bioRxivJClub
amR: an R package suite to predict antimicrobial resistance in bacterial pathogens
bioRxiv · · Preprint · Open access
Ghosh, Brenner + 7 more
Abstract ↗AI summary
The abstract is read at the publisher; the summary is JClub's.
amR predicts antimicrobial resistance in Shigella sonnei with a median Matthews Correlation Coefficient of 0.89 across 23 drugs and drug classes.
- Why it matters: Resistance is complex and spans multiple molecular scales, while existing computational tools are often black boxes and seldom capture cross-species or multi-drug patterns.
- What they did: The amR suite integrates genome and susceptibility data curation (from BV-BRC), multi-scale feature extraction, interpretable per species–drug machine learning, and Shiny visualization.
- The result: Applied to Shigella sonnei, amR achieves median MCC 0.89 across 23 drugs, enabling interpretable mechanism discovery and cross-drug/model hypothesis generation.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.
- Open access