Mining Conserved Local Structure from Functional Hierarchical Classification via Local Structure Comparison

Abstract

Local region conservation has been observed in recent years and become more and more important in structure biology. Recent researches point out that local conservation regions are correlated to protein functional sites and functions and studies show that some local conservation on sequence or structure are close to binding area. Hence, in order to realize how function works, we can discover local structure region to understand protein function via observation in local conservation. Furthermore, many researches show that function would be activate on the surface of protein structure, but not whole structure and local region conservation can be discovered from sequence, structure or both in current status. Sequence conservation has been discovered in recent researches. There are existing examples which show that structure conservation can be mapped from sequence conservation; however, it is still a problem to mining structure conservation via structure comparison. Structure conservation has become a hot topic to be discussed. Protein function needs to take place in local region to activate the biochemical reaction. Therefore, our motivation is to apply protein structure comparison algorithm to mining local structure conservation. Because these local structure conservations would be used to support structure or provide function, we use functional site to connect the relationship between local structure conservation and protein function. Given functional hierarchical classification, we can easily identify protein function and using proteins with the same EC number to mining or discover conservation which may be related to function. Furthermore, we try to extract local structure region associated to its protein functional site.