Solvent Accessibility Information Research Articles

Improved protein relative solvent accessibility prediction using deep multi-view feature learning framework

The accurate prediction of the relative solvent accessibility of a protein is critical to understanding its 3D structure and biological function. In this study, a novel deep multi-view feature learning (DMVFL) framework that integrates three different neural network units, i.e., bidirectional long short-term memory recurrent neural network, squeeze-and-excitation, and fully-connected hidden layer, with four sequence-based single-view features, i.e., position-specific scoring matrix, position-specific frequency matrix, predicted secondary structure, and roughly predicted three-state relative solvent accessibility probability, is developed to accurately predict relative solvent accessibility information of protein. On the basis of this newly developed framework, one new protein relative solvent accessibility predictor was proposed and called DMVFL-RSA, which employs a customized multiple feedback mechanism that helps to extract discriminative information embedded in the four single-view features. In benchmark tests on TEST524 and CASP14-derived (CASP14set) datasets, DMVFL-RSA outperforms other existing state-of-the-art protein relative solvent accessibility predictors when predicting two-state (exposure threshold of 25%), three-state (exposure thresholds of 9% and 36%), and four-state (exposure thresholds of 4%, 25%, and 50%) discrete values. For real-valued prediction on TEST524 and CASP14set, DMVFL-RSA has also gained high Pearson correlation coefficient values, indicating a positive correlation between the predicted and native relative solvent accessibility. Detailed analyses show that the major advantages of DMVFL-RSA lie in the high efficiency of the DMVFL framework, the applied multiple feedback mechanism, and the strong sensitivity of the sequence-based features. The web server of DMVFL-RSA is freely available at https://jun-csbio.github.io/DMVFL-RSA/for academic use. The standalone package of DMVFL-RSA is downloadable at https://github.com/XueQiangFan/DMVFL-RSA.

RNA Ensembles from Solvent Accessibility Data: Application to the SAM-I Riboswitch Aptamer Domain

Riboswitches are regulatory ribonucleic acid (RNA) elements that act as ligand-dependent conformational switches that recognize their cognate ligand via a binding pocket located in their aptamer domain. In the apo form, the aptamer domain is dynamic, requiring an ensemble representation of its structure. Here, as a proof-of-concept, we used solvent accessibility information to construct a pair of dynamical ensembles of the aptamer domain of the well-studied S-adenosylmethionine (SAM) class-I riboswitch in the absence (-SAM) and presence (+SAM) of SAM. To achieve this, we first generated a large conformational library and then reweighted conformers in the library using solvent-accessible surface area (SASA) data derived from recently reported light-activated structural examination of RNA (LASER) reactivities measured in the -SAM and +SAM states of the riboswitch. The differences in the resulting -SAM and +SAM ensembles are consistent with a SAM-dependent reshaping of the free-energy landscape of the aptamer domain. Within our -SAM ensemble, we identified a "transient" state that is missing a critical long-range contact, leading us to speculate that it may be representative of a folding intermediate. Further structural analysis also revealed that the transient state harbors a hidden binding pocket that is distinct from the SAM-binding pocket and is predicted by docking calculations to selectively bind small-molecule ligands. The SASA-based method we applied to the SAM-I riboswitch aptamer domain is general and could be used to construct dynamical ensembles for other riboswitch aptamer domains and, more broadly, other classes of structured RNAs.

LabCaS for Ranking Potential Calpain Substrate Cleavage Sites from Amino Acid Sequence.

Calpains are a family of Ca2+-dependent cysteine proteases involved in many important biological processes, where they selectively cleave relevant substrates at specific cleavage sites to regulate the function of the substrate proteins. Presently, our knowledge about the function of calpains and the mechanism of substrate cleavage is still limited due to the fact that the experimental determination and validation on calpain bindings are usually laborious and expensive. This chapter describes LabCaS, an algorithm that is designed for predicting the calpain substrate cleavage sites from amino acid sequences. LabCaS is built on a conditional random field (CRF) statistic model, which trains the cleavage site prediction on multiple features of amino acid residue preference, solvent accessibility information, pair-wise alignment similarity score, secondary structure propensity, and physical-chemistry properties. Large-scale benchmark tests have shown that LabCaS can achieve a reliable recognition of the cleavage sites for most calpain proteins with an average AUC score of 0.862. Due to the fast speed and convenience of use, the protocol should find its usefulness in large-scale calpain-based function annotations of the newly sequenced proteins. The online web server of LabCaS is freely available at http://www.csbio.sjtu.edu.cn/bioinf/LabCaS .

Gd(3+) Spin Labels Report the Conformation and Solvent Accessibility of Solution and Vesicle-Bound Melittin.

Although Gd(3+)-based spin labels have been shown to be an alternative to nitroxides for double electron-electron resonance (DEER) distance measurements at high fields, their ability to provide solvent accessibility information, as nitroxides do, has not been explored. In addition, the effect of the label type on the measured distance distribution has not been sufficiently characterized. In this work, we extended the applicability of Gd(3+) spin labels to solvent accessibility measurements on a peptide in model membranes, namely, large unilamellar vesicles (LUVs) using W-band (2)H Mims electron-nuclear double resonance (ENDOR) and electron spin echo envelope modulation (ESEEM) techniques and Gd(3+)-ADO3A-labeled melittin. In addition, we carried out Gd(3+)-Gd(3+) DEER distance measurements to probe the peptide conformation in solution and when bound to LUVs. A comparison with earlier results reported for the same system with nitroxide labels shows that, although in both cases the peptide binds parallel to the membrane surface, the Gd(3+)-ADO3A label tends to protrude from the membrane into the solvent, whereas the nitroxide does the opposite. This can be explained on the basis of the hydrophilicity of the Gd(3+)-ADO3A labels in contrast with the hydrophobicity of nitroxides. The distance distributions obtained from different labels are accordingly different, with the Gd(3+)-ADO3A yielding consistently broader distributions. These discrepancies are most pronounced when the peptide termini are labeled, which implies that such labeling positions may be inadvisible.

PROTEIN SUBCELLULAR MULTI-LOCALIZATION PREDICTION USING A MIN-MAX MODULAR SUPPORT VECTOR MACHINE

Prediction of protein subcellular localization is an important issue in computational biology because it provides important clues for the characterization of protein functions. Currently, much research has been dedicated to developing automatic prediction tools. Most, however, focus on mono-locational proteins, i.e., they assume that proteins exist in only one location. It should be noted that many proteins bear multi-locational characteristics and carry out crucial functions in biological processes. This work aims to develop a general pattern classifier for predicting multiple subcellular locations of proteins. We use an ensemble classifier, called the min-max modular support vector machine (M(3)-SVM), to solve protein subcellular multi-localization problems; and, propose a module decomposition method based on gene ontology (GO) semantic information for M(3)-SVM. The amino acid composition with secondary structure and solvent accessibility information is adopted to represent features of protein sequences. We apply our method to two multi-locational protein data sets. The M(3)-SVMs show higher accuracy and efficiency than traditional SVMs using the same feature vectors. And the GO decomposition also helps to improve prediction accuracy. Moreover, our method has a much higher rate of accuracy than existing subcellular localization predictors in predicting protein multi-localization.

Computational prediction of type III secreted proteins from gram-negative bacteria

BackgroundType III secretion system (T3SS) is a specialized protein delivery system in gram-negative bacteria that injects proteins (called effectors) directly into the eukaryotic host cytosol and facilitates bacterial infection. For many plant and animal pathogens, T3SS is indispensable for disease development. Recently, T3SS has also been found in rhizobia and plays a crucial role in the nodulation process. Although a great deal of efforts have been done to understand type III secretion, the precise mechanism underlying the secretion and translocation process has not been fully understood. In particular, defined secretion and translocation signals enabling the secretion have not been identified from the type III secreted effectors (T3SEs), which makes the identification of these important virulence factors notoriously challenging. The availability of a large number of sequenced genomes for plant and animal-associated bacteria demands the development of efficient and effective prediction methods for the identification of T3SEs using bioinformatics approaches.ResultsWe have developed a machine learning method based on the N-terminal amino acid sequences to predict novel type III effectors in the plant pathogen Pseudomonas syringae and the microsymbiont rhizobia. The extracted features used in the learning model (or classifier) include amino acid composition, secondary structure and solvent accessibility information. The method achieved a precision of over 90% on P. syringae in a cross validation study. In combination with a promoter screen for the type III specific promoters, this classifier trained on the P. syringae data was applied to predict novel T3SEs from the genomic sequences of four rhizobial strains. This application resulted in 57 candidate type III secreted proteins, 17 of which are confirmed effectors.ConclusionOur experimental results demonstrate that the machine learning method based on N-terminal amino acid sequences combined with a promoter screen could prove to be a very effective computational approach for predicting novel type III effectors in gram-negative bacteria. Our method and data are available to the public upon request.

Prediction of mono- and di-nucleotide-specific DNA-binding sites in proteins using neural networks

BackgroundDNA recognition by proteins is one of the most important processes in living systems. Therefore, understanding the recognition process in general, and identifying mutual recognition sites in proteins and DNA in particular, carries great significance. The sequence and structural dependence of DNA-binding sites in proteins has led to the development of successful machine learning methods for their prediction. However, all existing machine learning methods predict DNA-binding sites, irrespective of their target sequence and hence, none of them is helpful in identifying specific protein-DNA contacts. In this work, we formulate the problem of predicting specific DNA-binding sites in terms of contacts between the residue environments of proteins and the identity of a mononucleotide or a dinucleotide step in DNA. The aim of this work is to take a protein sequence or structural features as inputs and predict for each amino acid residue if it binds to DNA at locations identified by one of the four possible mononucleotides or one of the 10 unique dinucleotide steps. Contact predictions are made at various levels of resolution viz. in terms of side chain, backbone and major or minor groove atoms of DNA.ResultsSignificant differences in residue preferences for specific contacts are observed, which combined with other features, lead to promising levels of prediction. In general, PSSM-based predictions, supported by secondary structure and solvent accessibility, achieve a good predictability of ~70–80%, measured by the area under the curve (AUC) of ROC graphs. The major and minor groove contact predictions stood out in terms of their poor predictability from sequences or PSSM, which was very strongly (>20 percentage points) compensated by the addition of secondary structure and solvent accessibility information, revealing a predominant role of local protein structure in the major/minor groove DNA-recognition. Following a detailed analysis of results, a web server to predict mononucleotide and dinucleotide-step contacts using PSSM was developed and made available at or .ConclusionMost residue-nucleotide contacts can be predicted with high accuracy using only sequence and evolutionary information. Major and minor groove contacts, however, depend profoundly on the local structure. Overall, this study takes us a step closer to the ultimate goal of predicting mutual recognition sites in protein and DNA sequences.

COBEpro: a novel system for predicting continuous B-cell epitopes

Accurate prediction of B-cell epitopes has remained a challenging task in computational immunology despite several decades of research. Only 10% of the known B-cell epitopes are estimated to be continuous, yet they are often the targets of predictors because a solved tertiary structure is not required and they are integral to the development of peptide vaccines and engineering therapeutic proteins. In this article, we present COBEpro, a novel two-step system for predicting continuous B-cell epitopes. COBEpro is capable of assigning epitopic propensity scores to both standalone peptide fragments and residues within an antigen sequence. COBEpro first uses a support vector machine to make predictions on short peptide fragments within the query antigen sequence and then calculates an epitopic propensity score for each residue based on the fragment predictions. Secondary structure and solvent accessibility information (either predicted or exact) can be incorporated to improve performance. COBEpro achieved a cross-validated area under the curve (AUC) of the receiver operating characteristic up to 0.829 on the fragment epitopic propensity scoring task and an AUC up to 0.628 on the residue epitopic propensity scoring task. COBEpro is incorporated into the SCRATCH prediction suite at http://scratch.proteomics.ics.uci.edu.

Improved general regression network for protein domain boundary prediction

BackgroundProtein domains present some of the most useful information that can be used to understand protein structure and functions. Recent research on protein domain boundary prediction has been mainly based on widely known machine learning techniques, such as Artificial Neural Networks and Support Vector Machines. In this study, we propose a new machine learning model (IGRN) that can achieve accurate and reliable classification, with significantly reduced computations. The IGRN was trained using a PSSM (Position Specific Scoring Matrix), secondary structure, solvent accessibility information and inter-domain linker index to detect possible domain boundaries for a target sequence.ResultsThe proposed model achieved average prediction accuracy of 67% on the Benchmark_2 dataset for domain boundary identification in multi-domains proteins and showed superior predictive performance and generalisation ability among the most widely used neural network models. With the CASP7 benchmark dataset, it also demonstrated comparable performance to existing domain boundary predictors such as DOMpro, DomPred, DomSSEA, DomCut and DomainDiscovery with 70.10% prediction accuracy.ConclusionThe performance of proposed model has been compared favourably to the performance of other existing machine learning based methods as well as widely known domain boundary predictors on two benchmark datasets and excels in the identification of domain boundaries in terms of model bias, generalisation and computational requirements.

PRINTR: Prediction of RNA binding sites in proteins using SVM and profiles

Protein-RNA interactions play a key role in a number of biological processes such as protein synthesis, mRNA processing, assembly and function of ribosomes and eukaryotic spliceosomes. A reliable identification of RNA-binding sites in RNA-binding proteins is important for functional annotation and site-directed mutagenesis. We developed a novel method for the prediction of protein residues that interact with RNA using support vector machine (SVM) and position-specific scoring matrices (PSSMs). Two cases have been considered in the prediction of protein residues at RNA-binding surfaces. One is given the sequence information of a protein chain that is known to interact with RNA; the other is given the structural information. Thus, five different inputs have been tested. Coupled with PSI-BLAST profiles and predicted secondary structure, the present approach yields a Matthews correlation coefficient (MCC) of 0.432 by a 7-fold cross-validation, which is the best among all previous reported RNA-binding sites prediction methods. When given the structural information, we have obtained the MCC value of 0.457, with PSSMs, observed secondary structure and solvent accessibility information assigned by DSSP as input. A web server implementing the prediction method is available at the following URL: http://210.42.106.80/printr/ .

Improving the performance of DomainDiscovery of protein domain boundary assignment using inter-domain linker index

BackgroundKnowledge of protein domain boundaries is critical for the characterisation and understanding of protein function. The ability to identify domains without the knowledge of the structure – by using sequence information only – is an essential step in many types of protein analyses. In this present study, we demonstrate that the performance of DomainDiscovery is improved significantly by including the inter-domain linker index value for domain identification from sequence-based information. Improved DomainDiscovery uses a Support Vector Machine (SVM) approach and a unique training dataset built on the principle of consensus among experts in defining domains in protein structure. The SVM was trained using a PSSM (Position Specific Scoring Matrix), secondary structure, solvent accessibility information and inter-domain linker index to detect possible domain boundaries for a target sequence.ResultsImproved DomainDiscovery is compared with other methods by benchmarking against a structurally non-redundant dataset and also CASP5 targets. Improved DomainDiscovery achieves 70% accuracy for domain boundary identification in multi-domains proteins.ConclusionImproved DomainDiscovery compares favourably to the performance of other methods and excels in the identification of domain boundaries for multi-domain proteins as a result of introducing support vector machine with benchmark_2 dataset.

SSALN: An alignment algorithm using structure‐dependent substitution matrices and gap penalties learned from structurally aligned protein pairs

In template-based modeling of protein structures, the generation of the alignment between the target and the template is a critical step that significantly affects the accuracy of the final model. This paper proposes an alignment algorithm SSALN that learns substitution matrices and position-specific gap penalties from a database of structurally aligned protein pairs. In addition to the amino acid sequence information, secondary structure and solvent accessibility information of a position are used to derive substitution scores and position-specific gap penalties. In a test set of CASP5 targets, SSALN outperforms sequence alignment methods such as a Smith-Waterman algorithm with BLOSUM50 and PSI_BLAST. SSALN also generates better alignments than PSI_BLAST in the CASP6 test set. LOOPP server prediction based on an SSALN alignment is ranked the best for target T0280_1 in CASP6. SSALN is also compared with several threading methods and sequence alignment methods on the ProSup benchmark. SSALN has the highest alignment accuracy among the methods compared. On the Fischer's benchmark, SSALN performs better than CLUSTALW and GenTHREADER, and generates more alignments with accuracy >50%, >60% or >70% than FUGUE, but fewer alignments with accuracy >80% than FUGUE. All the supplemental materials can be found at http://www.cs.cornell.edu/ approximately jianq/research.htm.

Large‐scale prediction of disulphide bridges using kernel methods, two‐dimensional recursive neural networks, and weighted graph matching

The formation of disulphide bridges between cysteines plays an important role in protein folding, structure, function, and evolution. Here, we develop new methods for predicting disulphide bridges in proteins. We first build a large curated data set of proteins containing disulphide bridges to extract relevant statistics. We then use kernel methods to predict whether a given protein chain contains intrachain disulphide bridges or not, and recursive neural networks to predict the bonding probabilities of each pair of cysteines in the chain. These probabilities in turn lead to an accurate estimation of the total number of disulphide bridges and to a weighted graph matching problem that can be addressed efficiently to infer the global disulphide bridge connectivity pattern. This approach can be applied both in situations where the bonded state of each cysteine is known, or in ab initio mode where the state is unknown. Furthermore, it can easily cope with chains containing an arbitrary number of disulphide bridges, overcoming one of the major limitations of previous approaches. It can classify individual cysteine residues as bonded or nonbonded with 87% specificity and 89% sensitivity. The estimate for the total number of bridges in each chain is correct 71% of the times, and within one from the true value over 94% of the times. The prediction of the overall disulphide connectivity pattern is exact in about 51% of the chains. In addition to using profiles in the input to leverage evolutionary information, including true (but not predicted) secondary structure and solvent accessibility information yields small but noticeable improvements. Finally, once the system is trained, predictions can be computed rapidly on a proteomic or protein-engineering scale. The disulphide bridge prediction server (DIpro), software, and datasets are available through www.igb.uci.edu/servers/psss.html.

Three-stage prediction of protein -sheets by neural networks, alignments and graph algorithms

Protein beta-sheets play a fundamental role in protein structure, function, evolution and bioengineering. Accurate prediction and assembly of protein beta-sheets, however, remains challenging because protein beta-sheets require formation of hydrogen bonds between linearly distant residues. Previous approaches for predicting beta-sheet topological features, such as beta-strand alignments, in general have not exploited the global covariation and constraints characteristic of beta-sheet architectures. We propose a modular approach to the problem of predicting/assembling protein beta-sheets in a chain by integrating both local and global constraints in three steps. The first step uses recursive neural networks to predict pairing probabilities for all pairs of interstrand beta-residues from profile, secondary structure and solvent accessibility information. The second step applies dynamic programming techniques to these probabilities to derive binding pseudoenergies and optimal alignments between all pairs of beta-strands. Finally, the third step uses graph matching algorithms to predict the beta-sheet architecture of the protein by optimizing the global pseudoenergy while enforcing strong global beta-strand pairing constraints. The approach is evaluated using cross-validation methods on a large non-homologous dataset and yields significant improvements over previous methods. http://www.igb.uci.edu/servers/psss.html.

Clustering protein sequence and structure space with infinite Gaussian mixture models.

We describe a novel approach to the problem of automatically clustering protein sequences and discovering protein families, subfamilies etc., based on the theory of infinite Gaussian mixtures models. This method allows the data itself to dictate how many mixture components are required to model it, and provides a measure of the probability that two proteins belong to the same cluster. We illustrate our methods with application to three data sets: globin sequences, globin sequences with known three-dimensional structures and G-protein coupled receptor sequences. The consistency of the clusters indicate that our method is producing biologically meaningful results, which provide a very good indication of the underlying families and subfamilies. With the inclusion of secondary structure and residue solvent accessibility information, we obtain a classification of sequences of known structure which both reflects and extends their SCOP classifications. A supplementray web site containing larger versions of the figures is available at http://public.kgi.edu/approximately wid/PSB04/index.html