Our main source of information is currently Wikipedia. However, we are focusing our efforts in using more sources. In a near future we are planning to extract information from other public sources such as MedLine Plus or CDC webpage among others.
The data extraction process runs NLP tools over the texts retrieved from selected data sources such as Wikipedia. We are currently using MetaMap to extract the information from the texts. Other NLP tools will be used in the future.
The data will be publicly available to any user through a REST service. Users just need to register and provide some basic information to obtain a token that will allow them to query the DISNET database. However, users can have access to the REST API without a token. Nonetheless, we recommend creating an account and using your token if you want to save a history of your requests.