FaaPred: A SVM-Based Prediction Method for Fungal Adhesins and Adhesin-Like Proteins

Abstract

Adhesion constitutes one of the initial stages of infection in microbial diseases and is mediated by adhesins. Hence, identification and comprehensive knowledge of adhesins and adhesin-like proteins is essential to understand adhesin mediated pathogenesis and how to exploit its therapeutic potential. However, the knowledge about fungal adhesins is rudimentary compared to that of bacterial adhesins. In addition to host cell attachment and mating, the fungal adhesins play a significant role in homotypic and xenotypic aggregation, foraging and biofilm formation. Experimental identification of fungal adhesins is labor- as well as time-intensive. In this work, we present a Support Vector Machine (SVM) based method for the prediction of fungal adhesins and adhesin-like proteins. The SVM models were trained with different compositional features, namely, amino acid, dipeptide, multiplet fractions, charge and hydrophobic compositions, as well as PSI-BLAST derived PSSM matrices. The best classifiers are based on compositional properties as well as PSSM and yield an overall accuracy of 86%. The prediction method based on best classifiers is freely accessible as a world wide web based server at http://bioinfo.icgeb.res.in/faap. This work will aid rapid and rational identification of fungal adhesins, expedite the pace of experimental characterization of novel fungal adhesins and enhance our knowledge about role of adhesins in fungal infections.

Immunization with Pneumocystis Cross-Reactive Antigen 1 (Pca1) Protects Mice against Pneumocystis Pneumonia and Generates Antibody to Pneumocystis jirovecii

“…It encodes a 1,099-amino-acid protein of unknown function. Specifically, the protein does not have characteristics typical of fungal adhesins (16). Nor was there significant homology with closely related fungal species such as Schizosaccharomyces pombe.…”

MATEPRED-A-SVM-Based Prediction Method for Multidrug And Toxin Extrusion (MATE) Proteins

“…In order to avoid over fitting, SVM then finds a hyperplane separating the positive data from the negative ones in high dimensional space (Ben-Hur et al, 2008). SVM in this approach was implemented using LibSVM package (http://www.csie.ntu.edu.tw/$cjlin/libsvm/) (Chang and Lin, 2001) which allows us to optimize a number of parameters (Ramana and Gupta, 2009) and to use kernels (e.g., linear, polynomial, radial basis function, sigmoid) for obtaining the best hyperplane (Ramana and Gupta, 2010a). In this study Radial Basis Function (RBF) kernel was used.…”

“…This yields a fixed length input vector of 25 dimensions. where Xm = mean of all positions of hydrophobic amino acids, Xm ¼ P N i¼1 Xi=N; Xi = position of ith hydrophobic amino acid and N = total number of hydrophobic amino acids in the sequence (Ramana and Gupta, 2010a). e) Multiplet composition (MPC): Multiplets are homopolymers (Y) n and yield an input vector of 20-dimensions.where Y is any amino acid repeated n times with n !…”

“…O82855, Q87FN2, Q87IY5, Q87HE9, Q87MO9, Q87FV4, and Q87QD3) ( Table 3) and one protein from Shigella boydii (Accession no Q323U7) (Table 4) are having 12 transmembrane helices predicted using HMMTOP (Tusnády and Simon, 2001) server. These were assigned as 'MATE-like' proteins that could be investigated for their role in drug resistance (Ramana and Gupta, 2010a). We also analyzed for the presence of Pfam and PROSITE which suggested that out of seven proteins, four proteins from Vibrio (Q87FN2, Q87HE9, Q87FV4, and Q87QD3) (Tables 5 and 7) and one from Shigella boydii (Q323U7) (Tables 6 and 8 ) are the members of MFS family, and two more proteins from Vibrio (O82855 and Q87MO9) ( Table 5) belongs to matE family, hence these represent potential MATE proteins.…”

“…Owing to the time limit and cost of experiments, there is a demand to have computational methods to rapidly examine and interpret relevant data (Ramana and Gupta, 2010a). In this study, we attempted to develop a prediction tool for identification of MATE proteins on the basis of Position Specific Scoring Matrix (PSSM) using Support Vector Machine (SVM).…”