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.
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.
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.
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.
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.
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.
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
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.
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.
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.
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.
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.
Description:
Understanding the way how genes interact is one of the fundamental questions in systems biology. The modeling of gene regulations currently assumes that genes interact either instantaneously or with a certain amount of time delay. In this paper, we propose an information theory based novel two-phase gene regulatory network (GRN) inference algorithm using the Bayesian network formalism that can model both instantaneous and single-step time-delayed interactions between genes simultaneously. We show the effectiveness of our approach by applying it to the analysis of synthetic data as well as the Saccharomyces cerevisiae gene expression data.
Description:
Predicting the secondary structure of proteins from a primary sequence alone has been variously approached from either a classification or a generative model perspective. The most prominent classification methods have used neural networks, which involves mappings from a local window of residues in the sequence to the structural state of the central residue in the window, thus capturing the local interactions effectively. However, they fail to capture distant interactions among residues. The generative models based on Bayesian segmentation capture sequence structure relationships using generalized hidden Markov models with explicit state duration. They capture non-local interactions through a joint sequence-structure probability distribution based on structural segments. In this paper, we investigate a combined architecture of Bayesian segmentation at the first stage and neural network at the second stage which captures both local and non-local correlation, to increase the single sequence prediction accuracy. The combined architecture is further enhanced by using neural network optimization and ensemble techniques.
Description:
Due to various complexities, as well as noise and high dimensionality, reconstructing a gene regulatory network (GRN) from a high-throughput microarray data becomes computationally intensive.In our earlier work on causal model approach for GRN reconstruction, we had shown the superiority of Markov blanket (MB) algorithm compared to the algorithm using the existing Y and V causal models. In this paper, we show the MB algorithm can be enhanced further by application of the proposed constraint logic minimization (CLM) technique. We describe a framework for minimizing the constraint logic involved (condition independent tests) by exploiting the Markov blanket learning methods developed for a Bayesian network (BN). The constraint relationships are represented in the form of logic using K-map and with the aid of CLM increase the algorithm efficiency and the accuracy. We show improved results by investigations on both the synthetic as well as the real life yeast cell cycle data sets.
Coupling of cellular processes and their coordinated oscillations under continuous light in Cyanothece sp. ATCC 51142, a diazotrophic unicellular cyanobacterium
Description:
Dynamic Bayesian networks (DBN) are widely applied in Systems biology for modeling various biological networks, including gene regulatory networks and metabolic networks. The application of DBN models often requires data discretization. Although various discretization techniques exist, currently there is no consensus on which approach is most suitable. Popular discretization strategies within the bioinformatics community, such as interval and quantile discretization, are likely not optimal. In this paper, we propose a novel approach for data discretization for mutual information based learning of DBN. In this approach, the data are discretized so that the mutual information between parent and child nodes is maximized, subject to a suitable penalty put on the complexity of the discretization. A dynamic programming approach is used to find the optimal discretization threshold for each individual variable. Our approach iteratively learns both the network and the discretization scheme until a locally optimal solution is reached. Tests on real genetic networks confirm the effectiveness of the proposed method.
Description:
Because of the high dimensionality of the microarray data sets, feature selection (FS) has become an important challenge in molecular classification. Using the degree of differential prioritization (DDP) between relevance and antiredundancy, our proposed DDP-based FS technique is capable of achieving better accuracies than those previously reported, using a smaller predictor set. However, previously, we have neither devised nor used any method for determining the value of the DDP to be used for the data set of interest before the FS process. In this article, we propose a system for predicting the optimal value of the DDP, which costs less computationally than conventional tuning while maintaining the independence of the FS technique from the type of underlying classifier used