Supervised Learning Classification Models for Prediction of Plant Virus Encoded RNA Silencing Suppressors

Viral encoded RNA silencing suppressor proteins interfere with the host RNA silencing machinery, facilitating viral infection by evading host immunity. In plant hosts, the viral proteins have several basic science implications and biotechnology applications. However in silico identification of these proteins is limited by their high sequence diversity. In this study we developed supervised learning based classification models for plant viral RNA silencing suppressor proteins in plant viruses. We developed four classifiers based on supervised learning algorithms: J48, Random Forest, LibSVM and Naïve Bayes algorithms, with enriched model learning by correlation based feature selection. Structural and physicochemical features calculated for experimentally verified primary protein sequences were used to train the classifiers. The training features include amino acid composition; auto correlation coefficients; composition, transition, and distribution of various physicochemical properties; and pseudo amino acid composition. Performance analysis of predictive models based on 10 fold cross-validation and independent data testing revealed that the Random Forest based model was the best and achieved 86.11% overall accuracy and 86.22% balanced accuracy with a remarkably high area under the Receivers Operating Characteristic curve of 0.95 to predict viral RNA silencing suppressor proteins. The prediction models for plant viral RNA silencing suppressors can potentially aid identification of novel viral RNA silencing suppressors, which will provide valuable insights into the mechanism of RNA silencing and could be further explored as potential targets for designing novel antiviral therapeutics. Also, the key subset of identified optimal features may help in determining compositional patterns in the viral proteins which are important determinants for RNA silencing suppressor activities. The best prediction model developed in the study is available as a freely accessible web server pVsupPred at http://bioinfo.icgeb.res.in/pvsup/.     

Gene Network Rewiring to Study Melanoma Stage Progression and Elements Essential for Driving Melanoma

Metastatic melanoma patients have a poor prognosis, mainly attributable to the underlying heterogeneity in melanoma driver genes and altered gene expression profiles. These characteristics of melanoma also make the development of drugs and identification of novel drug targets for metastatic melanoma a daunting task. Systems biology offers an alternative approach to re-explore the genes or gene sets that display dysregulated behaviour without being differentially expressed. In this study, we have performed systems biology studies to enhance our knowledge about the conserved property of disease genes or gene sets among mutually exclusive datasets representing melanoma progression. We meta-analysed 642 microarray samples to generate melanoma reconstructed networks representing four different stages of melanoma progression to extract genes with altered molecular circuitry wiring as compared to a normal cellular state. Intriguingly, a majority of the melanoma network-rewired genes are not differentially expressed and the disease genes involved in melanoma progression consistently modulate its activity by rewiring network connections. We found that the shortlisted disease genes in the study show strong and abnormal network connectivity, which enhances with the disease progression. Moreover, the deviated network properties of the disease gene sets allow ranking/prioritization of different enriched, dysregulated and conserved pathway terms in metastatic melanoma, in agreement with previous findings. Our analysis also reveals presence of distinct network hubs in different stages of metastasizing tumor for the same set of pathways in the statistically conserved gene sets. The study results are also presented as a freely available database at http://bioinfo.icgeb.res.in/m3db/. The web-based database resource consists of results from the analysis presented here, integrated with cytoscape web and user-friendly tools for visualization, retrieval and further analysis.     

ModuleRole: A Tool for Modulization,Role Determination and Visualization in Protein-Protein Interaction Networks

Rapidly increasing amounts of (physical and genetic) protein-protein interaction (PPI) data are produced by various high-throughput techniques, and interpretation of these data remains a major challenge. In order to gain insight into the organization and structure of the resultant large complex networks formed by interacting molecules, using simulated annealing, a method based on the node connectivity, we developed ModuleRole, a user-friendly web server tool which finds modules in PPI network and defines the roles for every node, and produces files for visualization in Cytoscape and Pajek. For given proteins, it analyzes the PPI network from BioGRID database, finds and visualizes the modules these proteins form, and then defines the role every node plays in this network, based on two topological parameters Participation Coefficient and Z-score. This is the first program which provides interactive and very friendly interface for biologists to find and visualize modules and roles of proteins in PPI network. It can be tested online at the website http://www.bioinfo.org/modulerole/index.php, which is free and open to all users and there is no login requirement, with demo data provided by “User Guide” in the menu Help. Non-server application of this program is considered for high-throughput data with more than 200 nodes or user’s own interaction datasets. Users are able to bookmark the web link to the result page and access at a later time. As an interactive and highly customizable application, ModuleRole requires no expert knowledge in graph theory on the user side and can be used in both Linux and Windows system, thus a very useful tool for biologist to analyze and visualize PPI networks from databases such as BioGRID.

Availability

ModuleRole is implemented in Java and C, and is freely available at http://www.bioinfo.org/modulerole/index.php. Supplementary information (user guide, demo data) is also available at this website. API for ModuleRole used for this program can be obtained upon request.     

Mammalian Mitochondrial ncRNA Database

Mammalian Mitochondrial ncRNA is a web-based database, which provides specific information on non-coding RNA in mammals. This database includes easy searching, comparing with BLAST and retrieving information on predicted structure and its function about mammalian ncRNAs.

Availability

The database is available for free at http://www.iitm.ac.in/bioinfo/mmndb/     

PBEAM: A parallel implementation of BEAM for genome-wide inference of epistatic interactions

The software tool PBEAM provides a parallel implementation of the BEAM, which is the first algorithm for large scale epistatic interaction mapping, including genome-wide studies with hundreds of thousands of markers. BEAM describes markers and their interactions with a Bayesian partitioning model and computes the posterior probability of each marker sets via Markov Chain Monte Carlo (MCMC). PBEAM takes the advantage of simulating multiple Markov chains simultaneously. This design can efficiently reduce ~n-fold execution time in the circumstance of n CPUs. The implementation of PBEAM is based on MPI libraries.

Availability

PBEAM is available for download at http://bioinfo.au.tsinghua.edu.cn/pbeam/     

GIV: A Tool for Genomic Islands Visualization

A Genomic Islands (GI) is a chunk of DNA sequence in a genome whose origin can be traced back to other organisms or viruses. The detection of GIs plays an indispensable role in biomedical research, due to the fact that GIs are highly related to special functionalities such as disease-causing GIs - pathogenicity islands. It is also very important to visualize genomic islands, as well as the supporting features corresponding to the genomic islands in the genome. We have developed a program, Genomic Island Visualization (GIV), which displays the locations of genomic islands in a genome, as well as the corresponding supportive feature information for GIs. GIV was implemented in C++, and was compiled and executed on Linux/Unix operating systems.

Availability

GIV is freely available for non-commercial use at http://www5.esu.edu/cpsc/bioinfo/software/GIV     

PredPPCrys: Accurate Prediction of Sequence Cloning,Protein Production,Purification and Crystallization Propensity from Protein Sequences Using Multi-Step Heterogeneous Feature Fusion and Selection

X-ray crystallography is the primary approach to solve the three-dimensional structure of a protein. However, a major bottleneck of this method is the failure of multi-step experimental procedures to yield diffraction-quality crystals, including sequence cloning, protein material production, purification, crystallization and ultimately, structural determination. Accordingly, prediction of the propensity of a protein to successfully undergo these experimental procedures based on the protein sequence may help narrow down laborious experimental efforts and facilitate target selection. A number of bioinformatics methods based on protein sequence information have been developed for this purpose. However, our knowledge on the important determinants of propensity for a protein sequence to produce high diffraction-quality crystals remains largely incomplete. In practice, most of the existing methods display poorer performance when evaluated on larger and updated datasets. To address this problem, we constructed an up-to-date dataset as the benchmark, and subsequently developed a new approach termed ‘PredPPCrys’ using the support vector machine (SVM). Using a comprehensive set of multifaceted sequence-derived features in combination with a novel multi-step feature selection strategy, we identified and characterized the relative importance and contribution of each feature type to the prediction performance of five individual experimental steps required for successful crystallization. The resulting optimal candidate features were used as inputs to build the first-level SVM predictor (PredPPCrys I). Next, prediction outputs of PredPPCrys I were used as the input to build second-level SVM classifiers (PredPPCrys II), which led to significantly enhanced prediction performance. Benchmarking experiments indicated that our PredPPCrys method outperforms most existing procedures on both up-to-date and previous datasets. In addition, the predicted crystallization targets of currently non-crystallizable proteins were provided as compendium data, which are anticipated to facilitate target selection and design for the worldwide structural genomics consortium. PredPPCrys is freely available at http://www.structbioinfor.org/PredPPCrys.     

EPMLR: sequence-based linear B-cell epitope prediction method using multiple linear regression

Background

B-cell epitopes have been studied extensively due to their immunological applications, such as peptide-based vaccine development, antibody production, and disease diagnosis and therapy. Despite several decades of research, the accurate prediction of linear B-cell epitopes has remained a challenging task.

Results

In this work, based on the antigen’s primary sequence information, a novel linear B-cell epitope prediction model was developed using the multiple linear regression (MLR). A 10-fold cross-validation test on a large non-redundant dataset was performed to evaluate the performance of our model. To alleviate the problem caused by the noise of negative dataset, 300 experiments utilizing 300 sub-datasets were performed. We achieved overall sensitivity of 81.8%, precision of 64.1% and area under the receiver operating characteristic curve (AUC) of 0.728.

Conclusions

We have presented a reliable method for the identification of linear B cell epitope using antigen’s primary sequence information. Moreover, a web server EPMLR has been developed for linear B-cell epitope prediction: http://www.bioinfo.tsinghua.edu.cn/epitope/EPMLR/.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-014-0414-y) contains supplementary material, which is available to authorized users.     

Enhancing protein-vitamin binding residues prediction by multiple heterogeneous subspace SVMs ensemble

Background

Vitamins are typical ligands that play critical roles in various metabolic processes. The accurate identification of the vitamin-binding residues solely based on a protein sequence is of significant importance for the functional annotation of proteins, especially in the post-genomic era, when large volumes of protein sequences are accumulating quickly without being functionally annotated.

Results

In this paper, a new predictor called TargetVita is designed and implemented for predicting protein-vitamin binding residues using protein sequences. In TargetVita, features derived from the position-specific scoring matrix (PSSM), predicted protein secondary structure, and vitamin binding propensity are combined to form the original feature space; then, several feature subspaces are selected by performing different feature selection methods. Finally, based on the selected feature subspaces, heterogeneous SVMs are trained and then ensembled for performing prediction.

Conclusions

The experimental results obtained with four separate vitamin-binding benchmark datasets demonstrate that the proposed TargetVita is superior to the state-of-the-art vitamin-specific predictor, and an average improvement of 10% in terms of the Matthews correlation coefficient (MCC) was achieved over independent validation tests. The TargetVita web server and the datasets used are freely available for academic use at http://csbio.njust.edu.cn/bioinf/TargetVita or http://www.csbio.sjtu.edu.cn/bioinf/TargetVita.

Electronic supplementary material

The online version of this article (doi:10.1186/1471-2105-15-297) contains supplementary material, which is available to authorized users.     

jvenn: an interactive Venn diagram viewer

Background

Venn diagrams are commonly used to display list comparison. In biology, they are widely used to show the differences between gene lists originating from different differential analyses, for instance. They thus allow the comparison between different experimental conditions or between different methods. However, when the number of input lists exceeds four, the diagram becomes difficult to read. Alternative layouts and dynamic display features can improve its use and its readability.

Results

jvenn is a new JavaScript library. It processes lists and produces Venn diagrams. It handles up to six input lists and presents results using classical or Edwards-Venn layouts. User interactions can be controlled and customized. Finally, jvenn can easily be embeded in a web page, allowing to have dynamic Venn diagrams.

Conclusions

jvenn is an open source component for web environments helping scientists to analyze their data. The library package, which comes with full documentation and an example, is freely available at http://bioinfo.genotoul.fr/jvenn.     

CanGeneBase (CGB) ‐ a database on cancer related genes

The advent of genomic and proteomic technologies in this post-genomic era has urged the researchers to develop novel research strategies against cancer by targeting the human genes that would greatly facilitate to identify more promising treatment and to develop accurate early diagnosis for cancer. To harness the power of cancer genetic information towards better treatment we have developed a cancer gene database called CanGeneBase (CGB). It is a comprehensive data collection of cancer-related genes with the intention of helping the researchers to stay on a single platform to gain exclusive information on the genes of their interest. According to the Cancer Gene Data Curation Project, about 4,700 genes have been identified as being related to cancer. The present CanGeneBase covers about 12 different types of cancer which includes 190 unique gene entries. Each entry encompasses about 33 useful parameters to provide detailed information about specific gene. CanGeneBase is made in such a way that it can be easily accessed by either gene symbol or by the type of cancer.

Availability

The database is freely available at http://122.165.25.137/bioinfo/cancerdb/     

CPAD,Curated Protein Aggregation Database: A Repository of Manually Curated Experimental Data on Protein and Peptide Aggregation

Accurate distinction between peptide sequences that can form amyloid-fibrils or amorphous β-aggregates, identification of potential aggregation prone regions in proteins, and prediction of change in aggregation rate of a protein upon mutation(s) are critical to research on protein misfolding diseases, such as Alzheimer’s and Parkinson’s, as well as biotechnological production of protein based therapeutics. We have developed a Curated Protein Aggregation Database (CPAD), which has collected results from experimental studies performed by scientific community aimed at understanding protein/peptide aggregation. CPAD contains more than 2300 experimentally observed aggregation rates upon mutations in known amyloidogenic proteins. Each entry includes numerical values for the following parameters: change in rate of aggregation as measured by fluorescence intensity or turbidity, name and source of the protein, Uniprot and Protein Data Bank codes, single point as well as multiple mutations, and literature citation. The data in CPAD has been supplemented with five different types of additional information: (i) Amyloid fibril forming hexa-peptides, (ii) Amorphous β-aggregating hexa-peptides, (iii) Amyloid fibril forming peptides of different lengths, (iv) Amyloid fibril forming hexa-peptides whose crystal structures are available in the Protein Data Bank (PDB) and (v) Experimentally validated aggregation prone regions found in amyloidogenic proteins. Furthermore, CPAD is linked to other related databases and resources, such as Uniprot, Protein Data Bank, PUBMED, GAP, TANGO, WALTZ etc. We have set up a web interface with different search and display options so that users have the ability to get the data in multiple ways. CPAD is freely available at http://www.iitm.ac.in/bioinfo/CPAD/. The potential applications of CPAD have also been discussed.     

The evolutionary history of topological variations in the CPA/AT transporters

CPA/AT transporters are made up of scaffold and a core domain. The core domain contains two non-canonical helices (broken or reentrant) that mediate the transport of ions, amino acids or other charged compounds. During evolution, these transporters have undergone substantial changes in structure, topology and function. To shed light on these structural transitions, we create models for all families using an integrated topology annotation method. We find that the CPA/AT transporters can be classified into four fold-types based on their structure; (1) the CPA-broken fold-type, (2) the CPA-reentrant fold-type, (3) the BART fold-type, and (4) a previously not described fold-type, the Reentrant-Helix-Reentrant fold-type. Several topological transitions are identified, including the transition between a broken and reentrant helix, one transition between a loop and a reentrant helix, complete changes of orientation, and changes in the number of scaffold helices. These transitions are mainly caused by gene duplication and shuffling events. Structural models, topology information and other details are presented in a searchable database, CPAfold (cpafold.bioinfo.se).