A genome-scale transporter prediction and characterization system called TransportTP that combined homology-based and machine learning methods in a two-phase classification approach. First, traditional homology methods were employed to predict novel transporters based on sequence similarity to known classified proteins in the Transporter Classification Database (TCDB). Second, machine learning methods were used to integrate a variety of features to refine the initial predictions. A set of rules based on transporter features was developed by machine learning using well-curated proteomes as guides.
A web server that implements SVM models. Users can upload or paste protein sequences in Fasta format for transporter and substrate prediction. Six prediction modules have been provided on this web server: an amino acid composition based SVM, an AAIndex based SVM, a PSSM (SwissProt) based SVM, an AAIndex/PSSM (SwissProt) hybrid SVM, a PSSM (UniRef90) based SVM, and an AAIndex/PSSM (UniRef90) hybrid SVM. The TrSSP web server uses the amino acid composition module as the default.
Classification of transporters using efficient RBF networks with PSSM profiles and biochemical properties. Transporter-RBF could be effectively used to identify transporters and discriminating them into different classes and families.
Identifies and classifies efflux proteins in transporters. DeepEfflux associates 2D convolutional neural network (CNN) model with position-specific scoring matrix (PSSM) profiles to discover the hidden features of the data set. It aims to represent a biological sequence with a discrete model or a vector. This tool scans the sequences around the target residue to capture meaningful motif features and even hidden features.
Efflux proteins are membrane proteins, which are involved in the transportation of multidrugs. Efflux-RBF allows the classification of efflux proteins using radial basis function networks with position-specific scoring matrices and biochemical properties.
Realizes de novo prediction of substrates for membrane transporter proteins. TranCEP puts in relationship information based on amino acid composition, evolutionary information, and positional information to proceed. It implements the use of pairwise amino acid composition (PAAC) with evolutionary data in the form of multiple sequence alignments (MSA) with positional information.
Detects prokaryotic nucleobase-ascorbate transporter/nucleobase-cation symporter-2 (NAT/NCS2) transporters. NAT/NCS2 Hound is a web application that allows users to start from a specific protein and assign it to its corresponding subfamily and evolutionary cluster with additional information about substrate profiles and the detected key motifs. This application aims to ease investigation and grasp about homologs.