Protein structure prediction based on optimal hydrophobic core formation
- Authors: Nazmul, Rumana , Chetty, Madhu , Samudrala, Ram , Chalmers, David
- Date: 2012
- Type: Text , Conference paper
- Relation: 2012 IEEEE World Congress on Computational Intelligence Intelligence, Piscataway, NJ 10th-15th June 2012 p.1856-1864
- Full Text: false
- Reviewed:
- Description: The prediction of a minimum energy protein structure from its amino acid sequence represents an important and challenging problem in computational biology. In this paper, we propose a novel heuristic approach for protein structure prediction (PSP) based on the concept of optimal hydrophobic core formation. Using 2D HP model, a well-known set of substructures analogous to the secondary structures are obtained. Some sub-conformations are appropriately classified and then incorporated as prior knowledge. Unlike most of the popular PSP approaches which are stochastic in nature, the proposed method is deterministic. The effectiveness of the proposed algorithm is evaluated by well-known benchmark as well as non-benchmark sequences commonly used with 2D HP model. Maintaining similar accuracy as other core based and population based algorithms our method is significantly faster and reduces the computation time as it avoids blind search within the hydrophobic core (H-Core).
Conflict resolution based global search operators for long protein structures prediction
- Authors: Islam, Md , Chetty, Madhu , Murshed, Manzur
- Date: 2011
- Type: Text , Conference paper
- Relation: 18th International Conference on Neural Information Processing, ICONIP 2011; Shanghai; China; 13th to 17th November 2011; published in Neural Information Processing, (Lecture Notes in Computer Science series) Vol. 7062 (1) p.636-645
- Full Text: false
- Reviewed:
- Description: Most population based evolutionary algorithms (EAs) have struggled to accurately predict structure for long protein sequences. This is because conventional operators, i.e., crossover and mutation, cannot satisfy constraints (e.g., connected chain and self-avoiding-walk) of the complex combinatorial multi-modal problem, protein structure prediction (PSP). In this paper, we present novel crossover and mutation operators based on conflict resolution for handling long protein sequences in PSP using lattice models. To our knowledge, this is a pioneering work to address the PSP limitations for long sequences. Experiments carried out with long PDB sequences show the effectiveness of the proposed method. © 2011 Springer-Verlag.