PSI-predictor (Plant Subcellular localization Integrative predictor) is currently the most comprehensive and integrative subcellular location predictor for plants. Based on the wisdom of group-voting and artificial neural network, PSI integrated prediction results from 11 individual predictors to give accurate results on cytosol (cytos), endoplasmic reticulum (ER), extracellular (extra), golgi apparatus (golgi), membrane (membr), mitochondria (mito), nuclear (nucl), peroxisome (pero), plastid (plast) and vacuole (vacu). The community outperformed each individual predictor both on every subcellular location (¡Ý0.8) and overall, with an AUROC~0.932.

   MicroRNAs (miRNA) have been proven to serve as important post-transcription regulators in gene expression. To understand the function of miRNAs, it is necessary to figure out the target gene of miRNAs. Here we developed a novel miRNA target predictor which is based on support vector machine (SVM), a widely-used machine learning approach, combined with feature selection procedure. We considered different types of features including the flanking sequences of the potential targets and pattern information. The features selected were also analyzed to dig out the intrinsic mechanism of miRNA-target interaction.miRPredictor is available at http://bis.zju.edu.cn/mirpredictor/.

   MyBioNet is a web-based application for biological network analysis, which provides user-friendly web interfaces to visualize, edit and merge biological networks. In addition, MyBioNet integrated KEGG metabolic network data from 1366 organisms and allows users to search and navigate interesting networks. All KEGG metabolic network data is organized and stored in the MySQL database. MyBioNet is implemented in Flex/Actionscript and PHP languages and deployed on the Apache web server. MyBioNet is accessible through all the Flash-embedded browsers at http://bis.zju.edu.cn/mybionet/.

   PBSK Browser is a web server designed for processing PSI-MI, BioPAX, SBML and KGML files, which are all common standard pathway file formats widely used in systems biology. By using its query and browse modules users can extract pathway data of their interests from the biological pathway files in the form of HTML tables, translating these pathway files from machine-readable to human-readable.

  VIRS is an interactive web-based program designed for restriction endonuclease cut sites prediction and visualisation.
The system permits to simultaneously process batch DNA sequences, and produces visual restriction maps with several useful options for users' customisation. These options also perform in-depth analysis of the restriction maps, such as virtual electrophoretic result for digested fragments. Different from other analytical tools, VIRS not only displays visual outputs, but also provides the detailed properties of enzymes that are commercially avaialbe. All the information correlates with enzymes is stored in our database, which is updated monthly from the manufacturers' websites.

  Meta Protein WebServer is a meta-server to simplifies the protein structure and function prediction. Beyond providing a unified interface to nonexpert users and streamlined gateway to a selected subset of prediction servers to the bioinformatics community, it also allows fast and easy comparison of the prediction results from multiple predictors.  At present, Meta Protein WebServer provides access to a selected set of high-quality servers in the areas of primary structure prediction, secondary structure prediction, profile searches, tertiary structure prediction and more specialized fields like post-translational modification prediction, topology prediction, etc. We will provide more tools in proteomics prediction and protein interacteomics.