Biosemantics Group Anni 2.0
Category Cross-Omics>Data/Text Mining Systems/Tools
Abstract Anni 2.0 provides an ontology-based interface to Medical Literature Analysis and Retrieval System Online (Medline) and retrieves documents and associations for several classes of biomedical concepts, including genes, drugs and diseases, with proven text-mining technology.
It was designed to aid the researcher with a broad range of information needs.
Anni can be used for simple queries, such as:
(1) give me all the genes that are associated with "prostatic neoplasms". Another typical application of this tool is to explore the associations between a set of concepts, such as:
(2) a list of genes that were found to be differentially expressed in a DNA microarray experiment.
Anni can also be applied to literature-based knowledge discovery. For the last two (2) applications (above) a tutorial can be found on the manufacturer's website.
Note: Anni currently only supports human, mouse and rat genes.
In Anni, texts associated to a concept are characterized by a so-called 'concept profile'. A concept profile consists of a list of related concepts and each concept in the profile has a weight to signify its importance. Concept profiles can be used to retrieve associations between concepts in two ways:
1) Querying the concept weights in the concept profiles: e.g. a query with the concept "prostate cancer" on the set of all genes will retrieve the genes mentioned together with this concept in abstracts, sorted by strength of association as given by the weights in the concept profiles.
2) Concept profiles can be matched to identify similarities between concept profiles, for instance to identify genes associated with similar biological processes.
Anni does Not restrict the user's actions, but some of the options can be very memory intensive and computationally expensive, especially when large numbers of concept profiles are queried, matched, projected or clustered.
To exploit the full potential of Anni it is advisable to have a fast internet connection and an up-to-date computer with more than a gigabyte of free memory.
The technology behind Anni --
1) The ontology is based on the Unified Medical Language System (UMLS) and a gene dictionary. For each concept, it contains names, a definitions and/or links to external databases.
2) For many concepts, a set of documents has been retrieved pertaining to that concept.
3) Concepts mentioned in these documents were identified with the manufacturer's concept-recognition software.
4) In the concept profile of concept X, concepts that are typical for documents pertaining to concept X have a high weight.
5) By querying the concept files, you can find concepts that have a direct relationship with the query concept.
6) By matching concept profiles, you can find concepts that have many intermediate concepts in common. Concepts that are Not directly linked in Medline could turn out to be closely related.
Note: Anni is being updated regularly to incorporate the latest literature, which may lead to different results over time.
System Requirements
Contact manufacturer.
Manufacturer
The Biosemantics Group
- The Biosemantics Group Rotterdam
- Department of Medical Informatics
- Erasmus MC University Medical Center
- P.O. Box 1738, NL-3000 DR
- Rotterdam, 3015 GE
- The Netherlands
- Tel: +31-10-4087050 (Secr. Medical Informatics)
- Fax: +31-10-4089447 (Medical Informatics)
- Biosemantics Group Leiden
- Center for Human and Clinical Genetics
- Leiden University Medical Center
- P.O. Box 9600, 2300 RC Leiden, the Netherlands
- Einthovenweg 20, 2333 ZC Leiden, the Netherlands
- Tel: +31-71+31-71-5269400
- Fax: +31-71-5268285
Manufacturer Web Site Biosemantics Group Anni 2.0
Price Contact manufacturer.
G6G Abstract Number 20209
G6G Manufacturer Number 100431