Pairwise energies for polypeptide coarse-grained models derived from atomic force fields

被引:26
作者
Betancourt, Marcos R. [1 ]
Omovie, Sheyore J. [1 ]
机构
[1] Indiana Univ Purdue Univ, Dept Phys, Indianapolis, IN 46202 USA
关键词
biochemistry; biology computing; Boltzmann equation; knowledge based systems; molecular biophysics; molecular dynamics method; polymers; proteins; PROTEIN-STRUCTURE SIMULATIONS; QUASI-CHEMICAL APPROXIMATION; AMINO-ACIDS; STATISTICAL POTENTIALS; BIOMOLECULAR SYSTEMS; STRUCTURE PREDICTION; GLOBULAR-PROTEINS; CONTACT ENERGIES; CONFORMATIONS; REPRESENTATION;
D O I
10.1063/1.3137045
中图分类号
O64 [物理化学(理论化学)、化学物理学];
学科分类号
070304 ; 081704 ;
摘要
The energy parametrization of geometrically simplified versions of polypeptides, better known as polypeptide or protein coarse-grained models, is obtained from molecular dynamics and statistical methods. Residue pairwise interactions are derived by performing atomic-level simulations in explicit water for all 210 pairs of amino acids, where the amino acids are modified to closer match their structure and charges in polypeptides. Radial density functions are computed from equilibrium simulations for each pair of residues, from which statistical energies are extracted using the Boltzmann inversion method. The resulting models are compared to similar potentials obtained by knowledge based methods and to hydrophobic scales, resulting in significant similarities in spite of the model simplicity. However, it was found that glutamine, asparagine, lysine, and arginine are more attractive to other residues than anticipated, in part, due to their amphiphilic nature. In addition, equally charged residues appear more repulsive than expected. Difficulties in the calculation of knowledge based potentials and hydrophobicity scale for these cases, as well as sensitivity of the force field to polarization effects are suspected to cause this discrepancy. It is also shown that the coarse-grained model can identify native structures in decoy databases nearly as well as more elaborate knowledge based methods, in spite of its resolution limitations. In a test conducted with several proteins and corresponding decoys, the coarse-grained potential was able to identify the native state structure but not the original atomic force field.
引用
收藏
页数:11
相关论文
共 59 条
[1]   Multiscale modeling of biomolecular systems: in serial and in parallel [J].
Ayton, Gary S. ;
Noid, Will G. ;
Voth, Gregory A. .
CURRENT OPINION IN STRUCTURAL BIOLOGY, 2007, 17 (02) :192-198
[2]   A coarse-grained protein-protein potential derived from an all-atom force field [J].
Basdevant, Nathalie ;
Borgis, Daniel ;
Ha-Duong, Tap .
JOURNAL OF PHYSICAL CHEMISTRY B, 2007, 111 (31) :9390-9399
[3]   Statistical potentials extracted from protein structures: Are these meaningful potentials? [J].
BenNaim, A .
JOURNAL OF CHEMICAL PHYSICS, 1997, 107 (09) :3698-3706
[4]   MULTICANONICAL ALGORITHMS FOR 1ST ORDER PHASE-TRANSITIONS [J].
BERG, BA ;
NEUHAUS, T .
PHYSICS LETTERS B, 1991, 267 (02) :249-253
[5]   Knowledge-based potential for the polypeptide backbone [J].
Betancourt, Marcos R. .
JOURNAL OF PHYSICAL CHEMISTRY B, 2008, 112 (16) :5058-5069
[6]   Another look at the conditions for the extraction of protein knowledge-based potentials [J].
Betancourt, Marcos R. .
PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS, 2009, 76 (01) :72-85
[7]  
Betancourt MR, 1999, PROTEIN SCI, V8, P361
[8]   Protein sequence design by energy landscaping [J].
Betancourt, MR ;
Thirumalai, D .
JOURNAL OF PHYSICAL CHEMISTRY B, 2002, 106 (03) :599-609
[9]   Continuous anisotropic representation of coarse-grained potentials for proteins by spherical harmonics synthesis [J].
Buchete, NV ;
Straub, JE ;
Thirumalai, D .
JOURNAL OF MOLECULAR GRAPHICS & MODELLING, 2004, 22 (05) :441-450
[10]   Orientational potentials extracted from protein structures improve native fold recognition [J].
Buchete, NV ;
Straub, JE ;
Thirumalai, D .
PROTEIN SCIENCE, 2004, 13 (04) :862-874