Most proteins function only when folded into a particular 3D configuration. Recently, a class of proteins has been discovered that do not fold into any particular configuration; these are known as Intrinsically Unstructured (IU) proteins. We construct a classifier to identify IU regions in proteins based on features derived from protein sequence information alone, and evaluate it on out-of-sample data. Our results indicate that the resulting classifier represents a viable alternative to existing IU classifiers.
Mary Qu Yang, Jack Y. Yang