Annotation of the Active site Anatomy of Proteins Bioinformatics Approach

Abstract

Discover functional sites from Protein Data Bank (PDB) and annotate them with functional newlineinformation from biomedical literature and online servers . The main idea is to combine the newlineinformation from currently two detached data resources, protein structure information from PDB, newlineand functional annotations of residues from MEDLINE . More speci_cally, this research focuses newlineon the prediction of active sites by data mining recurrent spatial residue con_gurations (3D newlinepattern) in proteins. Contextual features of residues are extracted from biomedical literature to newlineprovide functional annotations. The results from both datasets are then combined to verify newlinepredicted functional sites by evidences of biological function. While existing approaches in newlineprotein structure data mining and biomedical literature mining has been used to generate data for newlineeach research domain, the combination of the datasets is a novel approach in protein newlinebioinformatics research. newline