Multimodal memetic framework for low-resolution protein structure prediction
- Authors: Nazmul, Rumana , Chetty, Madhu , Chowdhury, Ashan
- Date: 2020
- Type: Text , Journal article
- Relation: Swarm and Evolutionary Computation Vol. 52, no. (Feb 2020), p. 14
- Full Text: false
- Reviewed:
- Description: In this paper, we propose a systematic design of evolutionary optimization, namely Multimodal Memetic Framework (MMF), to effectively search the vast complex energy landscape. Our proposed memetic framework is implemented in hierarchical stages with the optimization of each stage performed in parallel in three different states: Exploratory, Exploitative and Central. Each state, with its own set of sub-populations, either explores or exploits by beneficial mixing of potential solutions to direct the search towards a global solution. Instead of implementing identical genetic operators, the proposed approach employs different selection and survival criteria in each state according to their designated task. The Exploratory state employs a knowledge-based initial population generation technique with appropriately tuned genetic operators to guide the search to the "nearest peak". The Exploitative state fine-tunes the individuals representing different regions by applying a building block based local search. Finally, by utilizing the imbibed knowledge from different peaks, the Central state carries out information-exchange among the highly fit solutions for exploring the undiscovered regions. The information exchange employs a novel non-random parental selection technique to distribute the reproduction opportunity intelligently among the individuals for making cross-over more effective. The method has been tested on a set of various benchmark protein sequences for 2D and 3D lattice models. The experimental results demonstrate the superiority of the proposed method over other state-of-the-art algorithms.
mDBN: motif based learning of gene regulatory networks using dynamic Bayesian networks
- Authors: Morshed, Nizamul , Chetty, Madhu , Nguyen, Vinh , Caelli, Terry
- Date: 2013
- Type: Text , Conference paper
- Relation: Proceedings of the Genetic and Evolutionary Computation Conference, GECCO'13, Association for Computing Machinery Inc. (ACM), 2013 p. 279-286
- Full Text: false
- Reviewed:
- Description: Solutions for deriving the most consistent Bayesian gene regulatory network model from given data sets using evolutionary algorithms typically only result in locally optimal solutions.