Utilization of protein intrinsic disorder knowledge in structural proteomics

Intrinsically disordered proteins (IDPs) and proteins with long disordered regions are highly abundant in various proteomes. Despite their lack of well-defined ordered structure, these proteins and regions are frequently involved in crucial biological processes. Although in recent years these proteins have attracted the attention of many researchers, IDPs represent a significant challenge for structural characterization since these proteins can impact many of the processes in the structure determination pipeline. Here we investigate the effects of IDPs on the structure determination process and the utility of disorder prediction in selecting and improving proteins for structural characterization. Examination of the extent of intrinsic disorder in existing crystal structures found that relatively few protein crystal structures contain extensive regions of intrinsic disorder. Although intrinsic disorder is not the only cause of crystallization failures and many structured proteins cannot be crystallized, filtering out highly disordered proteins from structure-determination target lists is still likely to be cost effective. Therefore it is desirable to avoid highly disordered proteins from structure-determination target lists and we show that disorder prediction can be applied effectively to enrich structure determination pipelines with proteins more likely to yield crystal structures. For structural investigation of specific proteins, disorder prediction can be used to improve targets for structure determination. Finally, a framework for considering intrinsic disorder in the structure determination pipeline is proposed.     

Inferring function using patterns of native disorder in proteins

Natively unstructured regions are a common feature of eukaryotic proteomes. Between 30% and 60% of proteins are predicted to contain long stretches of disordered residues, and not only have many of these regions been confirmed experimentally, but they have also been found to be essential for protein function. In this study, we directly address the potential contribution of protein disorder in predicting protein function using standard Gene Ontology (GO) categories. Initially we analyse the occurrence of protein disorder in the human proteome and report ontology categories that are enriched in disordered proteins. Pattern analysis of the distributions of disordered regions in human sequences demonstrated that the functions of intrinsically disordered proteins are both length- and position-dependent. These dependencies were then encoded in feature vectors to quantify the contribution of disorder in human protein function prediction using Support Vector Machine classifiers. The prediction accuracies of 26 GO categories relating to signalling and molecular recognition are improved using the disorder features. The most significant improvements were observed for kinase, phosphorylation, growth factor, and helicase categories. Furthermore, we provide predicted GO term assignments using these classifiers for a set of unannotated and orphan human proteins. In this study, the importance of capturing protein disorder information and its value in function prediction is demonstrated. The GO category classifiers generated can be used to provide more reliable predictions and further insights into the behaviour of orphan and unannotated proteins.     

Evolution of structurally disordered proteins promotes neostructuralization

Protein structure is generally more conserved than sequence, but for regions that can adopt different structures in different environments, does this hold true? Understanding how structurally disordered regions evolve altered secondary structure element propensities as well as conformational flexibility among paralogs are fundamental questions for our understanding of protein structural evolution. We have investigated the evolutionary dynamics of structural disorder in protein families containing both orthologs and paralogs using phylogenetic tree reconstruction, protein structure disorder prediction, and secondary structure prediction in order to shed light upon these questions. Our results indicate that the extent and location of structurally disordered regions are not universally conserved. As structurally disordered regions often have high conformational flexibility, this is likely to have an effect on how protein structure evolves as spatially altered conformational flexibility can also change the secondary structure propensities for homologous regions in a protein family.     

PONDR-FIT: A meta-predictor of intrinsically disordered amino acids

Protein intrinsic disorder is becoming increasingly recognized in proteomics research. While lacking structure, many regions of disorder have been associated with biological function. There are many different experimental methods for characterizing intrinsically disordered proteins and regions; nevertheless, the prediction of intrinsic disorder from amino acid sequence remains a useful strategy especially for many large-scale proteomic investigations. Here we introduced a consensus artificial neural network (ANN) prediction method, which was developed by combining the outputs of several individual disorder predictors. By eight-fold cross-validation, this meta-predictor, called PONDR-FIT, was found to improve the prediction accuracy over a range of 3 to 20% with an average of 11% compared to the single predictors, depending on the datasets being used. Analysis of the errors shows that the worst accuracy still occurs for short disordered regions with less than ten residues, as well as for the residues close to order/disorder boundaries. Increased understanding of the underlying mechanism by which such meta-predictors give improved predictions will likely promote the further development of protein disorder predictors. Access to PONDR-FIT is available at www.disprot.org.     

cnnAlpha: Protein disordered regions prediction by reduced amino acid alphabets and convolutional neural networks

Intrinsically disordered regions (IDR) play an important role in key biological processes and are closely related to human diseases. IDRs have great potential to serve as targets for drug discovery, most notably in disordered binding regions. Accurate prediction of IDRs is challenging because their genome wide occurrence and a low ratio of disordered residues make them difficult targets for traditional classification techniques. Existing computational methods mostly rely on sequence profiles to improve accuracy which is time consuming and computationally expensive. This article describes an ab initio sequence-only prediction method—which tries to overcome the challenge of accurate prediction posed by IDRs—based on reduced amino acid alphabets and convolutional neural networks (CNNs). We experiment with six different 3-letter reduced alphabets. We argue that the dimensional reduction in the input alphabet facilitates the detection of complex patterns within the sequence by the convolutional step. Experimental results show that our proposed IDR predictor performs at the same level or outperforms other state-of-the-art methods in the same class, achieving accuracy levels of 0.76 and AUC of 0.85 on the publicly available Critical Assessment of protein Structure Prediction dataset (CASP10). Therefore, our method is suitable for proteome-wide disorder prediction yielding similar or better accuracy than existing approaches at a faster speed.     

A practical overview of protein disorder prediction methods

In the past few years there has been a growing awareness that a large number of proteins contain long disordered (unstructured) regions that often play a functional role. However, these disordered regions are still poorly detected. Recognition of disordered regions in a protein is important for two main reasons: reducing bias in sequence similarity analysis by avoiding alignment of disordered regions against ordered ones, and helping to delineate boundaries of protein domains to guide structural and functional studies. As none of the available method for disorder prediction can be taken as fully reliable on its own, we present an overview of the methods currently employed highlighting their advantages and drawbacks. We show a few practical examples of how they can be combined to avoid pitfalls and to achieve more reliable predictions.     

Conservation of intrinsic disorder in protein domains and families: I. A database of conserved predicted disordered regions

Many protein regions have been shown to be intrinsically disordered, lacking unique structure under physiological conditions. These intrinsically disordered regions are not only very common in proteomes, but also crucial to the function of many proteins, especially those involved in signaling, recognition, and regulation. The goal of this work was to identify the prevalence, characteristics, and functions of conserved disordered regions within protein domains and families. A database was created to store the amino acid sequences of nearly one million proteins and their domain matches from the InterPro database, a resource integrating eight different protein family and domain databases. Disorder prediction was performed on these protein sequences. Regions of sequence corresponding to domains were aligned using a multiple sequence alignment tool. From this initial information, regions of conserved predicted disorder were found within the domains. The methodology for this search consisted of finding regions of consecutive positions in the multiple sequence alignments in which a 90% or more of the sequences were predicted to be disordered. This procedure was constrained to find such regions of conserved disorder prediction that were at least 20 amino acids in length. The results of this work included 3,653 regions of conserved disorder prediction, found within 2,898 distinct InterPro entries. Most regions of conserved predicted disorder detected were short, with less than 10% of those found exceeding 30 residues in length.     

Comparing and combining predictors of mostly disordered proteins

Intrinsically disordered proteins and regions carry out varied and vital cellular functions. Proteins with disordered regions are especially common in eukaryotic cells, with a subset of these proteins being mostly disordered, e.g., with more disordered than ordered residues. Two distinct methods have been previously described for using amino acid sequences to predict which proteins are likely to be mostly disordered. These methods are based on the net charge-hydropathy distribution and disorder prediction score distribution. Each of these methods is reexamined, and the prediction results are compared herein. A new prediction method based on consensus is described. Application of the consensus method to whole genomes reveals that approximately 4.5% of Yersinia pestis, 5% of Escherichia coli K12, 6% of Archaeoglobus fulgidus, 8% of Methanobacterium thermoautotrophicum, 23% of Arabidopsis thaliana, and 28% of Mus musculus proteins are mostly disordered. The unexpectedly high frequency of mostly disordered proteins in eukaryotes has important implications both for large-scale, high-throughput projects and also for focused experiments aimed at determination of protein structure and function.     

Protein disorder prediction by condensed PSSM considering propensity for order or disorder

Background  

More and more disordered regions have been discovered in protein sequences, and many of them are found to be functionally significant. Previous studies reveal that disordered regions of a protein can be predicted by its primary structure, the amino acid sequence. One observation that has been widely accepted is that ordered regions usually have compositional bias toward hydrophobic amino acids, and disordered regions are toward charged amino acids. Recent studies further show that employing evolutionary information such as position specific scoring matrices (PSSMs) improves the prediction accuracy of protein disorder. As more and more machine learning techniques have been introduced to protein disorder detection, extracting more useful features with biological insights attracts more attention.     

Prediction of disordered regions in proteins based on the meta approach

MOTIVATION: Intrinsically disordered regions in proteins have no unique stable structures without their partner molecules, thus these regions sometimes prevent high-quality structure determination. Furthermore, proteins with disordered regions are often involved in important biological processes, and the disordered regions are considered to play important roles in molecular interactions. Therefore, identifying disordered regions is important to obtain high-resolution structural information and to understand the functional aspects of these proteins. RESULTS: We developed a new prediction method for disordered regions in proteins based on the meta approach and implemented a web-server for this prediction method named 'metaPrDOS'. The method predicts the disorder tendency of each residue using support vector machines from the prediction results of the seven independent predictors. Evaluation of the meta approach was performed using the CASP7 prediction targets to avoid an overestimation due to the inclusion of proteins used in the training set of some component predictors. As a result, the meta approach achieved higher prediction accuracy than all methods participating in CASP7.     

Markov models of amino acid substitution to study proteins with intrinsically disordered regions

Background

Intrinsically disordered proteins (IDPs) or proteins with disordered regions (IDRs) do not have a well-defined tertiary structure, but perform a multitude of functions, often relying on their native disorder to achieve the binding flexibility through changing to alternative conformations. Intrinsic disorder is frequently found in all three kingdoms of life, and may occur in short stretches or span whole proteins. To date most studies contrasting the differences between ordered and disordered proteins focused on simple summary statistics. Here, we propose an evolutionary approach to study IDPs, and contrast patterns specific to ordered protein regions and the corresponding IDRs.

Results

Two empirical Markov models of amino acid substitutions were estimated, based on a large set of multiple sequence alignments with experimentally verified annotations of disordered regions from the DisProt database of IDPs. We applied new methods to detect differences in Markovian evolution and evolutionary rates between IDRs and the corresponding ordered protein regions. Further, we investigated the distribution of IDPs among functional categories, biochemical pathways and their preponderance to contain tandem repeats.

Conclusions

We find significant differences in the evolution between ordered and disordered regions of proteins. Most importantly we find that disorder promoting amino acids are more conserved in IDRs, indicating that in some cases not only amino acid composition but the specific sequence is important for function. This conjecture is also reinforced by the observation that for of our data set IDRs evolve more slowly than the ordered parts of the proteins, while we still support the common view that IDRs in general evolve more quickly. The improvement in model fit indicates a possible improvement for various types of analyses e.g. de novo disorder prediction using a phylogenetic Hidden Markov Model based on our matrices showed a performance similar to other disorder predictors.     

Intrinsic disorder and functional proteomics

The recent advances in the prediction of intrinsically disordered proteins and the use of protein disorder prediction in the fields of molecular biology and bioinformatics are reviewed here, especially with regard to protein function. First, a close look is taken at intrinsically disordered proteins and then at the methods used for their experimental characterization. Next, the major statistical properties of disordered regions are summarized, and prediction models developed thus far are described, including their numerous applications in functional proteomics. The future of the prediction of protein disorder and the future uses of such predictions in functional proteomics comprise the last section of this article.     

Flavors of protein disorder

Intrinsically disordered proteins are characterized by long regions lacking 3-D structure in their native states, yet they have been so far associated with 28 distinguishable functions. Previous studies showed that protein predictors trained on disorder from one type of protein often achieve poor accuracy on disorder of proteins of a different type, thus indicating significant differences in sequence properties among disordered proteins. Important biological problems are identifying different types, or flavors, of disorder and examining their relationships with protein function. Innovative use of computational methods is needed in addressing these problems due to relative scarcity of experimental data and background knowledge related to protein disorder. We developed an algorithm that partitions protein disorder into flavors based on competition among increasing numbers of predictors, with prediction accuracy determining both the number of distinct predictors and the partitioning of the individual proteins. Using 145 variously characterized proteins with long (>30 amino acids) disordered regions, 3 flavors, called V, C, and S, were identified by this approach, with the V subset containing 52 segments and 7743 residues, C containing 39 segments and 3402 residues, and S containing 54 segments and 5752 residues. The V, C, and S flavors were distinguishable by amino acid compositions, sequence locations, and biological function. For the sequences in SwissProt and 28 genomes, their protein functions exhibit correlations with the commonness and usage of different disorder flavors, suggesting different flavor-function sets across these protein groups. Overall, the results herein support the flavor-function approach as a useful complement to structural genomics as a means for automatically assigning possible functions to sequences.     

Prediction of protein disorder on amino acid substitutions

Intrinsically disordered regions of proteins are known to have many functional roles in cell signaling and regulatory pathways. The altered expression of these proteins due to mutations is associated with various diseases. Currently, most of the available methods focus on predicting the disordered proteins or the disordered regions in a protein. On the other hand, methods developed for predicting protein disorder on mutation showed a poor performance with a maximum accuracy of 70%. Hence, in this work, we have developed a novel method to classify the disorder-related amino acid substitutions using amino acid properties, substitution matrices, and the effect of neighboring residues that showed an accuracy of 90.0% with a sensitivity and specificity of 94.9 and 80.6%, respectively, in 10-fold cross-validation. The method was evaluated with a test set of 20% data using 10 iterations, which showed an average accuracy of 88.9%. Furthermore, we systematically analyzed the features responsible for the better performance of our method and observed that neighboring residues play an important role in defining the disorder of a given residue in a protein sequence. We have developed a prediction server to identify disorder-related mutations, and it is available at http://www.iitm.ac.in/bioinfo/DIM_Pred/.     

SPINE-D: accurate prediction of short and long disordered regions by a single neural-network based method

Short and long disordered regions of proteins have different preference for different amino acid residues. Different methods often have to be trained to predict them separately. In this study, we developed a single neural-network-based technique called SPINE-D that makes a three-state prediction first (ordered residues and disordered residues in short and long disordered regions) and reduces it into a two-state prediction afterwards. SPINE-D was tested on various sets composed of different combinations of Disprot annotated proteins and proteins directly from the PDB annotated for disorder by missing coordinates in X-ray determined structures. While disorder annotations are different according to Disprot and X-ray approaches, SPINE-D's prediction accuracy and ability to predict disorder are relatively independent of how the method was trained and what type of annotation was employed but strongly depend on the balance in the relative populations of ordered and disordered residues in short and long disordered regions in the test set. With greater than 85% overall specificity for detecting residues in both short and long disordered regions, the residues in long disordered regions are easier to predict at 81% sensitivity in a balanced test dataset with 56.5% ordered residues but more challenging (at 65% sensitivity) in a test dataset with 90% ordered residues. Compared to eleven other methods, SPINE-D yields the highest area under the curve (AUC), the highest Mathews correlation coefficient for residue-based prediction, and the lowest mean square error in predicting disorder contents of proteins for an independent test set with 329 proteins. In particular, SPINE-D is comparable to a meta predictor in predicting disordered residues in long disordered regions and superior in short disordered regions. SPINE-D participated in CASP 9 blind prediction and is one of the top servers according to the official ranking. In addition, SPINE-D was examined for prediction of functional molecular recognition motifs in several case studies.     

Uncertainty analysis in protein disorder prediction

A grand challenge in the proteomics and structural genomics era is the prediction of protein structure, including identification of those proteins that are partially or wholly unstructured. A number of predictors for identification of intrinsically disordered proteins (IDPs) have been developed over the last decade, but none can be taken as a fully reliable on its own. Using a single model for prediction is typically inadequate because prediction based on only the most accurate model ignores model uncertainty. In this paper, we present an empirical method to specify and measure uncertainty associated with disorder predictions. In particular, we analyze the uncertainty in the reference model itself and the uncertainty in data. This is achieved by training a set of models and developing several meta predictors on top of them. The best meta predictor achieved comparable or better results than any other single model, suggesting that incorporating different aspects of protein disorder prediction is important for the disorder prediction task. In addition, the best meta-predictor had more balanced sensitivity and specificity than any individual model. We also assessed the effects of changes in disorder prediction as a function of changes in the protein sequence. For collections of homologous sequences, we found that mutations caused many of the predicted disordered residues to be flipped to be predicted as ordered residues, while the reverse was observed much less frequently. These results suggest that disorder tendencies are more sensitive to allowed mutations than structure tendencies and the conservation of disorder is indeed less stable than conservation of structure. Availability: five meta-predictors and four single models developed for this study will be publicly freely accessible for non-commercial use.     

Metapredict: a fast,accurate, and easy-to-use predictor of consensus disorder and structure

Intrinsically disordered proteins and protein regions make up a substantial fraction of many proteomes in which they play a wide variety of essential roles. A critical first step in understanding the role of disordered protein regions in biological function is to identify those disordered regions correctly. Computational methods for disorder prediction have emerged as a core set of tools to guide experiments, interpret results, and develop hypotheses. Given the multiple different predictors available, consensus scores have emerged as a popular approach to mitigate biases or limitations of any single method. Consensus scores integrate the outcome of multiple independent disorder predictors and provide a per-residue value that reflects the number of tools that predict a residue to be disordered. Although consensus scores help mitigate the inherent problems of using any single disorder predictor, they are computationally expensive to generate. They also necessitate the installation of multiple different software tools, which can be prohibitively difficult. To address this challenge, we developed a deep-learning-based predictor of consensus disorder scores. Our predictor, metapredict, utilizes a bidirectional recurrent neural network trained on the consensus disorder scores from 12 proteomes. By benchmarking metapredict using two orthogonal approaches, we found that metapredict is among the most accurate disorder predictors currently available. Metapredict is also remarkably fast, enabling proteome-scale disorder prediction in minutes. Importantly, metapredict is a fully open source and is distributed as a Python package, a collection of command-line tools, and a web server, maximizing the potential practical utility of the predictor. We believe metapredict offers a convenient, accessible, accurate, and high-performance predictor for single-proteins and proteomes alike.     

The unfoldomics decade: an update on intrinsically disordered proteins

Background

Our first predictor of protein disorder was published just over a decade ago in the Proceedings of the IEEE International Conference on Neural Networks (Romero P, Obradovic Z, Kissinger C, Villafranca JE, Dunker AK (1997) Identifying disordered regions in proteins from amino acid sequence. Proceedings of the IEEE International Conference on Neural Networks, 1: 90–95). By now more than twenty other laboratory groups have joined the efforts to improve the prediction of protein disorder. While the various prediction methodologies used for protein intrinsic disorder resemble those methodologies used for secondary structure prediction, the two types of structures are entirely different. For example, the two structural classes have very different dynamic properties, with the irregular secondary structure class being much less mobile than the disorder class. The prediction of secondary structure has been useful. On the other hand, the prediction of intrinsic disorder has been revolutionary, leading to major modifications of the more than 100 year-old views relating protein structure and function. Experimentalists have been providing evidence over many decades that some proteins lack fixed structure or are disordered (or unfolded) under physiological conditions. In addition, experimentalists are also showing that, for many proteins, their functions depend on the unstructured rather than structured state; such results are in marked contrast to the greater than hundred year old views such as the lock and key hypothesis. Despite extensive data on many important examples, including disease-associated proteins, the importance of disorder for protein function has been largely ignored. Indeed, to our knowledge, current biochemistry books don't present even one acknowledged example of a disorder-dependent function, even though some reports of disorder-dependent functions are more than 50 years old. The results from genome-wide predictions of intrinsic disorder and the results from other bioinformatics studies of intrinsic disorder are demanding attention for these proteins.

Results

Disorder prediction has been important for showing that the relatively few experimentally characterized examples are members of a very large collection of related disordered proteins that are wide-spread over all three domains of life. Many significant biological functions are now known to depend directly on, or are importantly associated with, the unfolded or partially folded state. Here our goal is to review the key discoveries and to weave these discoveries together to support novel approaches for understanding sequence-function relationships.

Conclusion

Intrinsically disordered protein is common across the three domains of life, but especially common among the eukaryotic proteomes. Signaling sequences and sites of posttranslational modifications are frequently, or very likely most often, located within regions of intrinsic disorder. Disorder-to-order transitions are coupled with the adoption of different structures with different partners. Also, the flexibility of intrinsic disorder helps different disordered regions to bind to a common binding site on a common partner. Such capacity for binding diversity plays important roles in both protein-protein interaction networks and likely also in gene regulation networks. Such disorder-based signaling is further modulated in multicellular eukaryotes by alternative splicing, for which such splicing events map to regions of disorder much more often than to regions of structure. Associating alternative splicing with disorder rather than structure alleviates theoretical and experimentally observed problems associated with the folding of different length, isomeric amino acid sequences. The combination of disorder and alternative splicing is proposed to provide a mechanism for easily "trying out" different signaling pathways, thereby providing the mechanism for generating signaling diversity and enabling the evolution of cell differentiation and multicellularity. Finally, several recent small molecules of interest as potential drugs have been shown to act by blocking protein-protein interactions based on intrinsic disorder of one of the partners. Study of these examples has led to a new approach for drug discovery, and bioinformatics analysis of the human proteome suggests that various disease-associated proteins are very rich in such disorder-based drug discovery targets.

     

Prediction of Protein Binding Regions in Disordered Proteins

Many disordered proteins function via binding to a structured partner and undergo a disorder-to-order transition. The coupled folding and binding can confer several functional advantages such as the precise control of binding specificity without increased affinity. Additionally, the inherent flexibility allows the binding site to adopt various conformations and to bind to multiple partners. These features explain the prevalence of such binding elements in signaling and regulatory processes. In this work, we report ANCHOR, a method for the prediction of disordered binding regions. ANCHOR relies on the pairwise energy estimation approach that is the basis of IUPred, a previous general disorder prediction method. In order to predict disordered binding regions, we seek to identify segments that are in disordered regions, cannot form enough favorable intrachain interactions to fold on their own, and are likely to gain stabilizing energy by interacting with a globular protein partner. The performance of ANCHOR was found to be largely independent from the amino acid composition and adopted secondary structure. Longer binding sites generally were predicted to be segmented, in agreement with available experimentally characterized examples. Scanning several hundred proteomes showed that the occurrence of disordered binding sites increased with the complexity of the organisms even compared to disordered regions in general. Furthermore, the length distribution of binding sites was different from disordered protein regions in general and was dominated by shorter segments. These results underline the importance of disordered proteins and protein segments in establishing new binding regions. Due to their specific biophysical properties, disordered binding sites generally carry a robust sequence signal, and this signal is efficiently captured by our method. Through its generality, ANCHOR opens new ways to study the essential functional sites of disordered proteins.