Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Principal component”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 631 records · Page 35Linked to original sources
PubMed2006

Biomechanical features of gait waveform data associated with knee osteoarthritis: an application of principal component analysis.

This study compared the gait of 50 patients with end-stage knee osteoarthritis to a group of 63 age-matched asymptomatic control subjects. The analysis focused on three gait waveform measures that were selected based on previous literature demonstrating their relevance to knee osteoarthritis (OA): the knee flexion angle, flexion moment, and adduction moment. The objective was to determine the biomechanical features of these gait measures related to knee osteoarthritis. Principal component analysis was used as a data reduction tool, as well as a preliminary step for further analysis to determine gait pattern differences between the OA and the control groups. These further analyses included statistical hypothesis testing to detect group differences, and discriminant analysis to quantify overall group separation and to establish a hierarchy of discriminatory ability among the gait waveform features. The two groups were separated with a misclassification rate (estimated by cross-validation) of 8%. The discriminatory features of the gait waveforms were, in order of their discriminatory ability: the amplitude of the flexion moment, the range of motion of the flexion angle, the magnitude of the flexion moment during early stance, and the magnitude of the adduction moment during stance.

Aged↗
PubMed2003

Infant EEG spectral coherence data during quiet sleep: unrestricted principal components analysis--relation of factors to gestational age, medical risk, and neurobehavioral status.

EEG spectral coherence data in quiet sleep of 312 infants were evaluated, at 42 weeks post-menstrual age. All were medically healthy and living at home by time of evaluation. The sample consisted of prematurely bom infants with a wide spectrum of underlying risk factors, as well as healthy full-term infants. Initial 3040 coherence variables were reduced by principal components analysis in an unrestricted manner, which avoided the folding of spectral and spatial information into among-subject variance. One hundred fifty factors explained 90% of the total variance; 40 Varimax rotated factors explained 65% of the variance yielding a 50:1 data reduction. Factor loading patterns ranged from multiple spectral bands for a single electrode pair to multiple electrode pairs for a single spectral band and all intermediate possibilities. Simple left-right and anterior-posterior pairings were not observed within the factor loadings. By multiple regression analysis, the 40 factors significantly predicted gestational age at birth. By canonical correlation, significant relationships were demonstrated between the coherence factors and medical risk factors as well as neurobehavioral factors. Using discriminant analysis, the coherence factors successfully discriminated between infants with high and low medical risk status and between those with the best and worst neurobehavioral status. The two factors accounting for the most variance, and chosen across several analyses, indicated increased left central-temporal coherence from 6-24 Hz, and increased frontal-occipital coherence at 10 Hz, for the infants born closest to term with lowest medical risk factors and best neurobehavioral performance.

Electroencephalography↗
PubMed2005

Torsional resistance as a principal component of the structural design of long bones: comparative multivariate evidence in birds.

Here we study the occurrence of torsion-resisting morphological and histological features (thin bone walls, circular shaft cross-section, oblique collagen fibers, and laminar tissue arrangement) in a sample of 168 long bones from wings and legs of 22 bird species. These structural parameters were measured in mid diaphyseal undemineralized cross-sections and analyzed using uni-, bi-, and multivariate (principal components analysis) data analysis techniques. We found that the four variables are significantly and positively correlated, and that covariation between variables accounts for as much as 58% of the total variation. These results suggest that torsion is a main determinant of the macro- and microstructural design of long bones in birds. Humerus, ulna, and femur generally possess torsion-resisting features, while other bones (radius, carpometacarpus, tibiotarsus, tarsometatarsus, and foot phalanx) rather show bending/axial load-resisting structural properties. These results are congruent with in vivo strain data from the literature, which reported high torsional loading in humerus and ulna during flapping flight, but also in the subhorizontal avian femur during terrestrial locomotion. The precise function of the laminar tissue spatial arrangement, the role of pneumatization, and the influence of flight mode are discussed.

Animals↗
PubMed2002

Permutation-validated principal components analysis of microarray data.

BACKGROUND: In microarray data analysis, the comparison of gene-expression profiles with respect to different conditions and the selection of biologically interesting genes are crucial tasks. Multivariate statistical methods have been applied to analyze these large datasets. Less work has been published concerning the assessment of the reliability of gene-selection procedures. Here we describe a method to assess reliability in multivariate microarray data analysis using permutation-validated principal components analysis (PCA). The approach is designed for microarray data with a group structure. RESULTS: We used PCA to detect the major sources of variance underlying the hybridization conditions followed by gene selection based on PCA-derived and permutation-based test statistics. We validated our method by applying it to well characterized yeast cell-cycle data and to two datasets from our laboratory. We could describe the major sources of variance, select informative genes and visualize the relationship of genes and arrays. We observed differences in the level of the explained variance and the interpretability of the selected genes. CONCLUSIONS: Combining data visualization and permutation-based gene selection, permutation-validated PCA enables one to illustrate gene-expression variance between several conditions and to select genes by taking into account the relationship of between-group to within-group variance of genes. The method can be used to extract the leading sources of variance from microarray data, to visualize relationships between genes and hybridizations and to select informative genes in a statistically reliable manner. This selection accounts for the level of reproducibility of replicates or group structure as well as gene-specific scatter. Visualization of the data can support a straightforward biological interpretation.

Animals↗
PubMed2006

Quantitative trait loci analysis of phenotypic traits and principal components of maize tassel inflorescence architecture.

Maize tassel inflorescence architecture is relevant to efficient production of F(1) seed and yield performance of F(1) hybrids. The objectives of this study were to identify genetic relationships among seven measured tassel inflorescence architecture traits and six calculated traits in a maize backcross population derived from two lines with differing tassel architectures, and identify Quantitative Trait Loci (QTL) involved in the inheritance of those tassel inflorescence architecture traits. A Principal Component (PC) analysis was performed to examine relationships among correlated traits. Traits with high loadings for PC1 were branch number and branch number density, for PC2 were spikelet density on central spike and primary branch, and for PC3 were lengths of tassel and central spike. We detected 45 QTL for individual architecture traits and eight QTL for the three PCs. For control of inflorescence architecture, important QTL were found in bins 7.02 and 9.02. The interval phi034-ramosa1 (ral) in bin 7.02 was associated with six individual architecture trait QTL and explained the largest amount of phenotypic variation (17.3%) for PC1. Interval bnlg344-phi027 in bin 9.02 explained the largest amount of phenotypic variation (14.6%) for PC2. Inflorescence architecture QTL were detected in regions with candidate genes fasciated ear2, thick tassel dwarf1, and ral. However, the vast majority of QTL mapped to regions without known candidate genes, indicating positional cloning efforts will be necessary to identify these genes.

Chromosome Mapping↗
PubMed1996

Calculation of area of stabilometric signals using principal component analysis.

In stabilometry, the sway of the human body in an upright posture is studied by monitoring the displacement of its centre of pressure in the lateral (x) and anterio-posterior (y) directions. The area covered by this trace has been defined as that of an ellipse fitted to the data. Conventionally, its angle of inclination is found through linear regression (LR) on the data in the x-y plane. In the present paper, principal component analysis (PCA) is proposed as providing a more suitable basis for the estimation of angle and area. Results of simulations and stabilometric tests confirm large differences between area and angle estimates obtained by regression of x over y, and y over x, with PCA generally agreeing with either one or the other of the LRs. The PCA technique is therefore recommended as an improved basis for measuring area and inclination of stabilograms, or similar data sets.

Data Interpretation, Statistical↗
PubMed2000

Principal component analysis of the absorption and resonance Raman spectra of the metallochromic indicator antipyrylazo III.

Metallochromic indicators, whose spectral properties are changed in the presence of metal cations, are used mainly in biological studies to monitor Ca2+ and Mg2+ ions. Antipyrylazo III is such indicator, employed for mid-range Ca2+ concentrations (10-1000 microM). The stoichiometry of the interactions of antipyrylazo III with Ca2+, Mg2+, Ba2+, Sr2+ and Zn2+ ions and the relevant binding constants were studied by principal component analysis (PCA) of the absorption spectral changes. The resonance Raman spectra of the above systems were measured as well, and the resolved Raman spectra of the various species were calculated and assigned. The vibrational spectra are more featured, more characteristic of the binding ions and exhibit stronger relative spectral changes upon binding the cations. The basis sets of Raman spectra could thus be used as an analytical tool for these divalent metallic cations.

Barium↗
PubMed2002

Combining selective sequential extractions, X-ray absorption spectroscopy, and principal component analysis for quantitative zinc speciation in soil.

Selective sequential extractions (SSE) and, more recently, X-ray absorption fine-structure IXAFS) spectroscopy have been used to characterize the speciation of metal contaminants in soils and sediments. However, both methods have specific limitations when multiple metal species coexist in soils and sediments. In this study, we tested a combined approach, in which XAFS spectra were collected after each of 6 SSE steps, and then analyzed by multishell fitting, principal component analysis (PCA) and linear combination fits (LCF), to determine the Zn speciation in a smelter-contaminated, strongly acidic soil. In the topsoil, Zn was predominately found in the smelter-emitted minerals franklinite (60%) and sphalerite (30%) and as aqueous or outer-sphere Zn2+ (10%). In the subsoil, aqueous or outer-sphere Zn2+ prevailed (55%), but 45% of Zn was incorporated by hydroxy-Al interlayers of phyllosilicates. Formation of such Zn-bearing hydroxy-interlayers, which has been observed here for the first time, may be an important mechanism to reduce the solubility of Zn in those soils, which are too acidic to retain Zn by formation of inner-sphere sorption complexes, layered double hydroxides or phyllosilicates. The stepwise removal of Zn fractions by SSE significantly improved the identification of species by XAFS and PCA and their subsequent quantification by LCF. While SSE alone provided excellent estimates of the amount of mobile Zn species, it failed to identify and quantify Zn associated with mineral phases because of nonspecific dissolution and the precipitation of Zn oxalate. The systematic combination of chemical extraction, spectroscopy, and advanced statistical analysis allowed us to identify and quantify both mobile and recalcitrant species with high reliability and precision.

Adsorption↗
PubMed2006

Insights into age- and sickle-cell-disease-interaction using principal components analysis.

BACKGROUND: In the context of sickle cell anemia, peripheral blood indexes provide key information that is also potentially influenced by age. Therefore, it is necessary to understand the extent and nature of interactions between sickle cell anemia and age, especially in situations where there is a high prevalence of sickle cell anemia. METHODS: In a cross-sectional study of 374 subjects with varying hemoglobin S (HbS) status, we characterized the interaction between age and sickle hemoglobin using principal components analysis. RESULTS: Factor analysis in subjects with hemoglobin AA identified three orthogonal factors--normal erythropoiesis, presence of thalassemia and the aggregability potential of the blood. These three factors were differentially associated with hemoglobin status. Age influenced the association of factors #2 and #3 with hemoglobin status. CONCLUSION: Our findings suggest that the interaction between age and hemoglobin status needs to be considered in both clinical and public health settings.

Journal Article↗
PubMed2001

Evaluation of principal components analysis with high-performance liquid chromatography and photodiode array detection for the forensic differentiation of ballpoint pen inks.

Inks from seven black and eight blue ballpoint pens were separated by a high-performance liquid chromatography (HPLC) method utilizing a photodiode array detection (PDA). A classifier flowchart was designed for the chromatographic data based on the presence or absence of certain peaks at different wavelengths to qualitatively discriminate between the inks. The same data were quantitatively classified by principal components analysis (PCA) to estimate the separation between a pair of classes of ink samples. It was found that the black ballpoint pen inks were discriminated satisfactorily utilizing two-dimensional data of the peak areas and retention times at the optimum wavelengths. The blue pens were discriminated by analyzing the chromatographic data at four different wavelengths simultaneously with a cross-validated PCA. The results of this study indicated that HPLC-PDA coupled with chemometrics could make a powerful discriminating tool for the forensic chemist, especially when analyzing extensive and/or complex data.

Journal Article↗
PubMed2002

Modeling of gas absorption cross sections by use of principal-component-analysis model parameters.

Monitoring the amount of gaseous species in the atmosphere and exhaust gases by remote infrared spectroscopic methods calls for the use of a compilation of spectral data, which can be used to match spectra measured in a practical application. Model spectra are based on time-consuming line-by-line calculations of absorption cross sections in databases by use of temperature as input combined with path length and partial and total pressure. It is demonstrated that principal component analysis (PCA) can be used to compress the spectrum of absorption cross sections, which depend strongly on temperature, into a reduced representation of score values and loading vectors. The temperature range from 300 to 1000 K is studied. This range is divided into two subranges (300-650 K and 650-1000K), and separate PCA models are constructed for each. The relationship between the scores and the temperature values is highly nonlinear. It is shown, however, that because the score-temperature relationships are smooth and continuous, they can be modeled by polynomials of varying degrees. The accuracy of the data compression method is validated with line-by-line-calculated absorption data of carbon monoxide and water vapor. Relative deviations between the absorption cross sections reconstructed from the PCA model parameters and the line-by-line-calculated values are found to be smaller than 0.15% for cross sections exceeding 1.27 x 10(-21) cm(-1) atm(-1) (CO) and 0.20% for cross sections exceeding 4.03 x 10(-21) cm(-1) atm(-1) (H2O). The computing time is reduced by a factor of 10(4).

Journal Article↗
PubMed2003

Parametrization of dark-energy properties: a principal-component approach.

Considerable work has been devoted to the question of how best to parametrize the properties of dark energy, in particular, its equation of state w. We argue that, in the absence of a compelling model for dark energy, the parametrizations of functions about which we have no prior knowledge, such as w(z), should be determined by the data rather than by our ingrained beliefs or familiar series expansions. We find the complete basis of orthonormal eigenfunctions in which the principal components [weights of w(z)] that are determined most accurately are separated from those determined most poorly. Furthermore, we show that keeping a few of the best-measured modes can be an effective way of obtaining information about w(z).

Journal Article↗
PubMed2006

Improve survival prediction using principal components of gene expression data.

The purpose of many microarray studies is to find the association between gene expression and sample characteristics such as treatment type or sample phenotype. There has been a surge of efforts developing different methods for delineating the association. Aside from the high dimensionality of microarray data, one well recognized challenge is the fact that genes could be complicatedly inter-related, thus making many statistical methods inappropriate to use directly on the expression data. Multivariate methods such as principal component analysis (PCA) and clustering are often used as a part of the effort to capture the gene correlation, and the derived components or clusters are used to describe the association between gene expression and sample phenotype. We propose a method for patient population dichotomization using maximally selected test statistics in combination with the PCA method, which shows favorable results. The proposed method is compared with a currently well-recognized method.

Algorithms↗
PubMed2000

Principal component analysis and cluster analysis for the characterization of dental composites.

Various experimental dental materials were characterized using chemometric methods. The main aim of the study was to ascertain which composite materials present the best properties for use in restorative dentistry. Bisphenol-alpha-glycidyl methacrylate-based composites containing hydroxyapatite as a filler and a coupling agent were prepared using a photocuring polymerization procedure. Several chemical and mechanical properties of experimental composites were measured and the corresponding data were further studied using principal component analysis and cluster analysis. Results from the characterization allowed the most appropriate materials to be selected. Various composites presented acceptable general properties suggesting their suitability as substitutes for commercial materials in dentistry.

Cluster Analysis↗
PubMed2003

Thermoanalytical, chemical and principal component analysis of plant drugs.

Thermal decomposition and elemental content of commercial raw plant materials used in medicine-roots, rhizomes and bark originating from different medicinal plant species were analyzed. The thermal decomposition was performed using the derivatograph. The content of non-metallic (N, P, S, Cl, I and B) and metallic (Ca, Mg, Fe, Mn, Cu and Zn) elements was determined by spectrophotometric techniques after previous mineralization of samples. In order to obtain more clear classification of the analyzed plant materials principal component analysis (PCA) was applied. Interpretation of PCA results for three databases (thermoanalytical, non-metals and metals data sets) allows the statement that samples of roots, rhizomes and bark from the same plant species in majority of cases are characterized by similar elemental composition and similar course of their thermal decomposition. In this way the differences in general chemical composition of medicinal plants raw materials can be determined.

Differential Thermal Analysis↗
PubMed1994

Principal component analysis of gene frequencies and the origin of Basques.

The genetic peculiarity of the Basque population has long been noted. We aim to describe Basque distinctiveness in space and assess the internal Basque heterogeneity. All these aspects are relevant to the question of the origin of Basques. After a thorough literature search, a data base was created containing all the available data on gene frequencies in the Iberian Peninsula and France. Twenty-nine systems, comprising 71 alleles, were used to carry out a principal component (PC) analysis. The results show a sharp peak in the first PC in the Basque area, which remains even when the geographic scope is widened to include western Europe. As demonstrated by "wombling" analysis, the steeper slope in the first PC is found to the east of the Basque area, along the Pyrenees. Measures of genetic heterogeneity (such as FST values) within the Basque country, as compared to those for non-Basques, do not show a particular internal substructuration in the Basque population. The genetic results support a scenario in which the Basques are the product of in situ differentiation around the time of the Last Glacial Maximum (18,000 B.P.), in agreement with archaeological and linguistic data. Isolation from the surrounding populations has allowed the differentiation to last for millennia, but has erased the differences existing among Basques.

Alleles↗
PubMed1995

Principal component analysis and the scaled subprofile model compared to intersubject averaging and statistical parametric mapping: I. "Functional connectivity" of the human motor system studied with [15O]water PET.

Using [15O]water PET and a previously well studied motor activation task, repetitive finger-to-thumb opposition, we compared the spatial activation patterns produced by (1) global normalization and intersubject averaging of paired-image subtractions, (2) the mean differences of ANCOVA-adjusted voxels in Statistical Parametric Mapping, (3) ANCOVA-adjusted voxels followed by principal component analysis (PCA), (4) ANCOVA-adjustment of mean image volumes (mean over subjects at each time point) followed by F-masking and PCA, and (5) PCA with Scaled Subprofile Model pre- and postprocessing. All data analysis techniques identified large positive focal activations in the contralateral sensorimotor cortex and ipsilateral cerebellar cortex, with varying levels of activation in other parts of the motor system, e.g., supplementary motor area, thalamus, putamen; techniques 1-4 also produced extensive negative areas. The activation signal of interest constitutes a very small fraction of the total nonrandom signal in the original dataset, and the exact choice of data preprocessing steps together with a particular analysis procedure have a significant impact on the identification and relative levels of activated regions. The challenge for the future is to identify those preprocessing algorithms and data analysis models that reproducibly optimize the identification and quantification of higher-order sensorimotor and cognitive responses.

Adult↗
PubMed2005

Chromatographic classification and comparison of commercially available reversed-phase liquid chromatographic columns containing polar embedded groups/amino endcappings using principal component analysis.

Polar embedded phases have become increasingly popular in liquid chromatography (LC) analysis. These phases can produce diverse chromatographic selectivities as a result of their differing base silica, the type of polar embedded group (i.e. amide, urea, carbamate, ether or sulphonamide moieties) and the length of the alkyl ligand. Four column characterization protocols, using differing test probes, have been used to characterize 18 of these phases together with 17 alkyl phases (some of which contained novel polar endcapping, i.e. amino), which have been evaluated using principal component analysis (PCA). PCA provided graphical comparisons of the differences/similarities between these phases and between their corresponding C-alkyl, amino endcapped and enhanced polar selectivity phases.

Amines↗