Custom Solutions

A major challenge in the interpretation of high-throughput genomic data is understanding the functional associations between co-regulated genes. Previously, several approaches have been described to extract gene relationships from various biological databases using term-matching methods. However, more flexible automated methods are needed to identify functional relationships (both explicit and implicit) between genes from the biomedical literature. GeneIndexer utilizes artificial intelligence and computational linguistic techniques to automatically identify conceptual gene relationships from titles and abstracts in MEDLINE citations.

GeneIndexer is based upon proprietary research at the University of Tennessee by Ramin Homayouni, Michael Berry, Kevin Heinrich, and Lai Wei. GeneIndexer represents genes as vectors in lower-dimension (concept) space derived from the literature 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 rapidly mine the biomedical literature for large gene datasets and to make mechanistic or functional predictions that were not previously possible.

A very limited release of a tool based upon the GeneIndexer technology has already generated close to 300 unique users from both academic and commercial research labs. We now are releasing GeneIndexer inclusive of ALL genes contained in Entrez Gene and OMIM databases, making it the most up-to-date and accurate system of its kind.

To learn how to use the tool contact us at info@computablegenomix.com.