Abstract
Dietary supplements remain a relatively underexplored source for drug repurposing. A systematic approach to soliciting responses from a large consumer population is desirable to speed up innovation. We tested a workflow that mines unexpected benefits of dietary supplements from massive consumer reviews. A (non-exhaustive) list of regular expressions was used to screen over 2 million reviews on health and personal care products. The matched reviews were manually analyzed, and one supplement-disease pair was linked to biological databases for enriching the hypothesized association. The regular expressions found 169 candidate reviews, of which 45.6% described unexpected benefits of certain dietary supplements. The manual analysis showed some of the supplement-disease associations to be novel or in agreement with evidence published later in the literature. The hypothesis enrichment was able to identify meaningful function similarity between the supplement and the disease. The results demonstrated value of the workflow in identifying candidates for supplement repurposing.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 689-695 |
| Number of pages | 7 |
| Journal | AMIA ... Annual Symposium proceedings. AMIA Symposium |
| Volume | 2017 |
| State | Published - 2017 |
ASJC Scopus subject areas
- General Medicine