Computational prediction of type III and IV secreted effectors in gram-negative bacteria

Abstract

In this review, we provide an overview of the methods employed in four recent studies that described novel methods for computational prediction of secreted effectors from type III and IV secretion systems in Gram-negative bacteria. We present the results of these studies in terms of performance at accurately predicting secreted effectors and similarities found between secretion signals that may reflect biologically relevant features for recognition. We discuss the Web-based tools for secreted effector prediction described in these studies and announce the availability of our tool, the SIEVE server (http://www.sysbep.org/sieve). Finally, we assess the accuracies of the three type III effector prediction methods on a small set of proteins not known prior to the development of these tools that we recently discovered and validated using both experimental and computational approaches. Our comparison shows that all methods use similar approaches and, in general, arrive at similar conclusions. We discuss the possibility of an order-dependent motif in the secretion signal, which was a point of disagreement in the studies. Our results show that there may be classes of effectors in which the signal has a loosely defined motif and others in which secretion is dependent only on compositional biases. Computational prediction of secreted effectors from protein sequences represents an important step toward better understanding the interaction between pathogens and hosts.

FIG. 1.

Machine learning approaches to secreted effector identification. Each of the methods described in this review follows a similar process. Step 1, sets of known secreted effectors (positive examples) and proteins that are not secreted or assumed to be not secreted (negative examples) are chosen. Step 2, features of the protein sequence (e.g., amino acid conservation, sequence, phylogenetic distribution, etc.) are derived from all proteins and transformed into a numeric representation. Step 3, a machine learning algorithm (e.g., a support vector machine) learns to discriminate the positive examples from negative examples in a high-dimensional space formed by the chosen protein features. Step 4, the performance of the approach is assessed by applying the model learned in step 3 to independent examples that were not included in the training. Step 5, experimental validation must then be applied to finally determine whether or not a protein is secreted.