Prediction of DNA-binding residues from sequence

svmPRAT: SVM-based protein residue annotation toolkit

BACKGROUND

Over the last decade several prediction methods have been developed for determining the structural and functional properties of individual protein residues using sequence and sequence-derived information. Most of these methods are based on support vector machines as they provide accurate and generalizable prediction models.

RESULTS

We present a general purpose protein residue annotation toolkit (svmPRAT) to allow biologists to formulate residue-wise prediction problems. svmPRAT formulates the annotation problem as a classification or regression problem using support vector machines. One of the key features of svmPRAT is its ease of use in incorporating any user-provided information in the form of feature matrices. For every residue svmPRAT captures local information around the reside to create fixed length feature vectors. svmPRAT implements accurate and fast kernel functions, and also introduces a flexible window-based encoding scheme that accurately captures signals and pattern for training effective predictive models.

CONCLUSIONS

In this work we evaluate svmPRAT on several classification and regression problems including disorder prediction, residue-wise contact order estimation, DNA-binding site prediction, and local structure alphabet prediction. svmPRAT has also been used for the development of state-of-the-art transmembrane helix prediction method called TOPTMH, and secondary structure prediction method called YASSPP. This toolkit developed provides practitioners an efficient and easy-to-use tool for a wide variety of annotation problems.

AVAILABILITY

http://www.cs.gmu.edu/~mlbio/svmprat.

DNA-binding residues and binding mode prediction with binding-mechanism concerned models

Background

Protein-DNA interactions are essential for fundamental biological activities including DNA transcription, replication, packaging, repair and rearrangement. Proteins interacting with DNA can be classified into two categories of binding mechanisms - sequence-specific and non-specific binding. Protein-DNA specific binding provides a mechanism to recognize correct nucleotide base pairs for sequence-specific identification. Protein-DNA non-specific binding shows sequence independent interaction for accelerated targeting by interacting with DNA backbone. Both sequence-specific and non-specific binding residues contribute to their roles for interaction.

Results

The proposed framework has two stage predictors: DNA-binding residues prediction and binding mode prediction. In the first stage - DNA-binding residues prediction, the predictor for DNA specific binding residues achieves 96.45% accuracy with 50.14% sensitivity, 99.31% specificity, 81.70% precision, and 62.15% F-measure. The predictor for DNA non-specific binding residues achieves 89.14% accuracy with 53.06% sensitivity, 95.25% specificity, 65.47% precision, and 58.62% F-measure. While combining prediction results of sequence-specific and non-specific binding residues with OR operation, the predictor achieves 89.26% accuracy with 56.86% sensitivity, 95.63% specificity, 71.92% precision, and 63.51% F-measure. In the second stage, protein-DNA binding mode prediction achieves 75.83% accuracy while using support vector machine with multi-class prediction.

Conclusion

This article presents the design of a sequence based predictor aiming to identify sequence-specific and non-specific binding residues in a transcription factor with DNA binding-mechanism concerned. The protein-DNA binding mode prediction was introduced to help improve DNA-binding residues prediction. In addition, the results of this study will help with the design of binding-mechanism concerned predictors for other families of proteins interacting with DNA.

A threading-based method for the prediction of DNA-binding proteins with application to the human genome

Diverse mechanisms for DNA-protein recognition have been elucidated in numerous atomic complex structures from various protein families. These structural data provide an invaluable knowledge base not only for understanding DNA-protein interactions, but also for developing specialized methods that predict the DNA-binding function from protein structure. While such methods are useful, a major limitation is that they require an experimental structure of the target as input. To overcome this obstacle, we develop a threading-based method, DNA-Binding-Domain-Threader (DBD-Threader), for the prediction of DNA-binding domains and associated DNA-binding protein residues. Our method, which uses a template library composed of DNA-protein complex structures, requires only the target protein's sequence. In our approach, fold similarity and DNA-binding propensity are employed as two functional discriminating properties. In benchmark tests on 179 DNA-binding and 3,797 non-DNA-binding proteins, using templates whose sequence identity is less than 30% to the target, DBD-Threader achieves a sensitivity/precision of 56%/86%. This performance is considerably better than the standard sequence comparison method PSI-BLAST and is comparable to DBD-Hunter, which requires an experimental structure as input. Moreover, for over 70% of predicted DNA-binding domains, the backbone Root Mean Square Deviations (RMSDs) of the top-ranked structural models are within 6.5 A of their experimental structures, with their associated DNA-binding sites identified at satisfactory accuracy. Additionally, DBD-Threader correctly assigned the SCOP superfamily for most predicted domains. To demonstrate that DBD-Threader is useful for automatic function annotation on a large-scale, DBD-Threader was applied to 18,631 protein sequences from the human genome; 1,654 proteins are predicted to have DNA-binding function. Comparison with existing Gene Ontology (GO) annotations suggests that approximately 30% of our predictions are new. Finally, we present some interesting predictions in detail. In particular, it is estimated that approximately 20% of classic zinc finger domains play a functional role not related to direct DNA-binding.

Prodepth: predict residue depth by support vector regression approach from protein sequences only

Residue depth (RD) is a solvent exposure measure that complements the information provided by conventional accessible surface area (ASA) and describes to what extent a residue is buried in the protein structure space. Previous studies have established that RD is correlated with several protein properties, such as protein stability, residue conservation and amino acid types. Accurate prediction of RD has many potentially important applications in the field of structural bioinformatics, for example, facilitating the identification of functionally important residues, or residues in the folding nucleus, or enzyme active sites from sequence information. In this work, we introduce an efficient approach that uses support vector regression to quantify the relationship between RD and protein sequence. We systematically investigated eight different sequence encoding schemes including both local and global sequence characteristics and examined their respective prediction performances. For the objective evaluation of our approach, we used 5-fold cross-validation to assess the prediction accuracies and showed that the overall best performance could be achieved with a correlation coefficient (CC) of 0.71 between the observed and predicted RD values and a root mean square error (RMSE) of 1.74, after incorporating the relevant multiple sequence features. The results suggest that residue depth could be reliably predicted solely from protein primary sequences: local sequence environments are the major determinants, while global sequence features could influence the prediction performance marginally. We highlight two examples as a comparison in order to illustrate the applicability of this approach. We also discuss the potential implications of this new structural parameter in the field of protein structure prediction and homology modeling. This method might prove to be a powerful tool for sequence analysis.

PDA: an automatic and comprehensive analysis program for protein-DNA complex structures

BACKGROUND

Knowledge of protein-DNA interactions at the structural-level can provide insights into the mechanisms of protein-DNA recognition and gene regulation. Although over 1400 protein-DNA complex structures have been deposited into Protein Data Bank (PDB), the structural details of protein-DNA interactions are generally not available. In addition, current approaches to comparison of protein-DNA complexes are mainly based on protein sequence similarity while the DNA sequences are not taken into account. With the number of experimentally-determined protein-DNA complex structures increasing, there is a need for an automatic program to analyze the protein-DNA complex structures and to provide comprehensive structural information for the benefit of the whole research community.

RESULTS

We developed an automatic and comprehensive protein-DNA complex structure analysis program, PDA (for protein-DNA complex structure analyzer). PDA takes PDB files as inputs and performs structural analysis that includes 1) whole protein-DNA complex structure restoration, especially the reconstruction of double-stranded DNA structures; 2) an efficient new approach for DNA base-pair detection; 3) systematic annotation of protein-DNA interactions; and 4) extraction of DNA subsequences involved in protein-DNA interactions and identification of protein-DNA binding units. Protein-DNA complex structures in current PDB were processed and analyzed with our PDA program and the analysis results were stored in a database. A dataset useful for studying protein-DNA interactions involved in gene regulation was generated using both protein and DNA sequences as well as the contact information of the complexes. WebPDA was developed to provide a web interface for using PDA and for data retrieval.

CONCLUSION

PDA is a computational tool for structural annotations of protein-DNA complexes. It provides a useful resource for investigating protein-DNA interactions. Data from the PDA analysis can also facilitate the classification of protein-DNA complexes and provide insights into rational design of benchmarks. The PDA program is freely available at http://bioinfozen.uncc.edu/webpda.

ProteDNA: a sequence-based predictor of sequence-specific DNA-binding residues in transcription factors

This article presents the design of a sequence-based predictor named ProteDNA for identifying the sequence-specific binding residues in a transcription factor (TF). Concerning protein–DNA interactions, there are two types of binding mechanisms involved, namely sequence-specific binding and nonspecific binding. Sequence-specific bindings occur between protein sidechains and nucleotide bases and correspond to sequence-specific recognition of genes. Therefore, sequence-specific bindings are essential for correct gene regulation. In this respect, ProteDNA is distinctive since it has been designed to identify sequence-specific binding residues. In order to accommodate users with different application needs, ProteDNA has been designed to operate under two modes, namely, the high-precision mode and the balanced mode. According to the experiments reported in this article, under the high-precision mode, ProteDNA has been able to deliver precision of 82.3%, specificity of 99.3%, sensitivity of 49.8% and accuracy of 96.5%. Meanwhile, under the balanced mode, ProteDNA has been able to deliver precision of 60.8%, specificity of 97.6%, sensitivity of 60.7% and accuracy of 95.4%. ProteDNA is available at the following websites:

http://protedna.csbb.ntu.edu.tw/

http://protedna.csie.ntu.edu.tw/

http://bio222.esoe.ntu.edu.tw/ProteDNA/.

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

Background

DNA 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.

Results

Significant 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 .

Conclusion

Most 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.

Identification of DNA-binding proteins using structural, electrostatic and evolutionary features

DNA-binding proteins (DBPs) participate in various crucial processes in the life-cycle of the cells, and the identification and characterization of these proteins is of great importance. We present here a random forests classifier for identifying DBPs among proteins with known 3D structures. First, clusters of evolutionarily conserved regions (patches) on the surface of proteins were detected using the PatchFinder algorithm; earlier studies showed that these regions are typically the functionally important regions of proteins. Next, we trained a classifier using features like the electrostatic potential, cluster-based amino acid conservation patterns and the secondary structure content of the patches, as well as features of the whole protein, including its dipole moment. Using 10-fold cross-validation on a dataset of 138 DBPs and 110 proteins that do not bind DNA, the classifier achieved a sensitivity and a specificity of 0.90, which is overall better than the performance of published methods. Furthermore, when we tested five different methods on 11 new DBPs that did not appear in the original dataset, only our method annotated all correctly. The resulting classifier was applied to a collection of 757 proteins of known structure and unknown function. Of these proteins, 218 were predicted to bind DNA, and we anticipate that some of them interact with DNA using new structural motifs. The use of complementary computational tools supports the notion that at least some of them do bind DNA.

Cell cycle kinases predicted from conserved biophysical properties

Machine-learning techniques can classify functionally related proteins where homology-transfer as well as sequence and structure motifs fail. Here, we present a method that aimed at complementing homology-transfer in the identification of cell cycle control kinases from sequence alone. First, we identified functionally significant residues in cell cycle proteins through their high sequence conservation and biophysical properties. We then incorporated these residues and their features into support vector machines (SVM) to identify new kinases and more specifically to differentiate cell cycle kinases from other kinases and other proteins. As expected, the most informative residues tend to be highly conserved and tend to localize in the ATP binding regions of the kinases. Another observation confirmed that ATP binding regions are typically not found on the surface but in partially buried sites, and that this fact is correctly captured by accessibility predictions. Using these highly conserved, semi-buried residues and their biophysical properties, we could distinguish cell cycle S/T kinases from other kinase families at levels around 70-80% accuracy and 62-81% coverage. An application to the entire human proteome predicted at least 97 human proteins with limited previous annotations to be candidates for cell cycle kinases.

Detection of protein catalytic residues at high precision using local network properties

Background

Identifying the active site of an enzyme is a crucial step in functional studies. While protein sequences and structures can be experimentally characterized, determining which residues build up an active site is not a straightforward process. In the present study a new method for the detection of protein active sites is introduced. This method uses local network descriptors derived from protein three-dimensional structures to determine whether a residue is part of an active site. It thus does not involve any sequence alignment or structure similarity to other proteins. A scoring function is elaborated over a set of more than 220 proteins having different structures and functions, in order to detect protein catalytic sites with a high precision, i.e. with a minimal rate of false positives.

Results

The scoring function was based on the counts of first-neighbours on side-chain contacts, third-neighbours and residue type. Precision of the detection using this function was 28.1%, which represents a more than three-fold increase compared to combining closeness centrality with residue surface accessibility, a function which was proposed in recent years. The performance of the scoring function was also analysed into detail over a smaller set of eight proteins. For the detection of 'functional' residues, which were involved either directly in catalytic activity or in the binding of substrates, precision reached a value of 72.7% on this second set. These results suggested that our scoring function was effective at detecting not only catalytic residues, but also any residue that is part of the functional site of a protein.

Conclusion

As having been validated on the majority of known structural families, this method should prove useful for the detection of active sites in any protein with unknown function, and for direct application to the design of site-directed mutagenesis experiments.

Prediction of DNA-binding residues in proteins from amino acid sequences using a random forest model with a hybrid feature

MOTIVATION

In this work, we aim to develop a computational approach for predicting DNA-binding sites in proteins from amino acid sequences. To avoid overfitting with this method, all available DNA-binding proteins from the Protein Data Bank (PDB) are used to construct the models. The random forest (RF) algorithm is used because it is fast and has robust performance for different parameter values. A novel hybrid feature is presented which incorporates evolutionary information of the amino acid sequence, secondary structure (SS) information and orthogonal binary vector (OBV) information which reflects the characteristics of 20 kinds of amino acids for two physical-chemical properties (dipoles and volumes of the side chains). The numbers of binding and non-binding residues in proteins are highly unbalanced, so a novel scheme is proposed to deal with the problem of imbalanced datasets by downsizing the majority class.

RESULTS

The results show that the RF model achieves 91.41% overall accuracy with Matthew's correlation coefficient of 0.70 and an area under the receiver operating characteristic curve (AUC) of 0.913. To our knowledge, the RF method using the hybrid feature is currently the computationally optimal approach for predicting DNA-binding sites in proteins from amino acid sequences without using three-dimensional (3D) structural information. We have demonstrated that the prediction results are useful for understanding protein-DNA interactions.

AVAILABILITY

DBindR web server implementation is freely available at http://www.cbi.seu.edu.cn/DBindR/DBindR.htm.

Sequence-dependence and prediction of nucleotide solvent accessibility in double stranded DNA

Solvent accessibility of amino acid residues in proteins has been widely studied and many methods for its prediction from sequence and evolutionary information are available. Some of the advantages of studying amino acid solvent accessibility also apply to DNA. However, currently there are no methods to estimate the solvent accessibility of nucleotides, as most works on DNA structures have focused on elastic deformations and other structural attributes. In this work, an attempt has been made to analyze the distribution of different nucleotides in various accessibility ranges. Effect of neighboring nucleotides on the predictability of exposure has been evaluated by developing a linear perceptron model that takes sequence information as the input. Five different types of solvent accessibility (overall nucleotide, side chain, main chain, polar and non-polar) have been predicted. From the analysis, it is observed that Thymine stands out in terms of its higher exposed surface area, particularly its side chain and non-polar atoms. It is also concluded that the solvent accessibility of a nucleotide strongly depends on its sequence neighbors and can be predicted with fair success using this information.

Protein-DNA interactions: structural, thermodynamic and clustering patterns of conserved residues in DNA-binding proteins

Amino acid residues, which play important roles in protein function, are often conserved. Here, we analyze thermodynamic and structural data of protein–DNA interactions to explore a relationship between free energy, sequence conservation and structural cooperativity. We observe that the most stabilizing residues or putative hotspots are those which occur as clusters of conserved residues. The higher packing density of the clusters and available experimental thermodynamic data of mutations suggest cooperativity between conserved residues in the clusters. Conserved singlets contribute to the stability of protein–DNA complexes to a lesser extent. We also analyze structural features of conserved residues and their clusters and examine their role in identifying DNA-binding sites. We show that about half of the observed conserved residue clusters are in the interface with the DNA, which could be identified from their amino acid composition; whereas the remaining clusters are at the protein–protein or protein–ligand interface, or embedded in the structural scaffolds. In protein–protein interfaces, conserved residues are highly correlated with experimental residue hotspots, contributing dominantly and often cooperatively to the stability of protein–protein complexes. Overall, the conservation patterns of the stabilizing residues in DNA-binding proteins also highlight the significance of clustering as compared to single residue conservation.