Misclassification of class C G-protein-coupled receptors as a label noise problem

摘要: G-Protein-Coupled Receptors (GPCRs) are cell membrane proteins of relevance to biology and pharmacology. Their supervised classification in subtypes is hampered by label noise, which stems from a combination expert knowledge limitations lack clear correspondence between labels different representations the protein primary sequences. In this brief study, we describe systematic approach analysis GPCR misclassifications using Support Vector Machines use it assist discovery database labeling quality problems investigate extent sequence physicochemical transformations reflect subtype labeling. The proposed could enable filtering noise problem.