Using Parallel Isosurface Extraction in Superficial Molecular Modeling

Abstract

Protein-protein interactions are strictly correlated to the surface shape because beside a large number of structural amino acids composing the core there are few superficial amino acids that define the functionality. This study concerns the development of a tool that starting from the 3D atomic coordinates of a protein, as retrieved from the protein data bank (PDB), models the macromolecular surface in an implicit way using an approach that is more suitable for this kind of analysis than the parametric one. The marching cubes algorithm is used to process the volumetric description of the protein obtaining a precise representation of the corresponding surface. Because of the large amount of data to consider in studying whole protein families, this algorithm is implemented in parallel on a computer cluster to improve its performance. The parallel version of marching cubes is developed in ASSIST, a high level structured parallel programming system, obtaining a near optimal performance considering computational activities, and acceptable performance including I/O.