https://github.com/INCATools/neoplasmer
Neoplasm Entity Recognition: matching disease names to ontology classes
https://github.com/INCATools/neoplasmer
cancer entity-matching mondo ncit neoplasm ner nlp obofoundry
Last synced: about 1 month ago
JSON representation
Neoplasm Entity Recognition: matching disease names to ontology classes
- Host: GitHub
- URL: https://github.com/INCATools/neoplasmer
- Owner: INCATools
- License: bsd-3-clause
- Created: 2018-08-22T07:17:04.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2019-07-15T19:14:32.000Z (almost 6 years ago)
- Last Synced: 2025-03-01T06:39:19.128Z (about 2 months ago)
- Topics: cancer, entity-matching, mondo, ncit, neoplasm, ner, nlp, obofoundry
- Language: Prolog
- Homepage:
- Size: 88.9 KB
- Stars: 5
- Watchers: 3
- Forks: 0
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
[](https://zenodo.org/badge/latestdoi/13996/cmungall/neoplasmER)
# neoplasmer (ALPHA RELEASE)
Matches names of cancers and cancer-related conditions to ontology classes
## Usage (via Docker)
Currently the recommended way to do this is on the command line via the [neoplasmer.sh](neoplasmer.sh) bash script:
```
./neoplasmer.sh tests/data/vicc_input.txt
```
You do not need to install anything other than [Docker](http://docker.com/get-docker). The shell script is standalone.
The input file is a newline delimited list of terms. See [tests/data/](tests/data/) for examples.
The first execution will take a minute or two; some warning messages
may be printed, these can be ignored. Two directories will be created: `RDF-Cache` and `.cache`
Subsequent executions will be much faster
You can see example results in [scratch/vicc-results.tsv](scratch/vicc-results.tsv)
## Python client
First, start a service:
`./neoplasmer.sh --port 9055`
Then install python libs:
```
pip3 install -r requirements.txt
```
Run the test client:
```
python3 bin/neoplasmer-client.py 'lung cancer' 'brain glioma'
```
TODO: additional documentation on how to this works
## Running without docker
Install SWI-Prolog from http://www.swi-prolog.org
Run directly using [bin/neoplasmer](bin/neoplasmer)