Differentiation of probiotic and environmental Saccharomyces cerevisiae strains in animal feed

Aims: To establish an identification system for probiotic Saccharomyces cerevisiae strains based on artificial neural network (ANN)–assisted Fourier‐transform infrared (FTIR) spectroscopy to improve quality control of animal feed. Methods and Results: The ANN‐based system for differentiating environmental from probiotic S. cerevisiae strains comprises five authorized feed additive strains plus environmental strains isolated from different habitats. A total of 108 isolates were used as reference strains to create the ANN. DHPLC analysis and δ‐PCR were used as reference methods to type probiotic yeast isolates. The performance of the FTIR‐ANN was tested in an internal validation using unknown spectra of each reference strain. This validation step yielded a classification rate of 99·1 %. For an external validation, a test data set comprising 965 spectra of 63 probiotic and environmental S. cerevisiae isolates unknown to the ANN was used, resulting in a classification rate of 98·2 %. Conclusions: Our results demonstrate that probiotic S. cerevisiae strains in feed can be differentiated successfully from environmental isolates using both genotypic approaches and ANN‐based FTIR spectroscopy. Significance and Impact of the Study: FTIR‐based artificial neural network analysis provides a rapid and inexpensive technique for yeast identification both at the species and at the strain level in routine diagnostic laboratories, using a single sample preparation.     

Rapid analysis of disease state in liquid human serum combining infrared spectroscopy and “digital drying”

In recent years, the diagnosis of brain tumors has been investigated with attenuated total reflection‐Fourier transform infrared (ATR‐FTIR) spectroscopy on dried human serum samples to eliminate spectral interferences of the water component, with promising results. This research evaluates ATR‐FTIR on both liquid and air‐dried samples to investigate “digital drying” as an alternative approach for the analysis of spectra obtained from liquid samples. Digital drying approaches, consisting of water subtraction and least‐squares method, have demonstrated a greater random forest (RF) classification performance than the air‐dried spectra approach when discriminating cancer vs control samples, reaching sensitivity values higher than 93.0% and specificity values higher than 83.0%. Moreover, quantum cascade laser infrared (QCL‐IR) based spectroscopic imaging is utilized on liquid samples to assess the implications of a deep‐penetration light source on disease classification. The RF classification of QCL‐IR data has provided sensitivity and specificity amounting to 85.1% and 75.3% respectively.     

Reliable and rapid identification of Listeria monocytogenes and Listeria species by artificial neural network-based Fourier transform infrared spectroscopy

Differentiation of the species within the genus Listeria is important for the food industry but only a few reliable methods are available so far. While a number of studies have used Fourier transform infrared (FTIR) spectroscopy to identify bacteria, the extraction of complex pattern information from the infrared spectra remains difficult. Here, we apply artificial neural network technology (ANN), which is an advanced multivariate data-processing method of pattern analysis, to identify Listeria infrared spectra at the species level. A hierarchical classification system based on ANN analysis for Listeria FTIR spectra was created, based on a comprehensive reference spectral database including 243 well-defined reference strains of Listeria monocytogenes, L. innocua, L. ivanovii, L. seeligeri, and L. welshimeri. In parallel, a univariate FTIR identification model was developed. To evaluate the potentials of these models, a set of 277 isolates of diverse geographical origins, but not included in the reference database, were assembled and used as an independent external validation for species discrimination. Univariate FTIR analysis allowed the correct identification of 85.2% of all strains and of 93% of the L. monocytogenes strains. ANN-based analysis enhanced differentiation success to 96% for all Listeria species, including a success rate of 99.2% for correct L. monocytogenes identification. The identity of the 277-strain test set was also determined with the standard phenotypical API Listeria system. This kit was able to identify 88% of the test isolates and 93% of L. monocytogenes strains. These results demonstrate the high reliability and strong potential of ANN-based FTIR spectrum analysis for identification of the five Listeria species under investigation. Starting from a pure culture, this technique allows the cost-efficient and rapid identification of Listeria species within 25 h and is suitable for use in a routine food microbiological laboratory.     

Cross‐validation strategies for data with temporal,spatial, hierarchical,or phylogenetic structure

Ecological data often show temporal, spatial, hierarchical (random effects), or phylogenetic structure. Modern statistical approaches are increasingly accounting for such dependencies. However, when performing cross‐validation, these structures are regularly ignored, resulting in serious underestimation of predictive error. One cause for the poor performance of uncorrected (random) cross‐validation, noted often by modellers, are dependence structures in the data that persist as dependence structures in model residuals, violating the assumption of independence. Even more concerning, because often overlooked, is that structured data also provides ample opportunity for overfitting with non‐causal predictors. This problem can persist even if remedies such as autoregressive models, generalized least squares, or mixed models are used. Block cross‐validation, where data are split strategically rather than randomly, can address these issues. However, the blocking strategy must be carefully considered. Blocking in space, time, random effects or phylogenetic distance, while accounting for dependencies in the data, may also unwittingly induce extrapolations by restricting the ranges or combinations of predictor variables available for model training, thus overestimating interpolation errors. On the other hand, deliberate blocking in predictor space may also improve error estimates when extrapolation is the modelling goal. Here, we review the ecological literature on non‐random and blocked cross‐validation approaches. We also provide a series of simulations and case studies, in which we show that, for all instances tested, block cross‐validation is nearly universally more appropriate than random cross‐validation if the goal is predicting to new data or predictor space, or for selecting causal predictors. We recommend that block cross‐validation be used wherever dependence structures exist in a dataset, even if no correlation structure is visible in the fitted model residuals, or if the fitted models account for such correlations.     

A METHOD FOR ASSESSING PHYLOGENETIC LEAST SQUARES MODELS FOR SHAPE AND OTHER HIGH‐DIMENSIONAL MULTIVARIATE DATA

Studies of evolutionary correlations commonly use phylogenetic regression (i.e., independent contrasts and phylogenetic generalized least squares) to assess trait covariation in a phylogenetic context. However, while this approach is appropriate for evaluating trends in one or a few traits, it is incapable of assessing patterns in highly multivariate data, as the large number of variables relative to sample size prohibits parametric test statistics from being computed. This poses serious limitations for comparative biologists, who must either simplify how they quantify phenotypic traits, or alter the biological hypotheses they wish to examine. In this article, I propose a new statistical procedure for performing ANOVA and regression models in a phylogenetic context that can accommodate high‐dimensional datasets. The approach is derived from the statistical equivalency between parametric methods using covariance matrices and methods based on distance matrices. Using simulations under Brownian motion, I show that the method displays appropriate Type I error rates and statistical power, whereas standard parametric procedures have decreasing power as data dimensionality increases. As such, the new procedure provides a useful means of assessing trait covariation across a set of taxa related by a phylogeny, enabling macroevolutionary biologists to test hypotheses of adaptation, and phenotypic change in high‐dimensional datasets.     

Effects of phenotypic complementarity and phylogeny on the nested structure of mutualistic networks

Recent studies have started to unravel the structure of mutualistic networks, although few functional explanations underlying such structure have been explored. We used computer simulations to test whether complementarity between phenotypic traits of plants and animals can explain the pervasive tendency of specialists to interact with proper subsets of species that generalists interact with (nested interactions), and how phylogeny affects such interaction patterns. Simultaneously, we assessed whether complementarity and phylogenetic structure were associated with patterns of interaction in a real mutualistic community. Simulation results support that highly nested networks can emerge from phenotypic complementarity, particularly when several traits are involved. The hierarchical structure of phylogenetic relations can also contribute to increased nestedness because traits determining complementarity are then inherited in a correlated fashion. Phylogenetic effects on resulting generalization levels are often low, but can be detected. Results from the empirical network support a relevant role of complementarity and phylogenetic history on interaction patterns. Our results demonstrate that these factors can contribute to nestedness, which emphasize the necessity of considering evolutionary mechanisms in studies of community structure.     

Application of machine learning approaches for land cover monitoring in northern Cameroon

Machine learning (ML) models are a leading analytical technique used to monitor, map and quantify land use and land cover (LULC) and its change over time. Models such as k-nearest neighbour (kNN), support vector machines (SVM), artificial neural networks (ANN), and random forests (RF) have been used effectively to classify LULC types at a range of geographical scales. However, ML models have not been widely applied in African tropical regions due to methodological challenges that arise from relying on the coarse-resolution satellite images available for these areas. In this study, we compared the performance of four ML algorithms (kNN, SVM, ANN and RF) applied to LULC monitoring within the Mayo Rey department, North Province, Cameroon. We used satellite data from the Landsat 7 Enhanced Thematic Mapper Plus (ETM+) combined with 8 Operational Land Imager (OLI) images of northern Cameroon for November 2000 and November 2020. Our results showed that all four classification algorithms produced relatively high accuracy (overall classification accuracy >80%), with the RF model (> 90% classification accuracy) outperforming the kNN, SVM, and ANN models. We found that approximately 7% of all forested areas (dense forest and woody savanna) were converted to other land cover types between 2000 and 2020; this forest loss is particularly associated with an expansion of both croplands and built-up areas. Our study represents a novel application and comparison of statistical and ML approaches to LULC monitoring using coarse-resolution satellite images in an African tropical forest and savanna setting. The resulting land cover maps serve as an important baseline that will be useful to the Cameroon government for policy development, conservation planning, urban planning, and deforestation and agricultural monitoring.     

Evaluation of different biological data and computational classification methods for use in protein interaction prediction

Protein–protein interactions play a key role in many biological systems. High‐throughput methods can directly detect the set of interacting proteins in yeast, but the results are often incomplete and exhibit high false‐positive and false‐negative rates. Recently, many different research groups independently suggested using supervised learning methods to integrate direct and indirect biological data sources for the protein interaction prediction task. However, the data sources, approaches, and implementations varied. Furthermore, the protein interaction prediction task itself can be subdivided into prediction of (1) physical interaction, (2) co‐complex relationship, and (3) pathway co‐membership. To investigate systematically the utility of different data sources and the way the data is encoded as features for predicting each of these types of protein interactions, we assembled a large set of biological features and varied their encoding for use in each of the three prediction tasks. Six different classifiers were used to assess the accuracy in predicting interactions, Random Forest (RF), RF similarity‐based k‐Nearest‐Neighbor, Naïve Bayes, Decision Tree, Logistic Regression, and Support Vector Machine. For all classifiers, the three prediction tasks had different success rates, and co‐complex prediction appears to be an easier task than the other two. Independently of prediction task, however, the RF classifier consistently ranked as one of the top two classifiers for all combinations of feature sets. Therefore, we used this classifier to study the importance of different biological datasets. First, we used the splitting function of the RF tree structure, the Gini index, to estimate feature importance. Second, we determined classification accuracy when only the top‐ranking features were used as an input in the classifier. We find that the importance of different features depends on the specific prediction task and the way they are encoded. Strikingly, gene expression is consistently the most important feature for all three prediction tasks, while the protein interactions identified using the yeast‐2‐hybrid system were not among the top‐ranking features under any condition. Proteins 2006. © 2006 Wiley‐Liss, Inc.     

Neuro-fuzzy structural classification of proteins for improved protein secondary structure prediction

Fourier transform infrared (FTIR) spectroscopy is a very flexible technique for characterization of protein secondary structure. Measurements can be carried out rapidly in a number of different environments based on only small quantities of proteins. For this technique to become more widely used for protein secondary structure characterization, however, further developments in methods to accurately quantify protein secondary structure are necessary. Here we propose a structural classification of proteins (SCOP) class specialized neural networks architecture combining an adaptive neuro-fuzzy inference system (ANFIS) with SCOP class specialized backpropagation neural networks for improved protein secondary structure prediction. Our study shows that proteins can be accurately classified into two main classes "all alpha proteins" and "all beta proteins" merely based on the amide I band maximum position of their FTIR spectra. ANFIS is employed to perform the classification task to demonstrate the potential of this architecture with moderately complex problems. Based on studies using a reference set of 17 proteins and an evaluation set of 4 proteins, improved predictions were achieved compared to a conventional neural network approach, where structure specialized neural networks are trained based on protein spectra of both "all alpha" and "all beta" proteins. The standard errors of prediction (SEPs) in % structure were improved by 4.05% for helix structure, by 5.91% for sheet structure, by 2.68% for turn structure, and by 2.15% for bend structure. For other structure, an increase of SEP by 2.43% was observed. Those results were confirmed by a "leave-one-out" run with the combined set of 21 FTIR spectra of proteins.     

Bacterial phylogeny based on 16S and 23S rRNA sequence analysis

Abstract: Molecular phylogeny increasingly supports the understanding of organismal relationships and provides the basis for the classification of microorganisms according to their natural affiliations. Comparative sequence analysis of ribosomal RNAs or the corresponding genes currently is the most widely used approach for the reconstruction of microbial phylogeny. The highly and less conserved primary and higher order structure elements of rRNAs document the history of microbial evolution and are informative for definite phylogenetic levels. An optimal alignment of the primary structures and a careful data selection are prerequisites for reliable phylogenetic conclusions. rRNA based phylogenetic trees can be reconstructed and the significance of their topologies evaluated by applying distance, maximum parsimony and maximum likelihood methods of phylogeny inference in comparison, and by fortuitous or directed resampling of the data set. Phylogenetic trees based on almost equivalent data sets of bacterial 23S and 16S rRNAs are in good agreement and their overall topologies are supported by alternative phylogenetic markers such as elongation factors and ATPase subunits. Besides their phylogenetic information content, the differently conserved primary structure regions of rRNAs provide target sites for specific hybridization probes which have been proven to be powerful tools for the identification of microbes on the basis of their phylogenetic relationships.     

TRANSLATING BETWEEN MICROEVOLUTIONARY PROCESS AND MACROEVOLUTIONARY PATTERNS: THE CORRELATION STRUCTURE OF INTERSPECIFIC DATA

As species evolve along a phylogenetic tree, we expect closely related species to retain some phenotypic similarities due to their shared evolutionary histories. The amount of expected similarity depends both on the hierarchical phylogenetic structure, and on the specific magnitude and types of evolutionary changes that accumulate during each generation. In this study, we show how models of microevolutionary change can be translated into the resulting macroevolutionary patterns. We illustrate how the structure of phenotypic covariances expected in interspecific measurements can be derived, and how this structure depends on the microevolutionary forces guiding phenotypic change at each generation. We then explore the covariance structure expected from several simple microevolutionary models of phenotypic evolution, including various combinations of random genetic drift, directional selection, stabilizing selection, and environmental change, as well as models of punctuated or burst-like evolution. We find that stabilizing selection leads to patterns of exponential decrease of between species covariance with phylogenetic distance. This is different from the usual linear patterns of decrease assumed in most comparative and systematic methods. Nevertheless, linear patterns of decrease can result from many processes in addition to random genetic drift, such as directional and fluctuating selection as well as modes of punctuated change. Our framework can be used to develop methods for (1) phylogenetic reconstruction; (2) inference of the evolutionary process from comparative data; and (3) conducting or evaluating statistical analyses of comparative data while taking phylogenetic history into account.     

Alterations in plasma biochemical composition in NO deficiency induced by L‐NAME in mice analysed by Fourier Transform Infrared Spectroscopy

Mouse model of nitric oxide deficiency, induced by prolonged treatment with N^G‐nitro‐L‐arginine methyl ester (L‐NAME) was used for infrared spectroscopy (FTIR) analysis of plasma. L‐NAME leads to increased peripheral resistance and systemic hypertension. Classification of spectral response was by principal component analysis (PCA) and linear discriminant analysis (LDA). PCA allowed to separate each animal group showing that FTIR spectra are sensitive to development of NO‐deficiency on contrary to blood pressure values indicating hypertension. Globally, the most pronounced spectral alternations were observed in the second and third week of L‐NAME treatment indicating that infrared signature of blood plasma can serve as indicator of early and late stages of the disease. The PLS‐DA method provided >95% classification accuracy. Spectral features characteristic for L‐NAME treatment were mainly associated with an elevated level of proteins accompanied by a decrease of a tyrosine content and changes in lipids/phospholipid concentration. In our work we discuss these changes for which statistically significant differences (p < 0.05 – 0.005) were observed between spectra collected for each time‐point of the L‐NAME treatment versus control subjects. We demonstrated for the first time that NO‐deficiency and hypertension resulted in changes in biochemical profile of plasma that was detected by FTIR spectroscopy.

     

Bladder cancer diagnosis from bladder wash by Fourier transform infrared spectroscopy as a novel test for tumor recurrence

This study proposes Fourier Transform Infrared (FTIR) spectroscopy as a more sensitive, rapid, non‐destructive and operator‐independent analytical diagnostic method for bladder cancer recurrence from bladder wash than other routinely used urine cytology and cystoscopy methods. A total of 136 patients were recruited. FTIR spectroscopic experiments were carried out as a blind study, the classification results of which were then compared with those of cytology and cystoscopy. Firstly, 71 samples (n = 37; bladder cancer and n = 34; control) were studied with transmittance FTIR spectroscopy. After achieving successful differentiation of the groups, to develop a more rapid diagnostic tool and check the reproducibility of the results, the work was continued with different samples (n = 65 as n = 44; bladder cancer and n = 21; control), using the reflection mode (ATR) of FTIR spectroscopy by a different operator. The results revealed significant alterations in moleculer content in the cancer group. Based on the spectral differences, using transmittance FTIR spectroscopy coupled with chemometrics, the diseased group was successfully differentiated from the control. When only carcinoma group was taken into consideration a sensitivity value of 100% was achieved. Similar results were also obtained by ATR‐FTIR spectroscopy. This study shows the power of infrared spectroscopy in the diagnosis of bladder cancer.

     

The influence of multiple functional demands on morphological diversification: A test on turtle shells

Organismal parts are often involved in the performance of more than one function. The role of trade‐offs in influencing phenotypic evolution of such parts is well‐studied; less well‐understood is their role in influencing phenotypic diversity. Increases in the number of functions a part is involved in may inhibit subsequent diversification, as the number of trade‐offs increases. Alternately, such an increase might promote phenotypic diversification, by increasing adaptive landscape complexity and promoting specialization for different roles. We compare these predictions by testing whether aquatic turtle shells, which resist loads, act as hydrodynamic elements, facilitate self‐righting, and exchange heat with the environment, differ in phenotypic diversity from those of terrestrial species, which perform all the same functions except for hydrodynamics. We used 53 3D landmarks digitized on 2722 specimens of 274 hard‐shelled turtle species to quantify shell shape variation, and a set of phylogenetic hypotheses to examine evolutionary patterns. Terrestrial turtles consistently had higher phenotypic diversity than aquatic species. Differences are not due to differences in the rates of evolution between the two groups, but rather differences in evolutionary mode. Thus this study supports the traditional view of the role of multiple functions in determining phenotypic diversity.     

Label‐free quantitative chemical imaging and classification analysis of adipogenesis using mouse embryonic stem cells

Stem cells have received much attention recently for their potential utility in regenerative medicine. The identification of their differentiated progeny often requires complex staining procedures, and is challenging for intermediary stages which are a priori unknown. In this work, the ability of label‐free quantitative coherent anti‐Stokes Raman scattering (CARS) micro‐spectroscopy to identify populations of intermediate cell states during the differentiation of murine embryonic stem cells into adipocytes is assessed. Cells were imaged at different days of differentiation by hyperspectral CARS, and images were analysed with an unsupervised factorization algorithm providing Raman‐like spectra and spatially resolved maps of chemical components. Chemical decomposition combined with a statistical analysis of their spatial distributions provided a set of parameters that were used for classification analysis. The first 2 principal components of these parameters indicated 3 main groups, attributed to undifferentiated cells, cells differentiated into committed white pre‐adipocytes, and differentiating cells exhibiting a distinct protein globular structure with adjacent lipid droplets. An unsupervised classification methodology was developed, separating undifferentiated cell from cells in other stages, using a novel method to estimate the optimal number of clusters. The proposed unsupervised classification pipeline of hyperspectral CARS data offers a promising new tool for automated cell sorting in lineage analysis.      

Robust Classification of Functional and Quantitative Image Data Using Functional Mixed Models

Summary This article introduces new methods for performing classification of complex, high‐dimensional functional data using the functional mixed model (FMM) framework. The FMM relates a functional response to a set of predictors through functional fixed and random effects, which allows it to account for various factors and between‐function correlations. The methods include training and prediction steps. In the training steps we train the FMM model by treating class designation as one of the fixed effects, and in the prediction steps we classify the new objects using posterior predictive probabilities of class. Through a Bayesian scheme, we are able to adjust for factors affecting both the functions and the class designations. While the methods can be used in any FMM framework, we provide details for two specific Bayesian approaches: the Gaussian, wavelet‐based FMM (G‐WFMM) and the robust, wavelet‐based FMM (R‐WFMM). Both methods perform modeling in the wavelet space, which yields parsimonious representations for the functions, and can naturally adapt to local features and complex nonstationarities in the functions. The R‐WFMM allows potentially heavier tails for features of the functions indexed by particular wavelet coefficients, leading to a down‐weighting of outliers that makes the method robust to outlying functions or regions of functions. The models are applied to a pancreatic cancer mass spectroscopy data set and compared with other recently developed functional classification methods.     

Phylogenetic systematics of microorganisms inhabiting thermal environments

Thermal habitats harbor specialized communities of thermophilic microorganisms, primarily prokaryotes. This review considers modern systematics of prokaryotes and the place of thermophilic archaea and bacteria in it. Among the existing hierarchical classifications of prokaryotes, the bulk of attention is given to the one accepted in the current second edition of "Bergey's Manual of Systematic Bacteriology", which is primarily based on 16S rRNA phylogeny and phenotypic properties of the organisms. Analysis of the genomics data shows that they on the whole agree with the 16S rRNA-based system, although revealing the significance of the evolutionary role of lateral transfer, duplication, and loss of genes. According to the classification elaborated in the current edition of "Bergey's Manual", the prokaryotes currently culturable under laboratory conditions are distributed among 26 phyla, two of which belong to the domain Archaea and 24 to the domain Bacteria. Six phyla contain exclusively thermophiles, and eleven phyla contain thermophiles along with mesophiles, thermophiles being usually separated phylogenetically and representing high-level taxa (classes, orders). In light of the data on the topology of the 16S rRNA-based phylogenetic tree and some other data, this review discusses the probable hyperthermophilic nature of the universal common ancestor.     

Comparative methods for association studies: a case study on metabolite variation in a Brassica rapa core collection

Background

Association mapping is a statistical approach combining phenotypic traits and genetic diversity in natural populations with the goal of correlating the variation present at phenotypic and allelic levels. It is essential to separate the true effect of genetic variation from other confounding factors, such as adaptation to different uses and geographical locations. The rapid availability of large datasets makes it necessary to explore statistical methods that can be computationally less intensive and more flexible for data exploration.

Methodology/Principal Findings

A core collection of 168 Brassica rapa accessions of different morphotypes and origins was explored to find genetic association between markers and metabolites: tocopherols, carotenoids, chlorophylls and folate. A widely used linear model with modifications to account for population structure and kinship was followed for association mapping. In addition, a machine learning algorithm called Random Forest (RF) was used as a comparison. Comparison of results across methods resulted in the selection of a set of significant markers as promising candidates for further work. This set of markers associated to the metabolites can potentially be applied for the selection of genotypes with elevated levels of these metabolites.

Conclusions/Significance

The incorporation of the kinship correction into the association model did not reduce the number of significantly associated markers. However incorporation of the STRUCTURE correction (Q matrix) in the linear regression model greatly reduced the number of significantly associated markers. Additionally, our results demonstrate that RF is an interesting complementary method with added value in association studies in plants, which is illustrated by the overlap in markers identified using RF and a linear mixed model with correction for kinship and population structure. Several markers that were selected in RF and in the models with correction for kinship, but not for population structure, were also identified as QTLs in two bi-parental DH populations.     

Quick divergence but slow convergence during ecotype formation in lake and stream stickleback pairs of variable age

When genetic constraints restrict phenotypic evolution, diversification can be predicted to evolve along so‐called lines of least resistance. To address the importance of such constraints and their resolution, studies of parallel phenotypic divergence that differ in their age are valuable. Here, we investigate the parapatric evolution of six lake and stream threespine stickleback systems from Iceland and Switzerland, ranging in age from a few decades to several millennia. Using phenotypic data, we test for parallelism in ecotypic divergence between parapatric lake and stream populations and compare the observed patterns to an ancestral‐like marine population. We find strong and consistent phenotypic divergence, both among lake and stream populations and between our freshwater populations and the marine population. Interestingly, ecotypic divergence in low‐dimensional phenotype space (i.e. single traits) is rapid and seems to be often completed within 100 years. Yet, the dimensionality of ecotypic divergence was highest in our oldest systems and only there parallel evolution of unrelated ecotypes was strong enough to overwrite phylogenetic contingency. Moreover, the dimensionality of divergence in different systems varies between trait complexes, suggesting different constraints and evolutionary pathways to their resolution among freshwater systems.     

Random forests, a novel approach for discrimination of fish populations using parasites as biological tags

Due to the complexity of host-parasite relationships, discrimination between fish populations using parasites as biological tags is difficult. This study introduces, to our knowledge for the first time, random forests (RF) as a new modelling technique in the application of parasite community data as biological markers for population assignment of fish. This novel approach is applied to a dataset with a complex structure comprising 763 parasite infracommunities in population samples of Atlantic cod, Gadus morhua, from the spawning/feeding areas in five regions in the North East Atlantic (Baltic, Celtic, Irish and North seas and Icelandic waters). The learning behaviour of RF is evaluated in comparison with two other algorithms applied to class assignment problems, the linear discriminant function analysis (LDA) and artificial neural networks (ANN). The three algorithms are used to develop predictive models applying three cross-validation procedures in a series of experiments (252 models in total). The comparative approach to RF, LDA and ANN algorithms applied to the same datasets demonstrates the competitive potential of RF for developing predictive models since RF exhibited better accuracy of prediction and outperformed LDA and ANN in the assignment of fish to their regions of sampling using parasite community data. The comparative analyses and the validation experiment with a 'blind' sample confirmed that RF models performed more effectively with a large and diverse training set and a large number of variables. The discrimination results obtained for a migratory fish species with largely overlapping parasite communities reflects the high potential of RF for developing predictive models using data that are both complex and noisy, and indicates that it is a promising tool for parasite tag studies. Our results suggest that parasite community data can be used successfully to discriminate individual cod from the five different regions of the North East Atlantic studied using RF.