Title: Craft: A Machine Learning Approach to Dengue Subtyping
Authors: van Zyl D, Dunaiski M, Tegally H, Baxter C, , de Oliveira T, Xavier J.
Journal: ,doi: 10.1101/2025.02.10.637410.: (2025)
Abstract
Motivation The dengue virus poses a major global health threat, with nearly 390 million infections annually. A recently proposed hierarchical dengue nomenclature system enhances spatial resolution by defining major and minor lineages within genotypes, aiding efforts to track viral evolution. While current subtyping tools â Genome Detective, GLUE, and NextClade â rely on computationally intensive sequence alignment and phylogenetic inference, machine learning presents a promising alternative for achieving accurate and rapid classification.ResultsWe present Craft (ChaosRandomForest), a machine learning framework for dengue subtyping. We demonstrate that Craft is capable of faster classification speeds while matching or surpassing the accuracy of existing tools. Craft achieves 99.5% accuracy on a hold-out test set and processes over 140 000 sequences per minute. Notably, Craft maintains remarkably high accuracy even when classifying sequence segments as short as 700 nucleotides.Contactdanielvanzyl@sun.ac.zaSupplementary informationA supplemental table acknowledging the authors of the GISAID dengue sequences is available atBioinformaticsonline.
Download: Full text paper
Citation: van Zyl D, Dunaiski M, Tegally H, Baxter C, , de Oliveira T, Xavier J. Craft: A Machine Learning Approach to Dengue Subtyping ,doi: 10.1101/2025.02.10.637410.: (2025).