Researchers in Switzerland and Germany recently published an article in Public Library of Science Computational Biology about using Google’s PageRank algorithm to predict cancer growth: Google Goes Cancer: Improving Outcome Prediction for Cancer Patients by Network-Based Ranking of Marker Genes. (Now, in the interest of full disclosure, I have to admit that I didn’t read the whole paper in PLoS Computational Biology. I did, however, read a fascinating review and digest by on the paper on Txchnologist: Googling Cancer: Search Algorithms Can Scan Disease for Patient Risk.)
What I find so fascinating is that it never would have occurred to me to look at cancer the same way we looking at search ranking:
[G]enes 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. … Reliable prediction of survival and response to therapy based on molecular markers bears a great potential to improve and personalize patient therapies in the future.
What do you think about applying the PageRank algorithm to cancer detection? What other technologies or algorithms do we have that could be re-purposed this way?
 Winter C, Kristiansen G, Kersting S, Roy J, Aust D, et al. (2012) Google Goes Cancer: Improving Outcome Prediction for Cancer Patients by Network-Based Ranking of Marker Genes. PLoS Comput Biol 8(5): e1002511. doi:10.1371/journal.pcbi.1002511