|Learn more about the benefits of a paid subscription to BRENDA|
AMENDA (Automatic Mining of ENzyme DAta) is a supplement to BRENDA that is available to the public since BRENDA release 5.2 (December 2005). It contains a large amount of enzyme data which are automatically extracted from more than 20 million PubMed references (titles and abstracts).
Contents of AMENDA(January 2010)
As a subset of FRENDA, AMENDA currently covers enzyme-specific information on their occurences in organisms (more than 200,000 records, compared to about 50,000 records in BRENDA), (sub)cellular localizations (more than 25,000 records, compared to about 22,000 records in BRENDA) and source tissues (roughly 130,000 records, compared to about 61,000 records in BRENDA).
More than 20 million PubMed reference - titles and when available abstracts - (status: June 2010) are analyzed in a cooccurence based textmining approach.
AMENDA uses a dictionary-based approach for detecting named entities in titles
and abstracts. Search terms for enzyme names, organism names, localization, and sources and tissues
are compiled from public sources.
The text mining approach described above was tested on a manually annotated text
corpus of 100 randomly selected references (listed in BRENDA as containing tissue
information). A precision of approximately 87% was achieved (this means there were 13%
false positives among the results). The precision is currently being re-evaluated by means of a
larger text corpus (1000 abstracts).
The AMENDA supplement is freely accessible for academic users. Commercial use requires a license - See copyright notice