Statistical analysis of insect preference in two-choice experiments

Many studies of insect behavior in relation to chemicals from different plants require the use of statistical tests for determining whether attraction, repulsion, or neutrality is significant. In this paper, we propose a simple and efficient nonparametric statistical procedure for testing hypotheses about insect preference in two-choice experiments with individual insects. Three criteria are provided in order to detect the following alternatives to neutrality: (i) general attraction (or repulsion) in a sample population, (ii) strong variability of the individual responses, and (iii) slight but similar behavioral effects. Illustrations are given from two-choice experiments concerning the European corn borer (Ostrinia nubilalisHbn.) female's oviposition behavior.     

Statistical Screening of Medium Components for Recombinant Production of Pseudomonas aeruginosa ATCC 9027 Rhamnolipids by Nonpathogenic Cell Factory Pseudomonas putida KT2440

Rhamnolipids (RLs) produced by the opportunistic human pathogen Pseudomonas aeruginosa are considered as potential candidates for the next generation of surfactants. Large-scale production of RLs depends on progress in strain engineering, medium design, operating strategies, and purification procedures. In this work, the rhlAB genes extracted from a mono_RLs_producing strain of P. aeruginosa (ATCC 9027) were introduced to an appropriate safety host Pseudomonas putida KT2440. The capability of the recombinant strain was evaluated in various media. As a prerequisite for optimal medium design, a set of 32 experiments was performed in two steps for screening a number of macro-nutritional compounds. In the experiments, a two-level fractional factorial design resolution IV was followed by a two-level full factorial one. By means of this approach, it was observed that glycerol, yeast extract, and peptone have significant positive influence on recombinant RLs production while the yeast extract/peptone two-factor and glycerol/yeast extract/peptone three-factor interactions have considerable negative effects. A wide range of variation from 0 to 570 mg/l was obtained for RLs production during the screening experiments indicating the importance of medium optimization. The results point out the opportunity for possible higher yields of RLs through further screening, mixture/combined mixture designs, and high-cell-density cultivations.     

Optimisation of medium composition for clavulanic acid production by Streptomyces clavuligerus

Among four different commercially available nitrogen sources containing soybean derivatives, a protein extract of soybean gave the highest yield for clavulanic acid production by Streptomyces clavuligerus. A statistical method based on factorial design of experiments was applied to optimise the medium. An empirical model was obtained by applying response surface statistical analysis. The analysis of variance showed that concentrations of protein extract of soybean and glycerol and the interaction between these two variables were significant at 95% level of confidence. The maximum clavulanic acid concentration obtained in 72 h was 1.2 g l^–1.     

Cyber War Game in Temporal Networks

In a cyber war game where a network is fully distributed and characterized by resource constraints and high dynamics, attackers or defenders often face a situation that may require optimal strategies to win the game with minimum effort. Given the system goal states of attackers and defenders, we study what strategies attackers or defenders can take to reach their respective system goal state (i.e., winning system state) with minimum resource consumption. However, due to the dynamics of a network caused by a node’s mobility, failure or its resource depletion over time or action(s), this optimization problem becomes NP-complete. We propose two heuristic strategies in a greedy manner based on a node’s two characteristics: resource level and influence based on k-hop reachability. We analyze complexity and optimality of each algorithm compared to optimal solutions for a small-scale static network. Further, we conduct a comprehensive experimental study for a large-scale temporal network to investigate best strategies, given a different environmental setting of network temporality and density. We demonstrate the performance of each strategy under various scenarios of attacker/defender strategies in terms of win probability, resource consumption, and system vulnerability.     

A simulation study comparing the impact of experimental error on the performance of experimental designs and artificial neural networks used for process screening

Many variables and their interactions can affect a biotechnological process. Testing a large number of variables and all their possible interactions is a cumbersome task and its cost can be prohibitive. Several screening strategies, with a relatively low number of experiments, can be used to find which variables have the largest impact on the process and estimate the magnitude of their effect. One approach for process screening is the use of experimental designs, among which fractional factorial and Plackett–Burman designs are frequent choices. Other screening strategies involve the use of artificial neural networks (ANNs). The advantage of ANNs is that they have fewer assumptions than experimental designs, but they render black-box models (i.e., little information can be extracted about the process mechanics). In this paper, we simulate a biotechnological process (fed-batch growth of bakers yeast) to analyze and compare the effect of random experimental errors of different magnitudes and statistical distributions on experimental designs and ANNs. Except for the situation in which the error has a normal distribution and the standard deviation is constant, it was not possible to determine a clear-cut rule for favoring one screening strategy over the other. Instead, we found that the data can be better analyzed using both strategies simultaneously.     

Adaptive Firefly Algorithm: Parameter Analysis and its Application

As a nature-inspired search algorithm, firefly algorithm (FA) has several control parameters, which may have great effects on its performance. In this study, we investigate the parameter selection and adaptation strategies in a modified firefly algorithm — adaptive firefly algorithm (AdaFa). There are three strategies in AdaFa including (1) a distance-based light absorption coefficient; (2) a gray coefficient enhancing fireflies to share difference information from attractive ones efficiently; and (3) five different dynamic strategies for the randomization parameter. Promising selections of parameters in the strategies are analyzed to guarantee the efficient performance of AdaFa. AdaFa is validated over widely used benchmark functions, and the numerical experiments and statistical tests yield useful conclusions on the strategies and the parameter selections affecting the performance of AdaFa. When applied to the real-world problem — protein tertiary structure prediction, the results demonstrated improved variants can rebuild the tertiary structure with the average root mean square deviation less than 0.4Å and 1.5Å from the native constrains with noise free and 10% Gaussian white noise.     

Novel analytic criteria and effective plate designs for quality control in genome-scale RNAi screens

One of the most fundamental challenges in genome-wide RNA interference (RNAi) screens is to glean biological significance from mounds of data, which relies on the development and adoption of appropriate analytic methods and designs for quality control (QC) and hit selection. Currently, a Z-factor-based QC criterion is widely used to evaluate data quality. However, this criterion cannot take into account the fact that different positive controls may have different effect sizes and leads to inconsistent QC results in experiments with 2 or more positive controls with different effect sizes. In this study, based on a recently proposed parameter, strictly standardized mean difference (SSMD), novel QC criteria are constructed for evaluating data quality in genome-wide RNAi screens. Two good features of these novel criteria are: (1) SSMD has both clear original and probability meanings for evaluating the differentiation between positive and negative controls and hence the SSMD-based QC criteria have a solid probabilistic and statistical basis, and (2) these QC criteria obtain consistent QC results for multiple positive controls with different effect sizes. In addition, I propose multiple plate designs and the guidelines for using them in genome-wide RNAi screens. Finally, I provide strategies for using the SSMD-based QC criteria and effective plate design together to improve data quality. The novel SSMD-based QC criteria, effective plate designs, and related guidelines and strategies may greatly help to obtain high quality of data in genome-wide RNAi screens.     

Ephrin-Eph signaling in embryonic tissue separation

The physical separation of the embryonic regions that give rise to the tissues and organs of multicellular organisms is a fundamental aspect of morphogenesis. Pioneer experiments by Holtfreter had shown that embryonic cells can sort based on “tissue affinities,” which have long been considered to rely on differences in cell-cell adhesion. However, vertebrate embryonic tissues also express a variety of cell surface cues, in particular ephrins and Eph receptors, and there is now firm evidence that these molecules are systematically used to induce local repulsion at contacts between different cell types, efficiently preventing mixing of adjacent cell populations.     

Statistical significance analysis of nuclear magnetic resonance-based metabonomics data

Use of nuclear magnetic resonance (NMR)-based metabonomics to search for human disease biomarkers is becoming increasingly common. For many researchers, the ultimate goal is translation from biomarker discovery to clinical application. Studies typically involve investigators from diverse educational and training backgrounds, including physicians, academic researchers, and clinical staff. In evaluating potential biomarkers, clinicians routinely use statistical significance testing language, whereas academicians typically use multivariate statistical analysis techniques that do not perform statistical significance evaluation. In this article, we outline an approach to integrate statistical significance testing with conventional principal components analysis data representation. A decision tree algorithm is introduced to select and apply appropriate statistical tests to loadings plot data, which are then heat map color-coded according to P score, enabling direct visual assessment of statistical significance. A multiple comparisons correction must be applied to determine P scores from which reliable inferences can be made. Knowledge of means and standard deviations of statistically significant buckets enabled computation of effect sizes and study sizes for a given statistical power. Methods were demonstrated using data from a previous study. Integrated metabonomics data assessment methodology should facilitate translation of NMR-based metabonomics discovery of human disease biomarkers to clinical use.     

A statistical method for the analysis of nonlinear temperature time series from compost

Temperature is widely accepted as a critical indicator of aerobic microbial activity during composting but, to date, little effort has been made to devise an appropriate statistical approach for the analysis of temperature time series. Nonlinear, time-correlated effects have not previously been considered in the statistical analysis of temperature data from composting, despite their importance and the ubiquity of such features. A novel mathematical model is proposed here, based on a modified Gompertz function, which includes nonlinear, time-correlated effects. Methods are shown to estimate initial values for the model parameter. Algorithms in SAS are used to fit the model to different sets of temperature data from passively aerated compost. Methods are then shown for testing the goodness-of-fit of the model to data. Next, a method is described to determine, in a statistically rigorous manner, the significance of differences among the time-correlated characteristics of the datasets as described using the proposed model. An extra-sum-of-squares method was selected for this purpose. Finally, the model and methods are used to analyze a sample dataset and are shown to be useful tools for the statistical comparison of temperature data in composting.     

Path planning versus cue responding: a bio-inspired model of switching between navigation strategies

In this article, we describe a new computational model of switching between path-planning and cue-guided navigation strategies. It is based on three main assumptions: (i) the strategies are mediated by separate memory systems that learn independently and in parallel; (ii) the learning algorithms are different in the two memory systems—the cue-guided strategy uses a temporal-difference (TD) learning rule to approach a visible goal, whereas the path-planning strategy relies on a place-cell-based graph-search algorithm to learn the location of a hidden goal; (iii) a strategy selection mechanism uses TD-learning rule to choose the most successful strategy based on past experience. We propose a novel criterion for strategy selection based on the directions of goal-oriented movements suggested by the different strategies. We show that the selection criterion based on this “common currency” is capable of choosing the best among TD-learning and planning strategies and can be used to solve navigational tasks in continuous state and action spaces. The model has been successfully applied to reproduce rat behavior in two water-maze tasks in which the two strategies were shown to interact. The model was used to analyze competitive and cooperative interactions between different strategies during these tasks as well as relative influence of different types of sensory cues.     

A blocking strategy to improve gene selection for classification of gene expression data

Because of high dimensionality, machine learning algorithms typically rely on feature selection techniques in order to perform effective classification in microarray gene expression data sets. However, the large number of features compared to the number of samples makes the task of feature selection computationally hard and prone to errors. This paper interprets feature selection as a task of stochastic optimization, where the goal is to select among an exponential number of alternative gene subsets the one expected to return the highest generalization in classification. Blocking is an experimental design strategy which produces similar experimental conditions to compare alternative stochastic configurations in order to be confident that observed differences in accuracy are due to actual differences rather than to fluctuations and noise effects. We propose an original blocking strategy for improving feature selection which aggregates in a paired way the validation outcomes of several learning algorithms to assess a gene subset and compare it to others. This is a novelty with respect to conventional wrappers, which commonly adopt a sole learning algorithm to evaluate the relevance of a given set of variables. The rationale of the approach is that, by increasing the amount of experimental conditions under which we validate a feature subset, we can lessen the problems related to the scarcity of samples and consequently come up with a better selection. The paper shows that the blocking strategy significantly improves the performance of a conventional forward selection for a set of 16 publicly available cancer expression data sets. The experiments involve six different classifiers and show that improvements take place independent of the classification algorithm used after the selection step. Two further validations based on available biological annotation support the claim that blocking strategies in feature selection may improve the accuracy and the quality of the solution. The first validation is based on retrieving PubMEd abstracts associated to the selected genes and matching them to regular expressions describing the biological phenomenon underlying the expression data sets. The biological validation that follows is based on the use of the Bioconductor package GoStats in order to perform Gene Ontology statistical analysis.     

Optimization of Bacteriocin Production by Batch Fermentation of Lactobacillus plantarum LPCO10

Optimization of bacteriocin production by Lactobacillus plantarum LPCO10 was explored by an integral statistical approach. In a prospective series of experiments, glucose and NaCl concentrations in the culture medium, inoculum size, aeration of the culture, and growth temperature were statistically combined using an experimental 2³_5-2 fractional factorial two-level design and tested for their influence on maximal bacteriocin production by L. plantarum LPCO10. After the values for the less-influential variables were fixed, NaCl concentration, inoculum size, and temperature were selected to study their optimal relationship for maximal bacteriocin production. This was achieved by a new experimental 3²_3-1 fractional factorial three-level design which was subsequently used to build response surfaces and analyzed for both linear and quadratic effects. Results obtained indicated that the best conditions for bacteriocin production were shown with temperatures ranging from 22 to 27°C, salt concentration from 2.3 to 2.5%, and L. plantarum LPCO10 inoculum size ranging from 10^7.3 to 10^7.4 CFU/ml, fixing the initial glucose concentration at 2%, with no aeration of the culture. Under these optimal conditions, about 3.2 × 10⁴ times more bacteriocin per liter of culture medium was obtained than that used to initially purify plantaricin S from L. plantarum LPCO10 to homogeneity. These results indicated the importance of this study in obtaining maximal production of bacteriocins from L. plantarum LPCO10 so that bacteriocins can be used as preservatives in canned foods.     

Fuzzy Nonlinear Proximal Support Vector Machine for Land Extraction Based on Remote Sensing Image

Currently, remote sensing technologies were widely employed in the dynamic monitoring of the land. This paper presented an algorithm named fuzzy nonlinear proximal support vector machine (FNPSVM) by basing on ETM⁺ remote sensing image. This algorithm is applied to extract various types of lands of the city Da’an in northern China. Two multi-category strategies, namely “one-against-one” and “one-against-rest” for this algorithm were described in detail and then compared. A fuzzy membership function was presented to reduce the effects of noises or outliers on the data samples. The approaches of feature extraction, feature selection, and several key parameter settings were also given. Numerous experiments were carried out to evaluate its performances including various accuracies (overall accuracies and kappa coefficient), stability, training speed, and classification speed. The FNPSVM classifier was compared to the other three classifiers including the maximum likelihood classifier (MLC), back propagation neural network (BPN), and the proximal support vector machine (PSVM) under different training conditions. The impacts of the selection of training samples, testing samples and features on the four classifiers were also evaluated in these experiments.     

The analysis of a factorial series of insecticide tests

When a set of insecticidal toxicity tests yields parallel regression lines for the relationship between mortality probit and log dose, the potencies of the materials or conditions under test may be compared purely in terms of log L.D. 50's. The purpose of this paper is to suggest that, when tests have been made with all combinations of several different factors, standard methods for the statistical analysis of factorial experiments may be adapted to the examination of the relative potencies.
Data obtained by Potter & Gillham (1046), in a 2' factorial experiment on alternative storage conditions for insects before and after spraying and the adjuvant action of terpineol in a pyrethrins spray, are used in an example of the computations. Details are given of the test of parallelism of the regression lines, the factorial analysis of the log L.D. '50s, the estimation of the mean effects and interactions and their standard errors, the significance tests, and the preparation of summary tables.     

PRODUCTION OF NARINGINASE FROM A NEW SOIL ISOLATE,Bacillus methylotrophicus: ISOLATION,OPTIMIZATION AND SCALE-UP STUDIES

Five strains of naringin-degrading bacteria were isolated and found to be positive for extracellular naringinase activity. The one that showed highest activity in the selective medium was identified by 16S rRNA analysis as Bacillus methylotrophicus. The best combination of carbon–nitrogen source was determined by employing two-level full factorial analyses, comprising 24 experiments in shake flasks. Sucrose–yeast extract showed significant increase in naringinase activity (7.46 U/L) compared to the basal medium. Naringinase production was found to be inducible and naringin was found to be the best inducer among naringin, naringenin, hesperidin, and L-rhamnose. Inoculum size of 2% (v/v) and age of 48 hr favored naringinase and biomass production. Highest naringinase activity of 8 U/L was observed at the initial medium pH of 6. Response surface modeling was applied based on central composite design to determine the effects of three independent variables (sucrose, yeast extract, and naringin) and their mutual interactions. In total, 20 experiments were conducted and a statistical model was developed, which predicted naringinase production of 10.61 U/L. Subsequently, verification experiments were conducted and validity of the model was verified. Bioreactor studies conducted with the optimized medium showed an enzyme production of 12.05 U/L within 34 hr of fermentation.     

Polyglutamic acid (PGA) production by Bacillus sp. SAB-26: application of Plackett–Burman experimental design to evaluate culture requirements

A locally isolated thermostable Bacillus strain producing polyglutamic acid (PGA) was characterized and identified based on 16S rRNA sequencing. Phylogenetic analysis revealed its closeness to Bacillus licheniformis. To evaluate the effect of different culture conditions on the production of PGA, Plackett–Burman factorial design was carried out. Fifteen variables were examined for their significance on PGA production. Among those variables, K₂HPO₄, KH₂PO₄, (NH₄)₂SO₄ and casein hydrolysate were found to be the most significant variables that encourage PGA production. A correlation between cellular growth, PGA and the produced traces of polysaccharides was illustrated. An inverse relationship practice between cell dry weights and the produced PGA was demonstrated. On the other hand, a direct proportional relation was shown between polysaccharides on one side and cell dry weight and produced PGA on the other. The preoptimized medium, based on statistical analysis, showed a production of 33.5 g/l PGA, which is more than three times the basal medium.     

Significance of gene ranking for classification of microarray samples

Many methods for classification and gene selection with microarray data have been developed. These methods usually give a ranking of genes. Evaluating the statistical significance of the gene ranking is important for understanding the results and for further biological investigations, but this question has not been well addressed for machine learning methods in existing works. Here, we address this problem by formulating it in the framework of hypothesis testing and propose a solution based on resampling. The proposed r-test methods convert gene ranking results into position p-values to evaluate the significance of genes. The methods are tested on three real microarray data sets and three simulation data sets with support vector machines as the method of classification and gene selection. The obtained position p-values help to determine the number of genes to be selected and enable scientists to analyze selection results by sophisticated multivariate methods under the same statistical inference paradigm as for simple hypothesis testing methods.     

Use of a Plackett-Burman statistical design to determine the effect of selected amino acids on monoclonal antibody production in CHO cells

Culture media design is central to the optimization of monoclonal antibody (mAb) production. Although general strategies do not currently exist for optimization of culture media, the combined use of statistical design and analysis of experiments and strategies based on simple material balances can facilitate culture media design. In this study, we evaluate the effect of selected amino acids on the growth rate and monoclonal antibody production of a Chinese hamster ovary DG-44 (CHO-DG44) cell line. These amino acids were selected based on their relative mass fraction in the specific mAb produced in this study, their consumption rate during bioreactor experiments, and also through a literature review. A Plackett-Burman statistical design was conducted to minimize the number of experiments needed to obtain statistically relevant information. The effect of this set of amino acids was evaluated during exponential cell culture (considering viable cell concentration and the specific growth rate as main output variables) and during the high cell-density stage (considering mAb final concentration and specific productivity as relevant output variables). For this particular cell line, leucine (Leu) and arginine (Arg) had the highest negative and positive effects on cell viability, respectively; Leu and threonine (Thr) had the highest negative effect on growth rate, and valine (Val) and Arg demonstrated the highest positive impact on mAb final concentration. Results suggest the pertinence of a two-stage strategy for amino acid supplementation, with a mixture optimized for cell growth and a different amino acid mixture for mAb production at high density.     

Analysis of the effect of design parameters and their interactions on the strength of dental restorations with endodontic posts,using finite element models and statistical analysis

Many previous studies, both in vitro and with model simulations, have been conducted in an attempt to reach a full understanding of how the different design parameters of an endodontically restored tooth affect its mechanical strength. However, differences in the experimental set-up or modelling conditions and the limited number of parameters studied in each case prevent us from obtaining clear conclusions about the real significance of each parameter. In this work, a new approach is proposed for this purpose based on the combination of a validated three-dimensional parametric biomechanical model of the restored tooth and statistical analysis using full factorial analysis of variance. A two-step approach with two virtual tests (with, respectively, 128 and 81 finite element models) was used in the present work to study the effect of several design parameters on the strength of a restored incisor, using full factorial designs. Within the limitations of this study, and for cases where the parameters are within the ranges that were tested, the conclusions indicate that the material of the post is the most significant factor as far as its strength is concerned, the use of a low Young's modulus being preferable for this component. Once the post material has been chosen, the geometry of the post is of less importance than the Young's modulus selected for the core or, especially, for the crown.