1 - 17 of 17 results

S4TE / Searching algorithm for Type-IV secretion system Effectors

Permits in silico screening of proteobacteria genomes. S4TE predicts type IV effectors (T4Es) based on the combined use of 13 distinctive features. It analyses the genome architecture and its hit content through the visualization of the length and distribution of intergenic regions and the distribution of the hits according to local gene density. The tool is based on characteristics of known T4Es from different bacterial species, genera and even classes.

SSE-ACC / SSE amino acid composition

Permits to represent protein sequence features. SSE-ACC uses amino acid composition (AAC), k-mer composition, and amino acid composition methods to extract concerned features. It is able to generate 100-dimensional feature vectors. The first 60 dimensions are used to describe the frequency of each amino acid in each of the three possible secondary structure elements and the last 40 dimensions represent the frequency of each amino acid having each of the two possible solvent accessibility states.

BEAN / Bacterial Effector Analyzer

An integrated web resource to predict, analyse and store type III secreted effectors (T3SEs). BEAN 2.0 includes three major components. First, it provides an accurate T3SE predictor based on a hybrid approach. Using independent testing data, we show that BEAN 2.0 achieves a sensitivity of 86.05% and a specificity of 100%. Second, it integrates a set of online sequence analysis tools. Users can further perform functional analysis of putative T3SEs in a seamless way, such as subcellular location prediction, functional domain scan and disorder region annotation. Third, it compiles a database covering 1215 experimentally verified T3SEs and constructs two T3SE-related networks that can be used to explore the relationships among T3SEs.

RF T3SPs / Random Forest algorithm for Type III Secreted Proteins

Predicts novel Type III secretion systems (T3SPs) using position-specific residue conservation profiles. RF T3SPs is based on a random forests model. It gives a high receiver operating curve (AUC) of 0.9277 for the 10-fold cross validation and an accuracy of 92.56 per cent for the test set. The tool is able to identify distinct residues for T3SP prediction. It provides help to elucidate the secretion mechanism and accelerate understanding of pathogenic mechanisms.

T346Hunter / Type Three, Four and Six secretion system Hunter

A web-based tool for the identification and localisation of type III, type IV and type VI secretion systems (T3SS, T4SS and T6SS, respectively) clusters in bacterial genomes. T346Hunter makes use of a database of HMM profiles and protein sequences to automatically annotate and localise T3SS, T4SS and T6SS in user-supplied bacterial genomes. By exploring the available scientific literature, we constructed a database of protein components that captures the diversity of these three types of secretion systems. Once the database search is performed and the secretion systems clusters have been localised, the system presents the results in a comprehensive and user-friendly formatted document, which can be accessed online or downloaded. Furthermore, T346Hunter accepts submissions of both complete and unfinished genomes.

T3SS effector prediction

Predicts the existence of type III secretion system (T3SS) signals in amino acid sequences. T3SS effector prediction is a machine learning approach to identify potential T3SS effectors by their N-terminal amino acid sequence using a sliding window procedure in combination with artificial neural networks (ANN, feedforward type) and support vector machine (SVM) classifiers, together with a comprehensive prediction of potential T3SS effectors for 918 bacterial genomes.


Calculates the total amino acid composition (Aac) conditional probability difference, i.e., the likelihood ratio of a sequence being a T3S or a non-T3S protein. With T3_MM, known T3S and non-T3S proteins were found to well approximate two distinct normal distributions. The model could distinguish validated T3S and non-T3S proteins with a 5-fold cross-validation sensitivity of 83.9% at a specificity of 90.3%. T3_MM was also shown to be more robust, accurate, simple, and statistically quantitative, when compared with other T3S protein prediction models.


A specialized database of annotated T3SS effector (T3SE) sequences containing 1089 records from 46 bacterial species compiled from the literature and public protein databases. Procedures have been defined for i) comprehensive annotation of experimental status of effectors, ii) submission and curation review of records by users of the database, and iii) the regular update of T3SEdb existing and new records. Keyword fielded and sequence searches (BLAST, regular expression) are supported for both experimentally verified and hypothetical T3SEs.


Predicts effector proteins secreted by Type IV secretion systems of Gram-negative bacteria. T4EffPred was developed by computing four classes of sequence features such as amino acid composition, residue pair composition, position-specific scoring matrix (PSSM) composition and auto covariance transformation of PSMM profiles to train a support vector machine (SVM)_based classification model. On benchmark tests, the tool can discriminate type-IVA effectors and non-effectors with overover 93% accuracy and discriminate type-IVB effectors and non-effectors with overover 95% accuracy. It is the firstly announced de novo predictor which can widely predict effectors in Gram-negative bactericial genomes.