Exploratory Visualization of Misclassified GPCRs from Their Transformed Unaligned Sequences Using Manifold Learning Techniques

摘要: Class C G-protein-coupled receptors (GPCRs) are cell mem- brane 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 unaligned transfor- mation sequences. To investigate this, we focus sequences have been misclassified using supervised methods. These visualized, a nonlinear dimensionality reduction technique phylogenetic trees, then characterized against rest data and, partic- ularly, cases own subtype. This should help discriminate between different types misclassification build hypotheses about database quality problems extent which GPCR sequence transformations limit subtype discriminability. The re- ported experiments provide proof concept for proposed method.