Pyrazinamide plays an important role in tuberculosis treatment; however, its use is complicated by side-effects and challenges with reliable drug susceptibility testing. Resistance to pyrazinamide is largely driven by mutations in pyrazinamidase (pncA), responsible for drug activation, but genetic heterogeneity has hindered development of a molecular diagnostic test. We proposed to use information on how variants were likely to affect the 3D structure of pncA to identify variants likely to lead to pyrazinamide resistance. We curated 610 pncA mutations with high confidence experimental and clinical information on pyrazinamide susceptibility. The molecular consequences of each mutation on protein stability, conformation, and interactions were computationally assessed using our comprehensive suite of graph-based signature methods, mCSM. The molecular consequences of the variants were used to train a classifier with an accuracy of 80%. Our model was tested against internationally curated clinical datasets, achieving up to 85% accuracy. Screening of 600 Victorian clinical isolates identified a set of previously unreported variants, which our model had a 71% agreement with drug susceptibility testing. Here, we have shown the 3D structure of pncA can be used to accurately identify pyrazinamide resistance mutations. SUSPECT-PZA is freely available at: http:// biosig.unimelb.edu.au/suspect_pza/. Tuberculosis (TB), caused by Mycobacterium tuberculosis, is the leading cause of infectious disease death worldwide. In 2017, 10 million people fell ill, and 1.6 million died, from tuberculosis 1. While a range of antibiotics are available to treat TB, treatment is prolonged, and the increasing emergence of drug-resistant bacteria is a considerable threat to global health. In 2017 alone, an estimated 558,000 people developed multi-drug-resistant tuberculosis (MDR-TB), resistant to the two first-line drugs rifampicin and isoniazid 1. Pyrazinamide (PZA) is a first-line drug that exhibits unique sterilizing activity towards both drug-susceptible and MDR-TB 2. It is responsible for the killing of the persistent tubercle bacilli during the initial intensive phase of chemotherapy, allowing treatment to be shortened from 9 months to 6 months for drug susceptible cases 3. PZA therapy has been linked to improved outcomes for both non-MDR and MDR-TB, and is being considered as part of the future regimens in combinations with bedaquiline, delamanid, PA-824 and moxifloxacin, which are currently in phase three trials 4,5. Despite the highly important role of PZA in clinical outcomes, resistance has largely been underestimated, with up to 20% of non-MDR-TB patients PZA resistant 6. Being a central drug in current and future regimens, it is important to be able to rapidly and accurately identify resistant isolates and track the emergence and spread of drug resistant strains. In vitro drug susceptibility testing (DST) is challenging, expensive and time-consuming as PZA is effective against M. tuberculosis only at acidic pH, leading to false resis...