The Literature Lab™ data mining platform advances to quarterly PubMed database updates

Literature Lab™, from Acumenta Biotech, is a unique automated platform for functional analysis of genetic data through statistical mining of PubMed.  Literature Lab™ also functions to identify and score the strengths of co-occurrences between biological and biochemical terms in the literature.  

"Literature Lab is an easy to use automated functional analysis and data mining tool uniquely suited to uncover associations and co-occurrences among diseases, pathways, chemical actions, etc. in the literature. It was of great use to us in a recent study to uncover shared genetic etiology among allergic diseases”

Tesfaye Mersha, Assistant Professor, University of Cincinnati, Department of Pediatrics, Resolving the etiology of atopic disorders by using genetic analysis of racial ancestry. 2016. Journal of Allergy and Clinical Immunology. S0091-6749(16)30256-1.

“One of the most powerful strengths of the Literature Lab™ platform is that it addresses two big data issues”, explains Damon Anderson PhD, Vice President of Business Development.  “First, modern technologies are producing genetic data at unprecedented rates, often resulting in a backlog of experimental questions with no real actionable answers.  Second, the PubMed literature record is expanding at an ever increasing rate, resulting in a huge resource of critical information that remains relatively untapped”.

The most recent Literature Lab™ database update, January 1, 1990 to March 31, 2016, includes 16,968,903 PubMed abstracts, an increase of 294,692 abstracts over December 31, 2015.  Abstracts mentioning at least one human gene has officially surpassed the 10 million mark, 10,089,362.

“Interrogation of PubMed by use of the Acumenta Biotech Gene Thesaurus™ coupled with statistical analysis of hits on genes and pathways, diseases, compounds/drugs, cell biology, etc., offers an unprecedented advantage over traditional manual searches”, states Paul Martinez, President and CEO.  “We have moved to quarterly database updates to keep pace with the rapid expansion of PubMed.  Frequent database updates also assure that discredited of otherwise removed literature does not accumulate, and is not therefore used in Literature Lab™ analysis.  Improvements and corrections to MeSH tagging are always incorporated.”

“We believe that these features are uniquely powerful in our automated approach to database interrogation and statistical analysis on the literature”, explains Martinez.  “Other tools have their databases periodically and cumulatively updated, and there is seldom time or resources to edit mistakes of the past.  With quarterly releases of the database for statistical analysis on gene lists, and automated "as of this second" searches on associations of interest, Literature Lab™ sets a benchmark for timeliness that is far ahead of other functional analysis tools.”