TrSSP is an integrative Support Vector Machine (SVM) based transporter substrate specificity predictor that is based on primary sequence information such as amino acid composition, AAIndex composition and PSSM profiles.
PPSP is a novel, versatile and comprehensive program which deployed with approach of Bayesian decision theory (BDT). PPSP could predict the potential phosphorylation sites accurately for approximately 70 PK (Protein Kinase) groups.
PhylCRM is a new cis-regulatory module (CRM) prediction algorithm. PhylCRM combines data for individual motif occurances scored on an alignment using previously described MONKEY scoring sheme (Moses et al., Genome Biology 5, R98, 2004) into a single CRM prediction. PhylCRM can scan very long genomic sequences for candidate CRMs by quantifying both motif clustering and conservation across arbitrarily many genomes using an evolutionary model consistent with the phylogeny of the genomes.
PSSpred (Protein Secondary Structure PREDiction) is a simple neural network training algorithm for accurate protein secondary structure prediction. It first collects multiple sequence alignments using PSI-BLAST. Amino-acid frequence and log-odds data with Henikoff weights are then used to train secondary structure, separately, based on the Rumelhart error backpropagation method. The final secondary structure prediction result is a combination of 7 neural network predictors from different profile data and parameters.
DoGSiteScorer is an automated pocket detection and analysis tool. Size, shape and physico-chemical features of automatically predicted pockets are annotated and incorporated into a support vector machine for druggability estimations.
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 (≥0.8) and overall, with an AUROC~0.932.