Comparative assessment of annotation tools reveals critical antimicrobial resistance knowledge gaps in Klebsiella pneumoniae.

Bacterial antimicrobial resistance (AMR) poses a significant public health threat. The increase of both global awareness and affordable whole genome sequencing has yielded an ever-growing collection of bacterial genome sequence datasets and corresponding antibiotic resistance metadata. This enables the use of computational techniques, including machine learning (ML), to predict phenotypes and discover novel AMR-associated variants. With the great variety of resistance mechanisms to interrogate and the number of datasets that can be mined, there is a need to identify where novel AMR marker discovery is most necessary. Multiple databases and annotation pipelines exist to annotate AMR variants known to be associated with resistance to specific antibiotics or antibiotic classes, however, the completeness of these databases varies, and for some antibiotics, even the most complete databases remain insufficient for accurate classification. Here, we build predictive ML models using only those known markers, which we call "minimal models" of resistance. We predict the binary resistance phenotypes of 20 major antimicrobials in the genomically diverse pathogen Klebsiella pneumoniae, allowing us to identify their shortcomings in phenotype prediction, thereby highlighting opportunities for novel marker discovery. We provide a critical review of the differences in annotation tools and databases commonly used in bacterial AMR studies, and outline guidance for the establishment of a standard dataset for the development and benchmarking of ML models of AMR.