A probabilistic method for annotation of olfactory receptor (OR) pseudogenes. The algorithm assesses the probability of an OR gene with intact open reading frame to encode a non-functional protein (i.e. pseudogene) by examining the deviation of its protein sequences from the OR functionally crucial consensus. The CORP algorithm was tested on a large dataset of OR genes and demonstrated excellent distinction between functional and non-functional ORs.
A web app designed for 3D structure prediction of G protein-coupled receptors. The target sequence is first threaded through the PDB libary by LOMETS to search for putative templates. If homologous templates are identified, a template-based fragment assembly procedure is used to construct full-length models. This procedure is extended from I-TASSER but with a GPCR-specific, knowledge-based force field to guide the structure assembly simulations.
Predicts G protein-coupled receptors (GPCRs) using cellular automaton (CA) data. GPCR-CA utilizes CA to reveal the pattern features hidden in piles of long and complicated protein sequences. Meanwhile, the gray-level co-occurrence matrix factors extracted from the CA images are used to represent the samples of proteins through their pseudo amino acid composition. GPCR-CA is a two-layer predictor: the first layer prediction engine is for identifying a query protein as GPCR on non-GPCR; if it is a GPCR protein, the process will automatically continue with the second-layer prediction engine to further identify its type among the following six functional classes: (a) rhodopsinlike, (b) secretin-like, (c) metabotrophic/glutamate/pheromone; (d) fungal pheromone, (e) cAMP receptor, and (f) frizzled/smoothened family.
Predicts G protein-coupled receptors (GPCRs) at five levels. GPCR-MPredictor first determines whether a protein sequence is a GPCR or a non-GPCR. If the predicted sequence is a GPCR, then it is further classified into family, subfamily, sub-subfamily, and subtype levels. Features are extracted using amino acid composition, pseudo amino acid composition, and dipeptide composition of protein sequences. The proposed hierarchical Genetic algorithm-based ensemble classifier exploits the prediction results of support vector machine (SVM), k-nearest neighbor (KNN), probabilistic neural networks (PNN), and J48 at each level.
0 - 0 of 0