Here are some web-servers that built by my lab.
POOE
POOE is a support vector machine-based method for predicting oomycete effectors, which use the sequence embeddings from a pre-trained large protein language model (ProtTrans) as input. POOE could achieve a highly accurate performance with an area under the precision-recall curve of 0.804 (area under the receiver operating characteristic curve = 0.893, accuracy = 0.874, precision = 0.777, recall = 0.684, and specificity= 0.936) in the five-fold cross-validation.
read more →DeepAraPPI
DeepAraPPI is an advanced platform designed for predicting protein-protein interactions (PPIs) in Arabidopsis by harnessing sequence, domain, and Gene Ontology (GO) information. The framework of DeepAraPPI includes three integral components: (i) a word2vec encoding-based Siamese recurrent convolutional neural network (RCNN) model; (ii) a Domain2vec encoding-based multiple-layer perceptron (MLP) model; and (iii) a GO2vec encoding-based MLP model
read more →InterSPPI
InterSPPI (v3) is a platform that could predict protein-protein interactions (PPIs) between host and pathogens. Currently, InterSPPI includes Arabidopsis-pathogen(v1.0 & v2.0), human-bacteria and human-virus PPI prediction web server.
read more →WDRR
WDRR is a new WD40 Repeat Recognition method, which uses predicted secondary structure information to generate candidate repeat segments, and further employs a profile-profile alignment to identify the correct WD40 repeats from candidate segments. The source code of WDRR is also available at: https://github.com/grittyy/WDRR.
read more →CKSAAP_OGlySite predictor of mucin-type O-glycosylation sites
As one of the most common protein post-translational modifications, glycosylation is involved in a variety of important biological processes. Computational identification of glycosylation sites in protein sequences becomes increasingly important in the post-genomic era. A new encoding scheme was employed to improve the prediction of mucin-type O-glycosylation sites in mammalian proteins.
read more →TIM-Finder: A TIM-barrel Fold Recognition System
TIM-Finder (Tim-barrel Fold Recognition System) is a computational tool to predict if a query sequence belongs to TIM-barrel protein or not. By integrating sequence evolutionary information, predicted secondary structure, and sequence motif information, TIM-Finder acquired fine performance.
read more →piNet
piNet is a resource for interactively exploring modular network models of plant immune response.
read more →SSEA-OMP
SSEA-OMP (secondary structure element alignment-based outer membrane protein discrimination system) is a web server for outer membrane protein discrimination. The JAVA source code and web server that implements the SSEA algorithm are publicly available.
read more →Type III effector predictor BEAN
BEAN is a machine learning based algorithm to predict type-III effectors in bacterial pathogens.
read more →CKSAAP_UbSite predictor of ubiquitination sites
CKSAAP_UbSite is a web server that could predict ubiquitination sites in proteins.
read more →