validation procedure, the efficiency of the prediction scores as high as 80% using neural networks based on evolutionary information. When the whole protein is taken into account by means of an HMM, a hybrid system is generated, whose emission probabilities are computed using the NN output (hidden neural networks). In this case, the predictor accuracy increases up to 88%. Further, when tested on a protein basis, the hybrid system can correctly predict 84% of the chains in the data set, with a gain of at least 27% over the NN predictor.     

Exploiting the past and the future in protein secondary structure prediction

MOTIVATION: Predicting the secondary structure of a protein (alpha-helix, beta-sheet, coil) is an important step towards elucidating its three-dimensional structure, as well as its function. Presently, the best predictors are based on machine learning approaches, in particular neural network architectures with a fixed, and relatively short, input window of amino acids, centered at the prediction site. Although a fixed small window avoids overfitting problems, it does not permit capturing variable long-rang information. RESULTS: We introduce a family of novel architectures which can learn to make predictions based on variable ranges of dependencies. These architectures extend recurrent neural networks, introducing non-causal bidirectional dynamics to capture both upstream and downstream information. The prediction algorithm is completed by the use of mixtures of estimators that leverage evolutionary information, expressed in terms of multiple alignments, both at the input and output levels. While our system currently achieves an overall performance close to 76% correct prediction--at least comparable to the best existing systems--the main emphasis here is on the development of new algorithmic ideas. AVAILABILITY: The executable program for predicting protein secondary structure is available from the authors free of charge. CONTACT: pfbaldi@ics.uci.edu, gpollast@ics.uci.edu, brunak@cbs.dtu.dk, paolo@dsi.unifi.it.     

Prediction of beta-turns in proteins using neural networks

The use of neural networks to improve empirical secondary structure prediction is explored with regard to the identification of the position and conformational class of beta-turns, a four-residue chain reversal. Recently an algorithm was developed for beta-turn predictions based on the empirical approach of Chou and Fasman using different parameters for three classes (I, II and non-specific) of beta-turns. In this paper, using the same data, an alternative approach to derive an empirical prediction method is used based on neural networks which is a general learning algorithm extensively used in artificial intelligence. Thus the results of the two approaches can be compared. The most severe test of prediction accuracy is the percentage of turn predictions that are correct and the neural network gives an overall improvement from 20.6% to 26.0%. The proportion of correctly predicted residues is 71%, compared to a chance level of about 58%. Thus neural networks provide a method of obtaining more accurate predictions from empirical data than a simpler method of deriving propensities.     

PROTINFO: Secondary and tertiary protein structure prediction

Information about the secondary and tertiary structure of a protein sequence can greatly assist biologists in the generation and testing of hypotheses, as well as design of experiments. The PROTINFO server enables users to submit a protein sequence and request a prediction of the three-dimensional (tertiary) structure based on comparative modeling, fold generation and de novo methods developed by the authors. In addition, users can submit NMR chemical shift data and request protein secondary structure assignment that is based on using neural networks to combine the chemical shifts with secondary structure predictions. The server is available at http://protinfo.compbio.washington.edu.     

Role of evolutionary information in predicting the disulfide-bonding state of cysteine in proteins.

A neural network-based predictor is trained to distinguish the bonding states of cysteine in proteins starting from the residue chain. Training is performed by using 2,452 cysteine-containing segments extracted from 641 nonhomologous proteins of well-resolved three-dimensional structure. After a cross-validation procedure, efficiency of the prediction scores were as high as 72% when the predictor is trained by using protein single sequences. The addition of evolutionary information in the form of multiple sequence alignment and a jury of neural networks increases the prediction efficiency up to 81%. Assessment of the goodness of the prediction with a reliability index indicates that more than 60% of the predictions have an accuracy level greater than 90%. A comparison with a statistical method previously described and tested on the same database shows that the neural network-based predictor is performing with the highest efficiency. Proteins 1999;36:340-346.     

Is it better to combine predictions?

We have compared the accuracy of the individual protein secondary structure prediction methods: PHD, DSC, NNSSP and Predator against the accuracy obtained by combing the predictions of the methods. A range of ways of combing predictions were tested: voting, biased voting, linear discrimination, neural networks and decision trees. The combined methods that involve 'learning' (the non-voting methods) were trained using a set of 496 non-homologous domains; this dataset was biased as some of the secondary structure prediction methods had used them for training. We used two independent test sets to compare predictions: the first consisted of 17 non-homologous domains from CASP3 (Third Community Wide Experiment on the Critical Assessment of Techniques for Protein Structure Prediction); the second set consisted of 405 domains that were selected in the same way as the training set, and were non-homologous to each other and the training set. On both test datasets the most accurate individual method was NNSSP, then PHD, DSC and the least accurate was Predator; however, it was not possible to conclusively show a significant difference between the individual methods. Comparing the accuracy of the single methods with that obtained by combing predictions it was found that it was better to use a combination of predictions. On both test datasets it was possible to obtain a approximately 3% improvement in accuracy by combing predictions. In most cases the combined methods were statistically significantly better (at P = 0.05 on the CASP3 test set, and P = 0.01 on the EBI test set). On the CASP3 test dataset there was no significant difference in accuracy between any of the combined method of prediction: on the EBI test dataset, linear discrimination and neural networks significantly outperformed voting techniques. We conclude that it is better to combine predictions.     

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.     

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).     

Protein structural motif prediction in multidimensional phi-psi space leads to improved secondary structure prediction.

A significant step towards establishing the structure and function of a protein is the prediction of the local conformation of the polypeptide chain. In this article, we present systems for the prediction of three new alphabets of local structural motifs. The motifs are built by applying multidimensional scaling (MDS) and clustering to pair-wise angular distances for multiple phi-psi angle values collected from high-resolution protein structures. The predictive systems, based on ensembles of bidirectional recurrent neural network architectures, and trained on a large non-redundant set of protein structures, achieve 72%, 66%, and 60% correct motif prediction on an independent test set for di-peptides (six classes), tri-peptides (eight classes) and tetra-peptides (14 classes), respectively, 28-30% above baseline statistical predictors. We then build a further system, based on ensembles of two-layered bidirectional recurrent neural networks, to map structural motif predictions into a traditional 3-class (helix, strand, coil) secondary structure. This system achieves 79.5% correct prediction using the "hard" CASP 3-class assignment, and 81.4% with a more lenient assignment, outperforming a sophisticated state-of-the-art predictor (Porter) trained in the same experimental conditions. The structural motif predictor is publicly available at: http://distill.ucd.ie/porter+/.     

Using artificially generated spectral data to improve protein secondary structure prediction from Fourier transform infrared spectra of proteins

Secondary structures of proteins have been predicted using neural networks from their Fourier transform infrared spectra. To improve the generalization ability of the neural networks, the training data set has been artificially increased by linear interpolation. The leave-one-out approach has been used to demonstrate the applicability of the method. Bayesian regularization has been used to train the neural networks and the predictions have been further improved by the maximum-likelihood estimation method. The networks have been tested and standard error of prediction (SEP) of 4.19% for alpha helix, 3.49% for beta sheet, and 3.15% for turns have been achieved. The results indicate that there is a significant decrease in the SEP for each type of structure parameter compared to previous works.     

Predicting protein secondary structure content. A tandem neural network approach.

A priori knowledge of secondary structure content can be of great use in theoretical and experimental determination of protein structure. We present a method that uses two computer-simulated neural networks placed in "tandem" to predict the secondary structure content of water-soluble, globular proteins. The first of the two networks, NET1, predicts a protein's helix and strand content given information about the protein's amino acid composition, molecular weight and heme presence. Because NET1 contained more adjustable parameters (network weights) than learning examples, this network experienced problems with memorization, which is the inability to generalize onto new, never-seen-before examples. To overcome this problem, we designed a second network, NET2, which learned to determine when NET1 was in a state of generalization. Together, these two networks produce prediction errors as low as 5.0% and 5.6% for helix and strand content, respectively, on a set of protein crystal structures bearing little homology to those used in network training. A comparison between three other methods including a multiple linear regression analysis, a non-hidden-node network analysis and a secondary structure assignment analysis reveals that our tandem neural network scheme is, indeed, the best method for predicting secondary structure content. The results of our analysis suggest that the knowledge of sequence information is not necessary for highly accurate predictions of protein secondary structure content.     

Protein contact prediction using patterns of correlation

We describe a new method for using neural networks to predict residue contact pairs in a protein. The main inputs to the neural network are a set of 25 measures of correlated mutation between all pairs of residues in two "windows" of size 5 centered on the residues of interest. While the individual pair-wise correlations are a relatively weak predictor of contact, by training the network on windows of correlation the accuracy of prediction is significantly improved. The neural network is trained on a set of 100 proteins and then tested on a disjoint set of 1033 proteins of known structure. An average predictive accuracy of 21.7% is obtained taking the best L/2 predictions for each protein, where L is the sequence length. Taking the best L/10 predictions gives an average accuracy of 30.7%. The predictor is also tested on a set of 59 proteins from the CASP5 experiment. The accuracy is found to be relatively consistent across different sequence lengths, but to vary widely according to the secondary structure. Predictive accuracy is also found to improve by using multiple sequence alignments containing many sequences to calculate the correlations.     

Prediction of N-linked glycan branching patterns using artificial neural networks

A model was developed for novel prediction of N-linked glycan branching pattern classification for CHO-derived N-linked glycoproteins. The model consists of 30 independent recurrent neural networks and uses predicted quantities of secondary structure elements and residue solvent accessibility as an input vector. The model was designed to predict the major component of a heterogeneous mixture of CHO-derived glycoforms of a recombinant protein under normal growth conditions. Resulting glycosylation prediction is classified as either complex-type or high mannose. The incorporation of predicted quantities in the input vector allowed for theoretical mutant N-linked glycan branching predictions without initial experimental analysis of protein structures. Primary amino acid sequence data were effectively eliminated from the input vector space based on neural network prediction analyses. This provided further evidence that localized protein secondary structure elements and conformational structure may play more important roles in determining glycan branching patterns than does the primary sequence of a polypeptide. A confidence interval parameter was incorporated into the model to enable identification of false predictions. The model was further tested using published experimental results for mutants of the tissue-type plasminogen activator protein [J. Wilhelm, S.G. Lee, N.K. Kalyan, S.M. Cheng, F. Wiener, W. Pierzchala, P.P. Hung, Alterations in the domain structure of tissue-type plasminogen activator change the nature of asparagine glycosylation. Biotechnology (N.Y.) 8 (1990) 321-325].     

Predicting surface exposure of amino acids from protein sequence

The amino acid residues on a protein surface play a key role in interaction with other molecules, determined many physical properties, and constrain the structure of the folded protein. A database of monomeric protein crystal structures was used to teach computer-simulated neural networks rules for predicting surface exposure from local sequence. These trained networks are able to correctly predict surface exposure for 72% of residues in a testing set using a binary model, (buried/exposed) and for 54% of residues using a ternary model (buried/intermediate/exposed). In the ternary model, only 11% of the exposed residues are predicted as buried and only 5% of the buried residues are predicted as exposed. Also, since the networks are able to predict exposure with a quantitative confidence estimate, it is possible to assign exposure for over half of the residues in a binary model with greater than 80% accuracy. Even more accurate predictions are obtained by making a consensus prediction of exposure for a homologous family. The effect of the local environment of an amino acid on its accessibility, though smaller than expected, is significant and accounts for the higher success rate of prediction than obtained with previously used criteria. In the absence of a three-dimensional structure, the ability to predict surface accessibility of amino acids directly from the sequence is a valuable tool in choosing sites of chemical modification or specific mutations and in studies of molecular interaction.     

Cross-validation of protein structural class prediction using statistical clustering and neural networks.

We present an approach to predicting protein structural class that uses amino acid composition and hydrophobic pattern frequency information as input to two types of neural networks: (1) a three-layer back-propagation network and (2) a learning vector quantization network. The results of these methods are compared to those obtained from a modified Euclidean statistical clustering algorithm. The protein sequence data used to drive these algorithms consist of the normalized frequency of up to 20 amino acid types and six hydrophobic amino acid patterns. From these frequency values the structural class predictions for each protein (all-alpha, all-beta, or alpha-beta classes) are derived. Examples consisting of 64 previously classified proteins were randomly divided into multiple training (56 proteins) and test (8 proteins) sets. The best performing algorithm on the test sets was the learning vector quantization network using 17 inputs, obtaining a prediction accuracy of 80.2%. The Matthews correlation coefficients are statistically significant for all algorithms and all structural classes. The differences between algorithms are in general not statistically significant. These results show that information exists in protein primary sequences that is easily obtainable and useful for the prediction of protein structural class by neural networks as well as by standard statistical clustering algorithms.     

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.     

Progress of 1D protein structure prediction at last

Accuracy of predicting protein secondary structure and solvent accessibility from sequence information has been improved significantly by using information contained in multiple sequence alignments as input to a neural 'network system. For the Asilomar meeting, predictions for 13 proteins were generated automatically using the publicly available prediction method PHD. The results confirm the estimate of 72% three-state prediction accuracy. The fairly accurate predictions of secondary structure segments made the tool useful as a starting point for modeling of higher dimensional aspects of protein structure. © 1995 Wiley-Liss, Inc.     

Prediction of the disulfide-bonding state of cysteine in proteins

The bonding states of cysteine play important functional and structural roles in proteins. In particular, disulfide bond formation is one of the most important factors influencing the three-dimensional fold of proteins. Proteins of known structure were used to teach computer-simulated neural networks rules for predicting the disulfide-bonding state of a cysteine given only its flanking amino acid sequence. Resulting networks make accurate predictions on sequences different from those used in training, suggesting that local sequence greatly influences cysteines in disulfide bond formation. The average prediction rate after seven independent network experiments is 81.4% for disulfide-bonded and 80.0% for non-disulfide-bonded scenarios. Predictive accuracy is related to the strength of network output activities. Network weights reveal interesting position-dependent amino acid preferences and provide a physical basis for understanding the correlation between the flanking sequence and a cysteine's disulfide-bonding state. Network predictions may be used to increase or decrease the stability of existing disulfide bonds or to aid the search for potential sites to introduce new disulfide bonds.     

Protein secondary structure prediction using three neural networks and a segmental semi Markov model

Prediction of protein secondary structure is an important step towards elucidating its three dimensional structure and its function. This is a challenging problem in bioinformatics. Segmental semi Markov models (SSMMs) are one of the best studied methods in this field. However, incorporating evolutionary information to these methods is somewhat difficult. On the other hand, the systems of multiple neural networks (NNs) are powerful tools for multi-class pattern classification which can easily be applied to take these sorts of information into account.To overcome the weakness of SSMMs in prediction, in this work we consider a SSMM as a decision function on outputs of three NNs that uses multiple sequence alignment profiles. We consider four types of observations for outputs of a neural network. Then profile table related to each sequence is reduced to a sequence of four observations. In order to predict secondary structure of each amino acid we need to consider a decision function. We use an SSMM on outputs of three neural networks. The proposed SSMM has discriminative power and weights over different dependency models for outputs of neural networks. The results show that the accuracy of our model in predictions, particularly for strands, is considerably increased.