Building protein-protein interaction networks for Leishmania species through protein structural information

Abstract

Background: Systematic analysis of a parasite interactome is a key approach to understand different biological processes. It makes possible to elucidate disease mechanisms, to predict protein functions and to select promising targets for drug development. Currently, several approaches for protein interaction prediction for non-model species incorporate only small fractions of the entire proteomes and their interactions. Based on this perspective, this study presents an integration of computational methodologies, protein network predictions and comparative analysis of the protozoan species Leishmania braziliensis and Leishmania infantum. These parasites cause Leishmaniasis, a worldwide distributed and neglected disease, with limited treatment options using currently available drugs.

Results: The predicted interactions were obtained from a meta-approach, applying rigid body docking tests and template-based docking on protein structures predicted by different comparative modeling techniques. In addition, we trained a machine-learning algorithm (Gradient Boosting) using docking information performed on a curated set of positive and negative protein interaction data. Our final model obtained an AUC = 0.88, with recall = 0.69, specificity = 0.88 and precision = 0.83. Using this approach, it was possible to confidently predict 681 protein structures and 6198 protein interactions for L. braziliensis, and 708 protein structures and 7391 protein interactions for L. infantum. The predicted networks were integrated to protein interaction data already available, analyzed using several topological features and used to classify proteins as essential for network stability.

Conclusions: The present study allowed to demonstrate the importance of integrating different methodologies of interaction prediction to increase the coverage of the protein interaction of the studied protocols, besides it made available protein structures and interactions not previously reported.

Fig. 1

Performance evaluation through the AUC values obtained during the 100 training/tests of machine learning models used to predict interaction between proteins. GBM: Gradient Boosting Method; LM: Linear Regression Model; NB: Native Bayer; NN: Neural Network; RF: Random Forest; SVM: Support Vector Machine

Fig. 2

Protein-Protein Interaction Network using Cytoscape 3.5.1. a Network for L. braziliensis. b Network for L. infantum. The networks were colored according to the subcellular location

Fig. 3

Interaction Protein Networks predicted through structural information adding the networks predicted by Rezende et al. [38]. a Network for L. braziliensis. b Network for L. infantum. The networks were colored according with method of prediction interaction used

Fig. 4

Integration of the sub networks formed by the 20 proteins with the highest Degree of connectivity in predicted protein interaction networks of L. braziliensis (a) and L. infantum (b)

Fig. 5

Integration of the sub networks formed by the 20 proteins with the highest value of Bottlenecks in predicted protein interaction networks of L. braziliensis (a) and L. infantum (b)

Fig. 6

Integration of the sub networks formed by the 20 proteins with the highest value of Betweenness Centrality in predicted protein interaction networks of L. braziliensis (a) and L. infantum (b)