The Open UniversitySkip to content

A Hybrid Genetic Algorithm for 2D FCC Hydrophobic-Hydrophilic Lattice Model to Predict Protein Folding

Houqe, Tamjid; Chetty, Madhu and Dooley, Laurence S. (2006). A Hybrid Genetic Algorithm for 2D FCC Hydrophobic-Hydrophilic Lattice Model to Predict Protein Folding. In: ed. AI 2006: Advances in Artificial Intelligence. Lecture Notes in Computer Science. Springer, pp. 867–876.

DOI (Digital Object Identifier) Link:
Google Scholar: Look up in Google Scholar


This paper presents a Hybrid Genetic Algorithm (HGA) for the protein folding prediction (PFP) applications using the 2D face-centred-cube (FCC) Hydrophobic-Hydrophilic (HP) lattice model. This approach enhances the optimal core formation concept and develops effective and efficient strategies to implement generalized short pull moves to embed highly probable short motifs or building blocks and hence forms the hybridized GA for FCC model. Building blocks containing Hydrophobic (H) – Hydrophilic (P or Polar) covalent bonds are utilized such a way as to help form a core that maximizes the |fitness|. The HGA helps overcome the ineffective crossover and mutation operations that traditionally lead to the stuck condition, especially when the core becomes compact. PFP has been strategically translated into a multi-objective optimization problem and implemented using a swing function, with the HGA providing improved performance in the 2D FCC model compared with the Simple GA.

Item Type: Book Chapter
ISBN: 3-540-49787-0, 978-3-540-49787-5
Academic Unit/Department: Mathematics, Computing and Technology > Computing & Communications
Mathematics, Computing and Technology
Interdisciplinary Research Centre: Centre for Research in Computing (CRC)
Item ID: 10546
Depositing User: Laurence Dooley
Date Deposited: 08 Apr 2008
Last Modified: 14 Jan 2016 16:53
Share this page:


Scopus Citations

▼ Automated document suggestions from open access sources

Actions (login may be required)

Policies | Disclaimer

© The Open University   + 44 (0)870 333 4340