1 - 33 of 33 results


Provides prediction of protein subcellular localization for Gram-negative bacteria. PSORTb combines several methods, including homology analysis, identification of sorting signals and other motifs, and machine learning methods into an expert system for prediction of five subcellular localizations, given a complete amino acid sequence. This method is also able to handle situations where no prediction is possible, by assigning equal probabilities to each of the localization sites, again avoiding propagation of erroneous predictions.


An extension of the PSORT II program for protein subcellular location prediction. WoLF PSORT converts protein amino acid sequences into numerical localization features; based on sorting signals, amino acid composition and functional motifs such as DNA-binding motifs. After conversion, a simple k-nearest neighbor classifier is used for prediction. Using html, the evidence for each prediction is shown in two ways: (i) a list of proteins of known localization with the most similar localization features to the query, and (ii) tables with detailed information about individual localization features. WoLF PSORT not only provides subcellular localization prediction with competitive accuracy, but also provides detailed information relevant to protein localization to help users to form their own hypotheses.


Simultaneously detects signal peptides and predicts the topology of transmembrane proteins. Philius is a dynamic Bayesian network (DBN)-based approach to transmembrane protein topology prediction. The software is inspired by Phobius and tackles the problem of discriminating among four basic types of proteins: globular (G), globular with a signal peptide (SP+G), transmembrane (TM), and transmembrane with a signal peptide (SP+TM). It also supplies a set of confidence scores with each prediction.

PECAS / Prokaryotic and Eukaryotic Classical Analysis of Secretome

A pipeline for the prediction of secreted proteins. PECAS overcomes previously mentioned next-generation sequencing (NGS) issues and enables potential users to carry out predictions of secreted proteins in a single submission step (through the web interface) avoiding big data management issues. Users can perform classical secretome analysis (which is not currently offered in a pipeline format anywhere) on their sequences of interest by submitting their NGS data in a wide range of formats.


An integrated database providing comprehensive information on type VI secretion systems (T6SSs) in bacteria. SecReT6 offers a unique, readily explorable archive of known and putative T6SSs, and cognate effectors found in bacteria. It currently contains data on 11 167 core T6SS components mapping to 906 T6SSs found in 498 bacterial strains representing 240 species, as well as a collection of over 600 directly relevant references. Also collated and archived were 1340 diverse candidate secreted effectors which were experimentally shown and/or predicted to be delivered by T6SSs into target eukaryotic and/or prokaryotic cells as well as 196 immunity proteins. A broad range of T6SS gene cluster detection and comparative analysis tools are readily accessible via SecReT6, which may aid identification of effectors and immunity proteins around the T6SS core components.


Provides a platform to build reproducible and flexible pipelines for scalable secretome prediction. SecretSanta consists of a set of wrapper functions around a variety of command line tools. Users can pipe intermediate outputs between individual methods, run resource demanding stages in parallel, compare predictions between similar methods and trace back selected steps of the pipeline. It can facilitate comparisons of secretomes across multiple species or under various conditions and can lead to the discovery of novel classes of previously neglected secreted proteins.

HIPSEC / HIgh-level Production of SECreted proteins

Identifies protein characteristics that correlate with the production level of secreted proteins. HIPSEC provides a sequence-based predictor for extracellular protein production by Aspergillus Niger, with the explicit goal of interpreting which combinations of features are most predictive. The interpretation of the underlying model parameters shows that for both data sets similar properties are predictive for extracellular protein production.


A computational predictor that can be used to identify the secretory proteins of malaria parasite based on the protein sequence information alone. During the prediction process a protein sample was formulated with a 60D (dimensional) feature vector formed by incorporating the sequence evolution information into the general form of PseAAC (pseudo amino acid composition) via a grey system model, which is particularly useful for solving complicated problems that are lack of sufficient information or need to process uncertain information. It was observed by the jackknife test that iSMP-Grey achieved an overall success rate of 94.8%, remarkably higher than those by the existing predictors in this area.