Article citationsMore>>

Khan, J., Wei, J. S., Ringnér, M., Saal, L. H., Ladanyi, M., Westermann, F., Berthold, F., Schwab, M., Antonescu, C. R., & Peterson, C. (2001). Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks. Nature Medicine, 7, 673-679. doi:10.1038/89044

has been cited by the following article:

• TITLE: Principal Component Analyses in Anthropological Genetics

  AUTHORS: Xingdong Chen, Chao Chen, Li Jin

  KEYWORDS: Principal Component Analysis, Singular Value Decomposition, Human Genetics

  JOURNAL NAME: Advances in Anthropology, Vol.1 No.2, November 24, 2011

  ABSTRACT: Principal component analyses (PCA) is a statistical method for exploring and making sense of datasets with a large number of measurements (which can be thought of as dimensions) by reducing the dimensions to the few principal components (PCs) that explain the main patterns. Thus, the first PC is the mathematical combination of measurements that accounts for the largest amount of variability in the data. Here, we gave an interpretation about the principle of PCA and its original mathematical algorithm, singular variable decomposition (SVD). PCA can be used in study of gene expression; also PCA has a population genetics interpretation and can be used to identify differences in ancestry among populations and samples, through there are some limitations due to the dynamics of microevolution and historical processes, with advent of molecular techniques, PCA on Y chromosome, mtDNA, and nuclear DNA gave us more accurate interpretations than on classical markers. Furthermore, we list some new extensions and limits of PCA.