hdfs

Variant Interaction Analysis (VIA) is an application for identifying genomic variant interactions related with complex diseases. It uses Multifactor Dimensionality Dimension (MDR), a non-parametric statistical method for detecting and characterizing nonlinear interactions. It runs in a singularity container using Apache Spark for distributing the work, Hadoop File System for distributing the data and Apache ZooKeeper for synchronization. It is coded in Python.