Abstract: The development of drug resistance to rifampicin in tuberculosis and leprosy is a significant global problem, often leading to therapeutic failure. While genetic sequencing techniques are able to identify known resistance causing mutations, they still fall short of understanding underlying mechanisms and translating these to avoid therapeutic failure. Here we explore the use of structural information to bridge this gulf in knowledge, to guide the identification and characterization of novel mutations within the gene rpoB. With the current molecular-based gold-standard (Gene-Xpert MTB/RIF) focussing only on the Rifampicin Resistance Determining Region (RRDR; in grey), a structure-based resistance classifier which considers protein stability and interactions with other RNA polymerase subunits and nucleic acids is thought to be better representative of the biological processes underlying drug resistance. Our predictive binary classifier, SUSPECT-RIF, encapsulates the power of using structural information to interpret genomic variants. This power, in turn, can be used as a backbone to treatment strategies in tuberculosis patients presenting with novel mutations, and in stewardship efforts to minimize the occurrence of MDR-TB. We have made this model freely available through a user friendly web interface called SUSPECT-RIF, StrUctural Susceptibility PrEdiCTion for rifampicin. This will be a valuable resource to analyse any rpoB missense mutation, providing structural insight to help guide patient treatment decisions and screening programs.