Zhining Wen

Using support vector machine combined with auto covariance to predict protein–protein interactions from protein sequences

Compared to the available protein sequences of different organisms, the number of revealed protein–protein interactions (PPIs) is still very limited. So many computational methods have been developed to facilitate the identification of novel PPIs. However, the methods only using the information of protein sequences are more universal than those that depend on some additional information or predictions about the proteins. In this article, a sequence-based method is proposed by combining a new feature representation using auto covariance (AC) and support vector machine (SVM). AC accounts for the interactions between residues a certain distance apart in the sequence, so this method adequately takes the neighbouring effect into account. When performed on the PPI data of yeast Saccharomyces cerevisiae, the method achieved a very promising prediction result. An independent data set of 11 474 yeast PPIs was used to evaluate this prediction model and the prediction accuracy is 88.09%. The performance of this method is superior to those of the existing sequence-based methods, so it can be a useful supplementary tool for future proteomics studies. The prediction software and all data sets used in this article are freely available at http://www.scucic.cn/Predict_PPI/index.htm.

Classifying G protein-coupled receptors and nuclear receptors on the basis of protein power spectrum from fast Fourier transform

Summary.As the potential drug targets, G-protein coupled receptors (GPCRs) and nuclear receptors (NRs) are the focuses in pharmaceutical research. It is of great practical significance to develop an automated and reliable method to facilitate the identification of novel receptors. In this study, a method of fast Fourier transform-based support vector machine was proposed to classify GPCRs and NRs from the hydrophobicity of proteins. The models for all the GPCR families and NR subfamilies were trained and validated using jackknife test and the results thus obtained are quite promising. Meanwhile, the performance of the method was evaluated on GPCR and NR independent datasets with good performance. The good results indicate the applicability of the method. Two web servers implementing the prediction are available at http://chem.scu.edu.cn/blast/Pred-GPCR and http://chem.scu.edu.cn/blast/Pred-NR.

Delaunay triangulation with partial least squares projection to latent structures: a model for G-protein coupled receptors classification and fast structure recognition

Summary.As an important transmembrane protein family in eukaryon, G-protein coupled receptors (GPCRs) play a significant role in cellular signal transduction and are important targets for drug design. However, it is very difficult to resolve their tertiary structure by X-ray crystallography. In this study, we have developed a Delaunay model, which constructs a series of simplexes with latent variables to classify the families of GPCRs and projects unknown sequences to principle component space (PC-space) to predict their topology. Computational results show that, for the classification of GPCRs, the method achieves the accuracy of 91.0 and 87.6% for Class A, more than 80% for the other three classes in differentiating GPCRs from non-GPCRs and 70% for discriminating between four major classes of GPCR, respectively. When recognizing the structure of GPCRs, all the N-terminals of sequences can be determined correctly. The maximum accuracy of predicting transmembrane segments is achieved in the 7th transmembrane segment of Rhodopsin, which is 99.4%, and the average error is 2.1 amino acids, which is the lowest in all of the segments prediction. This method could provide structural information of a novel GPCR as a tool for experiments and other algorithms of structure prediction of GPCRs. Academic users should send their request for the MATLAB program for classifying GPCRs and predicting the topology of them at liml@scu.edu.cn.

Using pseudo amino acid composition to predict transmembrane regions in protein: cellular automata and Lempel-Ziv complexity

Summary.Transmembrane (TM) proteins represent about 20–30% of the protein sequences in higher eukaryotes, playing important roles across a range of cellular functions. Moreover, knowledge about topology of these proteins often provides crucial hints toward their function. Due to the difficulties in experimental structure determinations of TM protein, theoretical prediction methods are highly preferred in identifying the topology of newly found ones according to their primary sequences, useful in both basic research and drug discovery. In this paper, based on the concept of pseudo amino acid composition (PseAA) that can incorporate sequence-order information of a protein sequence so as to remarkably enhance the power of discrete models (Chou, K. C., Proteins: Structure, Function, and Genetics, 2001, 43: 246–255), cellular automata and Lempel-Ziv complexity are introduced to predict the TM regions of integral membrane proteins including both α-helical and β-barrel membrane proteins, validated by jackknife test. The result thus obtained is quite promising, which indicates that the current approach might be a quite potential high throughput tool in the post-genomic era. The source code and dataset are available for academic users at liml@scu.edu.cn.

Predicting disease-associated substitution of a single amino acid by analyzing residue interactions

BackgroundThe rapid accumulation of data on non-synonymous single nucleotide polymorphisms (nsSNPs, also called SAPs) should allow us to further our understanding of the underlying disease-associated mechanisms. Here, we use complex networks to study the role of an amino acid in both local and global structures and determine the extent to which disease-associated and polymorphic SAPs differ in terms of their interactions to other residues.ResultsWe found that SAPs can be well characterized by network topological features. Mutations are probably disease-associated when they occur at a site with a high centrality value and/or high degree value in a protein structure network. We also discovered that study of the neighboring residues around a mutation site can help to determine whether the mutation is disease-related or not. We compiled a dataset from the Swiss-Prot variant pages and constructed a model to predict disease-associated SAPs based on the random forest algorithm. The values of total accuracy and MCC were 83.0% and 0.64, respectively, as determined by 5-fold cross-validation. With an independent dataset, our model achieved a total accuracy of 80.8% and MCC of 0.59, respectively.ConclusionsThe satisfactory performance suggests that network topological features can be used as quantification measures to determine the importance of a site on a protein, and this approach can complement existing methods for prediction of disease-associated SAPs. Moreover, the use of this method in SAP studies would help to determine the underlying linkage between SAPs and diseases through extensive investigation of mutual interactions between residues.

In silico method for systematic analysis of feature importance in microRNA-mRNA interactions

BackgroundMicroRNA (miRNA), which is short non-coding RNA, plays a pivotal role in the regulation of many biological processes and affects the stability and/or translation of mRNA. Recently, machine learning algorithms were developed to predict potential miRNA targets. Most of these methods are robust but are not sensitive to redundant or irrelevant features. Despite their good performance, the relative importance of each feature is still unclear. With increasing experimental data becoming available, research interest has shifted from higher prediction performance to uncovering the mechanism of microRNA-mRNA interactions.ResultsSystematic analysis of sequence, structural and positional features was carried out for two different data sets. The dominant functional features were distinguished from uninformative features in single and hybrid feature sets. Models were developed using only statistically significant sequence, structural and positional features, resulting in area under the receiver operating curves (AUC) values of 0.919, 0.927 and 0.969 for one data set and of 0.926, 0.874 and 0.954 for another data set, respectively. Hybrid models were developed by combining various features and achieved AUC of 0.978 and 0.970 for two different data sets. Functional miRNA information is well reflected in these features, which are expected to be valuable in understanding the mechanism of microRNA-mRNA interactions and in designing experiments.ConclusionsDiffering from previous approaches, this study focused on systematic analysis of all types of features. Statistically significant features were identified and used to construct models that yield similar accuracy to previous studies in a shorter computation time.

Novel Feature for Catalytic Protein Residues Reflecting Interactions with Other Residues

Owing to their potential for systematic analysis, complex networks have been widely used in proteomics. Representing a protein structure as a topology network provides novel insight into understanding protein folding mechanisms, stability and function. Here, we develop a new feature to reveal correlations between residues using a protein structure network. In an original attempt to quantify the effects of several key residues on catalytic residues, a power function was used to model interactions between residues. The results indicate that focusing on a few residues is a feasible approach to identifying catalytic residues. The spatial environment surrounding a catalytic residue was analyzed in a layered manner. We present evidence that correlation between residues is related to their distance apart most environmental parameters of the outer layer make a smaller contribution to prediction and ii catalytic residues tend to be located near key positions in enzyme folds. Feature analysis revealed satisfactory performance for our features, which were combined with several conventional features in a prediction model for catalytic residues using a comprehensive data set from the Catalytic Site Atlas. Values of 88.6 for sensitivity and 88.4 for specificity were obtained by 10fold crossvalidation. These results suggest that these features reveal the mutual dependence of residues and are promising for further study of structurefunction relationship.

Studying Peptides Biological Activities Based on Multidimensional Descriptors (E) Using Support Vector Regression

A quantitative multidimensional amino acids descriptors E (E1–E5) has been introduced in bioactive peptides Quantitative Structure–Activity Relationship (QSAR) study. These descriptors correlate well with hydrophobicity, size, preferences for amino acids to occur in α-helices, composition and the net charge, respectively. They were then applied to construct characterization and QSAR analysis on 48 angiotensin-converting enzyme (ACE) inhibitors dipeptides, 55 ACE inhibitors tripeptides and 48 bitter tasting dipeptides by support vector regression (SVR). The leave one out cross validation Q(CV)2 were 0.886, 0.985 and 0.912, the root mean square error (RMSE) were 0.250, 0.021 and 0.123, respectively. The results showed that, in comparison with the conventional descriptors, the new descriptor (E) is a useful structure characterization method for peptide QSAR analysis. The importance of each parameter or property at each position in peptides is estimated by the value of the model RMSE obtained using leave-one-parameter-out (LOPO) approach in the SVR model. This will be provided with certain guidance meaning to design and exploit peptide analogues. The results also indicate that SVR can be used as an alternative powerful modeling tool for peptide QSAR studies, and give one advice (LOPO) about evaluating the importance of parameter in SVR model. Moreover, it also offered an idea about nonlinear relation between bioactive of peptides and their structural descriptors E. The establishment of such methods will be a very meaningful work to peptide bioactive investigation in peptide analogue drug design.

Effects of neighboring sequence environment in predicting cleavage sites of signal peptides.

Signal peptide has a pivotal role in the translocation of secretory protein. Some models have been designed to predict its cleavage site. It is reported that the cleavage site has relationship with the neighboring sequence environment, i.e., hydrophobic core h-region, and the specific patterns in c-region. In some studies, this finding does facilitate the prediction of cleavage site. However, in these models, sequence environment information is merely taken account of as model inputs and no detailed investigation into its effect on the prediction of cleavage site has been made. In this work, we analyze the constraint on cleave site placed by the hydrophobic core of signal peptide and then use it to improve the performance of the signal peptide cleavage site prediction. Our model is designed as follows: firstly, a sliding window is used to scan sample and artificial neural network (ANN) is employed to give cleavage site/non-cleavage site scores. Then, based on an estimated hydrophobic h-region a correcting function is proposed to improve the prediction result, in which the sequence environment is taken into account. A trend of cleavage site is indicated by our analysis for each position, which is consistent with experimental findings. Through this correcting step, the improvement of prediction accuracy is over 7%. It therefore demonstrates the neighboring sequence environment is helpful for determination of cleavage site. Program written in Matlab can be downloaded from http://www.scucic.cn/combined model/source code.html.

Expression dynamics and relations with nearby genes of rat transposable elements across 11 organs, 4 developmental stages and both sexes

BackgroundTEs pervade mammalian genomes. However, compared with mice, fewer studies have focused on the TE expression patterns in rat, particularly the comparisons across different organs, developmental stages and sexes. In addition, TEs can influence the expression of nearby genes. The temporal and spatial influences of TEs remain unclear yet.ResultsTo evaluate the TEs transcription patterns, we profiled their transcript levels in 11 organs for both sexes across four developmental stages of rat. The results show that most short interspersed elements (SINEs) are commonly expressed in all conditions, which are also the major TE types with commonly expression patterns. In contrast, long terminal repeats (LTRs) are more likely to exhibit specific expression patterns. The expression tendency of TEs and genes are similar in most cases. For example, few specific genes and TEs are in the liver, muscle and heart. However, TEs perform superior over genes on classing organ, which imply their higher organ specificity than genes. By associating the TEs with the closest genes in genome, we find their expression levels are correlated, independent of their distance in some cases.ConclusionsTEs sex-dependently associate with nearest genes. A gene would be associated with more than one TE. Our works can help to functionally annotate the genome and further understand the role of TEs in gene regulation.