Releases | Open Source Science

translator-openpredict - Translator OpenPredict 0.2.1

Changelog

Fix publish package GitHub action

Full Changelog: https://github.com/MaastrichtU-IDS/translator-openpredict/compare/v0.2.0...v0.2.1

- Jupyter Notebook
Published by vemonet about 3 years ago

translator-openpredict - Translator OpenPredict 0.2.0

Changelog

Add TRAPI class to the openpredict package, so users can easily deploy their own TRAPI based on their prediction functions

Full Changelog: https://github.com/MaastrichtU-IDS/translator-openpredict/compare/v0.1.0...v0.2.0

- Jupyter Notebook
Published by vemonet about 3 years ago

translator-openpredict - OpenPredict Translator API 0.1.0

Major refactor of OpenPredict

OpenPredict now uses dvc (data version control) and DagsHub (a platform to publish the data) to handle all data files required to train the models and run the predictions that are all in the data/ folder at the root of the repository (instead of having half of them committed to git, and the other half to be downloaded from some obscure servers, now every single CSV input and model output at stored in the data/ folder).

dvc/DagsHub works and looks a lot like git/GitHub, but specialized for large data files (and it can also be used to store metadata about your runs). The repo size limit for open source projects on DagsHub is 10G

You can find the data used for OpenPredict (prediction + similarity + evidence path + drkg model) at https://dagshub.com/vemonet/translator-openpredict

There is now a decorator @trapi_predict to mark a functions that return predictions that can be integrated automatically in a TRAPI query. It allows the dev to specify which relations this prediction function can resolve in a TRAPI query. So the dev just need to insure that his prediction functions take the input we expect, and returns the predictions in the expected format (cf. the code example below, note that it is vastly inspired from ElasticSearch and BioThings return formats). Then the predictions generated by this function can be automatically integrated to our TRAPI API, and a simple GET endpoint to query the prediction individually is also automatically generated

```python from openpredict import trapi_predict, PredictOptions, PredictOutput

@trapipredict(path='/predict', name="Get predicted targets for a given entity", description="Return the predicted targets for a given entity: drug (DrugBank ID) or disease (OMIM ID), with confidence scores.", relations=[ { 'subject': 'biolink:Drug', 'predicate': 'biolink:treats', 'object': 'biolink:Disease', }, { 'subject': 'biolink:Disease', 'predicate': 'biolink:treatedby', 'object': 'biolink:Drug', }, ] ) def getpredictions( inputid: str, options: PredictOptions ) -> PredictOutput: # Add the code the load the model and get predictions here predictions = { "hits": [ { "id": "DB00001", "type": "biolink:Drug", "score": 0.12345, "label": "Leipirudin", } ], "count": 1, } return predictions ```

When someone wants to add a new prediction model to the Translator OpenPredict API they can either create a new folder under src/ in the existing translator-openpredict repo, and add all the python files they need to train and run the prediction (and use the decorator to annotate the prediction function). Or do it in a separate repository published to GitHub, with data stored using dvc . So we can easily import the code and data required to run the prediction from the OpenPredict API. There is a template repository to help people get started with the recommended architecture: https://github.com/MaastrichtU-IDS/cookiecutter-openpredict-api

bash pip install cookiecutter cookiecutter https://github.com/MaastrichtU-IDS/cookiecutter-openpredict-api

Now use hatch instead of poetry for build process

Full Changelog: https://github.com/MaastrichtU-IDS/translator-openpredict/compare/v0.0.8...v0.1.0

- Jupyter Notebook
Published by vemonet about 3 years ago

translator-openpredict - OpenPredict API 0.0.8

Last version with the TRAPI API defined in the package. Uses embedded RDFLib triplestore

What's Changed

fix: translator-ops branch is removed by @pahmadi8740 in https://github.com/MaastrichtU-IDS/translator-openpredict/pull/29
Update Jenkinsfile by @pahmadi8740 in https://github.com/MaastrichtU-IDS/translator-openpredict/pull/30
fix local deployment servers in openapi schema by @elifozkn in https://github.com/MaastrichtU-IDS/translator-openpredict/pull/31
Kgxpredict by @arifx in https://github.com/MaastrichtU-IDS/translator-openpredict/pull/38
add evidence path by @elifozkn in https://github.com/MaastrichtU-IDS/translator-openpredict/pull/39

New Contributors

@pahmadi8740 made their first contribution in https://github.com/MaastrichtU-IDS/translator-openpredict/pull/29
@elifozkn made their first contribution in https://github.com/MaastrichtU-IDS/translator-openpredict/pull/31

Full Changelog: https://github.com/MaastrichtU-IDS/translator-openpredict/compare/v0.0.7...v0.0.8

- Jupyter Notebook
Published by vemonet about 3 years ago

translator-openpredict - OpenPredict 0.0.7 using GraphDB backend

OpenPredict 0.0.7 still using a GraphDB backend in production

- Jupyter Notebook
Published by vemonet about 4 years ago

translator-openpredict - Dec2021Demo

Release for the Translator December 2021 Demo

- Jupyter Notebook
Published by vemonet over 4 years ago

translator-openpredict - OpenPredict 0.0.6

Improve the OpenPredict API storage and reuse of models when new embeddings are added
Use .ttl file locally to store OpenPredict metadata
Make the /predict call compatible with the BioThings Explorer operations annotations

- Jupyter Notebook
Published by vemonet about 5 years ago

translator-openpredict - OpenPredict 0.0.5

Improve openpredict pip package: * Include openapi.yml and all files from the data folder in the openpredict package * Now generating RDF from the classifier training scores * Fix issue with the server URL, add a new argument: --server-url, default to / * Improve examples and documentation