Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/bacpop/amr_reactapp

AMR prediction from S. pneumoniae assemblies in the browser

https://github.com/bacpop/amr_reactapp

Science Score: 10.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ○
    codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: pubmed.ncbi, ncbi.nlm.nih.gov
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (9.5%) to scientific vocabulary

Keywords

amr genomics pneumococcus wasm
Last synced: 10 months ago · JSON representation

Repository

AMR prediction from S. pneumoniae assemblies in the browser

Basic Info
  • Host: GitHub
  • Owner: bacpop
  • License: mit
  • Language: JavaScript
  • Default Branch: main
  • Homepage: https://amr.poppunk.net
  • Size: 23.3 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 2
  • Releases: 0
Topics
amr genomics pneumococcus wasm
Created over 4 years ago · Last pushed over 4 years ago
Metadata Files
Readme License

README.md

Azure Static Web Apps CI/CD

AMIMA

AMR prediction tool for S.pneumoniae

Overview

https://amr.poppunk.net/ is a tool to predict antimicrobial resistance in S.pneumoniae. It applies linear models on genetic sequence data to return a probability of resistance to the five antibiotics - Penicillin - Chloramphenicol - Erythromycin - Tetracycline - Trimethoprim/Sulfamethoxazole

Intended use

Files in FASTA format can be uploaded via a drag and drop area. Submission of multiple files at a time is possible. Files should cover the whole genome to ensure the models can be applied correctly.

Results are displayed in a table, giving the probability of resistance to the respective antibiotic.

The table can be downloaded in CSV format.

Don't use this tool for clinical practice.

Methods

The models applied are logistic ElasticNet models trained on data from the USA and South Africa from the GPS database.

Input features that are generated from the FASTA files are unitigs, which are nucleotide sequences of variable length.

The models have been tested on independent datasets from Massachusetts and Maela (Thailand). The predicted binary resistance status (at a probability threshold of 0.5) was tested against the true recorded phenotype and Balanced Accuracies were calculated:

|Antibiotic|Massachusetts|Maela| |----------|-------------|-----| |Penicillin|0.933|0.836| |Chlorampehnicol| |0.819| |Erythromycin|0.959|0.961| |Tetracycline|0.953|0.940| |Trimethoprim/Sulfamethoxazole|0.954|0.837|

The website was build using React.js. The backend code can be found here.

Contributors

This tool was developed by Marie Gronemeyer and John Lees.

Owner

  • Name: Bacterial population genetics
  • Login: bacpop
  • Kind: organization
  • Email: contact@bacpop.org
  • Location: United Kingdom

Pathogen Informatics and Modelling @ EMBL-EBI / Bacterial Evolutionary Epidemiology Group @ Imperial College London

GitHub Events

Total
Last Year

Dependencies

package.json npm
  • @testing-library/jest-dom ^5.15.1
  • @testing-library/react ^11.2.7
  • @testing-library/user-event ^12.8.3
  • react ^17.0.2
  • react-csv ^2.0.3
  • react-dom ^17.0.2
  • react-dropzone ^11.4.2
  • react-scripts 4.0.3
  • spinners-react ^1.0.6
  • web-vitals ^1.1.2