Identification of efflux proteins using efficient radial basis function networks with position‐specific scoring matrices and biochemical properties

Abstract

Efflux proteins are membrane proteins, which are involved in the transportation of multidrugs. The annotation of efflux proteins in genomic sequences would aid to understand the function. Although the percentage of membrane proteins in genomes is estimated to be 25-30%, there is no information about the content of efflux proteins. For annotating such class of proteins it is necessary to develop a reliable method to identify efflux proteins from amino acid sequence information. In this work, we have developed a method based on radial basis function networks using position specific scoring matrices (PSSM) and amino acid properties. We noticed that the C-terminal domain of efflux proteins contain vital information for discrimination. Our method showed an accuracy of 78 and 92% in discriminating efflux proteins from transporters and membrane proteins, respectively using fivefold cross-validation. We utilized our method for annotating the genomes E. coli and P. aeruginosa and it predicted 8.7 and 9.2% of proteins as efflux proteins in these genomes, respectively. The predicted efflux proteins have been compared with available experimental data and we observed a very good agreement between them. Further, we developed a web server for classifying efflux proteins and it is freely available at http://rbf.bioinfo.tw/∼sachen/EFFLUXpredict/Efflux-RBF.php. We suggest that our method could be an effective tool for annotating efflux proteins in genomic sequences.

Recent advances in features generation for membrane protein sequences: From multiple sequence alignment to pre‐trained language models

“…These frequencies are then used to generate a PSSM, which is a matrix of scores that reflects the likelihood of each possible amino acid at each position in the sequence. In recent years, the use of PSSM has gained popularity for protein prediction tasks [4,6,15,27]. PSSM has proven to be effective in many biological function prediction problems by capturing the degree of influence of each of the 20 amino acid substitutions to a given sequence at a specific position.…”

“…One of the most widely used methods for protein sequence analysis is the generation of features from the Position-Specific Scoring Matrix (PSSM) of Multiple Sequence Alignments (MSAs) [13]. This approach utilizes the evolutionary information contained in MSAs to generate a numerical representation of the protein sequence, which can be used for a variety of tasks, including protein classification, function prediction, and drug discovery [4,14,15].…”

Neural Network Based Identification of Trichoderma Species

“…Neural networks have also been employed for classifying proteins. Among most recent works, it can be referred to [25] and [38]. In [25], the authors employed position specific scoring matrices and amino acid properties to provide a technique based on radial basis function networks for identification of efflux proteins.…”

“…Among most recent works, it can be referred to [25] and [38]. In [25], the authors employed position specific scoring matrices and amino acid properties to provide a technique based on radial basis function networks for identification of efflux proteins. In [38], a novel ab initio predictor of protein enzymatic class was presented.…”

GAP: towards almost 100 percent prediction for β-strand-mediated aggregating peptides with distinct morphologies

“…A -strand is a helical repeating pattern with two residues per turn (Creighton, 1993), implying that the residues that are next to each other in the amino acid sequence (K, K þ 1) fall on alternate (opposite) faces of the helix, and the residues that are adjacent to each other on the same face of the helix are separated by a residue in the sequence (K, K þ 2). For each alternate (K, K þ 1; 1-2, 2-3, 3-4, 4-5 and 5-6) and adjacent (K, K þ 2; 1-3, 2-4, 3-5 and 4-6) residue pairs in 139 amyloid (Amyl139) and 168 amorphous -aggregating hexapeptides (Amor168), we have computed frequencies of residue pair types (i,j, where i and j are the 20 amino acids found in proteins) by using the following equation (Gromiha, 2010;Ou et al, 2013):…”