This is not the first time that this has been attempted, the SPIA [1] algorithm from 2008 is similarly inspired. It appears these authors were not aware of that paper though, as they don't cite or compare to it.
I hate when sites don't link to the original article for credit but just dump you at the homepage. :(
Also PLOS's search is fairly broken - had to do a google site: search.
EDIT: From the author summary on PLOS
"Recently, powerful methods have become available to systematically read genomic information of patient samples. The major remaining challenge is how to spot, among the thousands of changes, those few that are relevant for tumor aggressiveness and thereby affecting patient survival. Here, we make use of the fact that genes and proteins in a cell never act alone, but form a network of interactions. Finding the relevant information in big networks of web documents and hyperlinks has been mastered by Google with their PageRank algorithm. Similar to PageRank, we have developed an algorithm that can identify genes that are better indicators for survival than genes found by traditional algorithms."
[1] http://bioinformatics.oxfordjournals.org/content/25/1/75