Dataset Information

A comparison of principal component analysis and factor analysis strategies for uncovering pleiotropic factors.

ABSTRACT: Principal component analysis (PCA) and factor analysis (FA) are often used to uncover genetic factors that contribute to complex disease phenotypes. The purpose of such an analysis is to distill a genetic signal from a large number of correlated phenotype measurements. That signal can then be used in genetic analyses (e.g. linkage analysis), presumably leading to greater success at finding genes than one would achieve with any one raw trait. Although both PCA and FA have been used this way, there has been no comparison of their performance in the literature. We compared the ability of these two procedures to extract unobserved underlying genetic components from complex simulated data on nuclear families. We first simulated seven underlying genetic and environmentally determined traits. Then we derived two sets of 50 complex (observed) traits using algebraic combinations of the underlying components. We next performed PCA and FA on the complex traits. We assessed two aspects of the performance of the methods: (1) ability to detect the underlying genetic components; (2) whether the methods worked better when applied to raw traits or to residuals (after regressing out significant environmental covariates). Our results indicate that both the methods behave similarly in most cases, although FA generally produced factors that had stronger correlations with the underlying traits. We also found that using residuals in PCA or FA analyses greatly increased the probability that the PCs or factors detected common genetic components instead of common environmental factors, except if there was statistical interaction between genetic and environmental factors.

SUBMITTER: Wang X

PROVIDER: S-EPMC3042259 | biostudies-literature | 2009 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A comparison of principal component analysis and factor analysis strategies for uncovering pleiotropic factors.

Wang Xiaojing X Kammerer Candace M CM Anderson Stewart S Lu Jiang J Feingold Eleanor E

Genetic epidemiology 20090501 4

Principal component analysis (PCA) and factor analysis (FA) are often used to uncover genetic factors that contribute to complex disease phenotypes. The purpose of such an analysis is to distill a genetic signal from a large number of correlated phenotype measurements. That signal can then be used in genetic analyses (e.g. linkage analysis), presumably leading to greater success at finding genes than one would achieve with any one raw trait. Although both PCA and FA have been used this way, ther ...[more]

PMID: 19048641

Similar Datasets

Project description:BackgroundPrincipal component analysis is used to summarize matrix data, such as found in transcriptome, proteome or metabolome and medical examinations, into fewer dimensions by fitting the matrix to orthogonal axes. Although this methodology is frequently used in multivariate analyses, it has disadvantages when applied to experimental data. First, the identified principal components have poor generality; since the size and directions of the components are dependent on the particular data set, the components are valid only within the data set. Second, the method is sensitive to experimental noise and bias between sample groups. It cannot reflect the experimental design that is planned to manage the noise and bias; rather, it estimates the same weight and independence to all the samples in the matrix. Third, the resulting components are often difficult to interpret. To address these issues, several options were introduced to the methodology. First, the principal axes were identified using training data sets and shared across experiments. These training data reflect the design of experiments, and their preparation allows noise to be reduced and group bias to be removed. Second, the center of the rotation was determined in accordance with the experimental design. Third, the resulting components were scaled to unify their size unit.ResultsThe effects of these options were observed in microarray experiments, and showed an improvement in the separation of groups and robustness to noise. The range of scaled scores was unaffected by the number of items. Additionally, unknown samples were appropriately classified using pre-arranged axes. Furthermore, these axes well reflected the characteristics of groups in the experiments. As was observed, the scaling of the components and sharing of axes enabled comparisons of the components beyond experiments. The use of training data reduced the effects of noise and bias in the data, facilitating the physical interpretation of the principal axes.ConclusionsTogether, these introduced options result in improved generality and objectivity of the analytical results. The methodology has thus become more like a set of multiple regression analyses that find independent models that specify each of the axes.

Dataset Information

A comparison of principal component analysis and factor analysis strategies for uncovering pleiotropic factors.

Publications

A comparison of principal component analysis and factor analysis strategies for uncovering pleiotropic factors.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets