hAMRonization: Enhancing antimicrobial resistance prediction using the PHA4GE AMR detection specification and tooling
Bibliographic record
Abstract
Abstract The detection of antimicrobial resistance (AMR) markers directly from genomic or metagenomic data is becoming a standard clinical and public health procedure. This has resulted in the development of a number of different bioinformatic AMR prediction tools. Although many may implement similar principles, these tools differ significantly in their supported inputs, search algorithms, parameterisation, and underlying reference databases. Each of these tools generates a report of detected AMR genes or variants in a distinct, non-standard, format. This presents a huge barrier to the comparison of results and to the modularity of tools for AMR gene prediction within bioinformatic workflows. In collaboration with 17 public health laboratories across 10 countries, the Public Health Alliance for Genomic Epidemiology (PHA4GE) ( https://pha4ge.org ) data structures working group has developed and piloted a standardized output specification for the bioinformatic detection of AMR from microbial genomes. In this report, we discuss hAMRonization, a python package and command-line utility, which implements PHA4GE’s AMR specification to combine the outputs of disparate antimicrobial resistance gene detection tools into a single unified format. hAMRonization can be easily extended and currently supports 18 different tools (both species-agnostic and species-specific) for the detection of genes and/or variants conferring AMR. The harmonized reports are available in tabular form, JSON format or through an interactive HTML file (e.g., https://maguire-lab.github.io/assets/interactive_report_demo.html ) that can be opened within the browser for navigable data exploration. As of 2024-03-07 hAMRonization has been downloaded ∼12,500 times, incorporated into >9 public bioinformatic tools and workflows, and been internally adopted by several national and international public health groups. The hAMRonization tool and underlying specification are open-source and freely available through PyPI, conda and GitHub ( https://github.com/pha4ge/hAMRonization ).
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.010 | 0.019 |
| Meta-epidemiology (narrow) | 0.003 | 0.002 |
| Meta-epidemiology (broad) | 0.001 | 0.003 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.004 |
| Open science | 0.003 | 0.005 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.013 | 0.013 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".