GeneIndexer [Login]

Several computational approaches have been previously described to extract gene relationships from biological databases using term-matching methods. However, these methods are highly limited in their ability to synthesize discoveries from the literature. More flexible automated methods are required if both explicit and implicit gene relationships are to be successfully identified from the biomedical literature. GeneIndexer was developed to address this problem.

GeneIndexer utilizes artificial intelligence and computational linguistic techniques to identify conceptual gene relationships from titles and abstracts in MEDLINE citations automatically.

Using the scientific literature, GeneIndexer represents genes as vectors in space and deduces gene-to-gene and gene-to-keyword relationships. The method extracts features from the scientific literature that are not easily made or even possible by humans. Therefore, GeneIndexer allows researchers to mine the biomedical literature for large gene datasets rapidly and to make mechanistic or functional predictions that were not previously possible.

GeneIndexer includes ALL genes contained in Entrez Gene and OMIM databases, making it the most up-to-date and accurate system of its kind.