Metadata-Version: 2.1
Name: umls-graph
Version: 0.0.3a1
Summary: Build medical knowledge graph based on Unified Medical Language System (UMLS)
Home-page: https://github.com/dhchenx/umls-graph
Author: Donghua Chen
Author-email: douglaschan@126.com
License: MIT
Project-URL: Bug Reports, https://github.com/dhchenx/umls-graph/issues
Keywords: unified medical language system,UMLS,knowledge graph,medical knowledge,medical concept,neo4j
Platform: UNKNOWN
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Topic :: Software Development :: Build Tools
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3 :: Only
Requires-Python: >=3.6, <4
Description-Content-Type: text/markdown
Provides-Extra: dev
Provides-Extra: test
License-File: LICENSE

# UMLS-Graph

This toolkit aims to leverage biomedical concepts and their relationships in Unified Language Medical System (UMLS). 

## Prerequisite

Install MySQL Server 5.6 and import UMLS data into MySQL database. Please refer to [UMLS](https://www.nlm.nih.gov/research/umls/index.html) websites on how to install the UMLS database. 

## Installation

```pip
pip install umls-graph
```

## Let Codes Speak

```python
from umls_graph.dataset import make_umls_all

# MySQL database information
mysql_info = {}
mysql_info["database"] = "umls"
mysql_info["username"] = "root"
mysql_info["password"] = "{not gonna tell you}"
mysql_info["hostname"] = "localhost"

# read all UMLS tables and save them to csv formatted files in a folder
make_umls_all(mysql_info=mysql_info,save_folder="umls_datasets")

```

## License
The `umls-graph` project is provided by [Donghua Chen](https://github.com/dhchenx/umls-graph). 

NOTE: This project DOES NOT attach UMLS datasets due to the license issue. In addition, the processed data are not verified in actual clinical use.  Please be responsible for any use. 

