On position-specific scoring matrix for protein function prediction

Highly accurate prediction of protein self-interactions by incorporating the average block and PSSM information into the general PseAAC

It is a challenging task for fundamental research whether proteins can interact with their partners. Protein self-interaction (SIP) is a special case of PPIs, which plays a key role in the regulation of cellular functions. Due to the limitations of experimental self-interaction identification, it is very important to develop an effective biological tool for predicting SIPs based on protein sequences. In the study, we developed a novel computational method called RVM-AB that combines the Relevance Vector Machine (RVM) model and Average Blocks (AB) for detecting SIPs from protein sequences. Firstly, Average Blocks (AB) feature extraction method is employed to represent protein sequences on a Position Specific Scoring Matrix (PSSM). Secondly, Principal Component Analysis (PCA) method is used to reduce the dimension of AB vector for reducing the influence of noise. Then, by employing the Relevance Vector Machine (RVM) algorithm, the performance of RVM-AB is assessed and compared with the state-of-the-art support vector machine (SVM) classifier and other exiting methods on yeast and human datasets respectively. Using the fivefold test experiment, RVM-AB model achieved very high accuracies of 93.01% and 97.72% on yeast and human datasets respectively, which are significantly better than the method based on SVM classifier and other previous methods. The experimental results proved that the RVM-AB prediction model is efficient and robust. It can be an automatic decision support tool for detecting SIPs. For facilitating extensive studies for future proteomics research, the RVMAB server is freely available for academic use at http://219.219.62.123:8888/SIP_AB.

Subcellular localization prediction of apoptosis proteins based on evolutionary information and support vector machine

OBJECTIVES

In this paper, a high-quality sequence encoding scheme is proposed for predicting subcellular location of apoptosis proteins.

METHODS

In the proposed methodology, the novel evolutionary-conservative information is introduced to represent protein sequences. Meanwhile, based on the proportion of golden section in mathematics, position-specific scoring matrix (PSSM) is divided into several blocks. Then, these features are predicted by support vector machine (SVM) and the predictive capability of proposed method is implemented by jackknife test RESULTS: The results show that the golden section method is better than no segmentation method. The overall accuracy for ZD98 and CL317 is 98.98% and 91.11%, respectively, which indicates that our method can play a complimentary role to the existing methods in the relevant areas.

CONCLUSIONS

The proposed feature representation is powerful and the prediction accuracy will be improved greatly, which denotes our method provides the state-of-the-art performance for predicting subcellular location of apoptosis proteins.

Enhancing the Prediction of Transmembrane β-Barrel Segments with Chain Learning and Feature Sparse Representation

Transmembrane β-barrels (TMBs) are one important class of membrane proteins that play crucial functions in the cell. Membrane proteins are difficult wet-lab targets of structural biology, which call for accurate computational prediction approaches. Here, we developed a novel method named MemBrain-TMB to predict the spanning segments of transmembrane β-barrel from amino acid sequence. MemBrain-TMB is a statistical machine learning-based model, which is constructed using a new chain learning algorithm with input features encoded by the image sparse representation approach. We considered the relative status information between neighboring residues for enhancing the performance, and the matrix of features was translated into feature image by sparse coding algorithm for noise and dimension reduction. To deal with the diverse loop length problem, we applied a dynamic threshold method, which is particularly useful for enhancing the recognition of short loops and tight turns. Our experiments demonstrate that the new protocol designed in MemBrain-TMB effectively helps improve prediction performance.

RVMAB: Using the Relevance Vector Machine Model Combined with Average Blocks to Predict the Interactions of Proteins from Protein Sequences

Protein-Protein Interactions (PPIs) play essential roles in most cellular processes. Knowledge of PPIs is becoming increasingly more important, which has prompted the development of technologies that are capable of discovering large-scale PPIs. Although many high-throughput biological technologies have been proposed to detect PPIs, there are unavoidable shortcomings, including cost, time intensity, and inherently high false positive and false negative rates. For the sake of these reasons, in silico methods are attracting much attention due to their good performances in predicting PPIs. In this paper, we propose a novel computational method known as RVM-AB that combines the Relevance Vector Machine (RVM) model and Average Blocks (AB) to predict PPIs from protein sequences. The main improvements are the results of representing protein sequences using the AB feature representation on a Position Specific Scoring Matrix (PSSM), reducing the influence of noise using a Principal Component Analysis (PCA), and using a Relevance Vector Machine (RVM) based classifier. We performed five-fold cross-validation experiments on yeast and Helicobacter pylori datasets, and achieved very high accuracies of 92.98% and 95.58% respectively, which is significantly better than previous works. In addition, we also obtained good prediction accuracies of 88.31%, 89.46%, 91.08%, 91.55%, and 94.81% on other five independent datasets C. elegans, M. musculus, H. sapiens, H. pylori, and E. coli for cross-species prediction. To further evaluate the proposed method, we compare it with the state-of-the-art support vector machine (SVM) classifier on the yeast dataset. The experimental results demonstrate that our RVM-AB method is obviously better than the SVM-based method. The promising experimental results show the efficiency and simplicity of the proposed method, which can be an automatic decision support tool. To facilitate extensive studies for future proteomics research, we developed a freely available web server called RVMAB-PPI in Hypertext Preprocessor (PHP) for predicting PPIs. The web server including source code and the datasets are available at http://219.219.62.123:8888/ppi_ab/.

Constructing query-driven dynamic machine learning model with application to protein-ligand binding sites prediction

We are facing an era with annotated biological data rapidly and continuously generated. How to effectively incorporate new annotated data into the learning step is crucial for enhancing the performance of a bioinformatics prediction model. Although machine-learning-based methods have been extensively used for dealing with various biological problems, existing approaches usually train static prediction models based on fixed training datasets. The static approaches are found having several disadvantages such as low scalability and impractical when training dataset is huge. In view of this, we propose a dynamic learning framework for constructing query-driven prediction models. The key difference between the proposed framework and the existing approaches is that the training set for the machine learning algorithm of the proposed framework is dynamically generated according to the query input, as opposed to training a general model regardless of queries in traditional static methods. Accordingly, a query-driven predictor based on the smaller set of data specifically selected from the entire annotated base dataset will be applied on the query. The new way for constructing the dynamic model enables us capable of updating the annotated base dataset flexibly and using the most relevant core subset as the training set makes the constructed model having better generalization ability on the query, showing "part could be better than all" phenomenon. According to the new framework, we have implemented a dynamic protein-ligand binding sites predictor called OSML (On-site model for ligand binding sites prediction). Computer experiments on 10 different ligand types of three hierarchically organized levels show that OSML outperforms most existing predictors. The results indicate that the current dynamic framework is a promising future direction for bridging the gap between the rapidly accumulated annotated biological data and the effective machine-learning-based predictors. OSML web server and datasets are freely available at: http://www.csbio.sjtu.edu.cn/bioinf/OSML/ for academic use.

Efficient feature selection and classification of protein sequence data in bioinformatics

Bioinformatics has been an emerging area of research for the last three decades. The ultimate aims of bioinformatics were to store and manage the biological data, and develop and analyze computational tools to enhance their understanding. The size of data accumulated under various sequencing projects is increasing exponentially, which presents difficulties for the experimental methods. To reduce the gap between newly sequenced protein and proteins with known functions, many computational techniques involving classification and clustering algorithms were proposed in the past. The classification of protein sequences into existing superfamilies is helpful in predicting the structure and function of large amount of newly discovered proteins. The existing classification results are unsatisfactory due to a huge size of features obtained through various feature encoding methods. In this work, a statistical metric-based feature selection technique has been proposed in order to reduce the size of the extracted feature vector. The proposed method of protein classification shows significant improvement in terms of performance measure metrics: accuracy, sensitivity, specificity, recall, F-measure, and so forth.

An empirical study of different approaches for protein classification

Many domains would benefit from reliable and efficient systems for automatic protein classification. An area of particular interest in recent studies on automatic protein classification is the exploration of new methods for extracting features from a protein that work well for specific problems. These methods, however, are not generalizable and have proven useful in only a few domains. Our goal is to evaluate several feature extraction approaches for representing proteins by testing them across multiple datasets. Different types of protein representations are evaluated: those starting from the position specific scoring matrix of the proteins (PSSM), those derived from the amino-acid sequence, two matrix representations, and features taken from the 3D tertiary structure of the protein. We also test new variants of proteins descriptors. We develop our system experimentally by comparing and combining different descriptors taken from the protein representations. Each descriptor is used to train a separate support vector machine (SVM), and the results are combined by sum rule. Some stand-alone descriptors work well on some datasets but not on others. Through fusion, the different descriptors provide a performance that works well across all tested datasets, in some cases performing better than the state-of-the-art.

Aligning and Clustering Patterns to Reveal the Protein Functionality of Sequences

Discovering sequence patterns with variations unveils significant functions of a protein family. Existing combinatorial methods of discovering patterns with variations are computationally expensive, and probabilistic methods require more elaborate probabilistic representation of the amino acid associations. To overcome these shortcomings, this paper presents a new computationally efficient method for representing patterns with variations in a compact representation called Aligned Pattern Cluster (AP Cluster). To tackle the runtime, our method discovers a shortened list of non-redundant statistically significant sequence associations based on our previous work. To address the representation of protein functional regions, our pattern alignment and clustering step, presented in this paper captures the conservations and variations of the aligned patterns. We further refine our solution to allow more coverage of sequences via extending the AP Clusters containing only statistically significant patterns to Weak and Conserved AP Clusters. When applied to the cytochrome c, the ubiquitin, and the triosephosphate isomerase protein families, our algorithm identifies the binding segments as well as the binding residues. When compared to other methods, ours discovers all binding sites in the AP Clusters with superior entropy and coverage. The identification of patterns with variations help biologists to avoid time-consuming simulations and experimentations. (Software available upon request).

Ranking and compacting binding segments of protein families using aligned pattern clusters

Background

Discovering sequence patterns with variation can unveil functions of a protein family that are important for drug discovery. Exploring protein families using existing methods such as multiple sequence alignment is computationally expensive, thus pattern search, called motif finding in Bioinformatics, is used. However, at present, combinatorial algorithms result in large sets of solutions, and probabilistic models require a richer representation of the amino acid associations. To overcome these shortcomings, we present a method for ranking and compacting these solutions in a new representation referred to as Aligned Pattern Clusters (APCs). To tackle the problem of a large solution set, our method reveals a reduced set of candidate solutions without losing any information. To address the problem of representation, our method captures the amino acid associations and conservations of the aligned patterns. Our algorithm renders a set of APCs in which a set of patterns is discovered, pruned, aligned, and synthesized from the input sequences of a protein family.

Results

Our algorithm identifies the binding or other functional segments and their embedded residues which are important drug targets from the cytochrome c and the ubiquitin protein families taken from Unitprot. The results are independently confirmed by pFam's multiple sequence alignment. For cytochrome c protein the number of resulting patterns with variations are reduced by 76.62% from the number of original patterns without variations. Furthermore, all of the top four candidate APCs correspond to the binding segments with one of each of their conserved amino acid as the binding residue. The discovered proximal APCs agree with pFam and PROSITE results. Surprisingly, the distal binding site discovered by our algorithm is not discovered by pFam nor PROSITE, but confirmed by the three-dimensional cytochrome c structure. When applied to the ubiquitin protein family, our results agree with pFam and reveals six of the seven Lysine binding residues as conserved aligned columns with entropy redundancy measure of 1.0.

Conclusion

The discovery, ranking, reduction, and representation of a set of patterns is important to avert time-consuming and expensive simulations and experimentations during proteomic study and drug discovery.

Designing template-free predictor for targeting protein-ligand binding sites with classifier ensemble and spatial clustering

Accurately identifying the protein-ligand binding sites or pockets is of significant importance for both protein function analysis and drug design. Although much progress has been made, challenges remain, especially when the 3D structures of target proteins are not available or no homology templates can be found in the library, where the template-based methods are hard to be applied. In this paper, we report a new ligand-specific template-free predictor called TargetS for targeting protein-ligand binding sites from primary sequences. TargetS first predicts the binding residues along the sequence with ligand-specific strategy and then further identifies the binding sites from the predicted binding residues through a recursive spatial clustering algorithm. Protein evolutionary information, predicted protein secondary structure, and ligand-specific binding propensities of residues are combined to construct discriminative features; an improved AdaBoost classifier ensemble scheme based on random undersampling is proposed to deal with the serious imbalance problem between positive (binding) and negative (nonbinding) samples. Experimental results demonstrate that TargetS achieves high performances and outperforms many existing predictors. TargetS web server and data sets are freely available at: http://www.csbio.sjtu.edu.cn/bioinf/TargetS/ for academic use.

Design and analysis of classifier learning experiments in bioinformatics: survey and case studies

In many bioinformatics applications, it is important to assess and compare the performances of algorithms trained from data, to be able to draw conclusions unaffected by chance and are therefore significant. Both the design of such experiments and the analysis of the resulting data using statistical tests should be done carefully for the results to carry significance. In this paper, we first review the performance measures used in classification, the basics of experiment design and statistical tests. We then give the results of our survey over 1,500 papers published in the last two years in three bioinformatics journals (including this one). Although the basics of experiment design are well understood, such as resampling instead of using a single training set and the use of different performance metrics instead of error, only 21 percent of the papers use any statistical test for comparison. In the third part, we analyze four different scenarios which we encounter frequently in the bioinformatics literature, discussing the proper statistical methodology as well as showing an example case study for each. With the supplementary software, we hope that the guidelines we discuss will play an important role in future studies.

Protein-RNA interface residue prediction using machine learning: an assessment of the state of the art

Background

RNA molecules play diverse functional and structural roles in cells. They function as messengers for transferring genetic information from DNA to proteins, as the primary genetic material in many viruses, as catalysts (ribozymes) important for protein synthesis and RNA processing, and as essential and ubiquitous regulators of gene expression in living organisms. Many of these functions depend on precisely orchestrated interactions between RNA molecules and specific proteins in cells. Understanding the molecular mechanisms by which proteins recognize and bind RNA is essential for comprehending the functional implications of these interactions, but the recognition ‘code’ that mediates interactions between proteins and RNA is not yet understood. Success in deciphering this code would dramatically impact the development of new therapeutic strategies for intervening in devastating diseases such as AIDS and cancer. Because of the high cost of experimental determination of protein-RNA interfaces, there is an increasing reliance on statistical machine learning methods for training predictors of RNA-binding residues in proteins. However, because of differences in the choice of datasets, performance measures, and data representations used, it has been difficult to obtain an accurate assessment of the current state of the art in protein-RNA interface prediction.

Results

We provide a review of published approaches for predicting RNA-binding residues in proteins and a systematic comparison and critical assessment of protein-RNA interface residue predictors trained using these approaches on three carefully curated non-redundant datasets. We directly compare two widely used machine learning algorithms (Naïve Bayes (NB) and Support Vector Machine (SVM)) using three different data representations in which features are encoded using either sequence- or structure-based windows. Our results show that (i) Sequence-based classifiers that use a position-specific scoring matrix (PSSM)-based representation (PSSMSeq) outperform those that use an amino acid identity based representation (IDSeq) or a smoothed PSSM (SmoPSSMSeq); (ii) Structure-based classifiers that use smoothed PSSM representation (SmoPSSMStr) outperform those that use PSSM (PSSMStr) as well as sequence identity based representation (IDStr). PSSMSeq classifiers, when tested on an independent test set of 44 proteins, achieve performance that is comparable to that of three state-of-the-art structure-based predictors (including those that exploit geometric features) in terms of Matthews Correlation Coefficient (MCC), although the structure-based methods achieve substantially higher Specificity (albeit at the expense of Sensitivity) compared to sequence-based methods. We also find that the expected performance of the classifiers on a residue level can be markedly different from that on a protein level. Our experiments show that the classifiers trained on three different non-redundant protein-RNA interface datasets achieve comparable cross-validation performance. However, we find that the results are significantly affected by differences in the distance threshold used to define interface residues.

Conclusions

Our results demonstrate that protein-RNA interface residue predictors that use a PSSM-based encoding of sequence windows outperform classifiers that use other encodings of sequence windows. While structure-based methods that exploit geometric features can yield significant increases in the Specificity of protein-RNA interface residue predictions, such increases are offset by decreases in Sensitivity. These results underscore the importance of comparing alternative methods using rigorous statistical procedures, multiple performance measures, and datasets that are constructed based on several alternative definitions of interface residues and redundancy cutoffs as well as including evaluations on independent test sets into the comparisons.

A framework for incorporating functional interrelationships into protein function prediction algorithms

The functional annotation of proteins is one of the most important tasks in the post-genomic era. Although many computational approaches have been developed in recent years to predict protein function, most of these traditional algorithms do not take interrelationships among functional terms into account, such as different GO terms usually coannotate with some common proteins. In this study, we propose a new functional similarity measure in the form of Jaccard coefficient to quantify these interrelationships and also develop a framework for incorporating GO term similarity into protein function prediction process. The experimental results of cross-validation on S. cerevisiae and Homo sapiens data sets demonstrate that our method is able to improve the performance of protein function prediction. In addition, we find that small size terms associated with a few of proteins obtain more benefit than the large size ones when considering functional interrelationships. We also compare our similarity measure with other two widely used measures, and results indicate that when incorporated into function prediction algorithms, our proposed measure is more effective. Experiment results also illustrate that our algorithms outperform two previous competing algorithms, which also take functional interrelationships into account, in prediction accuracy. Finally, we show that our method is robust to annotations in the database which are not complete at present. These results give new insights about the importance of functional interrelationships in protein function prediction.

KUPS: constructing datasets of interacting and non-interacting protein pairs with associated attributions

KUPS (The University of Kansas Proteomics Service) provides high-quality protein–protein interaction (PPI) data for researchers developing and evaluating computational models for predicting PPIs by allowing users to construct ready-to-use data sets of interacting protein pairs (IPPs), non-interacting protein pairs (NIPs) and associated features. Multiple filters and options allow the user to control the make-up of the IPPs and NIPs as well as the quality of the resultant data sets. Each data set is built from the overall database, which includes 185 446 IPPs and ∼1.5 billion NIPs from five primary databases: IntAct, HPRD, MINT, UniProt and the Gene Ontology. The IPP set can be set to specific model organisms, interaction types and experimental evidence. The NIP set can be generated using four different strategies, which can alleviate biased estimation problems. Lastly, multiple features can be provided for all of the IPP and NIP pairs. Additionally, KUPS provides two benchmark data sets to help researchers compare their algorithms to existing approaches. KUPS is freely available at http://www.ittc.ku.edu/chenlab.