Zhi Liang Ji

SVM-Prot: web-based support vector machine software for functional classification of a protein from its primary sequence

Prediction of protein function is of significance in studying biological processes. One approach for function prediction is to classify a protein into functional family. Support vector machine (SVM) is a useful method for such classification, which may involve proteins with diverse sequence distribution. We have developed a web-based software, SVMProt, for SVM classification of a protein into functional family from its primary sequence. SVMProt classification system is trained from representative proteins of a number of functional families and seed proteins of Pfam curated protein families. It currently covers 54 functional families and additional families will be added in the near future. The computed accuracy for protein family classification is found to be in the range of 69.1-99.6%. SVMProt shows a certain degree of capability for the classification of distantly related proteins and homologous proteins of different function and thus may be used as a protein function prediction tool that complements sequence alignment methods. SVMProt can be accessed at http://jing.cz3.nus.edu.sg/cgi-bin/svmprot.cgi.

TTD: Therapeutic Target Database.

A number of proteins and nucleic acids have been explored as therapeutic targets. These targets are subjects of interest in different areas of biomedical and pharmaceutical research and in the development and evaluation of bioinformatics, molecular modeling, computer-aided drug design and analytical tools. A publicly accessible database that provides comprehensive information about these targets is therefore helpful to the relevant communities. The Therapeutic Target Database (TTD) is designed to provide information about the known therapeutic protein and nucleic acid targets described in the literature, the targeted disease conditions, the pathway information and the corresponding drugs/ligands directed at each of these targets. Cross-links to other databases are also introduced to facilitate the access of information about the sequence, 3D structure, function, nomenclature, drug/ligand binding properties, drug usage and effects, and related literature for each target. This database can be accessed at http://xin.cz3.nus.edu.sg/group/ttd/ttd.asp and it currently contains entries for 433 targets covering 125 disease conditions along with 809 drugs/ligands directed at each of these targets. Each entry can be retrieved through multiple methods including target name, disease name, drug/ligand name, drug/ligand function and drug therapeutic classification.

Enzyme family classification by support vector machines

One approach for facilitating protein function prediction is to classify proteins into functional families. Recent studies on the classification of G‐protein coupled receptors and other proteins suggest that a statistical learning method, Support vector machines (SVM), may be potentially useful for protein classification into functional families. In this work, SVM is applied and tested on the classification of enzymes into functional families defined by the Enzyme Nomenclature Committee of IUBMB. SVM classification system for each family is trained from representative enzymes of that family and seed proteins of Pfam curated protein families. The classification accuracy for enzymes from 46 families and for non‐enzymes is in the range of 50.0% to 95.7% and 79.0% to 100% respectively. The corresponding Matthews correlation coefficient is in the range of 54.1% to 96.1%. Moreover, 80.3% of the 8,291 correctly classified enzymes are uniquely classified into a specific enzyme family by using a scoring function, indicating that SVM may have certain level of unique prediction capability. Testing results also suggest that SVM in some cases is capable of classification of distantly related enzymes and homologous enzymes of different functions. Effort is being made to use a more comprehensive set of enzymes as training sets and to incorporate multi‐class SVM classification systems to further enhance the unique prediction accuracy. Our results suggest the potential of SVM for enzyme family classification and for facilitating protein function prediction. Our software is accessible at http://jing.cz3.nus.edu.sg/cgi‐bin/svmprot.cgi. Proteins 2004.

Therapeutic Targets: Progress of Their Exploration and Investigation of Their Characteristics

Modern drug discovery is primarily based on the search and subsequent testing of drug candidates acting on a preselected therapeutic target. Progress in genomics, protein structure, proteomics, and disease mechanisms has led to a growing interest in and effort for finding new targets and more effective exploration of existing targets. The number of reported targets of marketed and investigational drugs has significantly increased in the past 8 years. There are 1535 targets collected in the therapeutic target database compared with ∼500 targets reported in a 1996 review. Knowledge of these targets is helpful for molecular dissection of the mechanism of action of drugs and for predicting features that guide new drug design and the search for new targets. This article summarizes the progress of target exploration and investigates the characteristics of the currently explored targets to analyze their sequence, structure, family representation, pathway association, tissue distribution, and genome location features for finding clues useful for searching for new targets. Possible “rules” to guide the search for druggable proteins and the feasibility of using a statistical learning method for predicting druggable proteins directly from their sequences are discussed.

The Symbiodinium kawagutii genome illuminates dinoflagellate gene expression and coral symbiosis

Symbionts are adapted to work with corals Many corals have formed mutualistic associations with dinoflagellate symbionts, which are thought to provide nutrients and other benefits. To examine the underlying genetics of this association, S. Lin et al. sequenced the genome of the endosymbiont dinoflagellate Symbiodinium kawagutii. The genome includes gene number expansions and encodes microRNAs that show complementarity to genes within the coral genome. Such microRNAs may be involved in regulating coral genes. Furthermore, coral and S. kawagutii appear to share homologs of genes encoding specific nutrient transporters. The findings shed light on how symbiosis is established and maintained between dinoflagellates and corals. Science, this issue p. 691 The genome of the coral symbiont Symbiodinium reveals fundamental aspects of the coral-alga symbiosis. Dinoflagellates are important components of marine ecosystems and essential coral symbionts, yet little is known about their genomes. We report here on the analysis of a high-quality assembly from the 1180-megabase genome of Symbiodinium kawagutii. We annotated protein-coding genes and identified Symbiodinium-specific gene families. No whole-genome duplication was observed, but instead we found active (retro)transposition and gene family expansion, especially in processes important for successful symbiosis with corals. We also documented genes potentially governing sexual reproduction and cyst formation, novel promoter elements, and a microRNA system potentially regulating gene expression in both symbiont and coral. We found biochemical complementarity between genomes of S. kawagutii and the anthozoan Acropora, indicative of host-symbiont coevolution, providing a resource for studying the molecular basis and evolution of coral symbiosis.

TiSGeD: a database for tissue-specific genes

Summary: The tissue-specific genes are a group of genes whose function and expression are preferred in one or several tissues/cell types. Identification of these genes helps better understanding of tissue–gene relationship, etiology and discovery of novel tissue-specific drug targets. In this study, a statistical method is introduced to detect tissue-specific genes from more than 123 125 gene expression profiles over 107 human tissues, 67 mouse tissues and 30 rat tissues. As a result, a novel subject-specialized repository, namely the tissue-specific genes database (TiSGeD), is developed to represent the analyzed results. Auxiliary information of tissue-specific genes was also collected from biomedical literatures. Availability: http://bioinf.xmu.edu.cn/databases/TiSGeD/index.html Contact: appo@bioinf.xmu.edu.cn; zhiliang.ji@gmail.com

A support vector machines approach for virtual screening of active compounds of single and multiple mechanisms from large libraries at an improved hit-rate and enrichment factor.

Support vector machines (SVM) and other machine-learning (ML) methods have been explored as ligand-based virtual screening (VS) tools for facilitating lead discovery. While exhibiting good hit selection performance, in screening large compound libraries, these methods tend to produce lower hit-rate than those of the best performing VS tools, partly because their training-sets contain limited spectrum of inactive compounds. We tested whether the performance of SVM can be improved by using training-sets of diverse inactive compounds. In retrospective database screening of active compounds of single mechanism (HIV protease inhibitors, DHFR inhibitors, dopamine antagonists) and multiple mechanisms (CNS active agents) from large libraries of 2.986 million compounds, the yields, hit-rates, and enrichment factors of our SVM models are 52.4-78.0%, 4.7-73.8%, and 214-10,543, respectively, compared to those of 62-95%, 0.65-35%, and 20-1200 by structure-based VS and 55-81%, 0.2-0.7%, and 110-795 by other ligand-based VS tools in screening libraries of >or=1 million compounds. The hit-rates are comparable and the enrichment factors are substantially better than the best results of other VS tools. 24.3-87.6% of the predicted hits are outside the known hit families. SVM appears to be potentially useful for facilitating lead discovery in VS of large compound libraries.

miRClassify: An advanced web server for miRNA family classification and annotation

MicroRNA (miRNA) family is a group of miRNAs that derive from the common ancestor. Normally, members from the same miRNA family have similar physiological functions; however, they are not always conserved in primary sequence or secondary structure. Proper family prediction from primary sequence will be helpful for accurate identification and further functional annotation of novel miRNA. Therefore, we introduced a novel machine learning-based web server, the miRClassify, which can rapidly identify miRNA from the primary sequence and classify it into a miRNA family regardless of similarity in sequence and structure. Additionally, the medical implication of the miRNA family is also provided when it is available in PubMed. The web server is accessible at the link http://datamining.xmu.edu.cn/software/MIR/home.html.

Prediction of transporter family from protein sequence by support vector machine approach

Transporters play key roles in cellular transport and metabolic processes, and in facilitating drug delivery and excretion. These proteins are classified into families based on the transporter classification (TC) system. Determination of the TC family of transporters facilitates the study of their cellular and pharmacological functions. Methods for predicting TC family without sequence alignments or clustering are particularly useful for studying novel transporters whose function cannot be determined by sequence similarity. This work explores the use of a machine learning method, support vector machines (SVMs), for predicting the family of transporters from their sequence without the use of sequence similarity. A total of 10,636 transporters in 13 TC subclasses, 1914 transporters in eight TC families, and 168,341 nontransporter proteins are used to train and test the SVM prediction system. Testing results by using a separate set of 4351 transporters and 83,151 nontransporter proteins show that the overall accuracy for predicting members of these TC subclasses and families is 83.4% and 88.0%, respectively, and that of nonmembers is 99.3% and 96.6%, respectively. The accuracies for predicting members and nonmembers of individual TC subclasses are in the range of 70.7–96.1% and 97.6–99.9%, respectively, and those of individual TC families are in the range of 60.6–97.1% and 91.5–99.4%, respectively. A further test by using 26,139 transmembrane proteins outside each of the 13 TC subclasses shows that 90.4–99.6% of these are correctly predicted. Our study suggests that the SVM is potentially useful for facilitating functional study of transporters irrespective of sequence similarity. Proteins 2006.

Drug Adverse Reaction target Database (DART): Proteins related to adverse drug reactions

An adverse drug reaction (ADR) often results from interaction of a drug or its metabolites with specific protein targets important in normal cellular function. Knowledge about these targets is both important in facilitating the study of the mechanisms of ADRs and in new drug discovery. It is also useful in the development and testing of rational drug design and safety evaluation tools. The Drug Adverse Reaction Database (DART) is intended to provide comprehensive information about adverse effect targets of drugs described in the literature. Moreover, proteins involved in adverse effect targets of chemicals not yet confirmed as ADR targets are also included as potential targets. This database gives physiological function of each target, binding drugs/agonists/antagonists/activators/inhibitors, IC50 values of the inhibitors, corresponding adverse effects, and type of ADR induced by drug binding to a target. Cross-links to other databases are also introduced to facilitate the access of information about the sequence, 3-dimensional structure, function, and nomenclature of each target along with drug/ligand binding properties, and related literature. The database currently contains entries for 147 ADR targets and 89 potential targets. A total of 187 adverse reaction conditions, 257 drugs, and 1080 ligands known to bind to each of these targets are also currently described. Each entry can be retrieved through multiple search methods including target name, target physiological function, adverse effect, ligand name, and biological pathways. A special page is provided for contribution of new or additional information. This database can be accessed at http://xin.cz3.nus.edu.sg/group/drt/dart.asp.