Automated 3D Phenotype Analysis Using Data Mining

Abstract

The ability to analyze and classify three-dimensional (3D) biological morphology has lagged behind the analysis of other biological data types such as gene sequences. Here, we introduce the techniques of data mining to the study of 3D biological shapes to bring the analyses of phenomes closer to the efficiency of studying genomes. We compiled five training sets of highly variable morphologies of mammalian teeth from the MorphoBrowser database. Samples were labeled either by dietary class or by conventional dental types (e.g. carnassial, selenodont). We automatically extracted a multitude of topological attributes using Geographic Information Systems (GIS)-like procedures that were then used in several combinations of feature selection schemes and probabilistic classification models to build and optimize classifiers for predicting the labels of the training sets. In terms of classification accuracy, computational time and size of the feature sets used, non-repeated best-first search combined with 1-nearest neighbor classifier was the best approach. However, several other classification models combined with the same searching scheme proved practical. The current study represents a first step in the automatic analysis of 3D phenotypes, which will be increasingly valuable with the future increase in 3D morphology and phenomics databases.

Geographic Information Systems technology as a morphometric tool for quantifying morphological variation in an ammonoid clade

“…The occlusal surfaces of mammal teeth (Zuccotti et al, 1998;Jernvall and Selänne, 1999;Ungar and Williamson, 2000;M'Kirera and Ungar, 2003;Ungar, 2004;Evans et al, 2007;Plyusnin et al, 2008;Eronen et al, 2009;Wilson et al, 2012;Salazar-Ciudan and Marin-Riera, 2013), conodont elements (Manship et al, 2006) and various echinoderm skeletal elements (Zachos, 2012;Sheffield et al, 2012) have all been quantified via GISbased spatial analyses.…”

Introducing molaR: a New R Package for Quantitative Topographic Analysis of Teeth (and Other Topographic Surfaces)

“…Researchers interested in the form-function relationship of mammalian dentitions have begun supplementing traditional morphological measures with new metrics designed to reflect aspects of occlusal surface topography (e.g., Zuccotti et al 1998;M'Kirera and Ungar 2003;Evans et al 2007;Boyer 2008;Plyusnin et al 2008;Evans and Janis 2014;Winchester et al 2014;Allen et al 2015 Evans et al 2007). These metrics assess different aspects of dental surface topography over entire tooth crowns (or tooth rows) without requiring identification of homologous anatomic features or investigator-defined landmarks.…”

Novelty and “Homology-free” Morphometrics: What’s in a Name?

“…Assumptions about correspondence also ''creep in'' through the standardization for the size and orientation of the outline using the bestfitting ellipse (Ferson et al 1985) or through alignment by specific landmarks (e.g., Frieß and Baylac 2003). Analyses of three-dimensional surfaces by methods related to Fourier analysis (McPeek et al 2008) or by entirely different methods (Plyusnin et al 2008) also include steps for alignment and standardization that make implicit assumptions about homologies of the structure.…”