Additional file 1 of Label noise in subtype discrimination of class C G protein-coupled receptors: A systematic approach to the analysis of classification errors

This is a csv format file containing the table of 52 frequently misclassified sequences that were common to all four data transformations, as described in the Results section of the main text. It includes the following columns: GPCRDB identifier, GPCRDB true class, and predicted class for, in turn, the AAC, Digram, ACC and PDBT transformations. A strong agreement on the most-often predicted class C GPCR subtypes can be observed. (XLS 22 Kb)