Statistical analysis and graphical display of multivariate data on the Macintosh

Two Macintosh programs written for multivariate data analysisand multivariate data graphical display are presented. MacMulincludes principal component analysis (PCA), correspondenceanalysis (CA) and multiple correspondence analysis (MCA), witha complete, original and unified set of numerical aids to interpretation.GraphMu is designed for drawing collections of elementary graphics(curves, maps, graphical models) thus allowing comparisons betweenvariables, individuals, and principal axes planes of multivariatemethods. Both programs are self-documented applications andmake full use of the user-oriented graphical interface of theMacintosh to simplify the process of analysing data sets. Anexample is described to show the results obtained on a smallecological data set. Received on January 24, 1989; accepted on July 17, 1989     

Statistical and graphical methods for quality control determination of high-throughput screening data

High-throughput screening (HTS) is used in modern drug discovery to screen hundreds of thousands to millions of compounds on selected protein targets. It is an industrial-scale process relying on sophisticated automation and state-of-the-art detection technologies. Quality control (QC) is an integral part of the process and is used to ensure good quality data and mini mize assay variability while maintaining assay sensitivity. The authors describe new QC methods and show numerous real examples from their biologist-friendly Stat Server HTS application, a custom-developed software tool built from the commercially available S-PLUS and Stat Server statistical analysis and server software. This system remotely processes HTS data using powerful and sophisticated statistical methodology but insulates users from the technical details by outputting results in a variety of readily interpretable graphs and tables. It allows users to visualize HTS data and examine assay performance during the HTS campaign to quickly react to or avoid quality problems.     

On graphical and numerical representation of protein sequences

A new approach using a 3-D Cartesian coordinate system to represent protein sequences has been derived. By the 3-D Graphical representation we make a comparison of sequences belonging to nine different proteins.     

Statistical analysis of radioimmunoassay data

The statistical processing of radioimmunoassay data is discussed, with special emphasis on fitting the standard curve, screening the data for aberrant readings and combining separate estimations from a single sample.     

A graphical representation of genetic and physical maps: the Marey map.

A novel, simultaneous, visual representation of sex-specific genetic maps and physical maps is introduced. Such maps, called Marey maps, provide direct comparisons of multiple genetic maps and elucidate the relationship of recombination frequency to physical distance.     

GRR: graphical representation of relationship errors

SUMMARY: A graphical tool for verifying assumed relationships between individuals in genetic studies is described. GRR can detect many common errors using genotypes from many markers. AVAILABILITY: GRR is available at http://bioinformatics.well.ox.ac.uk/GRR.     

Complete genomes in WWW Entrez: data representation and analysis.

MOTIVATION: The large amount of genome sequence data now publicly available can be accessed through the National Center for Biotechnology Information (NCBI) Entrez search and retrieval system, making it possible to explore data of a breadth and scope exceeding traditional flatfile views. RESULTS: Here we report recent improvements for completely sequenced genomes from viruses, bacteria, and yeast. Flexible web based views, precomputed relationships, and immediate access to analytical tools provide scientists with a portal into the new insights to be gained from completed genome sequences. AVAILABILITY: Entrez Genomes can be accessed on the World Wide Web at http://www.ncbi.nlm.nih.gov/Entrez/Genome/ org.html.     

Statistical analysis of oligonucleotide microarray data

Microchip arrays have become one of the most rapidly growing techniques for monitoring gene expression at the genomic level and thereby gaining valuable insight about various important biological mechanisms. Examples of such mechanisms are: identifying disease-causing genes, genes involved in the regulation of some aspect of the cell cycle, etc. In this article, we discuss the problem of estimating gene expression based on a proper statistical model. More precisely, we show how the model introduced by Li and Wong can be used in its full bivariate generality to provide a new measure of gene expression from high-density oligonucleotide arrays. We also present a second gene expression index based on a new way of reducing the model into a simpler univariate model. In both cases, the gene expression indices are shown to be unbiased and to have lower variance than the established ones. Moreover, we present a bootstrap method aiming at providing non-parametric confidence intervals for the expression index.     

Statistical analysis of algal and water quality data

Data on cyanobacteria (blue-green algae) are generallycollected on a reactive basis, frequently in responseto bloom events. Such data presents a biased andincomplete snapshot of water quality. This paper looksat two typical data sets for UK waters showing thatwhile statistics may be used to describe the data theyare of limited use in forecasting. Suggestions ofappropriate tests for small and sparse data sets aremade.     

Statistical analysis of temporal evolution in single-neuron firing rates

A fundamental methodology in neurophysiology involves recording the electrical signals associated with individual neurons within brains of awake behaving animals. Traditional statistical analyses have relied mainly on mean firing rates over some epoch (often several hundred milliseconds) that are compared across experimental conditions by analysis of variance. Often, however, the time course of the neuronal firing patterns is of interest, and a more refined procedure can produce substantial additional information. In this paper we compare neuronal firing in the supplementary eye field of a macaque monkey across two experimental conditions. We take the electrical discharges, or 'spikes', to be arrivals in a inhomogeneous Poisson process and then model the firing intensity function using both a simple parametric form and more flexible splines. Our main interest is in making inferences about certain characteristics of the intensity, including the timing of the maximal firing rate. We examine data from 84 neurons individually and also combine results into a hierarchical model. We use Bayesian estimation methods and frequentist significance tests based on a nonparametric bootstrap procedure. We are thereby able to conclude that a substantial fraction of the neurons exhibit important temporal differences in firing intensity across the two conditions, and we quantify the effect across the population of neurons.     

Using process diagrams for the graphical representation of biological networks

With the increased interest in understanding biological networks, such as protein-protein interaction networks and gene regulatory networks, methods for representing and communicating such networks in both human- and machine-readable form have become increasingly important. Although there has been significant progress in machine-readable representation of networks, as exemplified by the Systems Biology Mark-up Language (SBML) (http://www.sbml.org) issues in human-readable representation have been largely ignored. This article discusses human-readable diagrammatic representations and proposes a set of notations that enhances the formality and richness of the information represented. The process diagram is a fully state transition-based diagram that can be translated into machine-readable forms such as SBML in a straightforward way. It is supported by CellDesigner, a diagrammatic network editing software (http://www.celldesigner.org/), and has been used to represent a variety of networks of various sizes (from only a few components to several hundred components).     

A minicomputer program for rapid graphical and statistical analysis of laboratory data

The utility of a FORTRAN program package, which enables the scientific investigator to make a rapid assessment of laboratory data is described. Data are submitted from the keyboard or specified disk files in the form of coordinate pairs. The program includes routines for plotting values as a series of X-Y pairs on the computer video monitor or for comparing the X and Y arrays via paired differences and Student's t-test. A least squares linear regression of plotted data may also be called. Data modification, curve fitting, and I/O are easily handled in either single pair or column format. Examples of both statistical and graphical data analysis are presented.     

Statistical design and the analysis of gene expression microarray data

Gene expression microarrays are an innovative technology with enormous promise to help geneticists explore and understand the genome. Although the potential of this technology has been clearly demonstrated, many important and interesting statistical questions persist. We relate certain features of microarrays to other kinds of experimental data and argue that classical statistical techniques are appropriate and useful. We advocate greater attention to experimental design issues and a more prominent role for the ideas of statistical inference in microarray studies.     

Statistical analysis of antigen receptor spectratype data

MOTIVATION: The effectiveness of vertebrate adaptive immunity depends crucially on the establishment and maintenance of extreme diversity in the antigen receptor repertoire. Spectratype analysis is a method used in clinical and basic immunological settings in which antigen receptor length diversity is assessed as a surrogate for functional diversity. The purpose of this paper is to describe the systematic derivation and application of statistical methods for the analysis of spectratype data. RESULTS: The basic probability model used for spectratype analysis is the multinomial model with n, the total number of counts, indeterminate. We derive the appropriate statistics and statistical procedures for testing hypotheses regarding differences in antigen receptor distributions and variable repertoire diversity in different treatment groups.We then apply these methods to spectratype data obtained from several healthy donors to examine the differences between normal CD4+ and CD8+ T cell repertoires, and to data from a thymus transplant patient to examine the development of repertoire diversity following the transplant.