PubGene Inc. was established in August 2001 in Boston, MA, by researchers at the Norwegian University of Science and Technology, and the Norwegian Radium Hospital. A subsidiary, PubGene AS, was established at the same time in Norway. In 2005, PubGene Inc. acquired Sencel Bioinformatics AS, and the PubGene Group comprises PubGene AS, Sencel Bioinformatics AS, and PubGene Inc.
The initial development dates back to 1998 based on access to MEDLINE and human gene name databases. In 2001, PubGene signed an agreement with the US National Institute of Health’s PubMed (MEDLINE) for extracting information from the PubMed database. PubGene received a lot of positive attention after publishing in Nature Genetics (2001/28) and Pharmacogenomics Journal (2001/1), and different interviews, e.g., in The Economist, The Wall Street Journal, and Reuters. In 2002, PubGene filed a US patent that was approved in 2007, covering the search concept and core technology.
The years from 2001 to 2003 were for a large part used to successfully document, quantify, and improve the precision and signal-to-noise ratios of the databases, as well as validate the relevant full-scale clinical data sets. The main pillars of the PubGene technology are the unique proprietary methods for analyzing and mining term and data associations from huge, hybrid collections of unstructured text. In 2004, the PubGene product was further extended with new features and data generated from additional data sources. PubGene signed license contracts with leading enterprises, such as Pfizer, Johnson & Johnson, Beckman Coulter, Mayo Clinic, and the Karolinska Hospital.
By the end of 2005, the PubGene strategy was further refined to develop the technology and deploy the resources broader for implementation of the COREMINE platform for domain-specific search engines. This included also community features enabling the user to make updates in the context networks and exchanging networks with information with other users. In parallel, the development of COREMINE Medical was started based on the COREMINE Platform. The service was launched September 2011.