Prediction and molecular insights into fungal adhesins and adhesin like proteins

Identification of Toxoplasma gondii adhesins through a machine learning approach

Toxoplasma gondii, as other apicomplexa, employs adhesins transmembrane proteins for binding and invasion to host cells. Search and characterization of adhesins is pivotal in understanding Apicomplexa invasion mechanisms and targeting new druggable candidates. This work developed a machine learning software called ApiPredictor UniQE V2.0, based on two approaches: support vector machines and multilayer perceptron, to predict adhesins proteins from amino acid sequences. By using ApiPredictor UniQE V2.0, five SAG-Related Sequences (SRSs) were identified within the Toxoplasma gondii proteome. One of those candidates, TgSRS12B, was cloned in plasmid pEXP5-CT/TOPO and expressed in E. coli BL21 DE3. The resulting recombinant protein was purified via affinity chromatography. Co-precipitation assays in CaCo and Muller cells showed interactions between TgSRS12B-His-tagged and the membrane fractions from both human cell lines. In conclusion, we demonstrated that ApiPredictor UniQE V2.0, a bioinformatic free software, was able to identify TgSRS12B as a new adhesin protein.

Adhesins in the virulence of opportunistic fungal pathogens of human

Aspergillosis, candidiasis, and cryptococcosis are the most common cause of mycoses-related disease and death among immune-compromised patients. Adhesins are cell-surface exposed proteins or glycoproteins of pathogens that bind to the extracellular matrix (ECM) constituents or mucosal epithelial surfaces of the host cells. The forces of interaction between fungal adhesins and host tissues are accompanied by ligand binding, hydrophobic interactions and protein-protein aggregation. Adherence is the primary and critical step involved in the pathogenesis; however, there is limited information on fungal adhesins compared to that on the bacterial adhesins. Except a few studies based on screening of proteome for adhesin identification, majority are based on characterization of individual adhesins. Recently, based on their characteristic signatures, many putative novel fungal adhesins have been predicted using bioinformatics algorithms. Some of these novel adhesin candidates have been validated by in-vitro studies; though, most of them are yet to be characterised experimentally. Morphotype specific adhesin expression as well as tissue tropism are the crucial determinants for a successful adhesion process. This review presents a comprehensive overview of various studies on fungal adhesins and discusses the targetability of the adhesins and adherence phenomenon, for combating the fungal infection in a preventive or therapeutic mode.

A representation transfer learning approach for enhanced prediction of growth hormone binding proteins

Growth hormone binding proteins (GHBPs) are soluble proteins that play an important role in the modulation of signaling pathways pertaining to growth hormones. GHBPs are selective and bind non-covalently with growth hormones, but their functions are still not fully understood. Identification and characterization of GHBPs are the preliminary steps for understanding their roles in various cellular processes. As wet lab based experimental methods involve high cost and labor, computational methods can facilitate in narrowing down the search space of putative GHBPs. Performance of machine learning algorithms largely depends on the quality of features that it feeds on. Informative and non-redundant features generally result in enhanced performance and for this purpose feature selection algorithms are commonly used. In the present work, a novel representation transfer learning approach is presented for prediction of GHBPs. For their accurate prediction, deep autoencoder based features were extracted and subsequently SMO-PolyK classifier is trained. The prediction model is evaluated by both leave one out cross validation (LOOCV) and hold out independent testing set. On LOOCV, the prediction model achieved 89.8%% accuracy, with 89.4% sensitivity and 90.2% specificity and accuracy of 93.5%, sensitivity of 90.2% and specificity of 96.8% is attained on the hold out testing set. Further a comparison was made between the full set of sequence-based features, top performing sequence features extracted using feature selection algorithm, deep autoencoder based features and generalized low rank model based features on the prediction accuracy. Principal component analysis of the representative features along with t-sne visualization demonstrated the effectiveness of deep features in prediction of GHBPs. The present method is robust and accurate and may complement other wet lab based methods for identification of novel GHBPs.