Regularized Generalized Canonical Correlation Analysis: A Framework for Sequential Multiblock Component Methods.

A new framework for sequential multiblock component methods is presented. This framework relies on a new version of regularized generalized canonical correlation analysis (RGCCA) where various scheme functions and shrinkage constants are considered. Two types of between block connections are considered: blocks are either fully connected or connected to the superblock (concatenation of all blocks). The proposed iterative algorithm is monotone convergent and guarantees obtaining at convergence a stationary point of RGCCA. In some cases, the solution of RGCCA is the first eigenvalue/eigenvector of a certain matrix. For the scheme functions x, [Formula: see text], [Formula: see text] or [Formula: see text] and shrinkage constants 0 or 1, many multiblock component methods are recovered.

Influence of skin colour on the detection of cutaneous erythema and tanning phenomena using reflectance spectrophotometry.

BACKGROUND/PURPOSE: This research aims at assessing the influence of baseline skin colour on the ability of reflectance spectrophotometry to detect cutaneous erythema induced by a low concentration of methyl nicotinate (2.5 mM) (first objective), and to detect tanning induced by ultraviolet rays (UVA+UVB) at infra-erythemal doses (second objective). METHODS: Two independent studies were conducted to reach their respective objectives, on 27 women for the first study and on 12 women for the second study. Skin colour measurements were expressed in two different ways: percentages of reflected light at increasing wavelengths lambda (400 nm or =40 degrees. The assumption is that in the darkest skins, the emitted light is mainly absorbed by the melanin in the epidermis. Otherwise, after UV irradiation, the tanning was detectable only for individuals with fair to dark skin defined by ITA <50 degrees. This can be explained by the fact that UV stimulation of the fairest skin subjects, known to be melano-compromised individuals, can only produce a weak tanning that our study did not succeed in detecting.

Relationships between visual and tactile features and biophysical parameters in human facial skin.

BACKGROUND/PURPOSE: Skin properties, such as colour, hydration and texture, can be studied on a qualitative basis by a clinical assessment or on a quantitative basis using techniques that measure biophysical properties of the skin. The aim of this study was to explore the links between facial skin features and a range of skin biophysical parameters using multivariate methods. METHODS: A study was conducted on 256 female volunteers from Ile-de-France with apparent healthy skin, aged between 20 and 50, under controlled environmental conditions (mean+/-standard deviation: room temperature 22.9+/-0.3 degrees C; relative humidity 48.5+/-2.3%). The study included a medical questionnaire and a clinical examination of the skin performed by a dermatologist, and a biophysical evaluation of the skin properties. Seventy visual and tactile skin features were assessed on the forehead and the cheek using ordinal variables illustrated by photographic scales. Twenty-eight biophysical measurements were taken in the same areas using the following equipment: Chromameter, Evaporimeter, Corneometer, Skicon, Sebumeter, Sebutape, skin thermometer, skin pH-meter and Silflo. In order to group the variables illustrating a same unimodal phenomenon, a typology of the skin features and a typology of the biophysical parameters were carried out using a clustering method. Then, the relationships between each group of clinical features and each group of biophysical parameters were studied using a series of partial least squares (PLS) regressions. RESULTS: From eight groups of clinical features and three groups of biophysical parameters that were identified, 12 significant PLS regression models were built. Our findings suggest that differences in chromametric measurements express not only differences in skin colour but also differences in skin surface properties, such as skin vascularity status, thickness, and existence of wrinkles, and also demonstrate that the level of sebum excretion can affect other aspects of the skin surface. CONCLUSION: Some skin features assessed clinically do not appear to be linked to any biophysical parameter. This finding confirms that certain phenomena evaluated on the basis of visual or tactile skin features are not assessed on the basis of the biophysical properties of the skin measured by our bioengineering techniques. Indeed, visual skin features mainly appreciate the skin surface aspect, contrary to some biophysical surrogate markers known to provide information on underlying epidermal structures. Therefore, both clinical and biophysical assessments must be associated to supply a relevant and accurate approach for skin aspect characterisation.

Sun-reactive Skin Type in 4912 French adults participating in the SU.VI.MAX study.

Phototype classifications were initially developed in an attempt to predict the skin reactions of patients to phototherapy and are now widely used to advise individuals with regard to sun protection. A transversal study was conducted on the SU.VI.MAX cohort to estimate the frequency of sun-reactive skin features in a large, general adult population-based sample, and to describe the associations between these features. The data were collected 3 years after the beginning of the SU.VI.MAX nutritional intervention study on 4912 volunteers (2868 women aged 35-60 years and 2044 men aged 45-60 years). A multiple correspondence analysis was performed to study the associations between the features. The results showed that these features correspond to a one-dimensional phenomenon, which allowed us to establish a score to summarize skin sensitivity to sun exposure. Furthermore, we found a link between gender and phototype using the Césarini classification (phototype > or = IV: 37% of women, 47% of men). The analysis of the relationship with sun-reactive skin features and the score revealed the same trend. Phenotypic evaluation appears to be a good estimator of skin sensitivity to sun exposure for clinical screening or for use in research, and is easy to collect at a lower cost. Moreover, the sun sensitivity difference between gender should be considered in education about photoprotection.

Combining gene expression and molecular marker information for mapping complex trait genes: a simulation study.

A method for mapping complex trait genes using cDNA microarray and molecular marker data jointly is presented and illustrated via simulation. We introduce a novel approach for simulating phenotypes and genotypes conditionally on real, publicly available, microarray data. The model assumes an underlying continuous latent variable (liability) related to some measured cDNA expression levels. Partial least-squares logistic regression is used to estimate the liability under several scenarios where the level of gene interaction, the gene effect, and the number of cDNA levels affecting liability are varied. The results suggest that: (1) the usefulness of microarray data for gene mapping increases when both the number of cDNA levels in the underlying liability and the QTL effect decrease and when genes are coexpressed; (2) the correlation between estimated and true liability is large, at least under our simulation settings; (3) it is unlikely that cDNA clones identified as significant with partial least squares (or with some other technique) are the true responsible cDNAs, especially as the number of clones in the liability increases; (4) the number of putatively significant cDNA levels increases critically if cDNAs are coexpressed in a cluster (however, the proportion of true causal cDNAs within the significant ones is similar to that in a no-coexpression scenario); and (5) data reduction is needed to smooth out the variability encountered in expression levels when these are analyzed individually.

Prediction of clinical outcome with microarray data: a partial least squares discriminant analysis (PLS-DA) approach.

Partial least squares discriminant analysis (PLS-DA) is a partial least squares regression of a set Y of binary variables describing the categories of a categorical variable on a set X of predictor variables. It is a compromise between the usual discriminant analysis and a discriminant analysis on the significant principal components of the predictor variables. This technique is specially suited to deal with a much larger number of predictors than observations and with multicollineality, two of the main problems encountered when analysing microarray expression data. We explore the performance of PLS-DA with published data from breast cancer (Perou et al. 2000). Several such analyses were carried out: (1) before vs after chemotherapy treatment, (2) estrogen receptor positive vs negative tumours, and (3) tumour classification. We found that the performance of PLS-DA was extremely satisfactory in all cases and that the discriminant cDNA clones often had a sound biological interpretation. We conclude that PLS-DA is a powerful yet simple tool for analysing microarray data.

Use of predictive modeling for Propionibacterium strain classification.

Computed data analysis of biochemical or molecular profiles is currently used in studies of microbial taxonomy, epidemiology, and microbial diversity. We assessed the use of Partial Least Squares (PLS) regression for multivariate data analysis in bacteriology. We identified clear relationships between RAPD profiles of propionibacteria strains and their species classification, autolytic capacities, and their origins. The PLS regression also predicted species identity of some strains with RAPD profiles partially related to those of reference strains. The PLS analysis also allowed us to identify key characteristics to use to classify strains. PLS regression is particularly well adapted to i) describing a collection of bacterial isolates, ii) justifying bacterial groupings using several sets of data, and iii) predicting phenotypic characters of strains that have been classified by routine typing methods.

Relative contribution of intrinsic vs extrinsic factors to skin aging as determined by a validated skin age score.

OBJECTIVE: To assess the relative contribution of intrinsic aging vs lifestyle factors to facial skin age. DESIGN: Prospective analysis of a cohort. SETTING: Skin research institute. STUDY SUBJECTS: A cohort of 361 white women (age range, 18-80 years) with apparently healthy skin. MEASUREMENTS: Visual and tactile assessment of facial skin features. RESULTS: Twenty-four skin characteristics were used to build a skin age score (SAS). The relationship between the SAS and chronological age followed a linear model with 2 plateaus--1 before age 30 years and 1 after age 71 years. An analysis was performed to determine whether certain lifestyle habits known to have effects on skin aging were related to the discrepancies between chronological age and the SAS. Significant effects were identified for phototype, body mass index, menopausal status, degree of lifetime sun exposure, and number of years of cigarette smoking. However, these factors accounted for only 10% of the discrepancies. Moreover, most skin characteristics used reflected changes understood to represent intrinsic aging rather than photodamage or other extrinsic factors. CONCLUSIONS: An SAS can be generated from multiple discrete signs evaluated on facial skin and is an informative tool for quantifying skin aging. The SAS is influenced by factors already recognized to affect the aging phenotypes; however, factors related to the rate of intrinsic aging, presumably genetic in character, seem to play a larger role than previously suspected.