Tiantian Zhang, M. Georgiopoulos, G. Anagnostopoulos
Racing algorithms are often used for offline model selection, where models are compared in terms of their average performance over a collection of problems. In this paper, we present a new racing algorithm variant, Max-Race, which makes decisions based on the maximum performance of models. It is an online algorithm, whose goal is to optimally allocate computational resources in a portfolio of evolutionary algorithms, while solving a particular problem instance. It employs a hypothesis test based on extreme value theory in order to decide, which component algorithms to retire, while avoiding unnecessary computations. Experimental results confirm that Max-Race is able to identify the best individual with high precision and low computational overhead. When used as a scheme to select the best from a portfolio of algorithms, the results compare favorably to the ones of other popular algorithm portfolio approaches.
{"title":"Online model racing based on extreme performance","authors":"Tiantian Zhang, M. Georgiopoulos, G. Anagnostopoulos","doi":"10.1145/2576768.2598336","DOIUrl":"https://doi.org/10.1145/2576768.2598336","url":null,"abstract":"Racing algorithms are often used for offline model selection, where models are compared in terms of their average performance over a collection of problems. In this paper, we present a new racing algorithm variant, Max-Race, which makes decisions based on the maximum performance of models. It is an online algorithm, whose goal is to optimally allocate computational resources in a portfolio of evolutionary algorithms, while solving a particular problem instance. It employs a hypothesis test based on extreme value theory in order to decide, which component algorithms to retire, while avoiding unnecessary computations. Experimental results confirm that Max-Race is able to identify the best individual with high precision and low computational overhead. When used as a scheme to select the best from a portfolio of algorithms, the results compare favorably to the ones of other popular algorithm portfolio approaches.","PeriodicalId":123241,"journal":{"name":"Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115114572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the dynamic traveling salesman problem (DTSP), the weights and vertices of the graph representing the TSP are allowed to change during the optimization. This work first discusses some issues related to the use of evolutionary algorithms in the DTSP. When efficient algorithms used for the static TSP are applied with restart in the DTSP, we observe that only some edges are generally inserted in and removed from the best solutions after the changes. This result indicates a possible beneficial use of memory approaches, usually employed in cyclic dynamic environments. We propose a memory approach and a hybrid approach that combines our memory approach with the elitism-based immigrants genetic algorithm (EIGA). We compare these two algorithms to four existing algorithms and show that memory approaches can be beneficial for the DTSP with random changes.
{"title":"Use of explicit memory in the dynamic traveling salesman problem","authors":"R. Tinós, L. D. Whitley, A. Howe","doi":"10.1145/2576768.2598247","DOIUrl":"https://doi.org/10.1145/2576768.2598247","url":null,"abstract":"In the dynamic traveling salesman problem (DTSP), the weights and vertices of the graph representing the TSP are allowed to change during the optimization. This work first discusses some issues related to the use of evolutionary algorithms in the DTSP. When efficient algorithms used for the static TSP are applied with restart in the DTSP, we observe that only some edges are generally inserted in and removed from the best solutions after the changes. This result indicates a possible beneficial use of memory approaches, usually employed in cyclic dynamic environments. We propose a memory approach and a hybrid approach that combines our memory approach with the elitism-based immigrants genetic algorithm (EIGA). We compare these two algorithms to four existing algorithms and show that memory approaches can be beneficial for the DTSP with random changes.","PeriodicalId":123241,"journal":{"name":"Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115266636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
During the design of complex systems, software architects have to deal with a tangle of abstract artefacts, measures and ideas to discover the most fitting underlying architecture. A common way to structure these systems is in terms of their interacting software components, whose composition and connections need to be properly adjusted. Its abstract and highly combinatorial nature increases the complexity of the problem. In this scenario, Search-based Software Engineering (SBSE) may serve to support this decision making process from initial analysis models, since the discovery of component-based architectures can be formulated as a challenging multiple optimisation problem, where different metrics and configurations can be applied depending on the design requirements and its specific domain. Many-objective optimisation evolutionary algorithms can provide an interesting alternative to classical multi-objective approaches. This paper presents a comparative study of five different algorithms, including an empirical analysis of their behaviour in terms of quality and variety of the returned solutions. Results are also discussed considering those aspects of concern to the expert in the decision making process, like the number and type of architectures found. The analysis of many-objectives algorithms constitutes an important challenge, since some of them have never been explored before in SBSE.
{"title":"On the performance of multiple objective evolutionary algorithms for software architecture discovery","authors":"Aurora Ramírez, J. Romero, Sebastián Ventura","doi":"10.1145/2576768.2598310","DOIUrl":"https://doi.org/10.1145/2576768.2598310","url":null,"abstract":"During the design of complex systems, software architects have to deal with a tangle of abstract artefacts, measures and ideas to discover the most fitting underlying architecture. A common way to structure these systems is in terms of their interacting software components, whose composition and connections need to be properly adjusted. Its abstract and highly combinatorial nature increases the complexity of the problem. In this scenario, Search-based Software Engineering (SBSE) may serve to support this decision making process from initial analysis models, since the discovery of component-based architectures can be formulated as a challenging multiple optimisation problem, where different metrics and configurations can be applied depending on the design requirements and its specific domain. Many-objective optimisation evolutionary algorithms can provide an interesting alternative to classical multi-objective approaches. This paper presents a comparative study of five different algorithms, including an empirical analysis of their behaviour in terms of quality and variety of the returned solutions. Results are also discussed considering those aspects of concern to the expert in the decision making process, like the number and type of architectures found. The analysis of many-objectives algorithms constitutes an important challenge, since some of them have never been explored before in SBSE.","PeriodicalId":123241,"journal":{"name":"Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124396951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Martin Zaefferer, Jörg Stork, Martina Friese, A. Fischbach, B. Naujoks, T. Bartz-Beielstein
Real-world optimization problems may require time consuming and expensive measurements or simulations. Recently, the application of surrogate model-based approaches was extended from continuous to combinatorial spaces. This extension is based on the utilization of suitable distance measures such as Hamming or Swap Distance. In this work, such an extension is implemented for Kriging (Gaussian Process) models. Kriging provides a measure of uncertainty when determining predictions. This can be harnessed to calculate the Expected Improvement (EI) of a candidate solution. In continuous optimization, EI is used in the Efficient Global Optimization (EGO) approach to balance exploitation and exploration for expensive optimization problems. Employing the extended Kriging model, we show for the first time that EGO can successfully be applied to combinatorial optimization problems. We describe necessary adaptations and arising issues as well as experimental results on several test problems. All surrogate models are optimized with a Genetic Algorithm (GA). To yield a comprehensive comparison, EGO and Kriging are compared to an earlier suggested Radial Basis Function Network, a linear modeling approach, as well as model-free optimization with random search and GA. EGO clearly outperforms the competing approaches on most of the tested problem instances.
现实世界的优化问题可能需要耗时和昂贵的测量或模拟。近年来，基于代理模型的方法的应用从连续空间扩展到组合空间。这个扩展是基于适当的距离措施，如汉明或交换距离的利用。在这项工作中，对Kriging(高斯过程)模型实现了这样的扩展。克里格在确定预测时提供了一种不确定性的度量。这可以用来计算候选解决方案的预期改进(EI)。在连续优化中，EI被用于高效全局优化(EGO)方法中，以平衡昂贵优化问题的开采和勘探。利用扩展的Kriging模型，我们首次证明了EGO可以成功地应用于组合优化问题。我们描述了必要的调整和出现的问题，以及几个测试问题的实验结果。所有代理模型均采用遗传算法(GA)进行优化。为了进行全面的比较，EGO和Kriging与早期提出的径向基函数网络(Radial Basis Function Network)、线性建模方法以及随机搜索和遗传算法的无模型优化进行了比较。在大多数测试的问题实例上，EGO明显优于其他竞争方法。
{"title":"Efficient global optimization for combinatorial problems","authors":"Martin Zaefferer, Jörg Stork, Martina Friese, A. Fischbach, B. Naujoks, T. Bartz-Beielstein","doi":"10.1145/2576768.2598282","DOIUrl":"https://doi.org/10.1145/2576768.2598282","url":null,"abstract":"Real-world optimization problems may require time consuming and expensive measurements or simulations. Recently, the application of surrogate model-based approaches was extended from continuous to combinatorial spaces. This extension is based on the utilization of suitable distance measures such as Hamming or Swap Distance. In this work, such an extension is implemented for Kriging (Gaussian Process) models. Kriging provides a measure of uncertainty when determining predictions. This can be harnessed to calculate the Expected Improvement (EI) of a candidate solution. In continuous optimization, EI is used in the Efficient Global Optimization (EGO) approach to balance exploitation and exploration for expensive optimization problems. Employing the extended Kriging model, we show for the first time that EGO can successfully be applied to combinatorial optimization problems. We describe necessary adaptations and arising issues as well as experimental results on several test problems. All surrogate models are optimized with a Genetic Algorithm (GA). To yield a comprehensive comparison, EGO and Kriging are compared to an earlier suggested Radial Basis Function Network, a linear modeling approach, as well as model-free optimization with random search and GA. EGO clearly outperforms the competing approaches on most of the tested problem instances.","PeriodicalId":123241,"journal":{"name":"Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117241719","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Lingbo Li, M. Harman, Emmanuel Letier, Yuanyuan Zhang
Uncertainty is inevitable in real world requirement engineering. It has a significant impact on the feasibility of proposed solutions and thus brings risks to the software release plan. This paper proposes a multi-objective optimization technique, augmented with Monte-Carlo Simulation, that optimizes requirement choices for the three objectives of cost, revenue, and uncertainty. The paper reports the results of an empirical study over four data sets derived from a single real world data set. The results show that the robust optimal solutions obtained by our approach are conservative compared to their corresponding optimal solutions produced by traditional Multi-Objective Next Release Problem. We obtain a robustness improvement of at least 18% at a small cost (a maximum 0.0285 shift in the 2D Pareto-front in the unit space). Surprisingly we found that, though a requirement's cost is correlated with inclusion on the Pareto-front, a requirement's expected revenue is not.
{"title":"Robust next release problem: handling uncertainty during optimization","authors":"Lingbo Li, M. Harman, Emmanuel Letier, Yuanyuan Zhang","doi":"10.1145/2576768.2598334","DOIUrl":"https://doi.org/10.1145/2576768.2598334","url":null,"abstract":"Uncertainty is inevitable in real world requirement engineering. It has a significant impact on the feasibility of proposed solutions and thus brings risks to the software release plan. This paper proposes a multi-objective optimization technique, augmented with Monte-Carlo Simulation, that optimizes requirement choices for the three objectives of cost, revenue, and uncertainty. The paper reports the results of an empirical study over four data sets derived from a single real world data set. The results show that the robust optimal solutions obtained by our approach are conservative compared to their corresponding optimal solutions produced by traditional Multi-Objective Next Release Problem. We obtain a robustness improvement of at least 18% at a small cost (a maximum 0.0285 shift in the 2D Pareto-front in the unit space). Surprisingly we found that, though a requirement's cost is correlated with inclusion on the Pareto-front, a requirement's expected revenue is not.","PeriodicalId":123241,"journal":{"name":"Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121997074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper we propose the first genetic algorithm (GA)-based solver for jigsaw puzzles of unknown puzzle dimensions and unknown piece location and orientation. Our solver uses a novel crossover technique, and sets a new state-of-the-art in terms of the puzzle sizes solved and the accuracy obtained. The results are significantly improved, even when compared to previous solvers assuming known puzzle dimensions. Moreover, the solver successfully contends with a mixed bag of multiple puzzle pieces, assembling simultaneously all puzzles.
{"title":"Genetic algorithm-based solver for very large multiple jigsaw puzzles of unknown dimensions and piece orientation","authors":"Dror Sholomon, Omid David, N. Netanyahu","doi":"10.1145/2576768.2598289","DOIUrl":"https://doi.org/10.1145/2576768.2598289","url":null,"abstract":"In this paper we propose the first genetic algorithm (GA)-based solver for jigsaw puzzles of unknown puzzle dimensions and unknown piece location and orientation. Our solver uses a novel crossover technique, and sets a new state-of-the-art in terms of the puzzle sizes solved and the accuracy obtained. The results are significantly improved, even when compared to previous solvers assuming known puzzle dimensions. Moreover, the solver successfully contends with a mixed bag of multiple puzzle pieces, assembling simultaneously all puzzles.","PeriodicalId":123241,"journal":{"name":"Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128370157","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Multi-modal optimization involves two distinct tasks: identifying promising attraction basins and finding the local optima in these basins. Unfortunately, the second task can interfere with the first task if they are performed simultaneously. Specifically, the promise of an attraction basin is often estimated by the fitness of a single sample solution, so an attraction basin represented by a random sample solution can appear to be less promising than an attraction basin represented by its local optimum. The goal of thresheld convergence is to prevent these biased comparisons by disallowing local search while global search is still in progress. Ideally, thresheld convergence achieves this goal by using a distance threshold that is correlated to the size of the attraction basins in the search space. In this paper, a clustering-based method is developed to identify the scale of the search space which thresheld convergence can then exploit. The proposed method employed in the context of a multi-start particle swarm optimization algorithm has led to large improvements across a broad range of multi-modal problems.
{"title":"Identifying and exploiting the scale of a search space in particle swarm optimization","authors":"Yasser González-Fernández, Stephen Y. Chen","doi":"10.1145/2576768.2598280","DOIUrl":"https://doi.org/10.1145/2576768.2598280","url":null,"abstract":"Multi-modal optimization involves two distinct tasks: identifying promising attraction basins and finding the local optima in these basins. Unfortunately, the second task can interfere with the first task if they are performed simultaneously. Specifically, the promise of an attraction basin is often estimated by the fitness of a single sample solution, so an attraction basin represented by a random sample solution can appear to be less promising than an attraction basin represented by its local optimum. The goal of thresheld convergence is to prevent these biased comparisons by disallowing local search while global search is still in progress. Ideally, thresheld convergence achieves this goal by using a distance threshold that is correlated to the size of the attraction basins in the search space. In this paper, a clustering-based method is developed to identify the scale of the search space which thresheld convergence can then exploit. The proposed method employed in the context of a multi-start particle swarm optimization algorithm has led to large improvements across a broad range of multi-modal problems.","PeriodicalId":123241,"journal":{"name":"Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation","volume":"328 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124298806","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The implicit social structure of population groups have been previously investigated in the literature representing enhancements in the performance of optimization algorithms. Here we introduce an evolutionary algorithm inspired by animal hunting groups (i.e. wolves). The algorithm implicitly maintains diversity in the population and performs higher than two state of the art evolutionary algorithms in the investigated case studies in this article. The case studies are to evolve a hormone-inspired system called AHHS (Artificial Homeostatic Hormone Systems) to develop spatial patterns. The complex spatial patterns are developed in the absence of any explicit spatial information. The results achieved by AHHS are presented and compared with a previous work with Artificial Neural Network (ANNs) indicating higher performance of AHHS.
{"title":"Wolfpack-inspired evolutionary algorithm and a reaction-diffusion-based controller are used for pattern formation","authors":"Payam Zahadat, T. Schmickl","doi":"10.1145/2576768.2598262","DOIUrl":"https://doi.org/10.1145/2576768.2598262","url":null,"abstract":"The implicit social structure of population groups have been previously investigated in the literature representing enhancements in the performance of optimization algorithms. Here we introduce an evolutionary algorithm inspired by animal hunting groups (i.e. wolves). The algorithm implicitly maintains diversity in the population and performs higher than two state of the art evolutionary algorithms in the investigated case studies in this article. The case studies are to evolve a hormone-inspired system called AHHS (Artificial Homeostatic Hormone Systems) to develop spatial patterns. The complex spatial patterns are developed in the absence of any explicit spatial information. The results achieved by AHHS are presented and compared with a previous work with Artificial Neural Network (ANNs) indicating higher performance of AHHS.","PeriodicalId":123241,"journal":{"name":"Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126490232","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper proposes a new Neuro-Evolution (NE) method for automated controller design in agent-based systems. The method is Generational Neuro-Evolution (GeNE), and is comparatively evaluated with established NE methods in a multi-agent predator-prey task. This study is part of an ongoing research goal to derive efficient (minimising convergence time to optimal solutions) and scalable (effective for increasing numbers of agents) controller design methods for adapting agents in neuro-evolutionary multi-agent systems. Dissimilar to comparative NE methods, GeNE employs tiered selection and evaluation as its generational fitness evaluation mechanism and, furthermore, re-initializes the population each generation. Results indicate that GeNE is an appropriate controller design method for achieving efficient and scalable behavior in a multi-agent predator-prey task, where the goal was for multiple predator agents to collectively capture a prey agent. GeNE outperforms comparative NE methods in terms of efficiency (minimising the number of genotype evaluations to attain optimal task performance).
{"title":"Generational neuro-evolution: restart and retry for improvement","authors":"D. Shorten, G. Nitschke","doi":"10.1145/2576768.2598295","DOIUrl":"https://doi.org/10.1145/2576768.2598295","url":null,"abstract":"This paper proposes a new Neuro-Evolution (NE) method for automated controller design in agent-based systems. The method is Generational Neuro-Evolution (GeNE), and is comparatively evaluated with established NE methods in a multi-agent predator-prey task. This study is part of an ongoing research goal to derive efficient (minimising convergence time to optimal solutions) and scalable (effective for increasing numbers of agents) controller design methods for adapting agents in neuro-evolutionary multi-agent systems. Dissimilar to comparative NE methods, GeNE employs tiered selection and evaluation as its generational fitness evaluation mechanism and, furthermore, re-initializes the population each generation. Results indicate that GeNE is an appropriate controller design method for achieving efficient and scalable behavior in a multi-agent predator-prey task, where the goal was for multiple predator agents to collectively capture a prey agent. GeNE outperforms comparative NE methods in terms of efficiency (minimising the number of genotype evaluations to attain optimal task performance).","PeriodicalId":123241,"journal":{"name":"Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126457325","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Genome-scale metabolic modeling using constraint-based analysis is a powerful modeling paradigm for simulating metabolic networks. Models are generated via inference from genome annotations. However, errors in the annotation or the identity of a gene's function could lead to "metabolic inconsistency" rendering simulations infeasible. Uncovering the source of metabolic inconsistency is non-trivial due to network size and complexity. Recently published work uses genetic algorithms for curation by generating pools of models with randomly relaxed mass balance constraints. Models are evolved that allow feasible simulation while minimizing the number of constraints relaxed. Relaxed constraints represent metabolites likely to be the root of metabolic inconsistency. Although effective, the approach can result in numerous false positives. Here we present a strategy, MassChecker, which evaluates all of the relaxed mass balance constraints in each generation prior to the next round of evolution to determine if they had become consistent due to recombination/mutation. If so, these constraints are enforced. This approach was applied to the development of genome-scale metabolic model of B. anthracis. The model consisted of 1,049 reactions and 1,003 metabolites. The result was a 60% reduction in the number of relaxed mass balance constraints, significantly speeding up the curation process.
{"title":"Enhancing genetic algorithm-based genome-scale metabolic network curation efficiency","authors":"Eddy J. Bautista, R. Srivastava","doi":"10.1145/2576768.2598218","DOIUrl":"https://doi.org/10.1145/2576768.2598218","url":null,"abstract":"Genome-scale metabolic modeling using constraint-based analysis is a powerful modeling paradigm for simulating metabolic networks. Models are generated via inference from genome annotations. However, errors in the annotation or the identity of a gene's function could lead to \"metabolic inconsistency\" rendering simulations infeasible. Uncovering the source of metabolic inconsistency is non-trivial due to network size and complexity. Recently published work uses genetic algorithms for curation by generating pools of models with randomly relaxed mass balance constraints. Models are evolved that allow feasible simulation while minimizing the number of constraints relaxed. Relaxed constraints represent metabolites likely to be the root of metabolic inconsistency. Although effective, the approach can result in numerous false positives. Here we present a strategy, MassChecker, which evaluates all of the relaxed mass balance constraints in each generation prior to the next round of evolution to determine if they had become consistent due to recombination/mutation. If so, these constraints are enforced. This approach was applied to the development of genome-scale metabolic model of B. anthracis. The model consisted of 1,049 reactions and 1,003 metabolites. The result was a 60% reduction in the number of relaxed mass balance constraints, significantly speeding up the curation process.","PeriodicalId":123241,"journal":{"name":"Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130033642","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：