MetaMap Transfer (MMTx) Information

MMTx is an effort to make the MetaMap program available to biomedical researchers in a generic, configurable environment. MetaMap maps arbitrary text to concepts in the UMLS Metathesaurus; or, equivalently, it discovers Metathesaurus concepts in text.

Common uses of MetaMap include:

• Information extraction tasks
• Classification/categorization tasks
• Text summarization/question and answer tasks
• Data-mining tasks
• Knowledge discovery tasks
• Text understanding tasks
• UMLS Concept-based indexing and retrieval
• NLP tasks

Minimum requirements are:

• OS: Solaris/Windows NT/2000/XP, Linux, Mac OS/X
• Java 1.4 or better
• 400mb disk space for software
• 3GB disk space for each year's data per model
• 600 MB or more RAM/swap space

MMTx users can download the files from the UMLS Knowledge Source Server; in order to access the UMLSKS, users will need to obtain a Metathesaurus license number.

This project is designed to adhere to several principles;

• machine portable (via Java)
• modular
• re-usable
• maintainable
• documented
• configurable

However, it is not an end user product. Users will need a moderate amount of programming knowledge to use MMTx effectively. While the NLM cannot provide tutorials or training in the programming languages used, the links below represent helpful information in the use of MMTx in general.

MetaMap Transfer (MMTx) Home page
Technical FAQ
Short MMTx Overview briefing presented by Guy Divita on December 8, 2005
Java-Doc MMTx Class and API Documentation

If you have questions or comments regarding the use of MMTx, how you think it could be improved, and any other comments or ideas, please contact us at: mmtx@nlm.nih.gov.