Advances in genomic technologies have dramatically boosted research on genetic associations (Kim and Misra, 2007), including genome-wide association studies (Neale and Purcell, 2008). Rapid growth in this field is reflected in the burgeoning number of related publications in public access databases such as PubMed (http://www.ncbi.nlm.nih.gov/pubmed/). Providing access to published information in an easy, comprehensive and systematic fashion is a critical first step in the synthesis and translation of genomic research data; however, information overload makes the retrieval, curation and presentation of such data an extremely challenging task. Since 2001, we have systematically collected and curated data on genetic association retrieved from PubMed, and deposited them in a database (Lin et al., 2006). We recently developed a screening program for genetic association literature that uses a machine learning technique called support vector machine for automatic classification. The new application significantly increased the recall, specificity and precision of screening (Yu et al., 2008a). Along with the new screening tool, the deployment of a new web-based system called HuGE Navigator for querying and filtering the data (Yu et al., 2008b) makes the database
