Current developments and future directions of bio-inspired computation and implications for ecoinformatics

Evolutionary and neural computation has been used widely in solving various problems in biological ecosystems. This paper reviews some of the recent work in evolutionary computation and neural network ensembles that could be explored further in the context of ecoinformatics. Although these bio-inspired techniques were not developed specifically for ecoinformatics, their successes in solving complex problems in other fields demonstrate how these techniques could be adapted and used for tackling difficult problems in ecoinformatics. Firstly, we will review our work in modelling and model calibration, which is an important topic in ecoinformatics. Secondly one example will be given to illustrate how coevolutionary algorithms could be used in problem-solving. Thirdly, we will describe our work on neural network ensembles, which can be used for various classification and prediction problems in ecoinformatics. Finally, we will discuss ecosystem-inspired computational models and algorithms that could be explored as directions of future research.     

Designing convergent cellular automata

Cellular automata (CA) have been used by biologists to study dynamic non-linear systems where the interaction between cell behaviour and end-pattern is investigated. It is difficult to achieve convergence of a CA towards a specific static pattern and a common solution is to use genetic algorithms and evolve a ruleset that describes cell behaviour. This paper presents an alternative means of designing CA to converge to specific static patterns. A matrix model is introduced and analysed then a design algorithm is demonstrated. The algorithm is significantly less computationally intensive than equivalent evolutionary algorithms, and not limited in scale, complexity or number of dimensions.     

Influence of gene-linkage and recombination of evolutionary algorithms on the rate of evolution, genetic diversity and the response of evolving populations to disturbance

Both biological populations and fault tolerant evolvable hardware systems need to respond rapidly to changes in their dynamic environmental niche. Such changes can be caused by a disturbance event or fault occurring. Here I examine evolutionary algorithms, based on eukaryote sexual selection, which allow different levels of recombination of ‘genes’. The differences in recombination are based on ‘genes’ related to the optimisation process being either linked on a single ‘chromosome’ or being present on separate ‘chromosomes’. When genes are present on separate chromosomes the initial rate of evolution of a randomly generated population is faster than if the genes are linked on the same chromosome. However, when the optimisation problem is changed during the optimisation period, indicating a disturbance or fault occurring, the initial fitness of the linked population is higher and the rate of optimisation immediately after the disturbance is more rapid than for the non-linked populations. The genotypic and phenotypic diversity of the linked populations are also significantly higher immediately prior to the disturbance event. I propose this diversity provides the necessary variation to allow more rapid evolution following a disturbance. The results demonstrate the importance of population diversity in response to change, supporting theory from conservation biology.     

Evolution with material symbol systems

Pattee's semantic closure principle is used to study the characteristics and requirements of evolving material symbols systems. By contrasting agents that reproduce via genetic variation with agents that reproduce via self-inspection, we reach the conclusion that symbols are necessary to attain open-ended evolution, but only if the phenotypes of agents are the result of a material, self-organization process. This way, a study of the inter-dependencies of symbol and matter is presented. This study is based first on a theoretical treatment of symbolic representations, and secondly on simulations of simple agents with matter-symbol inter-dependencies. The agent-based simulations use evolutionary algorithms with indirectly encoded phenotypes. The indirect encoding is based on Fuzzy Development programs, which are procedures for combining fuzzy sets in such a way as to model self-organizing development processes.     

基于狄利克雷多项式过程模型与K-means 结合的菌群分析

群体分型是一种有助于更好的理解人类身心健康等复杂生物学问题的有效方法,聚类是一种为了对样本分组来降低复杂性的定义肠型的方法,而传统K-means聚类算法的K值选取无法确定,本文在传统K-means聚类算法的基础上进行了改进,并公开数据集上进行了验证,实验表明改进算法能够解决K值选取无法确定的问题,且聚类结果的稳定性、准确性和聚类质量都得到显著提高。将改进后的模型运用于肠道菌群OTUs数据,发现不仅能够有效地区分2-型糖尿病患者样本间的相似性,而且能鉴定出影响菌群结构异质性最大的OTUs菌,为临床解决2-型糖尿病问题提供了一种新的思路。     

Finding optimal vaccination strategies for pandemic influenza using genetic algorithms

In the event of pandemic influenza, only limited supplies of vaccine may be available. We use stochastic epidemic simulations, genetic algorithms (GA), and random mutation hill climbing (RMHC) to find optimal vaccine distributions to minimize the number of illnesses or deaths in the population, given limited quantities of vaccine. Due to the non-linearity, complexity and stochasticity of the epidemic process, it is not possible to solve for optimal vaccine distributions mathematically. However, we use GA and RMHC to find near optimal vaccine distributions. We model an influenza pandemic that has age-specific illness attack rates similar to the Asian pandemic in 1957-1958 caused by influenza A(H2N2), as well as a distribution similar to the Hong Kong pandemic in 1968-1969 caused by influenza A(H3N2). We find the optimal vaccine distributions given that the number of doses is limited over the range of 10-90% of the population. While GA and RMHC work well in finding optimal vaccine distributions, GA is significantly more efficient than RMHC. We show that the optimal vaccine distribution found by GA and RMHC is up to 84% more effective than random mass vaccination in the mid range of vaccine availability. GA is generalizable to the optimization of stochastic model parameters for other infectious diseases and population structures.     

Computational models of signalling networks for non-linear control

Artificial signalling networks (ASNs) are a computational approach inspired by the signalling processes inside cells that decode outside environmental information. Using evolutionary algorithms to induce complex behaviours, we show how chaotic dynamics in a conservative dynamical system can be controlled. Such dynamics are of particular interest as they mimic the inherent complexity of non-linear physical systems in the real world. Considering the main biological interpretations of cellular signalling, in which complex behaviours and robust cellular responses emerge from the interaction of multiple pathways, we introduce two ASN representations: a stand-alone ASN and a coupled ASN. In particular we note how sophisticated cellular communication mechanisms can lead to effective controllers, where complicated problems can be divided into smaller and independent tasks.     

Efficiency of energy conversion in model biological pumps: Optimization by linear nonequilibrium thermodynamic relations

Experimental investigations showed linear relations between flows and forces in some biological energy converters operating far from equilibrium. This observation cannot be understood on the basis of conventional nonequilibrium thermodynamics. Therefore, the efficiencies of a linear and a nonlinear mode of operation of an energy converter (a hypothetical redox-driven H⁺ pump) were compared. This comparison revealed that at physiological values of the forces and degrees of coupling (1) the force ratio permitting optimal efficiency was much higher in the linear than in the nonlinear mode and (2) the linear mode of operation was at least 10⁶-times more efficient that the nonlinear one. These observations suggest that the experimentally observed linear relations between flows and forces, particularly in the case of oxidative phosphorylation, may be due to a feedback regulation maintaining linear thermodynamic relations far from equilibrium. This regulation may have come about as the consequence of an evolutionary drive towards higher efficiency.     

Multi-trial Vector-based Whale Optimization Algorithm

The Whale Optimization Algorithm(WOA)is a swarm intelligence metaheuristic inspired by the bubble-net hunting tactic of humpback whales.In spite of its popularity due to simplicity,ease of implementation,and a limited number of param-eters,WOA's search strategy can adversely affect the convergence and equilibrium between exploration and exploitation in complex problems.To address this limitation,we propose a new algorithm called Multi-trial Vector-based Whale Opti-mization Algorithm(MTV-WOA)that incorporates a Balancing Strategy-based Trial-vector Producer(BS_TVP),a Local Strategy-based Trial-vector Producer(LS_TVP),and a Global Strategy-based Trial-vector Producer(GS_TVP)to address real-world optimization problems of varied degrees of difficulty.MTV-WOA has the potential to enhance exploitation and exploration,reduce the probability of being stranded in local optima,and preserve the equilibrium between exploration and exploitation.For the purpose of evaluating the proposed algorithm's performance,it is compared to eight metaheuristic algorithms utilizing CEC 2018 test functions.Moreover,MTV-WOA is compared with well-stablished,recent,and WOA variant algorithms.The experimental results demonstrate that MTV-WOA surpasses comparative algorithms in terms of the accuracy of the solutions and convergence rate.Additionally,we conducted the Friedman test to assess the gained results statistically and observed that MTV-WOA significantly outperforms comparative algorithms.Finally,we solved five engi-neering design problems to demonstrate the practicality of MTV-WOA.The results indicate that the proposed MTV-WOA can efficiently address the complexities of engineering challenges and provide superior solutions that are superior to those of other algorithms.     

A platform for evolving intelligently interactive adversaries

Entertainment software developers face significant challenges in designing games with broad appeal. One of the challenges concerns creating nonplayer (computer-controlled) characters that can adapt their behavior in light of the current and prospective situation, possibly emulating human behaviors. This adaptation should be inherently novel, unrepeatable, yet within the bounds of realism. Evolutionary algorithms provide a suitable method for generating such behaviors. This paper provides background on the entertainment software industry, and details a prior and current effort to create a platform for evolving nonplayer characters with genetic and behavioral traits within a World War I combat flight simulator.     

Process-based simulation library SALMO-OO for lake ecosystems. Part 2: Multi-objective parameter optimization by evolutionary algorithms

SALMO-OO represents an object-oriented simulation library for lake ecosystems that allows to determine generic model structures for certain lake categories. It is based on complex ordinary differential equations that can be assembled by alternative process equations for algal growth and grazing as well as zooplankton growth and mortality. It requires 128 constant parameters that are causally related to the metabolic, chemical and transport processes in lakes either estimated from laboratory and field experiments or adopted from the literature.An evolutionary algorithm (EA) was integrated into SALMO-OO in order to facilitate multi-objective optimization for selected parameters and to substitute them by optimum temperature and phosphate functions. The parameters were related to photosynthesis, respiration and grazing of the three algal groups diatoms, green algae and blue-green algae. The EA determined specific temperature and phosphate functions for same parameters for 3 lake categories that were validated by ecological data of six lakes from Germany and South Africa.The results of this study have demonstrated that: (1) the hybridization of ordinary differential equations by EA provide a sophisticated approach to fine-tune crucial parameters of complex ecological models, and (2) the multi-objective parameter optimization of SALMO-OO by EA has significantly improved the accuracy of simulation results for three different lake categories.     

The incorporation of epigenetics in artificial gene regulatory networks

Artificial gene regulatory networks are computational models that draw inspiration from biological networks of gene regulation. Since their inception they have been used to infer knowledge about gene regulation and as methods of computation. These computational models have been shown to possess properties typically found in the biological world, such as robustness and self organisation. Recently, it has become apparent that epigenetic mechanisms play an important role in gene regulation. This paper describes a new model, the Artificial Epigenetic Regulatory Network (AERN) which builds upon existing models by adding an epigenetic control layer. Our results demonstrate that AERNs are more adept at controlling multiple opposing trajectories when applied to a chaos control task within a conservative dynamical system, suggesting that AERNs are an interesting area for further investigation.     

Clustering hybrid regression: a novel computational approach to study and model biohydrogen production through dark fermentation

Clustering hybrid regression (CHR) approach was developed and evaluated using data from H(2)-producing glucose-based, suspended-cell bioreactor operated for 5 months. The aim was to describe the relationship between metabolic end products and H(2)-production rate. Self-organizing maps (SOM) were used to better visualize the dataset and to detect main metabolic patterns in bioprocess data. SOM detected three distinct metabolic patterns with butyrate, acetate and ethanol as dominant metabolites, respectively. Butyrate dominated metabolism was related to high H(2) production, while acetate and ethanol dominated metabolisms resulted in low H(2) production. CHR models performed well [mean square error (MSE) 0.55 and 0.56] in modeling the H(2)-production rate. The results validate the suitability of the CHR approach in describing the bioprocess behavior and in the modeling of H(2) production rate. The developed model can help in discovering key metabolic interactions and suitable process parameters from complex datasets, and increase the understanding of the bioprocesses occurring in engineered and natural environments.     

Evolving cell models for systems and synthetic biology

This paper proposes a new methodology for the automated design of cell models for systems and synthetic biology. Our modelling framework is based on P systems, a discrete, stochastic and modular formal modelling language. The automated design of biological models comprising the optimization of the model structure and its stochastic kinetic constants is performed using an evolutionary algorithm. The evolutionary algorithm evolves model structures by combining different modules taken from a predefined module library and then it fine-tunes the associated stochastic kinetic constants. We investigate four alternative objective functions for the fitness calculation within the evolutionary algorithm: (1) equally weighted sum method, (2) normalization method, (3) randomly weighted sum method, and (4) equally weighted product method. The effectiveness of the methodology is tested on four case studies of increasing complexity including negative and positive autoregulation as well as two gene networks implementing a pulse generator and a bandwidth detector. We provide a systematic analysis of the evolutionary algorithm’s results as well as of the resulting evolved cell models.     

Maximum likelihood with multiparameter models of substitution

Maximum-likelihood approaches to phylogenetic estimation have the potential of great flexibility, even though current implementations are highly constrained. One such constraint has been the limitation to one-parameter models of substitution. A general implementation of Newton's maximization procedure was developed that allows the maximum likelihood method to be used with multiparameter models. The Estimate and Maximize (EM) algorithm was also used to obtain a good approximation to the maximum likelihood for a certain class of multiparameter models. The condition for which a multiparameter model will only have a single maximum on the likelihood surface was identified. Two-and three-parameter models of substitution in base-paired regions of RNA sequences were used as examples for computer simulations to show that these implementations of the maximum likelihood method are not substantially slower than one-parameter models. Newton's method is much faster than the EM method but may be subject to divergence in some circumstances. In these cases the EM method can be used to restore convergence.     

A novel numerical optimization algorithm inspired from weed colonization

This paper introduces a novel numerical stochastic optimization algorithm inspired from colonizing weeds. Weeds are plants whose vigorous, invasive habits of growth pose a serious threat to desirable, cultivated plants making them a threat for agriculture. Weeds have shown to be very robust and adaptive to change in environment. Thus, capturing their properties would lead to a powerful optimization algorithm. It is tried to mimic robustness, adaptation and randomness of colonizing weeds in a simple but effective optimizing algorithm designated as Invasive Weed Optimization (IWO). The feasibility, the efficiency and the effectiveness of IWO are tested in details through a set of benchmark multi-dimensional functions, of which global and local minima are known. The reported results are compared with other recent evolutionary-based algorithms: genetic algorithms, memetic algorithms, particle swarm optimization, and shuffled frog leaping. The results are also compared with different versions of simulated annealing — a generic probabilistic meta-algorithm for the global optimization problem — which are simplex simulated annealing, and direct search simulated annealing. Additionally, IWO is employed for finding a solution for an engineering problem, which is optimization and tuning of a robust controller. The experimental results suggest that results from IWO are better than results from other methods. In conclusion, the performance of IWO has a reasonable performance for all the test functions.     

Cooperative combinatorial optimization: evolutionary computation case study

This paper presents a formalization of the notion of cooperation and competition of multiple systems that work toward a common optimization goal of the population using evolutionary computation techniques. It is proved that evolutionary algorithms are more expressive than conventional recursive algorithms, such as Turing machines. Three classes of evolutionary computations are introduced and studied: bounded finite, unbounded finite, and infinite computations. Universal evolutionary algorithms are constructed. Such properties of evolutionary algorithms as completeness, optimality, and search decidability are examined. A natural extension of evolutionary Turing machine (ETM) model is proposed to properly reflect phenomena of cooperation and competition in the whole population.