@article {Rudar2022.03.31.486647, author = {Josip Rudar and G. Brian Golding and Stefan C. Kremer and Mehrdad Hajibabaei}, title = {Decision Tree Ensembles Utilizing Multivariate Splits Are Effective at Investigating Beta-Diversity in Medically Relevant 16S Amplicon Sequencing Data}, elocation-id = {2022.03.31.486647}, year = {2022}, doi = {10.1101/2022.03.31.486647}, publisher = {Cold Spring Harbor Laboratory}, abstract = {Canonical distance and dissimilarity measures can fail to capture important relationships in high-throughput sequencing datasets since these measurements are unable to represent feature interactions. By learning a dissimilarity using decision tree ensembles, we can avoid this important pitfall. We used 16S rRNA data from the lumen and mucosa of the distal and proximal human colon and the stool of patients suffering from immune-mediated inflammatory diseases and compared how well the Jaccard and Aitchison metrics preserve the pairwise relationships between samples to dissimilarities learned using Random Forests, Extremely Randomized Trees, and LANDMark. We found that dissimilarities learned by unsupervised LANDMark models were better at capturing differences between communities in each set dataset. For example, differences in the microbial communities of colon{\textquoteright}s distal lumen and mucosa were better reflected using LANDMark dissimilarity (p <= 0.001, R2 = 0.476) than using the Jaccard distance (p <= 0.001, R2 = 0.313) or Random Forest dissimilarity (p <= 0.001, R2 = 0.237). In addition, applying Uniform Manifold Approximation and Projection to dissimilarity matrices and transforming the result using principal components analysis created two-dimensional projections that captured the main axes of variation while also preserving the pairwise distances between samples (eg: ρ = 0.8804, p <= 0.001 for the distal colon dissimilarities). Finally, supervised LANDMark models tend to outperform both Random Forest and Extremely Randomized Tree classifiers. Models employing multivariate splits can improve the analysis of complex high-throughput sequencing datasets. The improvements observed in this work likely result from the ability of these models to reduce noise from uninformative features. In an unsupervised setting, LANDMark models can preserve pairwise relationships between samples. When used in a supervised manner, these methods tend to learn a decision boundary that is more reflective of the biological variation within the dataset.Author Summary Distance and dissimilarity measures are often used to investigate the structure of biological communities. However, our investigation into two commonly used distance measures, the Jaccard and Aitchison distances, demonstrates that these measures can fail to capture important relationships in microbiome communities. This is likely due to their inability to identify dependencies between features. For example, both the Jaccard and Aitchison metrics are unable to identify subsets of samples where the presence of one feature depends on another. Previous research has found that Random Forest embeddings can be used to create an alternative dissimilarity measure for dimensionality reduction in genomic datasets. We show that dissimilarities learned by decision tree ensembles, especially those using base-estimators capable of partitioning data using oblique and non-linear cuts, can be superior since these approaches naturally model these interactions.Competing Interest StatementThe authors have declared no competing interest.}, URL = {https://www.biorxiv.org/content/early/2022/04/01/2022.03.31.486647}, eprint = {https://www.biorxiv.org/content/early/2022/04/01/2022.03.31.486647.full.pdf}, journal = {bioRxiv} }