A pipeline to build Qiime2 taxonomy classifiers for the UNITE database.
If you are interested in Fungi 🍄 you could use their genomic fingerprint 🧬 to identify them. Affordable PCR amplification and sequencing of the ITS gene gives you these nucleic acid fingerprints, and the UNITE team provides a database to gives these sequences a name.
We can predict the taxonomy of our fungal fingerprints using an old-school machine learning method: a supervised k-mer nb-classifier. But first, we need to prepare our database in a process called 'training.'
This is a pipeline that trains the UNITE ITS taxonomy database for use with Qiime2. You can run this pipeline yourself, but you don't have to! I've provided a ready to use pre-trained classifiers so you can simply run qiime feature-classifier classify-sklearn.
If you have questions about using Qiime2, ask on the Qiime2 forums.
If you have questions about the UNITE ITS database, contact the UNITE team.
If you have questions about this pipeline, please open a new issue!
Set up:
- Install Pixi
Install Nextflow into the global env
pixi global install -c conda-forge -c bioconda nextflow openjdk=17Here's the cool part; we can install the locked version of Qiime I commited to the repo! It's in the code!
pixi install# How to reset pixi, say when updating to a new version of Qiime2
rm pixi.toml pixi.lock rachis-qiime2-osx-64-conda.yml
rm -rf .pixi/
# Get new qiime distribution
wget https://raw.githubusercontent.com/qiime2/distributions/refs/heads/dev/2026.7/qiime2/released/rachis-qiime2-osx-64-conda.yml
# Import from the conda env
pixi init --platform osx-64 --import rachis-qiime2-osx-64-conda.yml
# Install
pixi run qiime info
# Add it directly to the repo?
git add pixi* rachis-qiime2-osx-64-conda.yml# Reports, timeline and trace save to ./results/
export NXF_OFFLINE=TRUE
nextflow run main.nf -resume
