https://github.com/ranking-agent/aragorn-ranker
Exposes TRAPI functions to add literature co-occurrence edges, convert publications to edge weights, and provide scores for answers.
https://github.com/ranking-agent/aragorn-ranker
ara ncats-translator trapi
Last synced: 4 months ago
JSON representation
Exposes TRAPI functions to add literature co-occurrence edges, convert publications to edge weights, and provide scores for answers.
- Host: GitHub
- URL: https://github.com/ranking-agent/aragorn-ranker
- Owner: ranking-agent
- License: mit
- Created: 2020-10-06T11:46:46.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2024-11-25T19:20:43.000Z (over 1 year ago)
- Last Synced: 2024-11-25T19:23:01.152Z (over 1 year ago)
- Topics: ara, ncats-translator, trapi
- Language: Python
- Homepage:
- Size: 19.2 MB
- Stars: 0
- Watchers: 2
- Forks: 1
- Open Issues: 29
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# ARAGORN-ranker
The ARAGORN ranker used by the ARAGORN ARA, which takes a TRAPI 1.5 message containing answers, and calculates numerical scores for each answer.
This is a upgraded port of code from robokop-messenger to perform omnicorp overlay and score for answer ranking.
Omicorp overlay attaches literature co-occurrence support graphs to each result, and the score operation calculates the overall score of the result. Together, the support graphs and the score are included as an analysis of of the result.
ARAGORN-ranker uses the omnicorp database to retrieve ontologies and perform literature co-occurrence calculations. Please see the link below that references that codebase.
## Demonstration
A live version of the API can be found [here](https://aragorn-ranker.renci.org/docs).
## Related Source Code
Below you will find references that detail the standards, web services and supporting tools that are part of ARAGORN.
* [ARAGORN](https://github.com/ranking-agent/aragorn)
* [Omnicorp](https://github.com/NCATS-Gamma/omnicorp)
### Installation
To run the web server directly:
#### Create a virtual Environment and activate.
cd
python -m venv venv
source venv/bin/activate
#### Install dependencies
pip install -r requirements.txt
#### Run Script
cd
./main.sh
### DOCKER
Or build an image and run it.
cd
docker build --tag .
Then start the container
docker run --name aragorn-ranker -p 8080:4868 aragorn-test
### Kubernetes configurations
Kubernetes configurations and helm charts for this project can be found at:
https://github.com/helxplatform/translator-devops/helm/aragorn-ranker