Class C G-protein-coupled receptors (GPCRs) are cell membrane proteins of great relevance to biology and pharmacology. Previous
research has revealed an upper boundary on the accuracy that can be
achieved in their classification into subtypes from the unaligned transformation of their sequences. To investigate this, we focus on sequences that have been misclassified using supervised methods. These are visualized, using a nonlinear dimensionality reduction technique and phylogenetic trees, and then characterized against the rest of the data and, particularly, against the rest of cases of their own subtype. This should help to discriminate between different types of misclassification and to build hypotheses about database quality problems and the extent to which GPCR sequence transformations limit subtype discriminability. The reported experiments provide a proof of concept for the proposed method.
CitationCárdenas, M.I., Vellido, A., König, C., Alquezar, R., Giraldo, J. Exploratory visualization of misclassified GPCRs from their transformed unaligned sequences using manifold learning techniques. A: International Work-Conference on Bioinformatics and Biomedical Engineering. "Proceedings IWBBIO 2014: International Work-Conference on Bioinformatics and Biomedical Engineering, Granada April, 7-9 2014". Granada: Copicentro Granada, 2014, p. 623-630.
All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder. If you wish to make any use of the work not provided for in the law, please contact: firstname.lastname@example.org