Proxi: a Python package for proximity network inference from metagenomic data
AbstractSummary: Recent technological advances in high-throughput metagenomic sequencing have provided unique opportunities for studying the diversity and dynamics of microbial communities under different health or environmental conditions. Graph-based representation of metagenomic data is a promising direction not only for analyzing microbial interactions but also for a broad range of machine learning tasks including feature selection, classification, clustering, anomaly detection, and dimensionality reduction. We present Proxi, an open source Python package for learning different types of proximity graphs from metagenomic data. Currently, three types of proximity graphs are supported: k-nearest neighbor (k-NN) graphs; radius-nearest neighbor (r-NN) graphs; and perturbed k-nearest neighbor (pk-NN) graphs.Availability: Proxi Python source code is freely available at https://bitbucket.org/idsrlab/proxi/.Contact:[email protected] information: Tutorials and online documentation are available at https://proxi.readthedocs.io