Customised fragments libraries for protein structure prediction based on structural class annotations

摘要: Background Since experimental techniques are time and cost consuming, in silico protein structure prediction is essential to produce conformations of targets. When homologous structures not available, fragment-based has become the approach choice. However, it still many issues including poor performance when targets’ lengths above 100 residues, excessive running times sub-optimal energy functions. Taking advantage reliable structural class software, we propose address some limitations methods by integrating constraints their fragment selection process.