Mycorrhiza: Genotype Assignment usingPhylogenetic Networks
This addresses genotype assignment for applications such as wildlife forensics and biodiversity monitoring, offering improved robustness under non-ideal conditions, though it is incremental as it builds on existing machine learning and phylogenetic methods.
The authors tackled the genotype assignment problem by introducing Mycorrhiza, a machine learning approach that uses phylogenetic networks for feature engineering and Random Forests for classification, achieving favorable accuracy compared to existing methods like STRUCTURE and Admixture, with significant gains on datasets with high FST or deviation from Hardy-Weinberg equilibrium.
Motivation The genotype assignment problem consists of predicting, from the genotype of an individual, which of a known set of populations it originated from. The problem arises in a variety of contexts, including wildlife forensics, invasive species detection and biodiversity monitoring. Existing approaches perform well under ideal conditions but are sensitive to a variety of common violations of the assumptions they rely on. Results In this article, we introduce Mycorrhiza, a machine learning approach for the genotype assignment problem. Our algorithm makes use of phylogenetic networks to engineer features that encode the evolutionary relationships among samples. Those features are then used as input to a Random Forests classifier. The classification accuracy was assessed on multiple published empirical SNP, microsatellite or consensus sequence datasets with wide ranges of size, geographical distribution and population structure and on simulated datasets. It compared favorably against widely used assessment tests or mixture analysis methods such as STRUCTURE and Admixture, and against another machine-learning based approach using principal component analysis for dimensionality reduction. Mycorrhiza yields particularly significant gains on datasets with a large average fixation index (FST) or deviation from the Hardy-Weinberg equilibrium. Moreover, the phylogenetic network approach estimates mixture proportions with good accuracy.