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 1,225 records · Page 68Linked to original sources
PubMed1992

Role of inferior temporal neurons in visual memory. I. Temporal encoding of information about visual images, recalled images, and behavioral context.

1. Lesions of the inferior temporal (IT) cortex selectively hamper monkeys in tasks requiring visual memory. A system that recognizes images must be able to encode a current stimulus, recall the code of a previous stimulus, compare the codes of the two stimuli, and make a decision on the basis of the outcome of the comparison. Therefore, IT neurons must be involved in at least one of these processes. To determine the specific role of IT neurons in visual memory, we measured the information conveyed in the neuronal responses about current patterns, recalled patterns, and behavioral context. 2. Two monkeys were trained to perform a sequential matching task using a set of 32 black and white Walsh patterns. In the course of an experiment, each pattern was presented repeatedly in sample, match, and nonmatch behavioral contexts. While the monkeys were performing the task, we recorded the activity of 76 neurons from area TE of IT. The neuronal responses to the stimuli were converted to spike density functions, and the resultant waveforms were quantified using their principal components. The relationships between the responses and the stimuli were studied using analysis of variance and information theory. 3. The analysis of variance was applied to the neuronal response waveforms using the context (sample, match, or nonmatch) and the patterns of the stimuli as independent variables and the spike count or the coefficients of the principal components as the dependent variables. We found that the waveforms of most neurons were significantly modulated by both the pattern and the context of the stimulus presentation. 4. We also analyzed the stimulus-response relationships using information theory. The input codes were based on the pattern and context of the stimuli, and the output codes were based on the spike count or the principal components of the responses. The neuronal response waveforms were found to convey significant amounts of information about both the pattern and context of the stimuli. Transmitted information was greatest when the response of a neuron was interpreted as a message about the combination of pattern and context. Nevertheless, there was information about context independent of pattern and vice versa. 5. We also used information theory to determine whether the neuronal responses to the second, or test, stimulus conveyed information about the pattern of the first, or sample, stimulus. The input codes were based on the patterns of the sample stimuli, and the output codes were based on the responses to the nonmatch test stimuli.(ABSTRACT TRUNCATED AT 400 WORDS)

Analysis of Variance↗
PubMed2004

Detailed exposure assessment for a molecular epidemiology study of benzene in two shoe factories in China.

OBJECTIVES: We carried out a detailed exposure assessment of benzene and toluene in two shoe factories in Tianjin, China. Our goal was to identify workers with a broad range of benzene exposures, for an epidemiologic study relating exposure to early biologic effects. METHODS: A comprehensive exposure survey program was initiated. Over a period of 16 months, 2783 personal solvent exposure samples were collected in two workplaces from 250 workers. Mixed-effects models were used to identify factors affecting exposure. Principal component analyses (PCA) and subsequent regression analyses on the scores of the identified principal components were used to relate potential co-exposures to various exposure sources present in the workplace. RESULTS: The mean benzene exposure level was 21.86 p.p.m. (10th-90th percentiles 5.23-50.63 p.p.m.) in the smaller shoe factory (factory A) and 3.46 p.p.m. (10th-90th percentiles 0.20-7.00 p.p.m.) in the larger shoe factory (factory B). Within-factory exposure levels differed among job titles and were higher for subjects directly involved in handling glues. In contrast, mean toluene levels were relatively similar in the two factories (factory A, 9.52 p.p.m.; factory B, 15.88 p.p.m.). A seasonal trend was identified for both benzene and toluene in factory B. This could be explained in part by changes in air movement and ventilation patterns occurring during the year. A seasonal trend was not present in the smaller shoe factory, where general ventilation was absent. Supplemental analysis showed that exposure levels to other hydrocarbons were low (< or =5 p.p.m.), less than 5% of their respective ACGIH threshold limit values, and generally comparable in the two factories. PCA showed that co-exposures in factory B could largely be explained by glue sources that were used in distinct areas in the workplace. CONCLUSIONS: We demonstrated the occurrence of a broad range of benzene exposure levels in two shoe manufacturing factories in Tianjin, China. Benzene and toluene exposures were determined in part by the degree of contact with glues, the benzene and toluene content of each glue, air movement and ventilation patterns. The availability of long-term monthly personal monitoring data provides an excellent opportunity to estimate individual exposures at different times during the 1 yr period of observation.

Adhesives↗
PubMed2003

Main inorganic component measurement of seawater using near-infrared spectroscopy.

The potential of near-infrared (NIR) spectroscopy to measure the main inorganic components of seawater as salt-manufacturing materials was investigated. A total of 72 seawater samples collected from six locations was used, and spectra (1100-1800 nm) were acquired by a NIR spectrophotometer with a 1-mm path length. Principal component analysis (PCA), canonical correlation analysis (CCA), and partial least-squares (PLS) regression were performed based on the reference inorganic components. As a result, the principal component analysis and canonical correlation analysis showed that the near-infrared spectra could be related to the inorganic components of seawater. The partial least-squares regression analysis showed that the inorganic components (ion concentration of Cl, Na+, K+, SO4(2-), and Ca2+) could be predicted with good accuracy using NIR spectra and their second derivatives. For Cl ion and K+ ion concentrations, the accuracy was high.

Algorithms↗
PubMed1991

Lateral geniculate neurons in behaving primates. III. Response predictions of a channel model with multiple spatial-to-temporal filters.

1. For the experiments reported in these papers, we recorded the responses of lateral geniculate (LGN) neurons to a large set of two-dimensional, black and white patterns based on Walsh functions and to a set of test stimuli. In the first two papers we reported that these neurons encode stimulus-related information in both the strength and the shape of the response waveforms and that there are more than two independent components in the response. These results cannot be explained by existing models. This paper provides a model of LGN neurons that not only accounts for the foregoing observations, but also yields predictions confirmed by direct tests. 2. The model represents a neuron as a set of three parallel channels. The input to each channel is an array of pixel luminances. Each channel consists of an input nonlinearity cascaded into a linear spatial-to-temporal filter. The output of each channel is a basic waveform, a principal component. The response of the neuron is the sum of the outputs of the three channels. 3. The model accounted for much of the variance in the coefficients of the first three principal components of the neuronal responses to the set of Walsh stimuli. Using parameters derived from the responses of neurons to the Walsh stimuli only, the model also predicted the responses to "center-surround" annuli of different contrasts and mean luminances, as well as to superpositions of pairs of Walsh patterns. The model made statistically significant predictions of the coefficients of two of the principal components of these responses. 4. After the parameters of the model had been fit to reproduce the responses of neurons to the Walsh stimuli, we found that the input nonlinearity of the model was compressed at both the high and low luminance levels. This compression produced response saturation that closely resembled the response saturation of neurons reported in the first paper in this series. Although not absolutely smooth, the spatial filter for the first channel had a dominant excitatory or inhibitory center and an antagonistic surround. Thus this spatial filter accounted for both the center and the surround structures of previous models of LGN receptive fields. There was greater variety in the structures of the spatial filters for the second and third channels, but none had a center-surround organization. Many of the spatial filters for these higher channels contained oriented ridges or valleys. Other spatial filters were dominated by a bipolar pair of pixels. 5. The model of LGN neurons that we present in this paper represents an extension over previous models in four ways. First, the model is capable of explaining the responses of neurons to a wider range of luminances than previous models. Second, the model is capable of explaining the shapes of the response waveforms as well as their magnitudes. Third, the concept of a single receptive field is extended to a series of spatial-to-temporal filters. Fourth, the model suggests that LGN neurons provide a description of both the brightness and the form of a stimulus in their response waveforms.

Animals↗
PubMed1989

A simple quantitative screening test for the detection of extracranial carotid artery disease.

A simple screening test, using continuous wave Doppler ultrasound, for the detection of all grades of extracranial carotid artery disease has been described. The test is composed of two parts: (1) the determination of the direction of flow at the orbit and (2) on-line principal component factor analysis of the maximum frequency envelope of the Doppler shifted signal obtained from the common carotid artery. A total of 154 vessel segments have been investigated; 69 normal, 41 with a stenosis of 10-49%, 32 with a stenosis of 50-99% and 12 occlusions. Of these, 70 vessel segments were assessed prospectively and they formed the data base from which the principal components and the classification factor were calculated. The remaining 84 vessel segments were analysed prospectively on-line. The combined results gave an overall sensitivity to the detection of disease of 90% and a specificity of 77%. It has been shown that although classification of Doppler waveforms by principal component analysis is a fairly sophisticated technique it is possible, by careful design of the algorithms, to design a near real-time on-line analysis system for derived waveforms such as the maximum frequency envelope.

Algorithms↗
PubMed2002

Interactive exploration of microarray gene expression patterns in a reduced dimensional space.

The very high dimensional space of gene expression measurements obtained by DNA microarrays impedes the detection of underlying patterns in gene expression data and the identification of discriminatory genes. In this paper we show the use of projection methods such as principal components analysis (PCA) to obtain a direct link between patterns in the genes and patterns in samples. This feature is useful in the initial interactive pattern exploration of gene expression data and data-driven learning of the nature and types of samples. Using oligonucleotide microarray measurements of 40 samples from different normal human tissues, we show that distinct patterns are obtained when the genes are projected on a two-dimensional plane spanned by the loadings of the two major principal components. These patterns define the particular genes associated with a sample class (i.e., tissue). When used separately from the other genes, these class-specific (i.e., tissue-specific) genes in turn define distinct tissue patterns in the projection space spanned by the scores of the two major principal components. In this study, PCA projection facilitated discriminatory gene selection for different tissues and identified tissue-specific gene expression signatures for liver, skeletal muscle, and brain samples. Furthermore, it allowed the classification of nine new samples belonging to these three types using the linear combination of the expression levels of the tissue-specific genes determined from the first set of samples. The application of the technique to other published data sets is also discussed.

Gene Expression Profiling↗
PubMed2006

Estimating the gasoline components and formulations toxicity to microalgae (Tetraselmis chuii) and oyster (Crassostrea rhizophorae) embryos: an approach to minimize environmental pollution risk.

Even though petrochemical contamination frequently occurs in the form of oil spills, it is thought that a greater danger to coastal habitats is posed by chronic petrochemical toxicity associated with urban run-off, in which gasoline water-soluble-fraction (WSF) plays an important role. The hypothesis of the entrepreneurs, who were associated to the scientists uncharged of this research, was that recycled petrochemical waste may provide different gasoline formulations, having different toxic properties; the correlation between the gasoline formulations and their components' toxicological effects might contribute to the reformulation of the products, in such a way that the gasoline generated could be less toxic and less harmful to the environment. The aim of this research was to determine the toxic effects of 14 different types of gasoline (formulated, in accordance with National Petroleum Agency standards, from petrochemical waste), on Tetraselmis chuii (microalgae culture) and Crassostrea rhizophorae (embryos). Microalgae and oyster embryos were exposed to different gasoline formulations water-soluble fractions (WSF) at a range of concentrations (0%, 4.6%, 10.0%, 22.0%, 46.0%, and 100%), for 96 and 24h, respectively. The tests were carried out under controlled conditions. End-points have been CI50-96h (concentration causing 50% growth inhibition in microalgae cultures) and EC50-24h (concentration causing abnormalities on 50% of the exposed embryos). Through these procedures, gasoline formulations, which represent the lowest environmental risk, were selected. Bioassays carried out on the 8 different gasoline components aimed to correlate gasoline toxicity with the toxic potential of its components. The analysis of principal components showed that the C9DI, a mixture of aromatic hydrocarbons of 9 carbon atoms, had the highest level of toxic potential, followed by C9S (a mixture of aromatics with 9-11 carbon atoms) and heavy naphtha. The results showed gasoline formulations 1-4 (monoaromatic hydrocarbons being the most conspicuous components) to be the least toxic, whilst formulations 12-14 (having higher content of C9DI, C9S and naphtha) were found to be the most harmful to organisms. This study led to the identification of the most toxic WSF gasoline components (C9DI and C9S), and to the possibility of developing more eco-compatible gasoline formulations.

Animals↗
PubMed1999

A novel local PCA-based method for detecting activation signals in fMRI.

A novel local principal component analysis (LPCA) technique is presented for activation signal detection in functional magnetic resonance imaging (fMRI) without explicit knowledge about the shape of the model activation signal. Unlike the traditional PCA methods, our LPCA algorithm is based on a measure of separation between two clusters formed by the signal segments in active periods and inactive periods, which is computed in an eigen-subspace. In addition, we only applied PCA to the temporal sequence of each individual voxel instead of applying PCA to the fMRI data set. In our algorithm, we first applied a linear regression procedure to alleviate the baseline drift artifact. Then, the baseline-corrected temporal signals were partitioned into active and inactive segments according to the paradigm used for the fMRI data acquisition. Principal components were computed from all these segments for each voxel by PCA. By projecting the segments of each voxel onto a linear subspace formed by the corresponding most dominant principal components, two separate clusters were formed from active and inactive segments. An activation measure was defined based on the degree of separation between these two clusters in the projection space. We show experimental results on the activation signal detection from various sets of fMRI data with different types of stimulation by using the proposed LPCA algorithm and the standard t-test method for comparison. Our experiments indicate that the LPCA algorithm in general provides substantial signal-to-noise ratio improvement over the t-test method.

Algorithms↗
PubMed1999

Using response models to estimate channel capacity for neuronal classification of stationary visual stimuli using temporal coding.

Both spike count and temporal modulation are known to carry information about which of a set of stimuli elicited a response; but how much information temporal modulation adds remains a subject of debate. This question usually is addressed by examining the results of a particular experiment that depend on the specific stimuli used. Developing a response model allows us to ask how much more information is carried by the best use of response strength and temporal modulation together (that is, the channel capacity using a code incorporating both) than by the best use of spike count alone (the channel capacity using the spike count code). This replaces dependence on a particular data set with dependence on the accuracy of the model. The model is constructed by finding statistical rules obeyed by all the observed responses and assuming that responses to stimuli not presented in our experiments obey the same rules. We assume that all responses within the observed dynamic range, even if not elicited by a stimulus in our experiment, could be elicited by some stimulus. The model used here is based on principal component analysis and includes both response strength and a coarse (+/-10 ms) representation of temporal modulation. Temporal modulation at finer time scales carries little information about the identity of stationary visual stimuli (although it may carry information about stimulus motion or change), and we present evidence that, given its variability, it should not be expected to do so. The model makes use of a linear relation between the logarithms of mean and variance of responses, similar to the widely seen relation between mean and variance of spike count. Responses are modeled using truncated Gaussian distributions. The amount of stimulus-related information carried by spike count in our data are 0.35 and 0.31 bits in primary visual and inferior temporal cortices, respectively, rising to 0.52 and 0.37 bits for the two-principal-component code. The response model estimates that the channel capacity is 1.1 and 1.4 bits, respectively, using the spike count only, rising to 2.0 and 2.2 bits using two principal components. Thus using this representation of temporal modulation is nearly equivalent to adding a second independent cell using the spike count code. This is much more than estimated using transmitted information but far less than would be expected if all degrees of freedom provided by the individual spike times carried independent information.

Algorithms↗
PubMed1986

Application of pattern-recognition techniques in wavelength selection for instrumentally read reagent strips.

Pattern recognition techniques--discriminant analysis and principal component analysis--are utilized in selecting the wavelengths for monitoring, by reflectance spectroscopy, color-generating reactions involving uric acid and cholesterol in serum. The data base we used was accumulated by a rapid-scanning reflectance spectrophotometer that measured reflectance at 16 wavelengths every 5 s after the reaction was initiated. The data were then analyzed in multidimensional space mainframe computer with commercial statistical software packages. The most appropriate wavelengths were those that yielded the largest generalized distance between analyte concentration by discriminant analysis and the largest weighting coefficient by principal component analysis. For uric acid, taking the ratio of reflectance measured at two wavelengths instead of at a single wavelength much better separates the clinically significant concentrations. For cholesterol, the initiated. The data were then analyzed in multidimensional space hemoglobin, can be clearly demonstrated y the "pattern" generated with principal component analysis. generalized distance between analyte generalized distance between analyte concentration by discriminant

Cholesterol↗
PubMed2007

Evaluation of PCA and ICA of simulated ERPs: Promax vs. Infomax rotations.

Independent components analysis (ICA) and principal components analysis (PCA) are methods used to analyze event-related potential (ERP) and functional imaging (fMRI) data. In the present study, ICA and PCA were directly compared by applying them to simulated ERP datasets. Specifically, PCA was used to generate a subspace of the dataset followed by the application of PCA Promax or ICA Infomax rotations. The simulated datasets were composed of real background EEG activity plus two ERP simulated components. The results suggest that Promax is most effective for temporal analysis, whereas Infomax is most effective for spatial analysis. Failed analyses were examined and used to devise potential diagnostic strategies for both rotations. Finally, the results also showed that decomposition of subject averages yield better results than of grand averages across subjects.

Algorithms↗
PubMed2005

QSTR with extended topochemical atom indices. Part 5: Modeling of the acute toxicity of phenylsulfonyl carboxylates to Vibrio fischeri using genetic function approximation.

In continuation of our recent efforts to model the acute toxicity of 56 phenylsulfonyl carboxylates to Vibrio fischeri using principal component factor analysis, the present paper deals with modeling of the same data set with extended topochemical atom (ETA) indices using genetic function approximation (GFA) as the statistical tool. The statistical quality of the best model using ETA descriptors is as follows: n=56, Q2=0.771, Ra2=0.861, R=0.935, F=69.0 (df5,50), s=0.172, AVRES=0.128. This equation was better in statistical quality than that obtained previously using principal component factor analysis as the data-preprocessing step. An attempt was also made to model the data set with different nonETA parameters (topological indices including Wiener, Hosoya Z, molecular connectivity, kappa shape, Balaban J and E-State parameters apart from physicochemical parameters like AlogP98, MolRef and H_bond_acceptor) and the best model showed the following quality: n=56, Q2=0.805, Ra2=0.820, R=0.913, F=53.5 (df4,51), s=0.196, AVRES=0.136. An attempt to use both ETA and nonETA parameters lead to an equation which is marginally better than the best ETA model: n=56, Q2=0.779, Ra2=0.865, R=0.937, F=71.7 (df5,50), s=0.169, AVRES=0.127. Use of the ETA indices suggested negative contributions of steric bulk, functionality of C10, volume of substituents on C10 and functionalities of chloro and nitro substituents at X1 position and positive contributions of functionalities of C4 and C1 and presence of substituents with electronegative atoms, especially at R2 and R3 positions. Furthermore, absence of substituents at R2 and R3 positions decreases toxicity. This study corroborates the results obtained from principal component factor analysis and suggests that ETA parameters are sufficiently rich in chemical information to encode the structural features contributing significantly to the acute toxicity of phenylsulfonyl carboxylates to V. fischeri.

Aliivibrio fischeri↗
PubMed1998

Axial synergies during human upper trunk bending.

Upper trunk bending movements were accompanied by opposite movements of the lower body segments. These axial kinematic synergies maintained equilibrium during the movement performance by stabilizing the center of gravity (CG), which shifted on average across all the subjects by 1 +/- 4 cm in the anteroposterior direction and thus always remained within the support area. The aim of the present investigation was to provide an insight into the central control responsible for the performance of these synergies. The kinematic analysis was performed by the method of principal components (PC) analysis applied to the covariation between ankle, knee and hip joint angles and compared with CG shifts during upper trunk bending. Subjects were asked to perform backward or forward upper trunk bending in response to a tone. They were instructed to move as fast as possible or slowly (2 s), with high or low movement amplitudes. PC analysis showed a strong correlation between hip, knee and ankle joint changes. The first principal component (PC1) representing a multijoint movement with fixed ratios between joint angular changes, accounted, on average, for 99.7% +/- 0.2% of the total angular variance in the forward trunk movements and for 98.4% +/- 1.4% in the backward movements. The instructed voluntary regulation of the amplitude and velocity of the movement was achieved by adapting the bell-shaped profile of the velocity time course without changes in interjoint angular relations. Fixed ratios between changes in joint angles, represented by PC1, ensured localization of the CG within the support area during trunk bending. The ratios given by PC1 showed highly significant dependence on subjects, suggesting the adaptability of the central control to each subject's biomechanical peculiarities. Subject's intertrial variability of PC1 ratios was small, suggesting a stereotyped automatic interjoint coordination. When changing velocity and amplitude of the movement, the ratios remained the same in about half the subjects while in others slight variations were observed. A weak second principal component (PC2) was shown only for fast movements. In forward movements PC2 reflected the early knee flexion that seems related to the disturbances caused by the passive interaction between body segments, rather than to the effect of a central command. In fast backward movements, PC2 reflected the delay in hip extension relative to the movement onset in the ankle and knee that mirrors intersubject differences in the initiation process of the axial synergy. The results suggest that PC1 reflects the centrally controlled multijoint movement, defining the time course and amplitude of the movement and fixing the ratios between changes in joint angles. They support the hypothesis that the axial kinematic synergies result from a central automatic control that stabilizes the CG shift in the anteroposterior direction while performing the upper trunk bending.

Adaptation, Physiological↗
PubMed2001

Identification of the factors that influence the reproducibility of chromatographic retention data.

Principal component analysis was used to identify the parameters that influence the column-to-column and batch-to-batch reproducibility of retention times and retention factors measured on Symmetry C18, Kromasil C18, Luna C18 (2) and Vydac RP C18, all reversed-phase silica columns. We devised a procedure that allows the determination of the differences in column volume and packing density between two columns, provided that these columns are packed with identical stationary phases (i.e., phases that originate from the same batch). Principal component analysis of the retention times confirmed that the column-to-column variations of the column volume and the total porosity of the bed are the factors that influence the reproducibility of the retention times, the column volume being the major factor. For the fluctuations of the retention factors, the column phase ratios (or the bed porosities) and some specific, secondary retention mechanisms are responsible. All the C18 columns investigated proved to behave in a very similar fashion. Two principal components were always sufficient to characterize the variations of either the retention times or the retention factors.

Chromatography, Liquid↗
PubMed1996

Test of linear trend in eigenvalues of a covariance matrix with application to data analysis.

Principal component analysis and factor analysis are the most widely used tools for dimension reduction in data analysis. Both methods require some good criterion to judge the number of dimensions to be kept. The classical method focuses on testing the equality of eigenvalues. As real data hardly have this property, practitioners turn to some ad hoc criterion in judging the dimensionality of their data. One such popular method, the 'scree test' or 'scree plot' as described in many texts and statistical programs, is based on the trend in eigenvalues of sample covariance (correlation) matrix. The principal components or common factors corresponding to eigenvalues which exhibit a slow linear decrease are discarded in further data analysis. This paper develops a formal statistical test for the 'scree plot'. A special case of this test is the classical test for equality of eigenvalues which has been suggested in several texts as the criterion to decide the number of principal components to retain. Comparisons between equality of eigenvalues and the slow linear decrease in eigenvalues on some classical examples support the hypothesis of slow linear decrease. A physical background to such a phenomenon is also suggested.

Analysis of Variance↗
PubMed2005

Three-way partial least-squares regression for the simultaneous kinetic-enzymatic determination of xanthine and hypoxanthine in human urine.

The performance of three-way principal component analysis and three-way partial least-squares regression when applied to a complex kinetic-enzymatic system is studied, in order to investigate the analytical potential of the combined use of these chemometric technologies for non-selective enzymatic systems. A enzymatic-kinetic procedure for the simultaneous determination of hypoxanthine and xanthine in spiked samples of human urine is proposed. The chemical system involves two consecutive reactions catalyzed by xanthine oxidase (EC 1.17.3.2). This enzyme catalyzes the oxidation of hypoxanthine, first to xanthine and then to uric acid, a competitive inhibitor of the reactions. The influence of uric acid during quantitative determination was considered in the design of the calibration set. The sample and enzyme solution were mixed in a stopped-flow module and the reaction was monitored using a diode array spectrophotometer. The recorded data have an intrinsical three-component structure (samples, time and wavelength). This data array was studied via three-way principal component analysis and was modeled for quantitative purposes using a three-way partial least-squares calibration procedure. Results are compared with those obtained by applying classical bilinear PLS to the previously unfolded data matrix.

Humans↗
PubMed1985

Genetic markers of an aboriginal Taiwanese population.

A group of Taiwan aborigines, the Toroko, was typed for 21 classical genetic loci. This is part of an ongoing program aimed at a comprehensive study of Taiwan aborigines. In this first paper a short summary of historical, archeological, and anthropological data in the literature is made, and results of the present survey are compared with older results from other aborigine tribes. An analysis of other neighboring populations from southeast Asia has also been carried out in order to give a preliminary answer to the question of origin of Taiwanese aborigines. Fifteen populations were studied for 13 loci by tree analysis, principal components, and isolation by distance. Tree analysis and principal component analysis gave results in fairly good agreement and indicate three major population clusters: a northeast cluster (Ainu, Korea, Japan, and Ryukyu); a southeast cluster (south China, Thailand, Vietnam, Philippines, Taiwan, and Toroko); and a third cluster including Malaya and Borneo. The positions of Polynesia, Micronesia, and Melanesia are somewhat peripheral. Analysis of the tree shows some potential cases of convergence, perhaps owing to admixture, and of divergence. The analysis of isolation by distance shows that geographic propinquity is a reasonably good predictor of general similarity in this area.

Humans↗
PubMed1989

Pattern recognition study of QSAR substituent descriptors.

Parameter values for 59 common substituents and 74 descriptors used in QSAR studies were compiled. This data matrix was analysed by a variety of multivariate techniques. Linear regression confirmed that lipophilicity can be factorized into two terms, one related to molecular bulk and the other to polarity. Principal component analysis (PCA) of parameters revealed 5 significant principal components and a grouping of lipophilic, steric and electronic parameters. The different loadings of parameters with 5 PCA were also explored. The classification of substituents by cluster analysis (CA) proved rather disappointing. In contrast, the SIMCA method classified substituents of increasing bulk into 5 groups of increasing polarity.

Analysis of Variance↗