Welcome to iBLP

    Bioluminescent proteins are a class of proteins that widely distributed in many living organisms with various mechanisms of light emission including bioluminescence and chemiluminescence from luminous organisms. Identification of BLPs could help to discover many still unknown functions and promise great possibilities for medical and commercial advances. Thus, it is necessary to develop machine learning methods for identifying BLPs, which may provide fast and automatic annotations for candidate BLPs. iBLP is a server for the identification of bioluminescent proteins(BLPs) based on omputational method. In this study, we proposed a novel predicting framework for identifying BLPs based on eXtreme gradient boosting algorithm (XGBoost) and using sequence-derived features namely natural vector method(NV), composition transition distribution (CTD), g-gap dipeptide composition (g-gap DC) and pseudo amino acid composition (PseAAC) to formulate BLPs and non-BLPs samples. Then, we trained one general and three species-specific (bacteria, eukaryote and archaea) models. As a result, the AUC values of 0.920, 0.936, 0.924, 0.969 were achieved in predicting the BLPs in general, bacteria, eukaryote and archaea respectively based on the 10-fold cross-validation. We hope that our webserver will become a useful tool for carbonylation analysis and further experimental researches.