Predicting emerging technologies with the aid of text-based data mining: the micro approach

Text data mining should be useful for anticipating new technologies and new uses for existing technologies, insofar as one can attempt to connect comp lementary pieces of information across two different domains, or subsets, o f the scientific literature. The present study attempted to predict genetic engineering technologies that may impact on viral warfare in the future. T he analysis was carried out using a combination of conventional Medline sea rches and the package of advanced informatics techniques known collectively as Arrowsmith. The findings strongly indicate that genetic packaging techn ologies such as DEAE-dextran, cationic liposomes and cyclodextrins are plau sible candidates to enhance infections caused by viruses delivered via an a erosol route despite the fact that no studies have yet been reported that h ave examined this issue directly, and certainly not in the contexts of vira l disease or viral warfare. The critical factor was the overall strategy of approaching the problem: first, to define two specific fields explicitly ( in this case, genetic engineering and viral warfare) that are hypothesized to contain complementary information; second, to identify common factors th at bridge the two disciplines (i.e. research on viruses); and third, to pro gressively shape the query once initial findings are obtained. Thus, in con trast to some current perceptions, the process of text data mining is neith er automatic nor is it restricted to those who have access to macro analyse s using customized computer systems. (C) 2001 Elsevier Science Ltd. All rig hts reserved.