New paper: predicting pyrazinamide resistance

This paper has finally been published and you can find it here. It had a slightly tortuous journey from original preprint to updated preprint and now publication.

In brief, we use a range of structural, chemical and evolutional features to learn which missense mutations in PncA (encoded by pncA) are associated with resistance to pyrazinamide, one of the four first-line antibiotics used to treat tuberculosis.

This research output is designed to be reproducible; you can retrain all machine learning models and replot (nearly) all the figures in the paper using this GitHub repository.