Antifreeze proteins (AFPs), known as thermal hysteresis proteins, are ice-binding proteins. AFPs have been found in many fields such as in vertebrates, invertebrates, plants, bacteria, and fungi. Although the function of AFPs is common, the sequences and structures of them show a high degree of diversity. AFPs can be adsorbed in ice crystal surface and inhibit the growth of ice crystals in solution. However, the interaction between AFPs and ice crystal is not completely known for human beings. It is vitally significant to propose an automated means as a high-throughput tool to timely identify the AFPs. Analyzing physicochemical characteristics of AFPs sequences is very significant to understand the ice-protein interaction. In this manuscript, a predictor called "iAFP-Ense" was developed. The operation engine to run the AFPs prediction is an ensemble classifier formed by a voting system to fuse eleven different random forest classifiers based on feature extraction. We also compare our predictor with the AFP-PseAAC via the tenfold cross-validation on the same benchmark dataset. The comparison with the existing methods indicates the new predictor is very promising, meaning that many important key features which are deeply hidden in complicated protein sequences. The predictor used in this article is freely available at http://www.jci-bioinfo.cn/iAFP-Ense .

Enzymes play pivotal roles in most of the biological reaction. The catalytic residues of an enzyme are defined as the amino acids which are directly involved in chemical catalysis; the knowledge of these residues is important for understanding enzyme function. Given an enzyme, which residues are the catalytic sites, and which residues are not? This is the first important problem for in-depth understanding the catalytic mechanism and drug development. With the explosive of protein sequences generated during the post-genomic era, it is highly desirable for both basic research and drug design to develop fast and reliable method for identifying the catalytic sites of enzymes according to their sequences. To address this problem, we proposed a new predictor, called iCataly-PseAAC. In the prediction system, the peptide sample was formulated with sequence evolution information via grey system model GM(2,1). It was observed by the rigorous jackknife test and independent dataset test that iCataly-PseAAC was superior to exist predictions though its only use sequence information. As a user-friendly web server, iCataly-PseAAC is freely accessible at http://www.jci-bioinfo.cn/iCataly-PseAAC. A step-by-step guide has been provided on how to use the web server to get the desired results for the convenience of most experimental scientists.

Abstract. Inoxidizability of proteins is one of the most basic function attribute, and shares a sustainable effect for biological process in protein repair and regulate redox-sensitive signaling pathways. In the genome era, however, it is urgent to design an effective computation method to rapidly detect the antioxidant proteins based on sequence information due to the addition of the larger amount of sequence. We designed a novel automations computational algorithm named "iANOP-Enble". In this predictor, the protein sample was formulated by protein similarity scores matrix and amino acid prosperities information into Random Forest. The process of the new predictor algorithm to identify antioxidants protein is designed as a voting system, which consists of eleven sub-classifiers. In order to verify our algorithm availabilities, we adopted a fair comparison method that used the same bench data set. Finally, the result shows that our algorithm is more promising than existing method on the basis of the same standard of comparison