Large-scale prediction of long disordered regions in proteins using random forests

Background  

Many proteins contain disordered regions that lack fixed three-dimensional (3D) structure under physiological conditions but have important biological functions. Prediction of disordered regions in protein sequences is important for understanding protein function and in high-throughput determination of protein structures. Machine learning techniques, including neural networks and support vector machines have been widely used in such predictions. Predictors designed for long disordered regions are usually less successful in predicting short disordered regions. Combining prediction of short and long disordered regions will dramatically increase the complexity of the prediction algorithm and make the predictor unsuitable for large-scale applications. Efficient batch prediction of long disordered regions alone is of greater interest in large-scale proteome studies.     

Genome‐scale prediction of proteins with long intrinsically disordered regions

Proteins with long disordered regions (LDRs), defined as having 30 or more consecutive disordered residues, are abundant in eukaryotes, and these regions are recognized as a distinct class of biologically functional domains. LDRs facilitate various cellular functions and are important for target selection in structural genomics. Motivated by the lack of methods that directly predict proteins with LDRs, we designed Super‐fast predictor of proteins with Long Intrinsically DisordERed regions (SLIDER). SLIDER utilizes logistic regression that takes an empirically chosen set of numerical features, which consider selected physicochemical properties of amino acids, sequence complexity, and amino acid composition, as its inputs. Empirical tests show that SLIDER offers competitive predictive performance combined with low computational cost. It outperforms, by at least a modest margin, a comprehensive set of modern disorder predictors (that can indirectly predict LDRs) and is 16 times faster compared to the best currently available disorder predictor. Utilizing our time‐efficient predictor, we characterized abundance and functional roles of proteins with LDRs over 110 eukaryotic proteomes. Similar to related studies, we found that eukaryotes have many (on average 30.3%) proteins with LDRs with majority of proteomes having between 25 and 40%, where higher abundance is characteristic to proteomes that have larger proteins. Our first‐of‐its‐kind large‐scale functional analysis shows that these proteins are enriched in a number of cellular functions and processes including certain binding events, regulation of catalytic activities, cellular component organization, biogenesis, biological regulation, and some metabolic and developmental processes. A webserver that implements SLIDER is available at http://biomine.ece.ualberta.ca/SLIDER/ .Proteins 2014; 82:145–158. © 2013 Wiley Periodicals, Inc.     

PreDisorder: ab initio sequence-based prediction of protein disordered regions

Background  

Disordered regions are segments of the protein chain which do not adopt stable structures. Such segments are often of interest because they have a close relationship with protein expression and functionality. As such, protein disorder prediction is important for protein structure prediction, structure determination and function annotation.     

A neural-network based method for prediction of gamma-turns in proteins from multiple sequence alignment

In the present study, an attempt has been made to develop a method for predicting gamma-turns in proteins. First, we have implemented the commonly used statistical and machine-learning techniques in the field of protein structure prediction, for the prediction of gamma-turns. All the methods have been trained and tested on a set of 320 nonhomologous protein chains by a fivefold cross-validation technique. It has been observed that the performance of all methods is very poor, having a Matthew's Correlation Coefficient (MCC) 相似文献   

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.     

FoldUnfold: web server for the prediction of disordered regions in protein chain

Identification of disordered regions in polypeptide chains is very important because such regions are essential for protein function. A new parameter, namely mean packing density of residues has been introduced to detect disordered regions in a protein sequence. We have demonstrated that regions with weak expected packing density would be responsible for the appearance of disordered regions. Our method (FoldUnfold) has been tested on datasets of globular proteins (559 proteins) and long disordered protein segments (129 proteins) and showed improved performance over some other widely used methods, such as DISOPRED, PONDR VL3H, IUPred and GlobPlot. AVAILABILITY: The FoldUnfold server is available for users at http://skuld.protres.ru/~mlobanov/ogu/ogu.cgi. There is a link to our server through the web site of DisProt (http://www.disprot.org/predictors.php).     

Interactome-wide prediction of short, disordered protein interaction motifs in humans

Many of the specific functions of intrinsically disordered protein segments are mediated by Short Linear Motifs (SLiMs) interacting with other proteins. Well known examples include SLiMs that interact with 14-3-3, PDZ, SH2, SH3, and WW domains but the true extent and diversity of SLiM-mediated interactions is largely unknown. Here, we attempt to expand our knowledge of human SLiMs by applying in silico SLiM prediction to the human interactome. Combining data from seven different interaction databases, we analysed approximately 6000 protein-centred and 1600 domain-centred human interaction datasets of 3+ unrelated proteins that interact with a common partner. Results were placed in context through comparison to randomised datasets of similar size and composition. The search returned thousands of evolutionarily conserved, intrinsically disordered occurrences of hundreds of significantly enriched recurring motifs, including many that have never been previously identified (). In addition to True Positive results for at least 25 different known SLiMs, a striking number of "off-target" proteins/domains also returned significantly enriched known motifs. Often, this was due to the non-independence of the datasets, with many proteins sharing interaction partners or contributing interactions to multiple domain datasets. The majority of these motif classes, however, were also found to be significantly enriched in one or more randomised datasets. This highlights the need for care when interpreting motif predictions of this nature but also raises the possibility that SLiM occurrences may be successfully identified independently of interaction data. Although not as compositionally biased as previous studies, patterns matching known SLiMs tended to cluster into a few large groups of similar sequence, while novel predictions tended to be more distinctive and less abundant. Whether this is due to ascertainment bias or a true functional composition bias of SLiMs is not clear and warrants further investigation.     

iPcc: a novel feature extraction method for accurate disease class discovery and prediction

Gene expression profiling has gradually become a routine procedure for disease diagnosis and classification. In the past decade, many computational methods have been proposed, resulting in great improvements on various levels, including feature selection and algorithms for classification and clustering. In this study, we present iPcc, a novel method from the feature extraction perspective to further propel gene expression profiling technologies from bench to bedside. We define ‘correlation feature space’ for samples based on the gene expression profiles by iterative employment of Pearson’s correlation coefficient. Numerical experiments on both simulated and real gene expression data sets demonstrate that iPcc can greatly highlight the latent patterns underlying noisy gene expression data and thus greatly improve the robustness and accuracy of the algorithms currently available for disease diagnosis and classification based on gene expression profiles.     

BAsE-Seq: a method for obtaining long viral haplotypes from short sequence reads

Epidemiologists aim to inform the design of public health interventions with evidence on the evolution, emergence and spread of infectious diseases. Sequencing of pathogen genomes, together with date, location, clinical manifestation and other relevant data about sample origins, can contribute to describing nearly every aspect of transmission dynamics, including local transmission and global spread. The analyses of these data have implications for all levels of clinical and public health practice, from institutional infection control to policies for surveillance, prevention and treatment. This review highlights the range of epidemiological questions that can be addressed from the combination of genome sequence and traditional ‘line lists’ (tables of epidemiological data where each line includes demographic and clinical features of infected individuals). We identify opportunities for these data to inform interventions that reduce disease incidence and prevalence. By considering current limitations of, and challenges to, interpreting these data, we aim to outline a research agenda to accelerate the genomics-driven transformation in public health microbiology.     

Towards a general theory of neural computation based on prediction by single neurons

Although there has been tremendous progress in understanding the mechanics of the nervous system, there has not been a general theory of its computational function. Here I present a theory that relates the established biophysical properties of single generic neurons to principles of Bayesian probability theory, reinforcement learning and efficient coding. I suggest that this theory addresses the general computational problem facing the nervous system. Each neuron is proposed to mirror the function of the whole system in learning to predict aspects of the world related to future reward. According to the model, a typical neuron receives current information about the state of the world from a subset of its excitatory synaptic inputs, and prior information from its other inputs. Prior information would be contributed by synaptic inputs representing distinct regions of space, and by different types of non-synaptic, voltage-regulated channels representing distinct periods of the past. The neuron's membrane voltage is proposed to signal the difference between current and prior information ("prediction error" or "surprise"). A neuron would apply a Hebbian plasticity rule to select those excitatory inputs that are the most closely correlated with reward but are the least predictable, since unpredictable inputs provide the neuron with the most "new" information about future reward. To minimize the error in its predictions and to respond only when excitation is "new and surprising," the neuron selects amongst its prior information sources through an anti-Hebbian rule. The unique inputs of a mature neuron would therefore result from learning about spatial and temporal patterns in its local environment, and by extension, the external world. Thus the theory describes how the structure of the mature nervous system could reflect the structure of the external world, and how the complexity and intelligence of the system might develop from a population of undifferentiated neurons, each implementing similar learning algorithms.     

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.     

SPINE-D: Accurate Prediction of Short and Long Disordered Regions by a Single Neural-Network Based Method

Abstract

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. The server and databases are available at http://sparks.informatics.iupui.edu/.     

Comparing short protein substructures by a method based on backbone torsion angles

An efficient algorithm was characterized that determines the similarity in main chain conformation between short protein substructures. The algorithm computes Δt, the root mean square difference in ? and ψ torsion angles over a small number of amino acids (typically 3–5). Using this algorithm, large number of protein substrates comparisons were feasible. The parameter Δt was sensitive to variations in local protein conformation, and it correlates with Δr, the root mean square deviation in atomic coordinates. Values for Δt were obtained that define similarity thresholds, which determine whether two substructure are considered structurally similar. To set a lower bound on the similarity threshold, we estimated the component of Δt due to measurement noise fromcomparisons of independently refined coordinates of the same protein. A sample distribution of Δt from nonhomologous protein comparisons identified an upper bound on the similarity threshold, one that refrains from incorporating large numbers of nonmatching comparisons large numbers of nonmatching comparisons. Unlike methods based on Cα atoms alone, Δt was sensitive to rotations in the peptide plane, shown to occur in several proteins. Comparisons of homologus proteins by Δt showed that the active site torsion angles are highly conserved. The Δt method was applied to the α-chain of human hemoglobin, where it readily demonstrated the local differences in the structures of different ligation states.     

An assignment of intrinsically disordered regions of proteins based on NMR structures

Intrinsically disordered proteins (IDPs) do not adopt stable three-dimensional structures in physiological conditions, yet these proteins play crucial roles in biological phenomena. In most cases, intrinsic disorder manifests itself in segments or domains of an IDP, called intrinsically disordered regions (IDRs), but fully disordered IDPs also exist. Although IDRs can be detected as missing residues in protein structures determined by X-ray crystallography, no protocol has been developed to identify IDRs from structures obtained by Nuclear Magnetic Resonance (NMR). Here, we propose a computational method to assign IDRs based on NMR structures. We compared missing residues of X-ray structures with residue-wise deviations of NMR structures for identical proteins, and derived a threshold deviation that gives the best correlation of ordered and disordered regions of both structures. The obtained threshold of 3.2 Å was applied to proteins whose structures were only determined by NMR, and the resulting IDRs were analyzed and compared to those of X-ray structures with no NMR counterpart in terms of sequence length, IDR fraction, protein function, cellular location, and amino acid composition, all of which suggest distinct characteristics. The structural knowledge of IDPs is still inadequate compared with that of structured proteins. Our method can collect and utilize IDRs from structures determined by NMR, potentially enhancing the understanding of IDPs.     

New method for accurate prediction of solvent accessibility from protein sequence

A novel method was developed for predicting the solvent accessibility. Based on single sequence data, this method achieved 71.5% accuracy with a correlation coefficient of 0.42 in a database of 704 proteins with threshold of 20% for a two-state-defining solvent accessibility. Prediction in a data subset of 341 monomeric proteins achieved 72.7% accuracy with a correlation coefficient of 0. 43. On the average, prediction over short chains gives better results than that over long chains. With a solvent accessibility threshold of 20%, prediction over 236 monomeric proteins with chain length < 300 amino acid residues achieved 75.3% accuracy with a correlation coefficient of 0.44 by jackknife analysis, which is higher than that obtained by previous methods using multiple sequence alignments.     

Functional anthology of intrinsic disorder. 1. Biological processes and functions of proteins with long disordered regions

Identifying relationships between function, amino acid sequence, and protein structure represents a major challenge. In this study, we propose a bioinformatics approach that identifies functional keywords in the Swiss-Prot database that correlate with intrinsic disorder. A statistical evaluation is employed to rank the significance of these correlations. Protein sequence data redundancy and the relationship between protein length and protein structure were taken into consideration to ensure the quality of the statistical inferences. Over 200,000 proteins from the Swiss-Prot database were analyzed using this approach. The predictions of intrinsic disorder were carried out using PONDR VL3E predictor of long disordered regions that achieves an accuracy of above 86%. Overall, out of the 710 Swiss-Prot functional keywords that were each associated with at least 20 proteins, 238 were found to be strongly positively correlated with predicted long intrinsically disordered regions, whereas 302 were strongly negatively correlated with such regions. The remaining 170 keywords were ambiguous without strong positive or negative correlation with the disorder predictions. These functions cover a large variety of biological activities and imply that disordered regions are characterized by a wide functional repertoire. Our results agree well with literature findings, as we were able to find at least one illustrative example of functional disorder or order shown experimentally for the vast majority of keywords showing the strongest positive or negative correlation with intrinsic disorder. This work opens a series of three papers, which enriches the current view of protein structure-function relationships, especially with regards to functionalities of intrinsically disordered proteins, and provides researchers with a novel tool that could be used to improve the understanding of the relationships between protein structure and function. The first paper of the series describes our statistical approach, outlines the major findings, and provides illustrative examples of biological processes and functions positively and negatively correlated with intrinsic disorder.