Basically what the title says. I would like to validate a novel AMR predictor and I am looking for some standard datasets with clearly defined AMR gene content, similar to the CAMI challenge for metagenomic classification. It would be even better if they were accepted and widely used by the community.

The papers I've read so far seem to be either working with their own bacterial isolates or they don't compare their results to a ground truth at all, only to other classifiers. Does such data even exists, or should I just create my own?