Analysis of an optimal hidden Markov model for secondary structure prediction

Complementarity of the residue-level protein function and structure predictions in human proteins

Sequence-based predictors of the residue-level protein function and structure cover a broad spectrum of characteristics including intrinsic disorder, secondary structure, solvent accessibility and binding to nucleic acids. They were catalogued and evaluated in numerous surveys and assessments. However, methods focusing on a given characteristic are studied separately from predictors of other characteristics, while they are typically used on the same proteins. We fill this void by studying complementarity of a representative collection of methods that target different predictions using a large, taxonomically consistent, and low similarity dataset of human proteins. First, we bridge the gap between the communities that develop structure-trained vs. disorder-trained predictors of binding residues. Motivated by a recent study of the protein-binding residue predictions, we empirically find that combining the structure-trained and disorder-trained predictors of the DNA-binding and RNA-binding residues leads to substantial improvements in predictive quality. Second, we investigate whether diverse predictors generate results that accurately reproduce relations between secondary structure, solvent accessibility, interaction sites, and intrinsic disorder that are present in the experimental data. Our empirical analysis concludes that predictions accurately reflect all combinations of these relations. Altogether, this study provides unique insights that support combining results produced by diverse residue-level predictors of protein function and structure.

Computational Prediction of Secondary and Supersecondary Structures from Protein Sequences

Many new methods for the sequence-based prediction of the secondary and supersecondary structures have been developed over the last several years. These and older sequence-based predictors are widely applied for the characterization and prediction of protein structure and function. These efforts have produced countless accurate predictors, many of which rely on state-of-the-art machine learning models and evolutionary information generated from multiple sequence alignments. We describe and motivate both types of predictions. We introduce concepts related to the annotation and computational prediction of the three-state and eight-state secondary structure as well as several types of supersecondary structures, such as β hairpins, coiled coils, and α-turn-α motifs. We review 34 predictors focusing on recent tools and provide detailed information for a selected set of 14 secondary structure and 3 supersecondary structure predictors. We conclude with several practical notes for the end users of these predictive methods.

Protein secondary structure prediction using a small training set (compact model) combined with a Complex-valued neural network approach

BACKGROUND

Protein secondary structure prediction (SSP) has been an area of intense research interest. Despite advances in recent methods conducted on large datasets, the estimated upper limit accuracy is yet to be reached. Since the predictions of SSP methods are applied as input to higher-level structure prediction pipelines, even small errors may have large perturbations in final models. Previous works relied on cross validation as an estimate of classifier accuracy. However, training on large numbers of protein chains compromises the classifier ability to generalize to new sequences. This prompts a novel approach to training and an investigation into the possible structural factors that lead to poor predictions. Here, a small group of 55 proteins termed the compact model is selected from the CB513 dataset using a heuristics-based approach. In a prior work, all sequences were represented as probability matrices of residues adopting each of Helix, Sheet and Coil states, based on energy calculations using the C-Alpha, C-Beta, Side-chain (CABS) algorithm. The functional relationship between the conformational energies computed with CABS force-field and residue states is approximated using a classifier termed the Fully Complex-valued Relaxation Network (FCRN). The FCRN is trained with the compact model proteins.

RESULTS

The performance of the compact model is compared with traditional cross-validated accuracies and blind-tested on a dataset of G Switch proteins, obtaining accuracies of ∼81 %. The model demonstrates better results when compared to several techniques in the literature. A comparative case study of the worst performing chain identifies hydrogen bond contacts that lead to Coil ⇔ Sheet misclassifications. Overall, mispredicted Coil residues have a higher propensity to participate in backbone hydrogen bonding than correctly predicted Coils.

CONCLUSIONS

The implications of these findings are: (i) the choice of training proteins is important in preserving the generalization of a classifier to predict new sequences accurately and (ii) SSP techniques sensitive in distinguishing between backbone hydrogen bonding and side-chain or water-mediated hydrogen bonding might be needed in the reduction of Coil ⇔ Sheet misclassifications.

A critical assessment of hidden markov model sub-optimal sampling strategies applied to the generation of peptide 3D models

Hidden Markov Model derived structural alphabets are a probabilistic framework in which the complete conformational space of a peptidic chain is described in terms of probability distributions that can be sampled to identify conformations of largest probabilities. Here, we assess how three strategies to sample sub-optimal conformations-Viterbi k-best, forward backtrack and a taboo sampling approach-can lead to the efficient generation of peptide conformations. We show that the diversity of sampling is essential to compensate biases introduced in the estimates of the probabilities, and we find that only the forward backtrack and a taboo sampling strategies can efficiently generate native or near-native models. Finally, we also find such approaches are as efficient as former protocols, while being one order of magnitude faster, opening the door to the large scale de novo modeling of peptides and mini-proteins. © 2016 Wiley Periodicals, Inc.

SPINE X: improving protein secondary structure prediction by multistep learning coupled with prediction of solvent accessible surface area and backbone torsion angles

Accurate prediction of protein secondary structure is essential for accurate sequence alignment, three-dimensional structure modeling, and function prediction. The accuracy of ab initio secondary structure prediction from sequence, however, has only increased from around 77 to 80% over the past decade. Here, we developed a multistep neural-network algorithm by coupling secondary structure prediction with prediction of solvent accessibility and backbone torsion angles in an iterative manner. Our method called SPINE X was applied to a dataset of 2640 proteins (25% sequence identity cutoff) previously built for the first version of SPINE and achieved a 82.0% accuracy based on 10-fold cross validation (Q(3)). Surpassing 81% accuracy by SPINE X is further confirmed by employing an independently built test dataset of 1833 protein chains, a recently built dataset of 1975 proteins and 117 CASP 9 targets (critical assessment of structure prediction techniques) with an accuracy of 81.3%, 82.3% and 81.8%, respectively. The prediction accuracy is further improved to 83.8% for the dataset of 2640 proteins if the DSSP assignment used above is replaced by a more consistent consensus secondary structure assignment method. Comparison to the popular PSIPRED and CASP-winning structure-prediction techniques is made. SPINE X predicts number of helices and sheets correctly for 21.0% of 1833 proteins, compared to 17.6% by PSIPRED. It further shows that SPINE X consistently makes more accurate prediction in helical residues (6%) without over prediction while PSIPRED makes more accurate prediction in coil residues (3-5%) and over predicts them by 7%. SPINE X Server and its training/test datasets are available at http://sparks.informatics.iupui.edu/

Computational prediction of secondary and supersecondary structures

The sequence-based prediction of the secondary and supersecondary structures enjoys strong interest and finds applications in numerous areas related to the characterization and prediction of protein structure and function. Substantial efforts in these areas over the last three decades resulted in the development of accurate predictors, which take advantage of modern machine learning models and availability of evolutionary information extracted from multiple sequence alignment. In this chapter, we first introduce and motivate both prediction areas and introduce basic concepts related to the annotation and prediction of the secondary and supersecondary structures, focusing on the β hairpin, coiled coil, and α-turn-α motifs. Next, we overview state-of-the-art prediction methods, and we provide details for 12 modern secondary structure predictors and 4 representative supersecondary structure predictors. Finally, we provide several practical notes for the users of these prediction tools.

Critical assessment of high-throughput standalone methods for secondary structure prediction

Sequence-based prediction of protein secondary structure (SS) enjoys wide-spread and increasing use for the analysis and prediction of numerous structural and functional characteristics of proteins. The lack of a recent comprehensive and large-scale comparison of the numerous prediction methods results in an often arbitrary selection of a SS predictor. To address this void, we compare and analyze 12 popular, standalone and high-throughput predictors on a large set of 1975 proteins to provide in-depth, novel and practical insights. We show that there is no universally best predictor and thus detailed comparative studies are needed to support informed selection of SS predictors for a given application. Our study shows that the three-state accuracy (Q3) and segment overlap (SOV3) of the SS prediction currently reach 82% and 81%, respectively. We demonstrate that carefully designed consensus-based predictors improve the Q3 by additional 2% and that homology modeling-based methods are significantly better by 1.5% Q3 than ab initio approaches. Our empirical analysis reveals that solvent exposed and flexible coils are predicted with a higher quality than the buried and rigid coils, while inverse is true for the strands and helices. We also show that longer helices are easier to predict, which is in contrast to longer strands that are harder to find. The current methods confuse 1-6% of strand residues with helical residues and vice versa and they perform poorly for residues in the β- bridge and 3(10)-helix conformations. Finally, we compare predictions of the standalone implementations of four well-performing methods with their corresponding web servers.

Exact distribution of a pattern in a set of random sequences generated by a Markov source: applications to biological data

BACKGROUND

In bioinformatics it is common to search for a pattern of interest in a potentially large set of rather short sequences (upstream gene regions, proteins, exons, etc.). Although many methodological approaches allow practitioners to compute the distribution of a pattern count in a random sequence generated by a Markov source, no specific developments have taken into account the counting of occurrences in a set of independent sequences. We aim to address this problem by deriving efficient approaches and algorithms to perform these computations both for low and high complexity patterns in the framework of homogeneous or heterogeneous Markov models.

RESULTS

The latest advances in the field allowed us to use a technique of optimal Markov chain embedding based on deterministic finite automata to introduce three innovative algorithms. Algorithm 1 is the only one able to deal with heterogeneous models. It also permits to avoid any product of convolution of the pattern distribution in individual sequences. When working with homogeneous models, Algorithm 2 yields a dramatic reduction in the complexity by taking advantage of previous computations to obtain moment generating functions efficiently. In the particular case of low or moderate complexity patterns, Algorithm 3 exploits power computation and binary decomposition to further reduce the time complexity to a logarithmic scale. All these algorithms and their relative interest in comparison with existing ones were then tested and discussed on a toy-example and three biological data sets: structural patterns in protein loop structures, PROSITE signatures in a bacterial proteome, and transcription factors in upstream gene regions. On these data sets, we also compared our exact approaches to the tempting approximation that consists in concatenating the sequences in the data set into a single sequence.

CONCLUSIONS

Our algorithms prove to be effective and able to handle real data sets with multiple sequences, as well as biological patterns of interest, even when the latter display a high complexity (PROSITE signatures for example). In addition, these exact algorithms allow us to avoid the edge effect observed under the single sequence approximation, which leads to erroneous results, especially when the marginal distribution of the model displays a slow convergence toward the stationary distribution. We end up with a discussion on our method and on its potential improvements.

Impact of residue accessible surface area on the prediction of protein secondary structures

Background

The problem of accurate prediction of protein secondary structure continues to be one of the challenging problems in Bioinformatics. It has been previously suggested that amino acid relative solvent accessibility (RSA) might be an effective factor for increasing the accuracy of protein secondary structure prediction. Previous studies have either used a single constant threshold to classify residues into discrete classes (buries vs. exposed), or used the real-value predicted RSAs in their prediction method.

Results

We studied the effect of applying different RSA threshold types (namely, fixed thresholds vs. residue-dependent thresholds) on a variety of secondary structure prediction methods. With the consideration of DSSP-assigned RSA values we realized that improvement in the accuracy of prediction strictly depends on the selected threshold(s). Furthermore, we showed that choosing a single threshold for all amino acids is not the best possible parameter. We therefore used residue-dependent thresholds and most of residues showed improvement in prediction. Next, we tried to consider predicted RSA values, since in the real-world problem, protein sequence is the only available information. We first predicted the RSA classes by RVP-net program and then used these data in our method. Using this approach, improvement in prediction was also obtained.

Conclusion

The success of applying the RSA information on different secondary structure prediction methods suggest that prediction accuracy can be improved independent of prediction approaches. Thus, solvent accessibility can be considered as a rich source of information to help the improvement of these methods.

Accurate sequence-based prediction of catalytic residues

MOTIVATION

Prediction of catalytic residues provides useful information for the research on function of enzymes. Most of the existing prediction methods are based on structural information, which limits their use. We propose a sequence-based catalytic residue predictor that provides predictions with quality comparable to modern structure-based methods and that exceeds quality of state-of-the-art sequence-based methods.

RESULTS

Our method (CRpred) uses sequence-based features and the sequence-derived PSI-BLAST profile. We used feature selection to reduce the dimensionality of the input (and explain the input) to support vector machine (SVM) classifier that provides predictions. Tests on eight datasets and side-by-side comparison with six modern structure- and sequence-based predictors show that CRpred provides predictions with quality comparable to current structure-based methods and better than sequence-based methods. The proposed method obtains 15-19% precision and 48-58% TP (true positive) rate, depending on the dataset used. CRpred also provides confidence values that allow selecting a subset of predictions with higher precision. The improved quality is due to newly designed features and careful parameterization of the SVM. The features incorporate amino acids characterized by the highest and the lowest propensities to constitute catalytic residues, Gly that provides flexibility for catalytic sites and sequence motifs characteristic to certain catalytic reactions. Our features indicate that catalytic residues are on average more conserved when compared with the general population of residues and that highly conserved amino acids characterized by high catalytic propensity are likely to form catalytic sites. We also show that local (with respect to the sequence) hydrophobicity contributes towards the prediction.

Prediction of protein local structures and folding fragments based on building-block library

In recent years, protein structure prediction using local structure information has made great progress. In this study, a novel and effective method is developed to predict the local structure and the folding fragments of proteins. First, the proteins with known structures are split into fragments. Second, these fragments, represented by dihedrals, are clustered to produce the building blocks (BBs). Third, an efficient machine learning method is used to predict the local structures of proteins from sequence profiles. Finally, a bi-gram model, trained by an iterated algorithm, is introduced to simulate the interactions of these BBs. For test proteins, the building-block lattice is constructed, which contains all the folding fragments of the proteins. The local structures and the optimal fragments are then obtained by the dynamic programming algorithm. The experiment is performed on a subset of the PDB database with sequence identity less than 25%. The results show that the performance of the method is better than the method that uses only sequence information. When multiple paths are returned, the average classification accuracy of local structures is 72.27% and the average prediction accuracy of local structures is 67.72%, which is a significant improvement in comparison with previous studies. The method can predict not only the local structures but also the folding fragments of proteins. This work is helpful for the ab initio protein structure prediction and especially, the understanding of the folding process of proteins.

An evolutionary method for learning HMM structure: prediction of protein secondary structure

Background

The prediction of the secondary structure of proteins is one of the most studied problems in bioinformatics. Despite their success in many problems of biological sequence analysis, Hidden Markov Models (HMMs) have not been used much for this problem, as the complexity of the task makes manual design of HMMs difficult. Therefore, we have developed a method for evolving the structure of HMMs automatically, using Genetic Algorithms (GAs).

Results

In the GA procedure, populations of HMMs are assembled from biologically meaningful building blocks. Mutation and crossover operators were designed to explore the space of such Block-HMMs. After each step of the GA, the standard HMM estimation algorithm (the Baum-Welch algorithm) was used to update model parameters. The final HMM captures several features of protein sequence and structure, with its own HMM grammar. In contrast to neural network based predictors, the evolved HMM also calculates the probabilities associated with the predictions. We carefully examined the performance of the HMM based predictor, both under the multiple- and single-sequence condition.

Conclusion

We have shown that the proposed evolutionary method can automatically design the topology of HMMs. The method reads the grammar of protein sequences and converts it into the grammar of an HMM. It improved previously suggested evolutionary methods and increased the prediction quality. Especially, it shows good performance under the single-sequence condition and provides probabilistic information on the prediction result. The protein secondary structure predictor using HMMs (P.S.HMM) is on-line available http://www.binf.ku.dk/~won/pshmm.htm. It runs under the single-sequence condition.