Genome-enabled prediction of genetic values using radial basis function neural networks

The availability of high density panels of molecular markers has prompted the adoption of genomic selection (GS) methods in animal and plant breeding. In GS, parametric, semi-parametric and non-parametric regressions models are used for predicting quantitative traits. This article shows how to use neural networks with radial basis functions (RBFs) for prediction with dense molecular markers. We illustrate the use of the linear Bayesian LASSO regression model and of two non-linear regression models, reproducing kernel Hilbert spaces (RKHS) regression and radial basis function neural networks (RBFNN) on simulated data and real maize lines genotyped with 55,000 markers and evaluated for several trait-environment combinations. The empirical results of this study indicated that the three models showed similar overall prediction accuracy, with a slight and consistent superiority of RKHS and RBFNN over the additive Bayesian LASSO model. Results from the simulated data indicate that RKHS and RBFNN models captured epistatic effects; however, adding non-signal (redundant) predictors (interaction between markers) can adversely affect the predictive accuracy of the non-linear regression models.     

Experience-consistent modeling for radial basis function neural networks

We develop a new approach to the design of neural networks, which utilizes a collaborative framework of knowledge-driven experience. In contrast to the "standard" way of developing neural networks, which explicitly exploits experimental data, this approach incorporates a mechanism of knowledge-driven experience. The essence of the proposed scheme of learning is to take advantage of the parameters (connections) of neural networks built in the past for the same phenomenon (which might also exhibit some variability over time or space) for which are interested to construct the network on a basis of currently available data. We establish a conceptual and algorithmic framework to reconcile these two essential sources of information (data and knowledge) in the process of the development of the network. To make a presentation more focused and come up with a detailed quantification of the resulting architecture, we concentrate on the experience-based design of radial basis function neural networks (RBFNNs). We introduce several performance indexes to quantify an effect of utilization of the knowledge residing within the connections of the networks and establish an optimal level of their use. Experimental results are presented for low-dimensional synthetic data and selected datasets available at the Machine Learning Repository.     

Nonparametric discriminant analysis of phytoplankton species using data from analytical flow cytometry

BACKGROUND: Analytical flow cytometry (AFC) provides rapid and accurate measurement of particles from heterogeneous populations. AFC has been used to classify and identify phytoplankton species, but most methods of discriminant analysis of resulting data have depended on normality assumptions and outcomes have been disappointing. METHODS AND RESULTS: In this study, we consider nonparametric methods based on density estimation. In addition to the familiar kernel method, methods based on wavelets are also implemented. Full five-dimensional wavelet estimation proves to be computationally prohibitive with current workstation power, so we employ projection pursuit for reduction of dimensionality. AFC typically produces very large samples, so we also investigate data simplification through binning. Further modifications to the discrimination strategy are suggested by specific features of phytoplankton data, namely, a hierarchical group structure, the possible presence of many groups, and the likelihood of encountering an aberrant group in a test sample. CONCLUSIONS: We apply all the resultant procedures to appropriate subsets of a very large data set, demonstrate their efficacy, and compare their error rates with those of more conventional methods. We further show that incorporation of the specific features of phytoplankton data into the analysis leads to improved results and provides a general framework for analysis of such data.     

Comparison of five clustering algorithms to classify phytoplankton from flow cytometry data.

BACKGROUND: Artificial neural networks (ANNs) have been shown to be valuable in the analysis of analytical flow cytometric (AFC) data in aquatic ecology. Automated extraction of clusters is an important first stage in deriving ANN training data from field samples, but AFC data pose a number of challenges for many types of clustering algorithm. The fuzzy k-means algorithm recently has been extended to address nonspherical clusters with the use of scatter matrices. Four variants were proposed, each optimizing a different measure of clustering "goodness." METHODS: With AFC data obtained from marine phytoplankton species in culture, the four fuzzy k-means algorithm variants were compared with each other and with another multivariate clustering algorithm based on critical distances currently used in flow cytometry. RESULTS: One of the algorithm variants (adaptive distances, also known as the Gustafson--Kessel algorithm) was found to be robust and reliable, whereas the others showed various problems. CONCLUSIONS: The adaptive distances algorithm was superior in use to the clustering algorithms against which it was tested, but the problem of automatic determination of the number of clusters remains to be addressed.     

Analysis of phytoplankton by flow cytometry

Optical properties of eight algae species were measured on a flow cytometer. Forward and perpendicular light scatter measurements provide information on the size and shape of algae cells. The intensity of chlorophyll fluorescence varies greatly among the studied algae species and can be used to distinguish them. Measurements of chlorophyll fluorescence after excitation with different wavelengths provide a fluorescence excitation spectrum for each species over the available wavelength range. These spectra reflect the different photosynthetic pigment contents of the species. Staining algae cells with the DNA stains, Hoechst 33342 and DAPI, provides two additional optical parameters to distinguish algae populations: blue nuclear fluorescence and yellow granular fluorescence. The combination of these optical measurements enables the distinction of each algae species into a small cluster in a hyperspace of parameters. The automation of phytoplankton analysis on the flow cytometer may lead to the rapid and objective assessment of water quality.     

Parameter estimation for stiff equations of biosystems using radial basis function networks

Background  

The modeling of dynamic systems requires estimating kinetic parameters from experimentally measured time-courses. Conventional global optimization methods used for parameter estimation, e.g. genetic algorithms (GA), consume enormous computational time because they require iterative numerical integrations for differential equations. When the target model is stiff, the computational time for reaching a solution increases further.     

Improvement of phytoplankton culture isolation using single cell sorting by flow cytometry

Flow cytometry provides a tool to physically sort single algal cells in order to obtain clonal cultures. During sorting, cells are submitted to physical stress factors such as high fluidic pressure, exposure to the laser beam, electrostatic charges, deflection through high voltage fields, and collisions with container surfaces. All of these can damage the cells of interest and success rates for initiation of cultures from flow‐sorted cells are generally very low. We found that the addition of bovine serum albumin in the culture medium into which cells were sorted drastically improved the success of initiation of pico‐ and nano‐eukaryotic phytoplankton strains. Adding a mixture of antibiotics (Penicillin, Neomycin, Streptomycin) to the medium in order to slow down bacterial growth further improved culture development. This approach was successfully used to isolate taxonomically diverse strains, including novel taxa, from a fresh sample obtained in the English Channel and from enrichment cultures established during an Atlantic meridional transect cruise. We anticipate that these improvements will be useful to clone or purify existing cultures and to isolate novel cultures from oceanic samples.     

Potential of radial basis function neural networks in discriminating benign from malignant lesions of the lower urinary tract

OBJECTIVE: To investigate the potential value of morphometry and neural network tools for discriminating benign from malignant nuclei and lesions of the lower urinary tract. STUDY DESIGN: The study group consisted of 33 cases of lithiasis, 41 cases of inflammation, 66 cases of benign hyperplasia of the prostate, 4 cases of carcinoma in situ, 48 cases of grade 1 transitional cell carcinoma of the bladder (TCCB) and 123 cases of grade 2 and 3 TCCB. Images of routinely processed voided urine smears stained by the Giemsa technique were analyzed by a custom image analysis system. Analysis of the images gave a data set of features from 31,158 nuclei. A radial basis function (RBF)-type neural network was employed to discriminate benign from malignant nuclei, based on the extracted morphometric and textural features. Subsequently a second RBF classifier was employed to discriminate benign from malignant cases. The nuclei from 156 randomly selected cases (50% of total cases) was used as a training set, and the nuclei from the remaining 159 cases made up the test set. Similarly, in an attempt to discriminate at the patient level, the same 156 cases were used to train an RBF classifier; the remaining 159 cases were used for the test set. The cases used for training and testing the 2 classifiers (nuclear and patient level) were the same for the 2 kinds of classifiers. RESULTS: Application of the RBF classifier permitted the correct classification of 93.64% of benign nuclei and 85.61% of malignant, giving an overall accuracy of 84.45%. At the patient level the RBF classifier permitted an overall accuracy of 94.97%. These results were on the test sets. CONCLUSION: The role of nuclear morphologic features in the cytologic diagnosis of lower urinary tract alterations was confirmed by the results of this study. The observed overlap in feature space indicates that the nuclear characteristics do not form strictly separate clusters; that fact explains the difficulty morphologists have with reproducible identification of nuclei from the lower urinary tract. Application of RBF offers good classification at the nuclear and patient level and promises to become a powerful tool for everyday practice in the cytologic laboratory.     

Combining regression trees and radial basis function networks

We describe a method for non-parametric regression which combines regression trees with radial basis function networks. The method is similar to that of Kubat, who was first to suggest such a combination, but has some significant improvements. We demonstrate the features of the new method, compare its performance with other methods on DELVE data sets and apply it to a real world problem involving the classification of soybean plants from digital images.     

Predicting dominant phytoplankton quantities in a reservoir by using neural networks

A 14.6 m long profile from the northern part of the Hulun lake, the furthest north of the large lakes of China, has provided a sedimentary and diatom record since the late Glacial. The chronological sequence was established based on 10 radiocarbon dates. Sedimentological study and diatom analysis are synthesized for the reconstruction of the history of lake-level changes. The results show that the Hulun basin was not occupied by a lake during the Last Glaciation. A rapid transition to a deep lake occurred since 12850 yr B.P., and this high level phase lasted to 11200 yr B.P., although there existed several subordinate lake level fluctuations. An abrupt lake level drop and dry climatic conditions occurred during 11200–10600 yr B.P. The lake became deeper again from 10600 yr B.P. to 10300 yr B.P. Hulun lake at the early Holocene was characterized by the low lake-level, and the lake level rose again in 7200–5800 yr B.P., though the lake-levels changed quite variably. A dry condition occurred and lake level declined again during 5800–3000 yr B.P. The presence of the palaeosol on the top of this profile indicates the persistence of low lake levels after 3000 yr B.P. The comparison with the other lake-level records from northern China has suggested that the Hulun Lake shows a different lake level history from the lakes in monsoon areas.     

Constructing a query-able radial basis function artificial neural network

Artificial neural networks will be more widely accepted as standard engineering tools if their reasoning process can be made less opaque. This paper describes NetQuery, an explanation mechanism that extracts meaningful explanations from trained Radial Basis Function (RBF) networks. RBF networks are well suited for explanation generation because they contain a set of locally tuned units. Standard RBF networks are modified to identify dependencies between the inputs, to be sparsely connected, and to have an easily interpretable output layer. Given these modifications, the network architecture can be used to extract "Why?" and "Why not?" explanations from the network in terms of excitatory and inhibitory in-puts and their linear relationships, greatly simplified by a run-time pruning algorithm. These query results are validated by creating an expert system based on the explanations. NetQuery is also able to inform a user about a possible change in category for a given pattern by responding to a "How can I...?" query. This kind of query is extremely useful when analyzing the quality of a pattern set.     

Training radial basis function neural networks: effects of training set size and imbalanced training sets

Obtaining training data for constructing artificial neural networks (ANNs) to identify microbiological taxa is not always easy. Often, only small data sets with different numbers of observations per taxon are available. Here, the effect of both size of the training data set and of an imbalanced number of training patterns for different taxa is investigated using radial basis function ANNs to identify up to 60 species of marine microalgae. The best networks trained to discriminate 20, 40 and 60 species respectively gave overall percentage correct identification of 92, 84 and 77%. From 100 to 200 patterns per species was sufficient in networks trained to discriminate 20, 40 or 60 species. For 40 and 60 species data sets an imbalance in the number of training patterns per species always affected training success, the greater the imbalance the greater the effect. However, this could be largely compensated for by adjusting the networks using a posteriori probabilities, estimated as network output values.     

Identification of efflux proteins using efficient radial basis function networks with position‐specific scoring matrices and biochemical properties

Efflux proteins are membrane proteins, which are involved in the transportation of multidrugs. The annotation of efflux proteins in genomic sequences would aid to understand the function. Although the percentage of membrane proteins in genomes is estimated to be 25–30%, there is no information about the content of efflux proteins. For annotating such class of proteins it is necessary to develop a reliable method to identify efflux proteins from amino acid sequence information. In this work, we have developed a method based on radial basis function networks using position specific scoring matrices (PSSM) and amino acid properties. We noticed that the C‐terminal domain of efflux proteins contain vital information for discrimination. Our method showed an accuracy of 78 and 92% in discriminating efflux proteins from transporters and membrane proteins, respectively using fivefold cross‐validation. We utilized our method for annotating the genomes E. coli and P. aeruginosa and it predicted 8.7 and 9.2% of proteins as efflux proteins in these genomes, respectively. The predicted efflux proteins have been compared with available experimental data and we observed a very good agreement between them. Further, we developed a web server for classifying efflux proteins and it is freely available at http://rbf.bioinfo.tw/～sachen/EFFLUXpredict/Efflux‐RBF.php . We suggest that our method could be an effective tool for annotating efflux proteins in genomic sequences.Proteins 2013. © 2013 Wiley Periodicals, Inc.     

Syringe pumped high speed flow cytometry of oceanic phytoplankton.

BACKGROUND: Nanophytoplankton (2-20 microm) are less numerous than picophytoplankton (<2 microm) in the oceans but their biomass and production are comparable and sometimes higher. The accuracy of cytometry-based enumeration of phytoplankton ultimately depends on cell abundance and sample flow rate. Commercial flow cytometers in which sheath and core streams are driven by air pressure cannot produce sufficiently high, stable sample flow rate. The present study demonstrates the applicability of a syringe pump for flow cytometric enumeration of oceanic nanophytoplankton on two meridional transects across the Atlantic Ocean. METHODS: Commercially available syringe pumps were used to deliver live phytoplankton samples into a flow cell of standard flow cytometers (FACSort, FACSCalibur, BD) with increased flow rate of > 1.0 ml min(-) (1) compared to the normal air pressure sample delivery of < 0.1 ml min(-) (1). An auxiliary application of syringe pump flow cytometry for calibrating 0.5 microm bead concentration standards is also discussed. RESULTS: The results demonstrated that flow cytometry of samples injected at rates above 0.1 ml min(-) (1) is achievable and worthwhile. Counts of phytoplankton in air and syringe pumped samples agreed closely. Syringe pumping of samples offered a broader range of flow rates up to 0.8-1.0 ml min(-) (1) without detrimental effect on flow cytometric enumeration of cells. The increased number of coincidences at high flow rates led to an approximate 10% decrease of Cyanobacteria counts when the acquisition rate approached 1,000 particles s(-) (1), but seemed to have a lesser effect on counting rarer phytoplankton. The syringe pump flow cytometry allowed enumeration of phytoplankton groups at concentrations of 5-100 cells ml(-) (1), cell concentrations equivalent to those of Cyanobacteria in the twilight deep ocean. CONCLUSION: The proposed syringe pump modification of a FACS instrument represents a significant improvement for accurate enumeration of the less abundant phytoplankton and so gives better estimations of phytoplankton distribution and standing stocks.     

Multi-user system for analysis of data from flow cytometry.

A new program is described for the analysis of DNA histograms from flow cytometry. The fundamental model representing the cell population is similar to one described previously. It assumes the population is grouped into compartments, each consisting of cells having approximately the same DNA content. After staining the cells with an appropriate fluorochrome, the fluorescence distribution of cells within each compartment is assumed to be Gaussian. In the present algorithm, the parameters of the model can either be computed directly by the program from the data, or can be specified as input by the user. When synchronous cell populations lacking distinct G1 and G2/M phases are analyzed, the parameter values must first be obtained using an appropriate control. Percentages of cells in the various compartments are computed using a gradient search method described by Bevington.     

Identification of nuclei from apoptotic, necrotic, and viable lymphoid cells by using multiparameter flow cytometry.

BACKGROUND: Methods widely used to detect apoptosis do not allow us to easily distinguish between nuclei from viable or necrotic cells. Even if apoptosis and necrosis seem to occur as alternatives at the single cell level, they could be present simultaneously in a cell population much more frequently than expected. For this reason, attention was focused on attempting to recognize, by multiparameter flow cytometry, the characteristics of viable cells and of apoptotic or necrotic dead cells. METHODS: Apoptosis and necrosis were induced in vitro in murine thymocytes and lymphocytes from adult peripheral blood by using dexamethasone or prostaglandin E2 treatment and heat shock at 60 degrees C or hydrogen peroxide, respectively. Traditional methods, such as DNA gel electrophoresis and propidium iodide staining followed by single-fluorescence analysis or annexin-V-fluorescein isothiocyanate plus propidium iodide staining by using flow cytometry, were compared with a new method. This method consisted of combined light-scatter and red fluorescence analysis by flow cytometry after isolation of nuclei by hypotonic solution as well as high-dose detergent treatment and DNA staining with propidium iodide. RESULTS: Results showed that, although traditional methods such as DNA-gel electrophoresis and single-parameter fluorescence flow cytometry analysis were unable, as expected, to discriminate among viability, apoptosis, and necrosis, our new method has enabled us to easily identify nuclei from viable, apoptotic, and necrotic cells. Results obtained by using our method were comparable to those obtained by using two-color analysis of cells after propidium iodide/annexin V staining. CONCLUSIONS: A highly reproducible, inexpensive, rapid, and easily accessible method of analysis has been developed for simultaneously detecting apoptosis and necro sis.     

Evaluation of platelet function by flow cytometry

Platelet function in whole blood can be comprehensively evaluated by flow cytometry. Flow cytometry can be used to measure platelet reactivity, circulating activated platelets, platelet-platelet aggregates, leukocyte-platelet aggregates, procoagulant platelet-derived microparticles, and calcium flux. Clinical applications of whole blood flow cytometric assays of platelet function in disease states (e.g., acute coronary syndromes, angioplasty, and stroke) may include identification of patients who would benefit from additional antiplatelet therapy and prediction of ischemic events. Circulating monocyte-platelet aggregates appear to be a more sensitive marker of in vivo platelet activation than circulating P-selectin-positive platelets. Flow cytometry can also be used in the following clinical settings: monitoring of GPIIb-IIIa antagonist therapy, diagnosis of inherited deficiencies of platelet surface glycoproteins, diagnosis of storage pool disease, diagnosis of heparin-induced thrombocytopenia, and measurement of the rate of thrombopoiesis.     

Analysing phosphorylation-based signalling networks by phospho flow cytometry

Analysis of signalling events by classical biochemical approaches is limited as the outcome is an averaged readout for protein activation of a single protein within a cell population. This is a clear restriction when addressing signalling events in mixed populations or subpopulations of cells. By combining flow cytometry with a panel of phosphospecific antibodies against several signal molecules simultaneously in a multi-parameter phospho flow cytometry analysis it is possible to obtain a higher level of understanding of the signal transduction dynamics at a single cell level. In addition, analysis of mixed cell populations makes it possible to study cells ex vivo in a state more closely resembling the in vivo situation. The multimeric analysis yields information on combinations of signals turned on and off in specific settings such as disease (signal nodes) that can be used for biomarker analysis and for development of drug screening strategies. Prostaglandin E₂ (PGE₂) is known to signal through four G-protein coupled transmembrane receptors, EP1-4, activating a multitude of potential signalling pathways. The analysis of the PGE₂ signalling network elicited by activation of the four EP receptors in lymphoid cells revealing several signalling nodes is reviewed as an example.     

Using phytoplankton and flow cytometry to analyze grazing by marine organisms

Phytoplankton can, through their autofluorescent characteristics, be thought of as tracer particles in much the same way as fluorescent microspheres when used in particle uptake experiments. Flow cytometric techniques can be used to differentiate phytoplankton from other suspended particles by the two primary autofluorescing photosynthetic pigments, chlorophyll and phycoerythrin. Based on these characteristics, phytoplankton assemblages have been used to assess grazing rates, particle selectivity, and endocytotic abilities in various marine species, from single-celled organisms to higher invertebrates.