Adjusting for confounding due to population admixture when estimating the effect of candidate genes on quantitative traits

When analyzing the relationship between allelic variability and traits, a potential source of confounding is population admixture. An approach to adjusting for potential confounding due to population admixture when estimating the influence of allelic variability at a candidate gene is presented. The approach involves augmenting linear regression models with additional regressors. Family genotype data are used to define the regressors, and inclusion of the regressors ensures that, even in the presence of population admixture, the estimates of the regression coefficients that parameterize the influence of allelic variability on the trait are unbiased. The approach is illustrated through an analysis of the influence of apolipoprotein E genotype on plasma low density lipoprotein cholesterol concentrations.     

Multiple augmentation with partial missing regressors

In large cohort studies, it is common that a subset of the regressors may be missing for some study subjects by design or happenstance. In this article, we apply the multiple data augmentation techniques to semiparametric models for epidemiologic data when a subset of the regressors are missing for some subjects, under the assumption that the data are missing at random in the sense of Rubin (2004) and that the missingness probabilities depend jointly on the observable subset of regressors, on a set of observable extraneous variables and on the outcome. Computational algorithms for the Poor Man's and the Asymptotic Normal data augmentations are investigated. Simulation studies show that the data augmentation approach generates satisfactory estimates and is computationally affordable. Under certain simulation scenarios, the proposed approach can achieve asymptotic efficiency similar to the maximum likelihood approach. We apply the proposed technique to the Multi-Ethic Study of Atherosclerosis (MESA) data and the South Wales Nickel Worker Study data.     

The MASCA Approach Applied to Break Multicollinearities in Quantitative Structure-Activity Relationships

Since the regressors in multiple and multivariate regression analysis are intercorrelated, the coefficients of a regression of regressands on them are unreliable with respect to the predictive model power. Nonpredictive and predictive multicollinearity affect the ability to predict the biological activity (regressand) of novel drugs based on a function of physiochemical parameters (regressors), therefore. The nonpredictive multicollinearity can be broken by using the principal component regression analysis of the MASCA model. The working technique is exemplified on bispyridinium oxime antidotes, trimethoprim derivatives, and Taft's steric constant.     

Model diagnosis for parametric regression in high-dimensional spaces

We study tools for checking the validity of a parametric regressionmodel. When the dimension of the regressors is large, many ofthe existing tests face the curse of dimensionality or requiresome ordering of the data. Our tests are based on the residualempirical process marked by proper functions of the regressors.They are able to detect local alternatives converging to thenull at parametric rates. Parametric and nonparametric alternativesare considered. In the latter case, through a proper principalcomponent decomposition, we are able to derive smooth directionaltests which are asymptotically distribution-free under the nullmodel. The new tests take into account precisely the ‘geometryof the model’. A simulation study is carried through andan application to a real dataset is illustrated.     

Exploring relationships between phenological and weather data using smoothing

Stepwise regression is often used to draw associations between phenological records and weather data. For example, the dates that a species first flowers each year might be regressed on monthly mean temperatures for a period preceding flowering. The months that 'best' explain the variation in first flowering dates would be selected by stepwise regression. However, daily records of weather are usually available. Stepwise regression on daily temperatures would not be appropriate because of high correlations between neighbouring days. Smoothing methods provide a way of avoiding such difficulties. Regression coefficients can be smoothed by penalising differences in slopes between neighbouring regressors. The resultant curve of regression gradients is intuitively attractive. Various possible approaches to smoothing regression coefficients are discussed. We illustrate the use of one method, P-spline signal regression, which is particularly appropriate when there are many more regressors than observations. Smoothing can be applied to more than one set of regressors. This results in a multi-dimensional surface of regression coefficients. We use this approach to investigate how the time of year that a plant species tends to flower affects its relationship with temperature records. Using this method, we found that later species tend to be affected by later temperatures.     

Second-Order Designs in Two Stages

This study examines the comparative information intrinsic to each stage of a two-stage experiment. Aliasing at the first stage, possible confounding of effects between stages, and efficiency comparisons for the two stages are determined directly from the analysis. A practical advantage is that runs to be assigned prospectively to the first and second stages may be evaluated beforehand, independently of empirical data. Motivated by studies in the digestion of seafood wastes, a case study develops a central composite design in k = 3 regressors, first on augmenting a 2³ design with center run, then on augmenting a small composite design with center run. Other augmentations are considered as well. The study concludes with some minimal augmentations to a 2³ design with center run, so as to ensure full estimability in a second-order model in three regressors.     

Temporal analysis of cellular cytotoxicity and humoral factors during progession and regression of Rous sarcomas in Japanese quails.

Temporal appearance of cellular cytotoxicity and humoral activities including blocking and arming activities during the entire course of Rous sarcoma development in Japanese quails was examined by microcytotoxicity assay with comparison of animals bearing regressing tumors induced by a moderate dose of virus (regressors) and animals bearing growing tumors induced by a large dose of virus (progressors). Cellular cytotoxicity of the spleen cells in regressors was detected in a biphasic pattern; the first phase being observed as early as 3-5 days post inoculation (p.i.), followed by an eclipse period between 7-10 days p.i. which was the time of active tumor growth, and the second phase occurring after 12 days p.i. when the tumor had attained the maximum size. In progressors, only the first phase was observed. Instead, a stimulatory effect of the spleen cells on growth of target cells was noticed. Arming activity which confers cytotoxic activity on the normal spleen cells was demonstrated in the sera of regressors in the similar biphasic pattern as the cellular cytotoxicity; the early activity being present at 3 days p.i., and the late one after 19 days p.i. The former was detected by pre-incubation of serum with effector cells in microcytotoxicity assay and the latter by pre-incubation with target cells. In progressors, only the early arming activity which reacts with effector cells was demonstrated. Blocking activity which abrogates cellular cytotoxicity was demonstrated in both regressors and progressors but in different patterns of appearance, that is, blocking activity in regressors was only transiently demonstrated only by pre-incubation with effector cells at the time of maximum tumor growth, while the activity in progressors seemed to persist after the tumor reached the maximum size. Since the earlier activity was found to be effective at effector cell level, and the later one at both effector and target cell levels, participation of blocking factors of different types in progressors was also suggested.     

Applications of deep convolutional neural networks to predict length,circumference, and weight from mostly dewatered images of fish

Simple biometric data of fish aid fishery management tasks such as monitoring the structure of fish populations and regulating recreational harvest. While these data are foundational to fishery research and management, the collection of length and weight data through physical handling of the fish is challenging as it is time consuming for personnel and can be stressful for the fish. Recent advances in imaging technology and machine learning now offer alternatives for capturing biometric data. To investigate the potential of deep convolutional neural networks to predict biometric data, several regressors were trained and evaluated on data stemming from the FishL? Recognition System and manual measurements of length, girth, and weight. The dataset consisted of 694 fish from 22 different species common to Laurentian Great Lakes. Even with such a diverse dataset and variety of presentations by the fish, the regressors proved to be robust and achieved competitive mean percent errors in the range of 5.5 to 7.6% for length and girth on an evaluation dataset. Potential applications of this work could increase the efficiency and accuracy of routine survey work by fishery professionals and provide a means for longer‐term automated collection of fish biometric data.     

Estimating and controlling for spatial structure in the study of ecological communities

Aim Variation partitioning based on canonical analysis is the most commonly used analysis to investigate community patterns according to environmental and spatial predictors. Ecologists use this method in order to understand the pure contribution of the environment independent of space, and vice versa, as well as to control for inflated type I error in assessing the environmental component under spatial autocorrelation. Our goal is to use numerical simulations to compare how different spatial predictors and model selection procedures perform in assessing the importance of the spatial component and in controlling for type I error while testing environmental predictors. Innovation We determine for the first time how the ability of commonly used (polynomial regressors) and novel methods based on eigenvector maps compare in the realm of spatial variation partitioning. We introduce a novel forward selection procedure to select spatial regressors for community analysis. Finally, we point out a number of issues that have not been previously considered about the joint explained variation between environment and space, which should be taken into account when reporting and testing the unique contributions of environment and space in patterning ecological communities. Main conclusions In tests of species‐environment relationships, spatial autocorrelation is known to inflate the level of type I error and make the tests of significance invalid. First, one must determine if the spatial component is significant using all spatial predictors (Moran's eigenvector maps). If it is, consider a model selection for the set of spatial predictors (an individual‐species forward selection procedure is to be preferred) and use the environmental and selected spatial predictors in a partial regression or partial canonical analysis scheme. This is an effective way of controlling for type I error in such tests. Polynomial regressors do not provide tests with a correct level of type I error.     

Cell-mediated immunity to Friend virus-induced leukemia. II. Characteristics of primary cell-mediated cytotoxic response.

The primary cell-mediated cytotoxic response to a Friend virus-induced leukemia, FBL-3, in C57BL/6 mice was measured by the 125IUdR release assay. Intraperitoneal (i.p.) inoculation of 1 x 10(1) FBL-3 cells produced progressive tumor growth (progressors); subcutaneous (s.c.) inoculation of as many as 5 x 10(6) FBL-3 cells produced only transient tumor growth (regressors), and these mice would subsequently resist i.p. challenge of FBL-3 cells at 3 days after s.c. inoculation. The kinetics of the primary cell-mediated cytotoxic response of regressors was biphasic. Significant cytotoxicity could be detected at 3 to 5 days after s.c. inoculation of 5 x 10(6) FBL-3 cells peaked at days 10 to 14, declined to a very low level or became undetectable around days 20 to 30; then the reactivity reappeared and persisted at least up to 60 days. In progressors, the kinetics of the cell-mediated cytotoxic response was similar to the regressors, but the reactivity was much lower. The cytotoxic response was found to be T cell dependent, during both the first peak (days 10 to 14) and the second peak (days 40 to 60). In adoptive transfer experiments, lymphocytes from regressors gave 90% protection against i.p. challenge of FBL-3; lymphocytes from progressors only gave 40% protection.     

Nitric oxide-independent CTL suppression during tumor progression: association with arginase-producing (M2) myeloid cells

Most of the mice bearing a s.c. BW-Sp3 lymphoma tumor mount a CD8(+) T cell-mediated response resulting in tumor regression. Nonetheless, tumor progression occurs in some of the recipients and is associated with CTL inactivity. We demonstrated that T cell-activating APC were induced in regressors whereas T cell suppressive myeloid cells predominated in the spleen of progressors. Indeed, in vitro depletion of either the adherent or the CD11b(+) populations restored T cell cytotoxicity and proliferation in these mice. This CTL inhibition was cell-to-cell contact-dependent but not mediated by NO. However, the same progressor suppressive cells prevented the activity of in vitro-restimulated CTLs derived from regressors in a cell-to-cell contact and NO-dependent fashion. Thus, either the NO-dependent or -independent suppressive pathway prevailed, depending on the target CTL population. In addition, the suppressive population expressed a high arginase activity, suggesting an association of the suppressive phenotype with alternatively activated (M2) myeloid cells. However, the high arginase activity is not directly involved in the suppressive process. Our results provide new insights for myeloid cell-mediated CTL inhibition during cancer progression.     

Estimation of breeding values using selected pedigree records

Fish bred in tanks or ponds cannot be easily tagged individually. The parentage of any individual may be determined by DNA fingerprinting, but is sufficiently expensive that large numbers cannot be so finger-printed. The measurement of the objective trait can be made on a much larger sample relatively cheaply. This article deals with experimental designs for selecting individuals to be finger-printed and for the estimation of the individual and family breeding values. The general setup provides estimates for both genetic effects regarded as fixed or random and for fixed effects due to known regressors. The family effects can be well estimated when even very small numbers are finger-printed, provided that they are the individuals with the most extreme phenotypes.     

A program for logistic prediction modelling

A computer program has been developed that can be used for analysing a binary outcome variable and a set of regressors of type interval with a logistic (i.e. nonlinear) model.     

Individual toluene exposure in rotary printing: increasing accuracy of estimation by linear models based on protocols of daily activity and other measures

Industrial exposure varies distinctly both between persons and for each person over time. It is often not possible to measure individual exposure repeatedly due to high costs. Therefore, a method for assessment of exposure is needed that accounts for inter- and intraindividual variability. We consider a strategy suggested by Preller et al. (1995, Scandinavian Journal of Work, Environment, and Health 21, 504-512), the idea of which is to predict exposure on several days via a linear model using additional variables as regressors. Those additional variables are easier to obtain than exposure measurements and are assumed to influence exposure. The paper gives a theoretical proof of the use of this method. An example is given using toluene exposure data from a study in a rotogravure printing plant.     

Estimating Treatment Effects of Longitudinal Designs using Regression Models on Propensity Scores

Summary We derive regression estimators that can compare longitudinal treatments using only the longitudinal propensity scores as regressors. These estimators, which assume knowledge of the variables used in the treatment assignment, are important for reducing the large dimension of covariates for two reasons. First, if the regression models on the longitudinal propensity scores are correct, then our estimators share advantages of correctly specified model‐based estimators, a benefit not shared by estimators based on weights alone. Second, if the models are incorrect, the misspecification can be more easily limited through model checking than with models based on the full covariates. Thus, our estimators can also be better when used in place of the regression on the full covariates. We use our methods to compare longitudinal treatments for type II diabetes mellitus.     

Genetic linkage between immune response to GAT and the fate of RSV-induced tumors in chickens

Recent studies suggest that the gene locus controlling the fate of tumors induced by Rous sarcoma virus (RSV) is linked to theB histocompatibility complex. Birds carrying the dominant allele regress the tumor; homozygous recessives being unable to do so, develop large tumors and die. These are called progressors.The Bryan strain of RSV was inoculated into 220 6 week old Leghorns homozygous forB ¹ B ¹,B ² B ², orB ¹⁹ B ¹⁹ of which the percentages of progressors were 79, 22 and 56, respectively. The balance of each were regressors and survived.TheB ¹ B ¹ test birds were derived from special matings, i.e., high and low immune responders to the amino acid polymer, GAT. Of 67 tests progeny of theB ¹ B ¹ GAT-low mating, 63 or 94% proved to be progressors, and 6% were regressors. Of 84 test progeny of theB ¹ B ¹ GAT-high matings, 67% were progressors, and 33% were regressors. The difference between the high and low GAT responders is highly significant and indicates that the locus controlling the fate of RSV-induced tumors is closely linked to the locus controlling immune response to GAT. The latter maps within theIr region of theB histocompatibility complex.     

Are clinical parameters sufficient to model gait patterns in patients with cerebral palsy using a multilinear approach?

The aim of this study was to evaluate whether clinical parameters are sufficient using, a multilinear regression model, to reproduce the sagittal plane joint angles (hip, knee, and ankle) in cerebral palsy gait. A total of 154 patients were included. The two legs were considered (308 observations). Thirty-six clinical parameters were used as regressors (range of motion, muscle strength, and spasticity of the lower). From the clinical gait analysis, the joint angles of the sagittal plane were selected. Results showed that clinical parameter does not provide sufficient information to recover joint angles and/or that the multilinear regression model is not an appropriate solution.     

Correlation between qualitatively distributed predicting variables and chemical terms in acridine derivatives using principal component analysis

When biological variables are not continuously distributed, the multiple and multivariate regression analysis cannot be used to correlate these variables against chemical regressors. As the employment of discriminant analysis requires the homogeneity of dispersion matrices and, that n_hp where n_h= degree of freedom of hypothesis, p =number of chemical terms, the reliability and validity of this method is highly questionable here. An alternative method is based on the principal component analysis where multicategory variables of drug responses can be classified into measures of inactive, slightly active, sufficiently active, and highly active drugs, for instance. The rules for classification are based on biological sources that can be expressed by chemical terms, too. An example adapted from antitumor action of acridine derivatives shows the working technique.     

Effect of sampling effort on the regional chronology statistics and climate–growth relationships estimation

Regional chronology and climate–growth relationships assessment are known to be sensitive to sampling effort. To disentangle the respective benefits of increasing whether the number of plots or the number of trees per plot when investigating climate–growth relationships under temperate conditions, we propose to simulate samples from a set of 84 plots established in plantations of Corsican pine (Pinus nigra Arnold ssp. laricio Poiret var. Corsicana), within which 10 dominant trees were cored in 1992. The effect of sampling effort was investigated through 20 modalities of sampled plots (from 3 to 84) and 10 modalities of sampled trees per plot (from 1 to 10). Regional chronology was studied using the mean effective correlation and the expressed population signal, while climate–growth relationships were evaluated through correlation functions. The calculation of the correlation functions also allowed testing the effect of sampling effort on various climatic regressors presenting different climate–growth correlation strengths. The accuracy of the dendroecological investigations increased with increasing sample size: estimating climate sensitivity with a regional chronology built from a small sample led to a general under-estimation of the climate–growth correlations. Decreasing sample size also increased the risk of estimating (i) “false” non-significant correlations for the most influencing climatic regressors, and (ii) “false” significant correlations for the less influencing ones. Increasing the number of plots was found of a greater interest than increasing the number of trees per plot to improve the climate–growth relationships assessment. Finally, the analysis revealed that the improvement of the expressed population signal with increasing sampling effort did not linearly mirror the bettering in the climate–growth correlations assessment.