HiTaC: a Hierarchical Taxonomic Classifier for Fungal ITS Sequences

Summary Fungi naturally inhabit the human microbiome and can be causative agents of infections. Hence, an accurate and robust method for fungal ITS classification can help us gain a deeper insight into the dynamics of environmental communities and ultimately comprehend whether the abundance of certain species correlate with health and disease. Therefore, in this work we introduce HiTaC, a robust hierarchical machine learning model for accurate ITS classification. HiTaC is implemented as a QIIME2 plugin in order to facilitate its adoption in existing mycobiome analysis pipelines. We benchmarked it with seventeen popular software for taxonomic classification on real environmental sequencing data. HiTaC shows superior accuracy and sensitivity in classifying ITS sequences across different taxonomic ranks. Availability and implementation HiTaC is freely available on GitLab https://gitlab.com/dacs-hpi/hitac Contact vitor.piro@fu-berlin.de Supplementary information Supplementary data are available at bioRxiv online.