"Virus hunting" using radial distance weighted discrimination

TL;DR

This paper introduces Radial Distance Weighted Discrimination, a novel spherical classifier tailored for virus detection in DNA-seq data, outperforming traditional linear and kernel methods in generalizability.

Contribution

The paper proposes Radial DWD, a new spherical classification algorithm specifically designed for radial data distributions, improving virus detection accuracy.

Findings

Radial DWD outperforms linear SVM and traditional DWD in radial contexts.

Radial DWD demonstrates superior generalizability on simulated data.

Radial DWD achieves better virus detection results on real DNA-seq data.

Abstract

Motivated by the challenge of using DNA-seq data to identify viruses in human blood samples, we propose a novel classification algorithm called "Radial Distance Weighted Discrimination" (or Radial DWD). This classifier is designed for binary classification, assuming one class is surrounded by the other class in very diverse radial directions, which is seen to be typical for our virus detection data. This separation of the 2 classes in multiple radial directions naturally motivates the development of Radial DWD. While classical machine learning methods such as the Support Vector Machine and linear Distance Weighted Discrimination can sometimes give reasonable answers for a given data set, their generalizability is severely compromised because of the linear separating boundary. Radial DWD addresses this challenge by using a more appropriate (in this particular case) spherical separating boundary. Simulations show that for appropriate radial contexts, this gives much better generalizability than linear methods, and also much better than conventional kernel based (nonlinear) Support Vector Machines, because the latter methods essentially use much of the information in the data for determining the shape of the separating boundary. The effectiveness of Radial DWD is demonstrated for real virus detection.