Spread Science: Kaggle HIV and Win $500

Welcome to our new blog series, Spread Science, where we will detail a way for you to participate in and promote science. Hopefully, these organisations and projects will keep you entertained over the summer. We are going to look at Kaggle’s attempt to predict HIV progression.

Kaggle isn’t geared toward scientific activity, it is a site where people can post prediction and the best explained prediction will win a prize. For example, right now there is a project about the world cup…but there is some useful science going on.

There is a Kaggle project that is attempting to predict the spread of HIV. Quoting from the project’s description:

"This competition aims to do this by having contestants find markers in the HIV sequence which predict a change in the severity of the infection (as measured by viral load and CD4 counts).

Models can be trained using the records of 1,000 patients. To predict an improvement in a patient’s viral load, competitors will be provided with data on the nucleotide sequences of their Reverse Transcriptase (RT) their Protease (PR) and their viral load and CD4 count at the beginning of therapy. There is a brief discussion of the science of these variables in the Background section, but no knowledge of biology is necessary to succeed in this competition. Competitors’ predictions will be tested on a dataset containing 692 patients. 

There is $500 [USD] up for grabs, and the winner(s) will also have the opportunity to co-author a paper with the competition host."

To break that down, The organisers are looking at the mechanism that the virus uses to make copies of it self in the zombie cells. They think there is a link between that mechanism and the patient’s health, as determine by CD4 (white blood cell) count and viral load.

So, if that made sense to you, check out this project. Who knows, maybe you could co-author a paper, help AIDS patients and win $500. But hurry, you only have about 50 days to do this work. Good luck!