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.     

A New Supervised Over-Sampling Algorithm with Application to Protein-Nucleotide Binding Residue Prediction

Protein-nucleotide interactions are ubiquitous in a wide variety of biological processes. Accurately identifying interaction residues solely from protein sequences is useful for both protein function annotation and drug design, especially in the post-genomic era, as large volumes of protein data have not been functionally annotated. Protein-nucleotide binding residue prediction is a typical imbalanced learning problem, where binding residues are extremely fewer in number than non-binding residues. Alleviating the severity of class imbalance has been demonstrated to be a promising means of improving the prediction performance of a machine-learning-based predictor for class imbalance problems. However, little attention has been paid to the negative impact of class imbalance on protein-nucleotide binding residue prediction. In this study, we propose a new supervised over-sampling algorithm that synthesizes additional minority class samples to address class imbalance. The experimental results from protein-nucleotide interaction datasets demonstrate that the proposed supervised over-sampling algorithm can relieve the severity of class imbalance and help to improve prediction performance. Based on the proposed over-sampling algorithm, a predictor, called TargetSOS, is implemented for protein-nucleotide binding residue prediction. Cross-validation tests and independent validation tests demonstrate the effectiveness of TargetSOS. The web-server and datasets used in this study are freely available at http://www.csbio.sjtu.edu.cn/bioinf/TargetSOS/.     

GraphBind: protein structural context embedded rules learned by hierarchical graph neural networks for recognizing nucleic-acid-binding residues

Knowledge of the interactions between proteins and nucleic acids is the basis of understanding various biological activities and designing new drugs. How to accurately identify the nucleic-acid-binding residues remains a challenging task. In this paper, we propose an accurate predictor, GraphBind, for identifying nucleic-acid-binding residues on proteins based on an end-to-end graph neural network. Considering that binding sites often behave in highly conservative patterns on local tertiary structures, we first construct graphs based on the structural contexts of target residues and their spatial neighborhood. Then, hierarchical graph neural networks (HGNNs) are used to embed the latent local patterns of structural and bio-physicochemical characteristics for binding residue recognition. We comprehensively evaluate GraphBind on DNA/RNA benchmark datasets. The results demonstrate the superior performance of GraphBind than state-of-the-art methods. Moreover, GraphBind is extended to other ligand-binding residue prediction to verify its generalization capability. Web server of GraphBind is freely available at http://www.csbio.sjtu.edu.cn/bioinf/GraphBind/.     

NeSSM: A Next-Generation Sequencing Simulator for Metagenomics

Background

Metagenomics can reveal the vast majority of microbes that have been missed by traditional cultivation-based methods. Due to its extremely wide range of application areas, fast metagenome sequencing simulation systems with high fidelity are in great demand to facilitate the development and comparison of metagenomics analysis tools.

Results

We present here a customizable metagenome simulation system: NeSSM (Next-generation Sequencing Simulator for Metagenomics). Combining complete genomes currently available, a community composition table, and sequencing parameters, it can simulate metagenome sequencing better than existing systems. Sequencing error models based on the explicit distribution of errors at each base and sequencing coverage bias are incorporated in the simulation. In order to improve the fidelity of simulation, tools are provided by NeSSM to estimate the sequencing error models, sequencing coverage bias and the community composition directly from existing metagenome sequencing data. Currently, NeSSM supports single-end and pair-end sequencing for both 454 and Illumina platforms. In addition, a GPU (graphics processing units) version of NeSSM is also developed to accelerate the simulation. By comparing the simulated sequencing data from NeSSM with experimental metagenome sequencing data, we have demonstrated that NeSSM performs better in many aspects than existing popular metagenome simulators, such as MetaSim, GemSIM and Grinder. The GPU version of NeSSM is more than one-order of magnitude faster than MetaSim.

Conclusions

NeSSM is a fast simulation system for high-throughput metagenome sequencing. It can be helpful to develop tools and evaluate strategies for metagenomics analysis and it’s freely available for academic users at http://cbb.sjtu.edu.cn/~ccwei/pub/software/NeSSM.php.     

Plant-mPLoc: A Top-Down Strategy to Augment the Power for Predicting Plant Protein Subcellular Localization

One of the fundamental goals in proteomics and cell biology is to identify the functions of proteins in various cellular organelles and pathways. Information of subcellular locations of proteins can provide useful insights for revealing their functions and understanding how they interact with each other in cellular network systems. Most of the existing methods in predicting plant protein subcellular localization can only cover three or four location sites, and none of them can be used to deal with multiplex plant proteins that can simultaneously exist at two, or move between, two or more different location sites. Actually, such multiplex proteins might have special biological functions worthy of particular notice. The present study was devoted to improve the existing plant protein subcellular location predictors from the aforementioned two aspects. A new predictor called “Plant-mPLoc” is developed by integrating the gene ontology information, functional domain information, and sequential evolutionary information through three different modes of pseudo amino acid composition. It can be used to identify plant proteins among the following 12 location sites: (1) cell membrane, (2) cell wall, (3) chloroplast, (4) cytoplasm, (5) endoplasmic reticulum, (6) extracellular, (7) Golgi apparatus, (8) mitochondrion, (9) nucleus, (10) peroxisome, (11) plastid, and (12) vacuole. Compared with the existing methods for predicting plant protein subcellular localization, the new predictor is much more powerful and flexible. Particularly, it also has the capacity to deal with multiple-location proteins, which is beyond the reach of any existing predictors specialized for identifying plant protein subcellular localization. As a user-friendly web-server, Plant-mPLoc is freely accessible at http://www.csbio.sjtu.edu.cn/bioinf/plant-multi/. Moreover, for the convenience of the vast majority of experimental scientists, a step-by-step guide is provided on how to use the web-server to get the desired results. It is anticipated that the Plant-mPLoc predictor as presented in this paper will become a very useful tool in plant science as well as all the relevant areas.     

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/     

LAMP: A Database Linking Antimicrobial Peptides

The frequent emergence of drug-resistant bacteria has created an urgent demand for new antimicrobial agents. Traditional methods of novel antibiotic development are almost obsolete. Antimicrobial peptides (AMPs) are now regarded as a potential solution to revive the traditional methods of antibiotic development, although, until now, many AMPs have failed in clinical trials. A comprehensive database of AMPs with information about their antimicrobial activity and cytotoxicity will help promote the process of finding novel AMPs with improved antimicrobial activity and reduced cytotoxicity and eventually accelerate the speed of translating the discovery of new AMPs into clinical or preclinical trials. LAMP, a database linking AMPs, serves as a tool to aid the discovery and design of AMPs as new antimicrobial agents. The current version of LAMP has 5,547 entries, comprising 3,904 natural AMPs and 1,643 synthetic peptides. The database can be queried using either simply keywords or combinatorial conditions searches. Equipped with the detailed antimicrobial activity and cytotoxicity data, the cross-linking and top similar AMPs functions implemented in LAMP will help enhance our current understanding of AMPs and this may speed up the development of new AMPs for medical applications. LAMP is freely available at: http://biotechlab.fudan.edu.cn/database/lamp.     

Pep2Path: Automated Mass Spectrometry-Guided Genome Mining of Peptidic Natural Products

Nonribosomally and ribosomally synthesized bioactive peptides constitute a source of molecules of great biomedical importance, including antibiotics such as penicillin, immunosuppressants such as cyclosporine, and cytostatics such as bleomycin. Recently, an innovative mass-spectrometry-based strategy, peptidogenomics, has been pioneered to effectively mine microbial strains for novel peptidic metabolites. Even though mass-spectrometric peptide detection can be performed quite fast, true high-throughput natural product discovery approaches have still been limited by the inability to rapidly match the identified tandem mass spectra to the gene clusters responsible for the biosynthesis of the corresponding compounds. With Pep2Path, we introduce a software package to fully automate the peptidogenomics approach through the rapid Bayesian probabilistic matching of mass spectra to their corresponding biosynthetic gene clusters. Detailed benchmarking of the method shows that the approach is powerful enough to correctly identify gene clusters even in data sets that consist of hundreds of genomes, which also makes it possible to match compounds from unsequenced organisms to closely related biosynthetic gene clusters in other genomes. Applying Pep2Path to a data set of compounds without known biosynthesis routes, we were able to identify candidate gene clusters for the biosynthesis of five important compounds. Notably, one of these clusters was detected in a genome from a different subphylum of Proteobacteria than that in which the molecule had first been identified. All in all, our approach paves the way towards high-throughput discovery of novel peptidic natural products. Pep2Path is freely available from http://pep2path.sourceforge.net/, implemented in Python, licensed under the GNU General Public License v3 and supported on MS Windows, Linux and Mac OS X.

This is a PLOS Computational Biology Software Article.

     

PaGenBase: A Pattern Gene Database for the Global and Dynamic Understanding of Gene Function

Pattern genes are a group of genes that have a modularized expression behavior under serial physiological conditions. The identification of pattern genes will provide a path toward a global and dynamic understanding of gene functions and their roles in particular biological processes or events, such as development and pathogenesis. In this study, we present PaGenBase, a novel repository for the collection of tissue- and time-specific pattern genes, including specific genes, selective genes, housekeeping genes and repressed genes. The PaGenBase database is now freely accessible at http://bioinf.xmu.edu.cn/PaGenBase/. In the current version (PaGenBase 1.0), the database contains 906,599 pattern genes derived from the literature or from data mining of more than 1,145,277 gene expression profiles in 1,062 distinct samples collected from 11 model organisms. Four statistical parameters were used to quantitatively evaluate the pattern genes. Moreover, three methods (quick search, advanced search and browse) were designed for rapid and customized data retrieval. The potential applications of PaGenBase are also briefly described. In summary, PaGenBase will serve as a resource for the global and dynamic understanding of gene function and will facilitate high-level investigations in a variety of fields, including the study of development, pathogenesis and novel drug discovery.     

BGD: A Database of Bat Genomes

Bats account for ~20% of mammalian species, and are the only mammals with true powered flight. For the sake of their specialized phenotypic traits, many researches have been devoted to examine the evolution of bats. Until now, some whole genome sequences of bats have been assembled and annotated, however, a uniform resource for the annotated bat genomes is still unavailable. To make the extensive data associated with the bat genomes accessible to the general biological communities, we established a Bat Genome Database (BGD). BGD is an open-access, web-available portal that integrates available data of bat genomes and genes. It hosts data from six bat species, including two megabats and four microbats. Users can query the gene annotations using efficient searching engine, and it offers browsable tracks of bat genomes. Furthermore, an easy-to-use phylogenetic analysis tool was also provided to facilitate online phylogeny study of genes. To the best of our knowledge, BGD is the first database of bat genomes. It will extend our understanding of the bat evolution and be advantageous to the bat sequences analysis. BGD is freely available at: http://donglab.ecnu.edu.cn/databases/BatGenome/.     

GMEnzy: A Genetically Modified Enzybiotic Database

GMEs are genetically modified enzybiotics created through molecular engineering approaches to deal with the increasing problem of antibiotic resistance prevalence. We present a fully manually curated database, GMEnzy, which focuses on GMEs and their design strategies, production and purification methods, and biological activity data. GMEnzy collects and integrates all available GMEs and their related information into one web based database. Currently GMEnzy holds 186 GMEs from published literature. The GMEnzy interface is easy to use, and allows users to rapidly retrieve data according to desired search criteria. GMEnzy’s construction will increase the efficiency and convenience of improving these bioactive proteins for specific requirements, and will expand the arsenal available for researches to control drug-resistant pathogens. This database will prove valuable for researchers interested in genetically modified enzybiotics studies. GMEnzy is freely available on the Web at http://biotechlab.fudan.edu.cn/database/gmenzy/.     

Assignment of EC Numbers to Enzymatic Reactions with Reaction Difference Fingerprints

The EC numbers represent enzymes and enzyme genes (genomic information), but they are also utilized as identifiers of enzymatic reactions (chemical information). In the present work (ECAssigner), our newly proposed reaction difference fingerprints (RDF) are applied to assign EC numbers to enzymatic reactions. The fingerprints of reactant molecules minus the fingerprints of product molecules will generate reaction difference fingerprints, which are then used to calculate reaction Euclidean distance, a reaction similarity measurement, of two reactions. The EC number of the most similar training reaction will be assigned to an input reaction. For 5120 balanced enzymatic reactions, the RDF with a fingerprint length at 3 obtained at the sub-subclass, subclass, and main class level with cross-validation accuracies of 83.1%, 86.7%, and 92.6% respectively. Compared with three published methods, ECAssigner is the first fully automatic server for EC number assignment. The EC assignment system (ECAssigner) is freely available via: http://cadd.whu.edu.cn/ecassigner/.