Journal of Forensic Sciences · 2018 · 26 citations · 48 references
AgricultureBioinformaticsSoil SciencesSoil BiologySoil EcologySoil ScienceSoil BiodiversitySoil CorrelationSoil Fauna EcologySoil TaxonomyRandom Forest ClassificationSoil Biodiversity PatternsSoil BiogeographySoil Biota DiversitySpatial Autocorrelation Across ScalesSpatial Soil ClassificationSpatial VariabilityTemporal Variability
Soil DNA profiling has potential as a forensic tool to establish a link between soil collected at a crime scene and soil recovered from a suspect. However, a quantitative measure is needed to investigate the spatial/temporal variability across multiple scales prior to their application in forensic science. In this study, soil DNA profiles across Miami-Dade, FL, were generated using length heterogeneity PCR to target four taxa. The objectives of this study were to (i) assess the biogeographical patterns of soils to determine whether soil biota is spatially correlated with geographic location and (ii) evaluate five machine learning algorithms for their predictive ability to recognize biotic patterns which could accurately classify soils at different spatial scales regardless of seasonal collection. Results demonstrate that soil communities have unique patterns and are spatially autocorrelated. Bioinformatic algorithms could accurately classify soils across all scales with Random Forest significantly outperforming all other algorithms regardless of spatial level.
48
Classification and Regression by randomForest
Andy Liaw, Matthew C. Wiener · 2007 · 18.4K citations
PCR protocols — A guide to methods and applications
U.G. · Trends in Biochemical Sciences · 1990 · 11.8K citations
Classification and regression trees
J. Praagman · European Journal of Operational Research · 1985 · 10.2K citations
Universal primers for amplification of three non-coding regions of chloroplast DNA
Pierre Taberlet, Ludovic Gielly, Guy Pautou et al. · Plant Molecular Biology · 1991 · 5.7K citations