A knowledge-based initial population generation in memetic algorithm for protein structure prediction
- Authors: Nazmul, Rumana , Chetty, Madhu
- Date: 2013
- Type: Text , Conference paper
- Relation: 20th International Conference, ICONIP 2013 p. 546-553
- Full Text: false
- Reviewed:
- Description: Predicting the minimum energy protein structure from its amino acid sequence, even under the rather simplified HP lattice model, continues to be an important and challenging problem in computational biology. In this paper, we propose a novel initial population generation strategy for evolutionary algorithm incorporating domain knowledge based on the concept of maximum hydrophobic core formation for Protein structure prediction (PSP) problem. The proposed technique helps the optimization process to commence with diverse seeds and thereby aids in converging to the global solution quickly. The experimental results, conducted on PSP problem using HP benchmark sequences for 2D square and 3D cubic lattice model, demonstrate that the proposed evolutionary algorithm with new core-based population initialization technique is very effective in improving the optimization process in terms of convergence as well as in achieving the optimal energy.
A Markov-blanket-based model for gene regulatory network inference
- Authors: Ram, Ramesh , Chetty, Madhu
- Date: 2011
- Type: Text , Journal article
- Relation: Transactions on Computational Biology and Bioinformatics Vol. 8, no. 2 (2011), p.
- Full Text: false
- Reviewed:
- Description: An efficient two-step Markov blanket method for modeling and inferring complex regulatory networks from large-scale microarray data sets is presented. The inferred gene regulatory network (GRN) is based on the time series gene expression data capturing the underlying gene interactions. For constructing a highly accurate GRN, the proposed method performs: 1) discovery of a gene's Markov Blanket (MB), 2) formulation of a flexible measure to determine the network's quality, 3) efficient searching with the aid of a guided genetic algorithm, and 4) pruning to obtain a minimal set of correct interactions. Investigations are carried out using both synthetic as well as yeast cell cycle gene expression data sets. The realistic synthetic data sets validate the robustness of the method by varying topology, sample size, time delay, noise, vertex in-degree, and the presence of hidden nodes. It is shown that the proposed approach has excellent inferential capabilities and high accuracy even in the presence of noise. The gene network inferred from yeast cell cycle data is investigated for its biological relevance using well-known interactions, sequence analysis, motif patterns, and GO data. Further, novel interactions are predicted for the unknown genes of the network and their influence on other genes is also discussed.
A memetic approach to protein structure prediction in triangular lattices
- Authors: Islam, Md , Chetty, Madhu , Ullah, Abu , Steinhofel, Kathleen
- Date: 2011
- Type: Text , Conference paper
- Relation: 18th International Conference on Neural Information Processing, ICONIP 2011; Shanghai; China; 13- 17th November 2011; published in Neural Information Processing, (Lecture Notes in Computer Science series) Vol. 7062 p. 625-635
- Full Text: false
- Reviewed:
- Description: Protein structure prediction (PSP) remains one of the most challenging open problems in structural bioinformatics. Simplified models in terms of lattice structure and energy function have been proposed to ease the computational hardness of this combinatorial optimization problem. In this paper, we describe a clustered meme-based evolutionary approach for PSP using triangular lattice model. Under the framework of memetic algorithm, the proposed method extracts a pool of cultural information from different regions of the search space using data clustering technique. These highly observed local substructures, termed as meme, are then aggregated centrally for further refinements as second stage of evolution. The optimal utilization of 'explore-and-exploit' feature of evolutionary algorithms is ensured by the inherent parallel architecture of the algorithm and subsequent use of cultural information.
A model of the circadian clock in the cyanobacterium Cyanothece sp. ATCC 51142
- Authors: Nguyen, Vinh , Chetty, Madhu , Coppel, Ross , Gaudana, Sandeep , Wangikar, Pramod
- Date: 2013
- Type: Text , Journal article
- Relation: BMC Bioinformatics Vol. 14, no. (Supplement 2) (2013), p. s14-1-s14-9
- Full Text:
- Reviewed:
- Description: Background The over consumption of fossil fuels has led to growing concerns over climate change and global warming. Increasing research activities have been carried out towards alternative viable biofuel sources. Of several different biofuel platforms, cyanobacteria possess great potential, for their ability to accumulate biomass tens of times faster than traditional oilseed crops. The cyanobacterium Cyanothece sp. ATCC 51142 has recently attracted lots of research interest as a model organism for such research. Cyanothece can perform efficiently both photosynthesis and nitrogen fixation within the same cell, and has been recently shown to produce biohydrogen--a byproduct of nitrogen fixation--at very high rates of several folds higher than previously described hydrogen-producing photosynthetic microbes. Since the key enzyme for nitrogen fixation is very sensitive to oxygen produced by photosynthesis, Cyanothece employs a sophisticated temporal separation scheme, where nitrogen fixation occurs at night and photosynthesis at day. At the core of this temporal separation scheme is a robust clocking mechanism, which so far has not been thoroughly studied. Understanding how this circadian clock interacts with and harmonizes global transcription of key cellular processes is one of the keys to realize the inherent potential of this organism. Results In this paper, we employ several state of the art bioinformatics techniques for studying the core circadian clock in Cyanothece sp. ATCC 51142, and its interactions with other key cellular processes. We employ comparative genomics techniques to map the circadian clock genes and genetic interactions from another cyanobacterial species, namely Synechococcus elongatus PCC 7942, of which the circadian clock has been much more thoroughly investigated. Using time series gene expression data for Cyanothece, we employ gene regulatory network reconstruction techniques to learn this network de novo, and compare the reconstructed network against the interactions currently reported in the literature. Next, we build a computational model of the interactions between the core clock and other cellular processes, and show how this model can predict the behaviour of the system under changing environmental conditions. The constructed models significantly advance our understanding of the Cyanothece circadian clock functional mechanisms.
A priority based parental selection method for genetic algorithm
- Authors: Nazmul, Rumana , Chetty, Madhu
- Date: 2013
- Type: Text , Conference paper
- Relation: GECCO '13 , Amsterdam, July 6th-10th, 2013 ; published in Proceedings of the 15th annual conference companion on Genetic and evolutionary computation pg.125-126
- Full Text: false
- Reviewed:
- Description: Selection is an important and critical aspect in evolutionary computation. This paper presents a novel parental selection technique that includes the advantages of both the deterministic and the stochastic selection techniques and helps to reduce the loss of diversity by distributing the reproduction opportunity among all the members of the population. Moreover, the proposed selection strategy promotes the concept of non-random mating by clustering the population into groups according to the fitness values and then by persuading the mating between individuals from different groups based on performance determined dynamically over the evolution. Computational results using widely used benchmark functions show significant improvements in the convergence characteristics of the proposed selection method over two well-known selection techniques.
A robust ensemble regression model for reconstructing genetic networks
- Authors: Gamage, Hasini , Chetty, Madhu , Lim, Suryani , Hallinan, Jennifer , Nguyen, H.
- Date: 2023
- Type: Text , Conference paper
- Relation: 2023 International Joint Conference on Neural Networks, IJCNN 2023 Vol. 2023-June
- Full Text: false
- Reviewed:
- Description: Genetic networks contain important information about biological processes, including regulatory relationships and gene-gene interactions. Numerous methods, using high-dimensional gene expression data have been developed to capture these interactions. These gene expression data, generated using high-throughput technologies, are prone to noise. However, most existing network inference methods are unable to cope with noisy data, making genetic network reconstruction challenging. In this paper, we propose a novel ensemble regression model combining quantile regression and cross-validated Ridge regression, RidgeCV, to infer interactions from noisy gene expression data. The application of quantile regression to GRN inference is novel, and its design makes it appropriate for noisy data. RidgeCV also addresses other important issues, such as data overfitting and multicollinearity. First, each regression method is independently applied to gene expression data and the output of these methods, in the form of ranked gene lists, is aggregated using a novel gene score-based method by considering the gene rank and model importance. The model importance score is evaluated based on an adjusted coefficient of determination. This method implicitly includes majority voting by averaging each gene score value across all models. The proposed model was tested on the DREAM4 datasets and publicly available small-scale real-world network datasets. Experiments with noisy datasets showed that the proposed ensemble model is more accurate and efficient than other state-of-the-art methods. © 2023 IEEE.
A study on the importance of differential prioritization in feature selection using toy datasets
- Authors: Ooi, Chia , Teng, Shyh , Chetty, Madhu
- Date: 2008
- Type: Text , Conference paper
- Relation: Third IAPR International Conference, PRIB
- Full Text: false
- Reviewed:
- Description: Previous empirical works have shown the effectiveness of differential prioritization in feature selection prior to molecular classification. We now propose to determine the theoretical basis for the concept of differential prioritization through mathematical analyses of the characteristics of predictor sets found using different values of the DDP (degree of differential prioritization) from realistic toy datasets. Mathematical analyses based on analytical measures such as distance between classes are implemented on these predictor sets. We demonstrate that the optimal value of the DDP is capable of forming a predictor set which consists of classes of features which are well separated and are highly correlated to the target classes – a characteristic of a truly optimal predictor set. From these analyses, the necessity of adjusting the DDP based on the dataset of interest is confirmed in a mathematical manner, indicating that the DDP-based feature selection technique is superior to both simplistic rank-based selection and state-of-the-art equal-priorities scoring methods. Applying similar analyses to real-life multiclass microarray datasets, we obtain further proof of the theoretical significance of the DDP for practical applications
Adaptive regulatory genes cardinality for reconstructing genetic networks
- Authors: Chowdhury, Ahsan , Chetty, Madhu , Vinh, Nguyen
- Date: 2012
- Type: Text , Conference paper
- Relation: WCCI 2012 IEEE World Congress on Computational Intelligence
- Full Text: false
- Reviewed:
- Description: With the advent of microarray technology, researchers are able to determine cellular dynamics for thousands of genes simultaneously, thereby enabling reverse engineering of the gene regulatory network (GRN) from high-throughput time-series gene expression data. Amongst the various currently available models for inferring GRN, the S-System formalism is often considered as an excellent compromise between accuracy and mathematical tractability. In this paper, a novel approach for inferring GRN based on the decoupled S-System model, incorporating the new concept of adaptive regulatory genes cardinality, is proposed. Parameter learning for the S-System is carried out in an evolving manner using a versatile and robust Trigonometric Evolutionary Algorithm. The applicability and efficiency of the proposed method is studied using a well-known and widely studied synthetic network with various levels of noise, and excellent performance observed. Further, investigations of a 5 gene in-vivo synthetic biological network of Saccharomyces cerevisiae called IRMA, has succeeded in detecting higher number of correct regulations compared to other approaches reported earlier.
Adoption of blockchain technology : exploring the factors affecting organizational decision
- Authors: Malik, Saleem , Chadhar, Mehmood , Chetty, Madhu , Vatanasakdakul, Savanid
- Date: 2022
- Type: Text , Journal article , Review
- Relation: Human Behavior and Emerging Technologies Vol. 2022, no. (2022), p.
- Full Text:
- Reviewed:
- Description: Blockchain (BCT) is an emerging technology that promises many benefits for organizations, for instance, disintermediation, data security, data transparency, a single version of the truth, and trust among trading partners. Despite its multiple benefits, the adoption rate of BCT among organizations has not reached a significantly high level worldwide, thus requiring further research in this space. The present study addresses this issue in the Australian context. There is a knowledge gap in what specific factors, among the plethora of factors reported in the extant literature, affect the organizational adoption of BCT in Australia. To fill this gap, the study uses the qualitative interpretative research approach along with the technology-organization-environment (TOE) framework as a theoretical lens. The data was mainly drawn from the literature review and semi-structured interviews of the decision-makers and senior IT people from the BCT adopter and potential adopter organizations in Australia. According to the findings, perceived information transparency, perceived risks, organization innovativeness, organization learning capability, standards uncertainty, and competition intensity influence organizational adoption of BCT in Australia. These factors are exclusively identified in this study. The study also validates the influence of perceived benefits and perceived compatibility on BCT adoption that are reported in the past studies. Practically, these findings are helpful for the Australian government and public and private organizations to develop better policies and make informed decisions for the organizational adoption of BCT. The findings would guide decision-makers to think about the adoption of BCT strategically. The study also has theoretical implications explained in the discussion section. © 2022 Saleem Malik et al.
An adaptive strategy for assortative mating in genetic algorithm
- Authors: Nazmul, Rumana , Chetty, Madhu
- Date: 2013
- Type: Text , Conference paper
- Relation: 2013 IEEE Congress on Evolutionary Computation p. 2237-2244
- Full Text: false
- Reviewed:
- Description: In any traditional Genetic Algorithm (GA), recombination is a dominant search operator and capable of exploring the search space by sharing genetic information among the individuals in the population. However, a simple application of recombination alone is insufficient to guide convergence to an optimal solution. The selection of parents for recombination operation has a significant role in guiding the evolution towards the optimal solution and also for maintaining genetic diversity to avoid getting trapped in local minima. A non-random mating mimics the mechanism of reproduction in nature and is effective in maintaining diversity in population. This paper proposes a new strategy for selection of mating pairs based on a type of non-random mating called as assortative mating. The proposed mate selection scheme conserves the merits of both positive and negative assortative mating in a controlled manner by allowing mating between individuals having both similar and dissimilar phenotypes. For effective cross-over, it maintains genetic diversity in population by distributing the recombination among dissimilar individuals. Furthermore, it ensures the preservation and propagation of useful genetic information to the later stages of search by the selection of mates having similar phenotypes. Experimental results, using not only the five widely used benchmark functions but also twenty newly developed modified functions, are reported. The results show significant improvements in the convergence characteristics of the proposed mating strategy over existing nonrandom mating techniques.
An efficient boolean modelling approach for genetic network inference
- Authors: Gamage, Hasini , Chetty, Madhu , Shatte, Arian , Hallinan, Jennifer
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2021, Virtual, Online, 13-15 October 2021, 2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2021
- Full Text:
- Reviewed:
- Description: The inference of Gene Regulatory Networks (GRNs) from time series gene expression data is an effective approach for unveiling important underlying gene-gene relationships and dynamics. While various computational models exist for accurate inference of GRNs, many are computationally inefficient, and do not focus on simultaneous inference of both network topology and dynamics. In this paper, we introduce a simple, Boolean network model-based solution for efficient inference of GRNs. First, the microarray expression data are discretized using the average gene expression value as a threshold. This step permits an experimental approach of defining the maximum indegree of a network. Next, regulatory genes, including the self-regulations for each target gene, are inferred using estimated multivariate mutual information-based Min-Redundancy Max-Relevance Criterion, and further accurate inference is performed by a swapping operation. Subsequently, we introduce a new method, combining Boolean network regulation modelling and Pearson correlation coefficient to identify the interaction types (inhibition or activation) of the regulatory genes. This method is utilized for the efficient determination of the optimal regulatory rule, consisting AND, OR, and NOT operators, by defining the accurate application of the NOT operation in conjunction and disjunction Boolean functions. The proposed approach is evaluated using two real gene expression datasets for an Escherichia coli gene regulatory network and a fission yeast cell cycle network. Although the Structural Accuracy is approximately the same as existing methods (MIBNI, REVEAL, Best-Fit, BIBN, and CST), the proposed method outperforms all these methods with respect to efficiency and Dynamic Accuracy. © 2021 IEEE.
An exploratory study of the adoption of blockchain technology among Australian organizations : a theoretical model
- Authors: Malik, Saleem , Chadhar, Mehmood , Chetty, Madhu , Vatanasakdakul, Savanid
- Date: 2020
- Type: Text , Conference paper
- Relation: 17th European, Mediterranean, and Middle Eastern Conference on Information Systems, EMCIS 2020; Dubai; 25-26 November 2020 Vol. 402, p. 205-220
- Full Text:
- Reviewed:
- Description: Scholarly and commercial literature indicates several applications of Blockchain Technology (BCT) in different industries e.g. health, finance, supply chain, government, and energy. Despite abundant benefits reported and growing prominence, BCT has been facing various challenges across the globe, including low adoption by organizations. There is a dearth of studies that examined the organizational adoption of blockchain technology, particularly in Australia. This lack of uptake provides the rationale to initiate this research to identify the factors influencing the Australian organizations to adopt BCT. To achieve this, we conducted a qualitative study based on the Technology, Organization, Environment (TOE) framework. The study proposes a theoretical model grounded on the findings of semi-structured interviews of blockchain experts in Australia. The proposed model shows that the organizational adoption of blockchain is influenced by perceived benefits, compatibility, and complexity, organization innovativeness, organizational learning capability, competitive intensity, government support, trading partner readiness, and standards uncertainty. © 2020, Springer Nature Switzerland AG.
An improved memetic approach for protein structure prediction incorporating maximal hydrophobic core estimation concept
- Authors: Nazmul, Rumana , Chetty, Madhu , Chowdhury, Ahsan
- Date: 2021
- Type: Text , Journal article
- Relation: Knowledge-Based Systems Vol. 219, no. (2021), p. 104395
- Full Text: false
- Reviewed:
- Description: Protein Structure Prediction (PSP) from the primary amino acid sequence, even using a simplified Hydrophobic-Polar (HP) lattice model, continues to be extremely challenging. Finding an optimal conformation, even for a small sequence, by any of the currently known evolutionary approaches is computationally extensive and time consuming. Although Memetic Algorithms (MAs) have shown success in finding the optimal solution for PSP, no significant work on the incorporation of domain or problem specific knowledge into the search process to significantly improve their performance is reported. In this paper, we present an approach to incorporate such knowledge into the initial population to enhance the effectiveness of MA for PSP. The domain knowledge we propose to use is based on the concept of maximal ‘core’ formation by exploiting the fundamental property of the H residues to be at the core of the minimum energy optimal protein structure. A generic technique is proposed for estimating the maximal Hydrophobic core (H-core) in a protein sequence for 2D Square, 3D Cubic and a more complex and realistic 3D FCC (Face Centered Cubic) lattice models. Subsequently, the knowledge of this estimated core is incorporated in an MA. The experiments conducted using HP benchmark sequences for 2D Square, 3D Cubic and 3D FCC lattice models show that the proposed MA with the new core-based population initialization technique has superior performance to the existing methods in terms of convergence speed as well as minimal energy. © 2018 Elsevier B.V.
An improved method to infer gene regulatory network using s-system
- Authors: Chowdhury, Ahsan , Chetty, Madhu
- Date: 2011
- Type: Text , Conference paper
- Relation: IEEE Congress on Evolutionary Computation (IEEE CEC) p. 1012-1019
- Full Text: false
- Reviewed:
- Description: Abstract—Gene Regulatory Network (GRN) plays an important role in the understanding of complex biological systems. In most cases, high throughput microarray gene expression data is used for finding these regulatory relationships among genes. In this paper, we present a novel approach, based on decoupled SSystem model, for reverse engineering GRNs. In the proposed method, the genetic algorithm used for scoring the networks contains several useful features for accurate network inference, namely a Prediction Initialization (PI) algorithm to initialize the individuals, a Flip Operation (FO) for better mating of values and a restricted execution of Hill Climbing Local Search over few individuals. It also includes a novel refinement technique which utilizes the fit solutions of the genetic algorithm for optimizing sensitivity and specificity of the inferred network. Comparative studies and robustness analysis using standard benchmark data set show the superiority of the proposed method.
Assessing transformer oil quality using deep convolutional networks
- Authors: Alam, Mohammad , Karmakar, Gour , Islam, Syed , Kamruzzaman, Joarder , Chetty, Madhu , Lim, Suryani , Appuhamillage, Gayan , Chattopadhyay, Gopi , Wilcox, Steve , Verheyen, Vincent
- Date: 2019
- Type: Text , Conference proceedings , Conference paper
- Relation: 29th Australasian Universities Power Engineering Conference, AUPEC 2019
- Full Text:
- Reviewed:
- Description: Electrical power grids comprise a significantly large number of transformers that interconnect power generation, transmission and distribution. These transformers having different MVA ratings are critical assets that require proper maintenance to provide long and uninterrupted electrical service. The mineral oil, an essential component of any transformer, not only provides cooling but also acts as an insulating medium within the transformer. The quality and the key dissolved properties of insulating mineral oil for the transformer are critical with its proper and reliable operation. However, traditional chemical diagnostic methods are expensive and time-consuming. A transformer oil image analysis approach, based on the entropy value of oil, which is inexpensive, effective and quick. However, the inability of entropy to estimate the vital transformer oil properties such as equivalent age, Neutralization Number (NN), dissipation factor (tanδ) and power factor (PF); and many intuitively derived constants usage limit its estimation accuracy. To address this issue, in this paper, we introduce an innovative transformer oil analysis using two deep convolutional learning techniques such as Convolutional Neural Network (ConvNet) and Residual Neural Network (ResNet). These two deep neural networks are chosen for this project as they have superior performance in computer vision. After estimating the equivalent aging year of transformer oil from its image by our proposed method, NN, tanδ and PF are computed using that estimated age. Our deep learning based techniques can accurately predict the transformer oil equivalent age, leading to calculate NN, tanδ and PF more accurately. The root means square error of estimated equivalent age produced by entropy, ConvNet and ResNet based methods are 0.718, 0.122 and 0.065, respectively. ConvNet and ResNet based methods have reduced the error of the oil age estimation by 83% and 91%, respectively compared to that of the entropy method. Our proposed oil image analysis can calculate the equivalent age that is very close to the actual age for all images used in the experiment. © 2019 IEEE.
- Description: E1
Binary-organoid particle swarm optimisation for inferring genetic networks
- Authors: Chanthaphavong, Santi , Chetty, Madhu
- Date: 2010
- Type: Text , Conference paper
- Relation: Evolutionary Computation (CEC), 2010 IEEE Congress
- Full Text: false
- Reviewed:
- Description: A holistic understanding of genetic interactions is crucial in the analysis of complex biological systems. However, due to the dimensionality problem (less samples and large number of genes) of microarray data, obtaining an optimal gene regulatory network is not only difficult but also computationally expensive. In this paper, a Bayesian model for the genetic interactions using the Minimum Description Length as a scoring metric is proposed. For fast optimisation of the network structure, we propose a novel Swarm Intelligence algorithm called Binary-Organoid Particle Swarm (BORG-Swarm). In BORG-Swarm we introduce the concepts of probability threshold vector and particle drift to update particle positions. Experimental studies are carried out using real-life yeast cell cycle dataset. Results indicate that existing binary swarms fail to converge and suffer from long runtimes. In constrast, BORG-Swarm's fast convergence towards the global optimum becomes apparent from results of extensive simulations.
Blockchain based smart auction mechanism for distributed peer-to-peer energy trading
- Authors: Islam, Md Ezazul , Chetty, Madhu , Lim, Suryani , Chadhar, Mehmood , Islam, Syed
- Date: 2022
- Type: Text , Conference paper
- Relation: 55th Annual Hawaii International Conference on System Sciences, HICSS 2022, Virtual, online, 3-7 January 2022, Proceedings of the Annual Hawaii International Conference on System Sciences Vol. 2022-January, p. 6013-6022
- Full Text:
- Reviewed:
- Description: Blockchain based framework provides data immutability in a distributed network. In this paper, we investigate the application of blockchain for peer-to-peer (P2P) energy trading. Traditional energy trading systems use simple passing mechanisms and basic pricing methods, thus adversely affect the efficiency and buyers' social welfare. We propose a blockchain based energy trading mechanism that uses smart passing of unspent auction reservations to (a) minimise the time taken to settle an auction (convergence time), (b) maximise the number of auction settlement; and (c) incorporate second-price auction pricing to maximise buyers' social welfare in a distributed double auction environment. The entire mechanism is implemented within Hyperledger Fabric, an open-source blockchain framework, to manage the data and provide smart contracts. Experiments show that our approach minimises the convergence time, maximises the number of auction settlement, and increases the social welfare of buyers compared to existing methods. © 2022 IEEE Computer Society. All rights reserved.
Challenges and opportunities for blockchain technology adoption : a systematic review
- Authors: Chhina, Shipra , Chadhar, Mehmood , Vatanasakdakul, Savanid , Chetty, Madhu
- Date: 2019
- Type: Text , Conference paper
- Relation: 30th Australasian Conference on Information Systems (ACIS), 9-11 December, Perth (Australia)
- Full Text:
- Reviewed:
- Description: Blockchain technology promises to significantly impact current business processes in industries from various sectors and reduce transactional cost. Firms, suppliers, government, financial institutions etc. are anticipating a business model transformation through blockchain by accomplishing a decentralized architecture of interorganizational dealings without intermediaries. In spite of its immense potential, however, there are key challenges of blockchain implementation which need to be studied for identifying the opportunities arising and for its successful implementations in future. In this paper, we aim to identify these challenges for blockchain adoption and classify them for clearer understanding. To pursue this effectively, this paper follows a hybrid model of systematic literature review. This paper also explicitly enumerates future research opportunities to lead industry and researchers in correct directions
Clustered memetic algorithm for protein structure prediction
- Authors: Islam, M. D. , Chetty, Madhu
- Date: 2010
- Type: Text , Conference paper
- Relation: Evolutionary Computation (CEC), 2010 IEEE Congress
- Full Text:
- Reviewed:
Clustered memetic algorithm with local heuristics for ab initio protein structure prediction
- Authors: Islam, M. D. , Chetty, Madhu
- Date: 2013
- Type: Text , Journal article
- Relation: IEEE Transactions on Evolutionary Computation Vol. 17, no. 4 (2013), p. 558-576
- Full Text: false
- Reviewed:
- Description: Low-resolution protein models are often used within a hierarchical framework for structure prediction. However, even with these simplified but realistic protein models, the search for the optimal solution remains NP complete. The complexity is further compounded by the multimodal nature of the search space. In this paper, we propose a systematic design of an evolutionary search technique, namely the memetic algorithm (MA), to effectively search the vast search space by exploiting the domain-specific knowledge and taking cognizance of the multimodal nature of the search space. The proposed MA achieves this by incorporating various novel features: 1) a modified fitness function includes two additional terms to account for the hydrophobic and polar nature of the residues; 2) a systematic (rather than random) generation of population automatically prevents an occurrence of invalid conformations; 3) a generalized nonisomorphic encoding scheme implicitly eliminates generation of twins (similar conformations) in the population; 4) the identification of a meme (protein substructures) during optimization from different basins of attraction - a process that is equivalent to implicit applications of threading principles; 5) a clustering of the population corresponds to basins of attraction that allows evolution to overcome the complexity of multimodal search space, thereby avoiding search getting trapped in a local optimum; and 6) a 2-stage framework gathers domain knowledge (i.e., substructures or memes) from different basins of attraction for a combined execution in the second stage. Experiments conducted with different lattice models using known benchmark protein sequences and comparisons carried out with recently reported approaches in this journal show that the proposed algorithm has robustness, speed, accuracy, and superior performance. The approach is generic and can easily be extended for applications to other classes of problems.