The increasing availability of “big data” enables novel research approaches to chronic pain while also requiring novel techniques for data mining and knowledge discovery. We used machine learning to combine the knowledge about n = 535 genes identified empirically as relevant to pain with the knowledge about the functions of thousands of genes. Starting from an accepted description of chronic pain as displaying systemic features described by the terms “learning” and “neuronal plasticity,” a functional genomics analysis proposed that among the functions of the 535 “pain genes,” the biological processes “learning or memory” (P = 8.6 × 10−64) and “nervous system development” (P = 2.4 × 10−40) are statistically significantly overrepresented as compared with the annotations to these processes expected by chance. After establishing that the hypothesized biological processes were among important functional genomics features of pain, a subset of n = 34 pain genes were found to be annotated with both Gene Ontology terms. Published empirical evidence supporting their involvement in chronic pain was identified for almost all these genes, including 1 gene identified in March 2016 as being involved in pain. By contrast, such evidence was virtually absent in a randomly selected set of 34 other human genes. Hence, the present computational functional genomics–based method can be used for candidate gene selection, providing an alternative to established methods.
Machine-learned knowledge discovery in “big data” identified 34 pain genes that supported by empirical evidence qualify as candidate genes for pain chronification studies.
aDataBionics Research Group, University of Marburg, Hans-Meerwein-Straße, Marburg, Germany
bInstitute of Clinical Pharmacology, Goethe-University, Frankfurt, Germany
cDivision of Pain Medicine, Department of Anesthesiology, Intensive Care and Pain Medicine, University of Helsinki and Helsinki University Hospital, Helsinki, Finland
dDepartment of Psychology and Alan Edwards Centre for Research on Pain, McGill University, Montreal, QC, Canada
eFraunhofer Institute of Molecular Biology and Applied Ecology-Project Group Translational Medicine and Pharmacology (IME-TMP), Frankfurt am Main, Germany
Corresponding author. Address: Goethe-University, Theodor-Stern-Kai 7, 60590 Frankfurt am Main, Germany. Tel.: +49 69 6301 4589; fax: +49 69 6301 4354. E-mail address: firstname.lastname@example.org (J. Lötsch).
Sponsorships or competing interests that may be relevant to content are disclosed at the end of this article.
Supplemental digital content is available for this article. Direct URL citations appear in the printed text and are provided in the HTML and PDF versions of this article on the journal's Web site (www.painjournalonline.com).
Received March 17, 2016
Received in revised form August 04, 2016
Accepted August 09, 2016