Evaluation of disorder predictions in CASP9

PredIDR2: Improving accuracy of protein intrinsic disorder prediction by updating deep convolutional neural network and supplementing DisProt data

Intrinsically disordered proteins (IDPs) or regions (IDRs) are widespread in proteomes, and involved in several important biological processes and implicated in many diseases. Many computational methods for IDR prediction are being developed to decrease the gap between the low speed of experimental determination of annotated proteins and the rapid increase of non-annotated proteins, and their performances are blindly tested by the community-driven experiment, the Critical Assessment of protein Intrinsic Disorder (CAID). In this paper, we developed PredIDR2 series, an updated version of PredIDR tested in CAID2 in order to accurately predict intrinsically disordered regions from protein sequence. It includes four methods depending on the input features and the producing mode of the negative samples of the training set. PredIDR2 series (AUC_ROC = 0.952) perform remarkably better than our previous PredIDR (AUC_ROC = 0.933) for Disorder-PDB dataset of CAID2, which seems to be mainly attributed to the introduction of a new deep convolutional neural network and the augmentation of the training data, especially from DisProt database. PredIDR2 series outperform the state-of-the-art IDR prediction methods participated in CAID2 in terms of AUC_ROC, AUC_PR and DC_mae and belong to the seven top-performing methods in terms of MCC. PredIDR2 series can be freely used through the CAID Prediction Portal available at https://caid.idpcentral.org/portal or downloaded as a Singularity container from https://biocomputingup.it/shared/caid-predictors/.

Accurate and Fast Prediction of Intrinsic Disorder Using flDPnn

Intrinsically disordered proteins (IDPs) that include one or more intrinsically disordered regions (IDRs) are abundant across all domains of life and viruses and play numerous functional roles in various cellular processes. Due to a relatively low throughput and high cost of experimental techniques for identifying IDRs, there is a growing need for fast and accurate computational algorithms that accurately predict IDRs/IDPs from protein sequences. We describe one of the leading disorder predictors, flDPnn. Results from a recent community-organized Critical Assessment of Intrinsic Disorder (CAID) experiment show that flDPnn provides fast and state-of-the-art predictions of disorder, which are supplemented with the predictions of several major disorder functions. This chapter provides a practical guide to flDPnn, which includes a brief explanation of its predictive model, descriptions of its web server and standalone versions, and a case study that showcases how to read and understand flDPnn's predictions.

Protein embeddings predict binding residues in disordered regions

The identification of protein binding residues helps to understand their biological processes as protein function is often defined through ligand binding, such as to other proteins, small molecules, ions, or nucleotides. Methods predicting binding residues often err for intrinsically disordered proteins or regions (IDPs/IDPRs), often also referred to as molecular recognition features (MoRFs). Here, we presented a novel machine learning (ML) model trained to specifically predict binding regions in IDPRs. The proposed model, IDBindT5, leveraged embeddings from the protein language model (pLM) ProtT5 to reach a balanced accuracy of 57.2 ± 3.6% (95% confidence interval). Assessed on the same data set, this did not differ at the 95% CI from the state-of-the-art (SOTA) methods ANCHOR2 and DeepDISOBind that rely on expert-crafted features and evolutionary information from multiple sequence alignments (MSAs). Assessed on other data, methods such as SPOT-MoRF reached higher MCCs. IDBindT5's SOTA predictions are much faster than other methods, easily enabling full-proteome analyses. Our findings emphasize the potential of pLMs as a promising approach for exploring and predicting features of disordered proteins. The model and a comprehensive manual are publicly available at https://github.com/jahnl/binding_in_disorder .

Critical assessment of protein intrinsic disorder prediction (CAID) - Results of round 2

Protein intrinsic disorder (ID) is a complex and context-dependent phenomenon that covers a continuum between fully disordered states and folded states with long dynamic regions. The lack of a ground truth that fits all ID flavors and the potential for order-to-disorder transitions depending on specific conditions makes ID prediction challenging. The CAID2 challenge aimed to evaluate the performance of different prediction methods across different benchmarks, leveraging the annotation provided by the DisProt database, which stores the coordinates of ID regions when there is experimental evidence in the literature. The CAID2 challenge demonstrated varying performance of different prediction methods across different benchmarks, highlighting the need for continued development of more versatile and efficient prediction software. Depending on the application, researchers may need to balance performance with execution time when selecting a predictor. Methods based on AlphaFold2 seem to be good ID predictors but they are better at detecting absence of order rather than ID regions as defined in DisProt. The CAID2 predictors can be freely used through the CAID Prediction Portal, and CAID has been integrated into OpenEBench, which will become the official platform for running future CAID challenges.

Tutorial: a guide for the selection of fast and accurate computational tools for the prediction of intrinsic disorder in proteins

Intrinsic disorder is instrumental for a wide range of protein functions, and its analysis, using computational predictions from primary structures, complements secondary and tertiary structure-based approaches. In this Tutorial, we provide an overview and comparison of 23 publicly available computational tools with complementary parameters useful for intrinsic disorder prediction, partly relying on results from the Critical Assessment of protein Intrinsic Disorder prediction experiment. We consider factors such as accuracy, runtime, availability and the need for functional insights. The selected tools are available as web servers and downloadable programs, offer state-of-the-art predictions and can be used in a high-throughput manner. We provide examples and instructions for the selected tools to illustrate practical aspects related to the submission, collection and interpretation of predictions, as well as the timing and their limitations. We highlight two predictors for intrinsically disordered proteins, flDPnn as accurate and fast and IUPred as very fast and moderately accurate, while suggesting ANCHOR2 and MoRFchibi as two of the best-performing predictors for intrinsically disordered region binding. We link these tools to additional resources, including databases of predictions and web servers that integrate multiple predictive methods. Altogether, this Tutorial provides a hands-on guide to comparatively evaluating multiple predictors, submitting and collecting their own predictions, and reading and interpreting results. It is suitable for experimentalists and computational biologists interested in accurately and conveniently identifying intrinsic disorder, facilitating the functional characterization of the rapidly growing collections of protein sequences.

Computational prediction of disordered binding regions

One of the key features of intrinsically disordered regions (IDRs) is their ability to interact with a broad range of partner molecules. Multiple types of interacting IDRs were identified including molecular recognition fragments (MoRFs), short linear sequence motifs (SLiMs), and protein-, nucleic acids- and lipid-binding regions. Prediction of binding IDRs in protein sequences is gaining momentum in recent years. We survey 38 predictors of binding IDRs that target interactions with a diverse set of partners, such as peptides, proteins, RNA, DNA and lipids. We offer a historical perspective and highlight key events that fueled efforts to develop these methods. These tools rely on a diverse range of predictive architectures that include scoring functions, regular expressions, traditional and deep machine learning and meta-models. Recent efforts focus on the development of deep neural network-based architectures and extending coverage to RNA, DNA and lipid-binding IDRs. We analyze availability of these methods and show that providing implementations and webservers results in much higher rates of citations/use. We also make several recommendations to take advantage of modern deep network architectures, develop tools that bundle predictions of multiple and different types of binding IDRs, and work on algorithms that model structures of the resulting complexes.

Compositional Bias of Intrinsically Disordered Proteins and Regions and Their Predictions

Intrinsically disordered regions (IDRs) carry out many cellular functions and vary in length and placement in protein sequences. This diversity leads to variations in the underlying compositional biases, which were demonstrated for the short vs. long IDRs. We analyze compositional biases across four classes of disorder: fully disordered proteins; short IDRs; long IDRs; and binding IDRs. We identify three distinct biases: for the fully disordered proteins, the short IDRs and the long and binding IDRs combined. We also investigate compositional bias for putative disorder produced by leading disorder predictors and find that it is similar to the bias of the native disorder. Interestingly, the accuracy of disorder predictions across different methods is correlated with the correctness of the compositional bias of their predictions highlighting the importance of the compositional bias. The predictive quality is relatively low for the disorder classes with compositional bias that is the most different from the “generic” disorder bias, while being much higher for the classes with the most similar bias. We discover that different predictors perform best across different classes of disorder. This suggests that no single predictor is universally best and motivates the development of new architectures that combine models that target specific disorder classes.

Deep learning in prediction of intrinsic disorder in proteins

Intrinsic disorder prediction is an active area that has developed over 100 predictors. We identify and investigate a recent trend towards the development of deep neural network (DNN)-based methods. The first DNN-based method was released in 2013 and since 2019 deep learners account for majority of the new disorder predictors. We find that the 13 currently available DNN-based predictors are diverse in their topologies, sizes of their networks and the inputs that they utilize. We empirically show that the deep learners are statistically more accurate than other types of disorder predictors using the blind test dataset from the recent community assessment of intrinsic disorder predictions (CAID). We also identify several well-rounded DNN-based predictors that are accurate, fast and/or conveniently available. The popularity, favorable predictive performance and architectural flexibility suggest that deep networks are likely to fuel the development of future disordered predictors. Novel hybrid designs of deep networks could be used to adequately accommodate for diversity of types and flavors of intrinsic disorder. We also discuss scarcity of the DNN-based methods for the prediction of disordered binding regions and the need to develop more accurate methods for this prediction.

Identifying Intrinsically Disordered Protein Regions through a Deep Neural Network with Three Novel Sequence Features

The fast, reliable, and accurate identification of IDPRs is essential, as in recent years it has come to be recognized more and more that IDPRs have a wide impact on many important physiological processes, such as molecular recognition and molecular assembly, the regulation of transcription and translation, protein phosphorylation, cellular signal transduction, etc. For the sake of cost-effectiveness, it is imperative to develop computational approaches for identifying IDPRs. In this study, a deep neural structure where a variant VGG19 is situated between two MLP networks is developed for identifying IDPRs. Furthermore, for the first time, three novel sequence features—i.e., persistent entropy and the probabilities associated with two and three consecutive amino acids of the protein sequence—are introduced for identifying IDPRs. The simulation results show that our neural structure either performs considerably better than other known methods or, when relying on a much smaller training set, attains a similar performance. Our deep neural structure, which exploits the VGG19 structure, is effective for identifying IDPRs. Furthermore, three novel sequence features—i.e., the persistent entropy and the probabilities associated with two and three consecutive amino acids of the protein sequence—could be used as valuable sequence features in the further development of identifying IDPRs.

Surveying over 100 predictors of intrinsic disorder in proteins

INTRODUCTION

Intrinsic disorder prediction field develops, assesses, and deploys computational predictors of disorder in protein sequences and constructs and disseminates databases of these predictions. Over 40 years of research resulted in the release of numerous resources.

AREAS COVERED

We identify and briefly summarize the most comprehensive to date collection of over 100 disorder predictors. We focus on their predictive models, availability and predictive performance. We categorize and study them from a historical point of view to highlight informative trends.

EXPERT OPINION

We find a consistent trend of improvements in predictive quality as newer and more advanced predictors are developed. The original focus on machine learning methods has shifted to meta-predictors in early 2010s, followed by a recent transition to deep learning. The use of deep learners will continue in foreseeable future given recent and convincing success of these methods. Moreover, a broad range of resources that facilitate convenient collection of accurate disorder predictions is available to users. They include web servers and standalone programs for disorder prediction, servers that combine prediction of disorder and disorder functions, and large databases of pre-computed predictions. We also point to the need to address the shortage of accurate methods that predict disordered binding regions.

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.

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.

APOD: accurate sequence-based predictor of disordered flexible linkers

Motivation

Disordered flexible linkers (DFLs) are abundant and functionally important intrinsically disordered regions that connect protein domains and structural elements within domains and which facilitate disorder-based allosteric regulation. Although computational estimates suggest that thousands of proteins have DFLs, they were annotated experimentally in <200 proteins. This substantial annotation gap can be reduced with the help of accurate computational predictors. The sole predictor of DFLs, DFLpred, trade-off accuracy for shorter runtime by excluding relevant but computationally costly predictive inputs. Moreover, it relies on the local/window-based information while lacking to consider useful protein-level characteristics.

Results

We conceptualize, design and test APOD (Accurate Predictor Of DFLs), the first highly accurate predictor that utilizes both local- and protein-level inputs that quantify propensity for disorder, sequence composition, sequence conservation and selected putative structural properties. Consequently, APOD offers significantly more accurate predictions when compared with its faster predecessor, DFLpred, and several other alternative ways to predict DFLs. These improvements stem from the use of a more comprehensive set of inputs that cover the protein-level information and the application of a more sophisticated predictive model, a well-parametrized support vector machine. APOD achieves area under the curve = 0.82 (28% improvement over DFLpred) and Matthews correlation coefficient = 0.42 (180% increase over DFLpred) when tested on an independent/low-similarity test dataset. Consequently, APOD is a suitable choice for accurate and small-scale prediction of DFLs.

Availability and implementation

https://yanglab.nankai.edu.cn/APOD/.

IDP-Seq2Seq: identification of intrinsically disordered regions based on sequence to sequence learning

MOTIVATION

Related to many important biological functions, intrinsically disordered regions (IDRs) are widely distributed in proteins. Accurate prediction of IDRs is critical for the protein structure and function analysis. However, the existing computational methods construct the predictive models solely in the sequence space, failing to convert the sequence space into the 'semantic space' to reflect the structure characteristics of proteins. Furthermore, although the length-dependent predictors showed promising results, new fusion strategies should be explored to improve their predictive performance and the generalization.

RESULTS

In this study, we applied the Sequence to Sequence Learning (Seq2Seq) derived from natural language processing (NLP) to map protein sequences to 'semantic space' to reflect the structure patterns with the help of predicted residue-residue contacts (CCMs) and other sequence-based features. Furthermore, the Attention mechanism was used to capture the global associations between all residue pairs in the proteins. Three length-dependent predictors were constructed: IDP-Seq2Seq-L for long disordered region prediction, IDP-Seq2Seq-S for short disordered region prediction and IDP-Seq2Seq-G for both long and short disordered region predictions. Finally, these three predictors were fused into one predictor called IDP-Seq2Seq to improve the discriminative power and generalization. Experimental results on four independent test datasets and the CASP test dataset showed that IDP-Seq2Seq is insensitive with the ratios of long and short disordered regions and outperforms other competing methods.

AVAILABILITY AND IMPLEMENTATION

For the convenience of most experimental scientists, a user-friendly and publicly accessible web-server for the powerful new predictor has been established at http://bliulab.net/IDP-Seq2Seq/. It is anticipated that IDP-Seq2Seq will become a very useful tool for identification of IDRs.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Prediction of secondary structure population and intrinsic disorder of proteins using multitask deep learning

Recent research in predicting protein secondary structure populations (SSP) based on Nuclear Magnetic Resonance (NMR) chemical shifts has helped quantitatively characterise the structural conformational properties of intrinsically disordered proteins and regions (IDP/IDR). Different from protein secondary structure (SS) prediction, the SSP prediction assumes a dynamic assignment of secondary structures that seem correlate with disordered states. In this study, we designed a single-task deep learning framework to predict IDP/IDR and SSP respectively; and multitask deep learning frameworks to allow quantitative predictions of IDP/IDR evidenced by the simultaneously predicted SSP. According to independent test results, single-task deep learning models improve the prediction performance of shallow models for SSP and IDP/IDR. Also, the prediction performance was further improved for IDP/IDR prediction when SSP prediction was simultaneously predicted in multitask models. With p53 as a use case, we demonstrate how predicted SSP is used to explain the IDP/IDR predictions for each functional region.

APOD: accurate sequence-based predictor of disordered flexible linkers

MOTIVATION

Disordered flexible linkers (DFLs) are abundant and functionally important intrinsically disordered regions that connect protein domains and structural elements within domains and which facilitate disorder-based allosteric regulation. Although computational estimates suggest that thousands of proteins have DFLs, they were annotated experimentally in <200 proteins. This substantial annotation gap can be reduced with the help of accurate computational predictors. The sole predictor of DFLs, DFLpred, trade-off accuracy for shorter runtime by excluding relevant but computationally costly predictive inputs. Moreover, it relies on the local/window-based information while lacking to consider useful protein-level characteristics.

RESULTS

We conceptualize, design and test APOD (Accurate Predictor Of DFLs), the first highly accurate predictor that utilizes both local- and protein-level inputs that quantify propensity for disorder, sequence composition, sequence conservation and selected putative structural properties. Consequently, APOD offers significantly more accurate predictions when compared with its faster predecessor, DFLpred, and several other alternative ways to predict DFLs. These improvements stem from the use of a more comprehensive set of inputs that cover the protein-level information and the application of a more sophisticated predictive model, a well-parametrized support vector machine. APOD achieves area under the curve = 0.82 (28% improvement over DFLpred) and Matthews correlation coefficient = 0.42 (180% increase over DFLpred) when tested on an independent/low-similarity test dataset. Consequently, APOD is a suitable choice for accurate and small-scale prediction of DFLs.

AVAILABILITY AND IMPLEMENTATION

https://yanglab.nankai.edu.cn/APOD/.

Comparative Assessment of Intrinsic Disorder Predictions with a Focus on Protein and Nucleic Acid-Binding Proteins

With over 60 disorder predictors, users need help navigating the predictor selection task. We review 28 surveys of disorder predictors, showing that only 11 include assessment of predictive performance. We identify and address a few drawbacks of these past surveys. To this end, we release a novel benchmark dataset with reduced similarity to the training sets of the considered predictors. We use this dataset to perform a first-of-its-kind comparative analysis that targets two large functional families of disordered proteins that interact with proteins and with nucleic acids. We show that limiting sequence similarity between the benchmark and the training datasets has a substantial impact on predictive performance. We also demonstrate that predictive quality is sensitive to the use of the well-annotated order and inclusion of the fully structured proteins in the benchmark datasets, both of which should be considered in future assessments. We identify three predictors that provide favorable results using the new benchmark set. While we find that VSL2B offers the most accurate and robust results overall, ESpritz-DisProt and SPOT-Disorder perform particularly well for disordered proteins. Moreover, we find that predictions for the disordered protein-binding proteins suffer low predictive quality compared to generic disordered proteins and the disordered nucleic acids-binding proteins. This can be explained by the high disorder content of the disordered protein-binding proteins, which makes it difficult for the current methods to accurately identify ordered regions in these proteins. This finding motivates the development of a new generation of methods that would target these difficult-to-predict disordered proteins. We also discuss resources that support users in collecting and identifying high-quality disorder predictions.

Homology modeling in the time of collective and artificial intelligence

Homology modeling is a method for building protein 3D structures using protein primary sequence and utilizing prior knowledge gained from structural similarities with other proteins. The homology modeling process is done in sequential steps where sequence/structure alignment is optimized, then a backbone is built and later, side-chains are added. Once the low-homology loops are modeled, the whole 3D structure is optimized and validated. In the past three decades, a few collective and collaborative initiatives allowed for continuous progress in both homology and ab initio modeling. Critical Assessment of protein Structure Prediction (CASP) is a worldwide community experiment that has historically recorded the progress in this field. Folding@Home and Rosetta@Home are examples of crowd-sourcing initiatives where the community is sharing computational resources, whereas RosettaCommons is an example of an initiative where a community is sharing a codebase for the development of computational algorithms. Foldit is another initiative where participants compete with each other in a protein folding video game to predict 3D structure. In the past few years, contact maps deep machine learning was introduced to the 3D structure prediction process, adding more information and increasing the accuracy of models significantly. In this review, we will take the reader in a journey of exploration from the beginnings to the most recent turnabouts, which have revolutionized the field of homology modeling. Moreover, we discuss the new trends emerging in this rapidly growing field.

ODiNPred: comprehensive prediction of protein order and disorder

Structural disorder is widespread in eukaryotic proteins and is vital for their function in diverse biological processes. It is therefore highly desirable to be able to predict the degree of order and disorder from amino acid sequence. It is, however, notoriously difficult to predict the degree of local flexibility within structured domains and the presence and nuances of localized rigidity within intrinsically disordered regions. To identify such instances, we used the CheZOD database, which encompasses accurate, balanced, and continuous-valued quantification of protein (dis)order at amino acid resolution based on NMR chemical shifts. To computationally forecast the spectrum of protein disorder in the most comprehensive manner possible, we constructed the sequence-based protein order/disorder predictor ODiNPred, trained on an expanded version of CheZOD. ODiNPred applies a deep neural network comprising 157 unique sequence features to 1325 protein sequences together with the experimental NMR chemical shift data. Cross-validation for 117 protein sequences shows that ODiNPred better predicts the continuous variation in order along the protein sequence, suggesting that contemporary predictors are limited by the quality of training data. The inclusion of evolutionary features reduces the performance gap between ODiNPred and its peers, but analysis shows that it retains greater accuracy for the more challenging prediction of intermediate disorder.

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.

DISOselect: Disorder predictor selection at the protein level

The intense interest in the intrinsically disordered proteins in the life science community, together with the remarkable advancements in predictive technologies, have given rise to the development of a large number of computational predictors of intrinsic disorder from protein sequence. While the growing number of predictors is a positive trend, we have observed a considerable difference in predictive quality among predictors for individual proteins. Furthermore, variable predictor performance is often inconsistent between predictors for different proteins, and the predictor that shows the best predictive performance depends on the unique properties of each protein sequence. We propose a computational approach, DISOselect, to estimate the predictive performance of 12 selected predictors for individual proteins based on their unique sequence-derived properties. This estimation informs the users about the expected predictive quality for a selected disorder predictor and can be used to recommend methods that are likely to provide the best quality predictions. Our solution does not depend on the results of any disorder predictor; the estimations are made based solely on the protein sequence. Our solution significantly improves predictive performance, as judged with a test set of 1,000 proteins, when compared to other alternatives. We have empirically shown that by using the recommended methods the overall predictive performance for a given set of proteins can be improved by a statistically significant margin. DISOselect is freely available for non-commercial users through the webserver at http://biomine.cs.vcu.edu/servers/DISOselect/.

DEPICTER: Intrinsic Disorder and Disorder Function Prediction Server

Computational predictions of the intrinsic disorder and its functions are instrumental to facilitate annotation for the millions of unannotated proteins. However, access to these predictors is fragmented and requires substantial effort to find them and to collect and combine their results. The DEPICTER (DisorderEd PredictIon CenTER) server provides first-of-its-kind centralized access to 10 popular disorder and disorder function predictions that cover protein and nucleic acids binding, linkers, and moonlighting regions. It automates the prediction process, runs user-selected methods on the server side, visualizes the results, and outputs all predictions in a consistent and easy-to-parse format. DEPICTER also includes two accurate consensus predictors of disorder and disordered protein binding. Empirical tests on an independent (low similarity) benchmark dataset reveal that the computational tools included in DEPICTER generate accurate predictions that are significantly better than the results secured using sequence alignment. The DEPICTER server is freely available at http://biomine.cs.vcu.edu/servers/DEPICTER/.

Accuracy of protein-level disorder predictions

Experimental annotations of intrinsic disorder are available for 0.1% of 147 000 000 of currently sequenced proteins. Over 60 sequence-based disorder predictors were developed to help bridge this gap. Current benchmarks of these methods assess predictive performance on datasets of proteins; however, predictions are often interpreted for individual proteins. We demonstrate that the protein-level predictive performance varies substantially from the dataset-level benchmarks. Thus, we perform first-of-its-kind protein-level assessment for 13 popular disorder predictors using 6200 disorder-annotated proteins. We show that the protein-level distributions are substantially skewed toward high predictive quality while having long tails of poor predictions. Consequently, between 57% and 75% proteins secure higher predictive performance than the currently used dataset-level assessment suggests, but as many as 30% of proteins that are located in the long tails suffer low predictive performance. These proteins typically have relatively high amounts of disorder, in contrast to the mostly structured proteins that are predicted accurately by all 13 methods. Interestingly, each predictor provides the most accurate results for some number of proteins, while the best-performing at the dataset-level method is in fact the best for only about 30% of proteins. Moreover, the majority of proteins are predicted more accurately than the dataset-level performance of the most accurate tool by at least four disorder predictors. While these results suggests that disorder predictors outperform their current benchmark performance for the majority of proteins and that they complement each other, novel tools that accurately identify the hard-to-predict proteins and that make accurate predictions for these proteins are needed.

A comprehensive review and comparison of existing computational methods for intrinsically disordered protein and region prediction

Intrinsically disordered proteins and regions are widely distributed in proteins, which are associated with many biological processes and diseases. Accurate prediction of intrinsically disordered proteins and regions is critical for both basic research (such as protein structure and function prediction) and practical applications (such as drug development). During the past decades, many computational approaches have been proposed, which have greatly facilitated the development of this important field. Therefore, a comprehensive and updated review is highly required. In this regard, we give a review on the computational methods for intrinsically disordered protein and region prediction, especially focusing on the recent development in this field. These computational approaches are divided into four categories based on their methodologies, including physicochemical-based method, machine-learning-based method, template-based method and meta method. Furthermore, their advantages and disadvantages are also discussed. The performance of 40 state-of-the-art predictors is directly compared on the target proteins in the task of disordered region prediction in the 10th Critical Assessment of protein Structure Prediction. A more comprehensive performance comparison of 45 different predictors is conducted based on seven widely used benchmark data sets. Finally, some open problems and perspectives are discussed.

Quality and bias of protein disorder predictors

Disorder in proteins is vital for biological function, yet it is challenging to characterize. Therefore, methods for predicting protein disorder from sequence are fundamental. Currently, predictors are trained and evaluated using data from X-ray structures or from various biochemical or spectroscopic data. However, the prediction accuracy of disordered predictors is not calibrated, nor is it established whether predictors are intrinsically biased towards one of the extremes of the order-disorder axis. We therefore generated and validated a comprehensive experimental benchmarking set of site-specific and continuous disorder, using deposited NMR chemical shift data. This novel experimental data collection is fully appropriate and represents the full spectrum of disorder. We subsequently analyzed the performance of 26 widely-used disorder prediction methods and found that these vary noticeably. At the same time, a distinct bias for over-predicting order was identified for some algorithms. Our analysis has important implications for the validity and the interpretation of protein disorder, as utilized, for example, in assessing the content of disorder in proteomes.

Thermodynamically driven assemblies and liquid-liquid phase separations in biology

The sustenance of life depends on the high degree of organization that prevails through different levels of living organisms, from subcellular structures such as biomolecular complexes and organelles to tissues and organs. The physical origin of such organization is not fully understood, and even though it is clear that cells and organisms cannot maintain their integrity without consuming energy, there is growing evidence that individual assembly processes can be thermodynamically driven and occur spontaneously due to changes in thermodynamic variables such as intermolecular interactions and concentration. Understanding the phase separation in vivo requires a multidisciplinary approach, integrating the theory and physics of phase separation with experimental and computational techniques. This paper aims at providing a brief overview of the physics of phase separation and its biological implications, with a particular focus on the assembly of membraneless organelles. We discuss the underlying physical principles of phase separation from its thermodynamics to its kinetics. We also overview the wide range of methods utilized for experimental verification and characterization of phase separation of membraneless organelles, as well as the utility of molecular simulations rooted in thermodynamics and statistical physics in understanding the governing principles of thermodynamically driven biological self-assembly processes.

Taxonomic Landscape of the Dark Proteomes: Whole-Proteome Scale Interplay Between Structural Darkness, Intrinsic Disorder, and Crystallization Propensity

Growth rate of the protein sequence universe dramatically exceeds the speed of expansion for the protein structure universe, generating an immense dark proteome that includes proteins with unknown structure. A whole-proteome scale analysis of 5.4 million proteins from 987 proteomes in the three domains of life and viruses to systematically dissect an interplay between structural coverage, degree of putative intrinsic disorder, and predicted propensity for structure determination is performed. It has been found that Archaean and Bacterial proteomes have relatively high structural coverage and low amounts of disorder, whereas Eukaryotic and Viral proteomes are characterized by a broad spread of structural coverage and higher disorder levels. The analysis reveals that dark proteomes (i.e., proteomes containing high fractions of proteins with unknown structure) have significantly elevated amounts of intrinsic disorder and are predicted to be difficult to solve structurally. Although the majority of dark proteomes are of viral origin, many dark viral proteomes have at least modest crystallization propensity and only a handful of them are enriched in the intrinsic disorder. The disorder, structural coverage, and propensity are mapped for structural determination onto a novel proteome-level sequence similarity network to analyze the interplay of these characteristics in the taxonomic landscape.

Structural disorder and induced folding within two cereal, ABA stress and ripening (ASR) proteins

Abscisic acid (ABA), stress and ripening (ASR) proteins are plant-specific proteins involved in plant response to multiple abiotic stresses. We previously isolated the ASR genes and cDNAs from durum wheat (TtASR1) and barley (HvASR1). Here, we show that HvASR1 and TtASR1 are consistently predicted to be disordered and further confirm this experimentally. Addition of glycerol, which mimics dehydration, triggers a gain of structure in both proteins. Limited proteolysis showed that they are highly sensitive to protease degradation. Addition of 2,2,2-trifluoroethanol (TFE) however, results in a decreased susceptibility to proteolysis that is paralleled by a gain of structure. Mass spectrometry analyses (MS) led to the identification of a protein fragment resistant to proteolysis. Addition of zinc also induces a gain of structure and Hydrogen/Deuterium eXchange-Mass Spectrometry (HDX-MS) allowed identification of the region involved in the disorder-to-order transition. This study is the first reported experimental characterization of HvASR1 and TtASR1 proteins, and paves the way for future studies aimed at unveiling the functional impact of the structural transitions that these proteins undergo in the presence of zinc and at achieving atomic-resolution conformational ensemble description of these two plant intrinsically disordered proteins (IDPs).

Comprehensive review of methods for prediction of intrinsic disorder and its molecular functions

Computational prediction of intrinsic disorder in protein sequences dates back to late 1970 and has flourished in the last two decades. We provide a brief historical overview, and we review over 30 recent predictors of disorder. We are the first to also cover predictors of molecular functions of disorder, including 13 methods that focus on disordered linkers and disordered protein-protein, protein-RNA, and protein-DNA binding regions. We overview their predictive models, usability, and predictive performance. We highlight newest methods and predictors that offer strong predictive performance measured based on recent comparative assessments. We conclude that the modern predictors are relatively accurate, enjoy widespread use, and many of them are fast. Their predictions are conveniently accessible to the end users, via web servers and databases that store pre-computed predictions for millions of proteins. However, research into methods that predict many not yet addressed functions of intrinsic disorder remains an outstanding challenge.

AUCpreD: proteome-level protein disorder prediction by AUC-maximized deep convolutional neural fields

MOTIVATION

Protein intrinsically disordered regions (IDRs) play an important role in many biological processes. Two key properties of IDRs are (i) the occurrence is proteome-wide and (ii) the ratio of disordered residues is about 6%, which makes it challenging to accurately predict IDRs. Most IDR prediction methods use sequence profile to improve accuracy, which prevents its application to proteome-wide prediction since it is time-consuming to generate sequence profiles. On the other hand, the methods without using sequence profile fare much worse than using sequence profile.

METHOD

This article formulates IDR prediction as a sequence labeling problem and employs a new machine learning method called Deep Convolutional Neural Fields (DeepCNF) to solve it. DeepCNF is an integration of deep convolutional neural networks (DCNN) and conditional random fields (CRF); it can model not only complex sequence-structure relationship in a hierarchical manner, but also correlation among adjacent residues. To deal with highly imbalanced order/disorder ratio, instead of training DeepCNF by widely used maximum-likelihood, we develop a novel approach to train it by maximizing area under the ROC curve (AUC), which is an unbiased measure for class-imbalanced data.

RESULTS

Our experimental results show that our IDR prediction method AUCpreD outperforms existing popular disorder predictors. More importantly, AUCpreD works very well even without sequence profile, comparing favorably to or even outperforming many methods using sequence profile. Therefore, our method works for proteome-wide disorder prediction while yielding similar or better accuracy than the others.

AVAILABILITY AND IMPLEMENTATION

http://raptorx2.uchicago.edu/StructurePropertyPred/predict/

CONTACT

wangsheng@uchicago.edu, jinboxu@gmail.com

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Improving protein disorder prediction by deep bidirectional long short-term memory recurrent neural networks

Motivation

Capturing long-range interactions between structural but not sequence neighbors of proteins is a long-standing challenging problem in bioinformatics. Recently, long short-term memory (LSTM) networks have significantly improved the accuracy of speech and image classification problems by remembering useful past information in long sequential events. Here, we have implemented deep bidirectional LSTM recurrent neural networks in the problem of protein intrinsic disorder prediction.

Results

The new method, named SPOT-Disorder, has steadily improved over a similar method using a traditional, window-based neural network (SPINE-D) in all datasets tested without separate training on short and long disordered regions. Independent tests on four other datasets including the datasets from critical assessment of structure prediction (CASP) techniques and >10 000 annotated proteins from MobiDB, confirmed SPOT-Disorder as one of the best methods in disorder prediction. Moreover, initial studies indicate that the method is more accurate in predicting functional sites in disordered regions. These results highlight the usefulness combining LSTM with deep bidirectional recurrent neural networks in capturing non-local, long-range interactions for bioinformatics applications.

Availability and Implementation

SPOT-disorder is available as a web server and as a standalone program at: http://sparks-lab.org/server/SPOT-disorder/index.php .

Contact

j.hanson@griffith.edu.au or yuedong.yang@griffith.edu.au or yaoqi.zhou@griffith.edu.au.

Supplementary information

Supplementary data is available at Bioinformatics online.

Intrinsic Disorder and Semi-disorder Prediction by SPINE-D

Over the past decade, it has become evident that a large proportion of proteins contain intrinsically disordered regions, which play important roles in pivotal cellular functions. Many computational tools have been developed with the aim of identifying the level and location of disorder within a protein. In this chapter, we describe a neural network based technique called SPINE-D that employs a unique three-state design and can accurately capture disordered residues in both short and long disordered regions. SPINE-D was trained on a large database of 4229 non-redundant proteins, and yielded an AUC of 0.86 on a cross-validation test and 0.89 on an independent test. SPINE-D can also detect a semi-disordered state that is associated with induced folders and aggregation-prone regions in disordered proteins and weakly stable or locally unfolded regions in structured proteins. We implement an online web service and an offline stand-alone program for SPINE-D, they are freely available at http://sparks-lab.org/SPINE-D/ . We then walk you through how to use the online and offline SPINE-D in making disorder predictions, and examine the disorder and semi-disorder prediction in a case study on the p53 protein.

How disordered is my protein and what is its disorder for? A guide through the "dark side" of the protein universe

In the last 2 decades it has become increasingly evident that a large number of proteins are either fully or partially disordered. Intrinsically disordered proteins lack a stable 3D structure, are ubiquitous and fulfill essential biological functions. Their conformational heterogeneity is encoded in their amino acid sequences, thereby allowing intrinsically disordered proteins or regions to be recognized based on properties of these sequences. The identification of disordered regions facilitates the functional annotation of proteins and is instrumental for delineating boundaries of protein domains amenable to structural determination with X-ray crystallization. This article discusses a comprehensive selection of databases and methods currently employed to disseminate experimental and putative annotations of disorder, predict disorder and identify regions involved in induced folding. It also provides a set of detailed instructions that should be followed to perform computational analysis of disorder.

Genes encoding intrinsic disorder in Eukaryota have high GC content

We analyze a correlation between the GC content in genes of 12 eukaryotic species and the level of intrinsic disorder in their corresponding proteins. Comprehensive computational analysis has revealed that the disordered regions in eukaryotes are encoded by the GC-enriched gene regions and that this enrichment is correlated with the amount of disorder and is present across proteins and species characterized by varying amounts of disorder. The GC enrichment is a result of higher rate of amino acid coded by GC-rich codons in the disordered regions. Individual amino acids have the same GC-content profile between different species. Eukaryotic proteins with the disordered regions encoded by the GC-enriched gene segments carry out important biological functions including interactions with RNAs, DNAs, nucleotides, binding of calcium and metal ions, are involved in transcription, transport, cell division and certain signaling pathways, and are localized primarily in nucleus, cytosol and cytoplasm. We also investigate a possible relationship between GC content, intrinsic disorder and protein evolution. Analysis of a devised "age" of amino acids, their disorder-promoting capacity and the GC-enrichment of their codons suggests that the early amino acids are mostly disorder-promoting and their codons are GC-rich while most of late amino acids are mostly order-promoting.

Estimation of Position Specific Energy as a Feature of Protein Residues from Sequence Alone for Structural Classification

A set of features computed from the primary amino acid sequence of proteins, is crucial in the process of inducing a machine learning model that is capable of accurately predicting three-dimensional protein structures. Solutions for existing protein structure prediction problems are in need of features that can capture the complexity of molecular level interactions. With a view to this, we propose a novel approach to estimate position specific estimated energy (PSEE) of a residue using contact energy and predicted relative solvent accessibility (RSA). Furthermore, we demonstrate PSEE can be reasonably estimated based on sequence information alone. PSEE is useful in identifying the structured as well as unstructured or, intrinsically disordered region of a protein by computing favorable and unfavorable energy respectively, characterized by appropriate threshold. The most intriguing finding, verified empirically, is the indication that the PSEE feature can effectively classify disorder versus ordered residues and can segregate different secondary structure type residues by computing the constituent energies. PSEE values for each amino acid strongly correlate with the hydrophobicity value of the corresponding amino acid. Further, PSEE can be used to detect the existence of critical binding regions that essentially undergo disorder-to-order transitions to perform crucial biological functions. Towards an application of disorder prediction using the PSEE feature, we have rigorously tested and found that a support vector machine model informed by a set of features including PSEE consistently outperforms a model with an identical set of features with PSEE removed. In addition, the new disorder predictor, DisPredict2, shows competitive performance in predicting protein disorder when compared with six existing disordered protein predictors.

New encouraging developments in contact prediction: Assessment of the CASP11 results

This article provides a report on the state-of-the-art in the prediction of intra-molecular residue-residue contacts in proteins based on the assessment of the predictions submitted to the CASP11 experiment. The assessment emphasis is placed on the accuracy in predicting long-range contacts. Twenty-nine groups participated in contact prediction in CASP11. At least eight of them used the recently developed evolutionary coupling techniques, with the top group (CONSIP2) reaching precision of 27% on target proteins that could not be modeled by homology. This result indicates a breakthrough in the development of methods based on the correlated mutation approach. Successful prediction of contacts was shown to be practically helpful in modeling three-dimensional structures; in particular target T0806 was modeled exceedingly well with accuracy not yet seen for ab initio targets of this size (>250 residues). Proteins 2016; 84(Suppl 1):131-144. © 2015 Wiley Periodicals, Inc.

AUC-Maximized Deep Convolutional Neural Fields for Protein Sequence Labeling

Deep Convolutional Neural Networks (DCNN) has shown excellent performance in a variety of machine learning tasks. This paper presents Deep Convolutional Neural Fields (DeepCNF), an integration of DCNN with Conditional Random Field (CRF), for sequence labeling with an imbalanced label distribution. The widely-used training methods, such as maximum-likelihood and maximum labelwise accuracy, do not work well on imbalanced data. To handle this, we present a new training algorithm called maximum-AUC for DeepCNF. That is, we train DeepCNF by directly maximizing the empirical Area Under the ROC Curve (AUC), which is an unbiased measurement for imbalanced data. To fulfill this, we formulate AUC in a pairwise ranking framework, approximate it by a polynomial function and then apply a gradient-based procedure to optimize it. Our experimental results confirm that maximum-AUC greatly outperforms the other two training methods on 8-state secondary structure prediction and disorder prediction since their label distributions are highly imbalanced and also has similar performance as the other two training methods on solvent accessibility prediction, which has three equally-distributed labels. Furthermore, our experimental results show that our AUC-trained DeepCNF models greatly outperform existing popular predictors of these three tasks. The data and software related to this paper are available at https://github.com/realbigws/DeepCNF_AUC.

Natural protein sequences are more intrinsically disordered than random sequences

Most natural protein sequences have resulted from millions or even billions of years of evolution. How they differ from random sequences is not fully understood. Previous computational and experimental studies of random proteins generated from noncoding regions yielded inclusive results due to species-dependent codon biases and GC contents. Here, we approach this problem by investigating 10,000 sequences randomized at the amino acid level. Using well-established predictors for protein intrinsic disorder, we found that natural sequences have more long disordered regions than random sequences, even when random and natural sequences have the same overall composition of amino acid residues. We also showed that random sequences are as structured as natural sequences according to contents and length distributions of predicted secondary structure, although the structures from random sequences may be in a molten globular-like state, according to molecular dynamics simulations. The bias of natural sequences toward more intrinsic disorder suggests that natural sequences are created and evolved to avoid protein aggregation and increase functional diversity.

RaptorX-Property: a web server for protein structure property prediction

RaptorX Property (http://raptorx2.uchicago.edu/StructurePropertyPred/predict/) is a web server predicting structure property of a protein sequence without using any templates. It outperforms other servers, especially for proteins without close homologs in PDB or with very sparse sequence profile (i.e. carries little evolutionary information). This server employs a powerful in-house deep learning model DeepCNF (Deep Convolutional Neural Fields) to predict secondary structure (SS), solvent accessibility (ACC) and disorder regions (DISO). DeepCNF not only models complex sequence–structure relationship by a deep hierarchical architecture, but also interdependency between adjacent property labels. Our experimental results show that, tested on CASP10, CASP11 and the other benchmarks, this server can obtain ∼84% Q3 accuracy for 3-state SS, ∼72% Q8 accuracy for 8-state SS, ∼66% Q3 accuracy for 3-state solvent accessibility, and ∼0.89 area under the ROC curve (AUC) for disorder prediction.

There is Diversity in Disorder-"In all Chaos there is a Cosmos, in all Disorder a Secret Order"

The protein universe consists of a continuum of structures ranging from full order to complete disorder. As the structured part of the proteome has been intensively studied, stably folded proteins are increasingly well documented and understood. However, proteins that are fully, or in large part, disordered are much less well characterized. Here we collected NMR chemical shifts in a small database for 117 protein sequences that are known to contain disorder. We demonstrate that NMR chemical shift data can be brought to bear as an exquisite judge of protein disorder at the residue level, and help in validation. With the help of secondary chemical shift analysis we demonstrate that the proteins in the database span the full spectrum of disorder, but still, largely segregate into two classes; disordered with small segments of order scattered along the sequence, and structured with small segments of disorder inserted between the different structured regions. A detailed analysis reveals that the distribution of order/disorder along the sequence shows a complex and asymmetric distribution, that is highly protein-dependent. Access to ratified training data further suggests an avenue to improving prediction of disorder from sequence.

DisPredict: A Predictor of Disordered Protein Using Optimized RBF Kernel

Intrinsically disordered proteins or, regions perform important biological functions through their dynamic conformations during binding. Thus accurate identification of these disordered regions have significant implications in proper annotation of function, induced fold prediction and drug design to combat critical diseases. We introduce DisPredict, a disorder predictor that employs a single support vector machine with RBF kernel and novel features for reliable characterization of protein structure. DisPredict yields effective performance. In addition to 10-fold cross validation, training and testing of DisPredict was conducted with independent test datasets. The results were consistent with both the training and test error minimal. The use of multiple data sources, makes the predictor generic. The datasets used in developing the model include disordered regions of various length which are categorized as short and long having different compositions, different types of disorder, ranging from fully to partially disordered regions as well as completely ordered regions. Through comparison with other state of the art approaches and case studies, DisPredict is found to be a useful tool with competitive performance. DisPredict is available at https://github.com/tamjidul/DisPredict_v1.0.

High-throughput prediction of RNA, DNA and protein binding regions mediated by intrinsic disorder

Intrinsically disordered proteins and regions (IDPs and IDRs) lack stable 3D structure under physiological conditions in-vitro, are common in eukaryotes, and facilitate interactions with RNA, DNA and proteins. Current methods for prediction of IDPs and IDRs do not provide insights into their functions, except for a handful of methods that address predictions of protein-binding regions. We report first-of-its-kind computational method DisoRDPbind for high-throughput prediction of RNA, DNA and protein binding residues located in IDRs from protein sequences. DisoRDPbind is implemented using a runtime-efficient multi-layered design that utilizes information extracted from physiochemical properties of amino acids, sequence complexity, putative secondary structure and disorder and sequence alignment. Empirical tests demonstrate that it provides accurate predictions that are competitive with other predictors of disorder-mediated protein binding regions and complementary to the methods that predict RNA- and DNA-binding residues annotated based on crystal structures. Application in Homo sapiens, Mus musculus, Caenorhabditis elegans and Drosophila melanogaster proteomes reveals that RNA- and DNA-binding proteins predicted by DisoRDPbind complement and overlap with the corresponding known binding proteins collected from several sources. Also, the number of the putative protein-binding regions predicted with DisoRDPbind correlates with the promiscuity of proteins in the corresponding protein-protein interaction networks. Webserver: http://biomine.ece.ualberta.ca/DisoRDPbind/.

An Overview of Predictors for Intrinsically Disordered Proteins over 2010-2014

The sequence-structure-function paradigm of proteins has been changed by the occurrence of intrinsically disordered proteins (IDPs). Benefiting from the structural disorder, IDPs are of particular importance in biological processes like regulation and signaling. IDPs are associated with human diseases, including cancer, cardiovascular disease, neurodegenerative diseases, amyloidoses, and several other maladies. IDPs attract a high level of interest and a substantial effort has been made to develop experimental and computational methods. So far, more than 70 prediction tools have been developed since 1997, within which 17 predictors were created in the last five years. Here, we presented an overview of IDPs predictors developed during 2010-2014. We analyzed the algorithms used for IDPs prediction by these tools and we also discussed the basic concept of various prediction methods for IDPs. The comparison of prediction performance among these tools is discussed as well.

Disorder Prediction Methods, Their Applicability to Different Protein Targets and Their Usefulness for Guiding Experimental Studies

The role and function of a given protein is dependent on its structure. In recent years, however, numerous studies have highlighted the importance of unstructured, or disordered regions in governing a protein’s function. Disordered proteins have been found to play important roles in pivotal cellular functions, such as DNA binding and signalling cascades. Studying proteins with extended disordered regions is often problematic as they can be challenging to express, purify and crystallise. This means that interpretable experimental data on protein disorder is hard to generate. As a result, predictive computational tools have been developed with the aim of predicting the level and location of disorder within a protein. Currently, over 60 prediction servers exist, utilizing different methods for classifying disorder and different training sets. Here we review several good performing, publicly available prediction methods, comparing their application and discussing how disorder prediction servers can be used to aid the experimental solution of protein structure. The use of disorder prediction methods allows us to adopt a more targeted approach to experimental studies by accurately identifying the boundaries of ordered protein domains so that they may be investigated separately, thereby increasing the likelihood of their successful experimental solution.

Disordered regions in transmembrane proteins

The functions of transmembrane proteins in living cells are widespread; they range from various transport processes to energy production, from cell-cell adhesion to communication. Structurally, they are highly ordered in their membrane-spanning regions, but may contain disordered regions in the cytosolic and extra-cytosolic parts. In this study, we have investigated the disordered regions in transmembrane proteins by a stringent definition of disordered residues on the currently available largest experimental dataset, and show a significant correlation between the spatial distributions of positively charged residues and disordered regions. This finding suggests a new role of disordered regions in transmembrane proteins by providing structural flexibility for stabilizing interactions with negatively charged head groups of the lipid molecules. We also find a preference of structural disorder in the terminal--as opposed to loop--regions in transmembrane proteins, and survey the respective functions involved in recruiting other proteins or mediating allosteric signaling effects. Finally, we critically compare disorder prediction methods on our transmembrane protein set. While there are no major differences between these methods using the usual statistics, such as per residue accuracies, Matthew's correlation coefficients, etc.; substantial differences can be found regarding the spatial distribution of the predicted disordered regions. We conclude that a predictor optimized for transmembrane proteins would be of high value to the field of structural disorder.

DeepCNF-D: Predicting Protein Order/Disorder Regions by Weighted Deep Convolutional Neural Fields

Intrinsically disordered proteins or protein regions are involved in key biological processes including regulation of transcription, signal transduction, and alternative splicing. Accurately predicting order/disorder regions ab initio from the protein sequence is a prerequisite step for further analysis of functions and mechanisms for these disordered regions. This work presents a learning method, weighted DeepCNF (Deep Convolutional Neural Fields), to improve the accuracy of order/disorder prediction by exploiting the long-range sequential information and the interdependency between adjacent order/disorder labels and by assigning different weights for each label during training and prediction to solve the label imbalance issue. Evaluated by the CASP9 and CASP10 targets, our method obtains 0.855 and 0.898 AUC values, which are higher than the state-of-the-art single ab initio predictors.