PCA Beyond The Concept of Manifolds: Principal Trees, Metro Maps, and Elastic Cubic Complexes

TL;DR

This paper introduces principal cubic complexes, a flexible low-dimensional structure that generalizes principal manifolds, constructed via topological grammars and elastic energy minimization, with applications in genomics and microarray data visualization.

Contribution

It proposes principal cubic complexes as a new class of low-dimensional data approximators, extending principal manifolds with a novel construction method combining topological grammars and elastic energy minimization.

Findings

Principal cubic complexes generalize principal manifolds.

Application to bacterial genome analysis.

Visualization of microarray data as metro maps.

Abstract

Multidimensional data distributions can have complex topologies and variable local dimensions. To approximate complex data, we propose a new type of low-dimensional ``principal object'': a principal cubic complex. This complex is a generalization of linear and non-linear principal manifolds and includes them as a particular case. To construct such an object, we combine a method of topological grammars with the minimization of an elastic energy defined for its embedment into multidimensional data space. The whole complex is presented as a system of nodes and springs and as a product of one-dimensional continua (represented by graphs), and the grammars describe how these continua transform during the process of optimal complex construction. The simplest case of a topological grammar (``add a node'', ``bisect an edge'') is equivalent to the construction of ``principal trees'', an object useful in many practical applications. We demonstrate how it can be applied to the analysis of bacterial genomes and for visualization of cDNA microarray data using the ``metro map'' representation. The preprint is supplemented by animation: ``How the topological grammar constructs branching principal components (AnimatedBranchingPCA.gif)''.