The present tool developed as a part of transporter annotation at substrate level specificity of transporter proteins.
To demonstrate this study, we perform a systematic study of transporter proteins and create an integrative Support
Vector Machine (SVM) based transporter substrate specificity predictor called TrSSP that is based on primary sequence
information such as amino acid composition, AAIndex composition and PSSM profiles. We used to predict on seven classes
of substrate specific transporter (amino acid transporter, anion transporter, cation transporter, electron transporter,
protein/mRNA transporter, sugar transporter and other transporter) as well as transporter/non-transporter through
a five-fold cross-validation, our AAIndex and PSSM based hybrid model achieve an average accuracy 76.69% with
MCC 0.49. Benchmarking of TrSSP server on independent dataset achieve an average accuracy 77.64% with MCC 0.40.
Performance of our model is better than any existing methods and same time it will work for more substrate specific
Five diverse prediction modules based on various features of a protein sequence have been implemented on the World Wide
Web as a dynamic web server 'TrSSP' that provide wider options to the users extracting different features from their query
protein sequences e.g. the simple amino acid composition, sequence-order based dipeptide composition, Position Specific
Scoring Matrix (PSSM), including our best performing hybrid classifier.
Therefore, we believe that 'TrSSP' can serve as a better complement to accurately annotate the Arabidopsis thaliana
proteome. The complete list of subcellular predictions generated through ‘TrSSP’ is available under the