Entering edit mode
9.2 years ago
The simplest method would be to just run each chromosome (or a part thereof, depending on how many cores you have, how the data is stored, etc.) on a separate core somewhere on the cluster. This actually has nothing to do with hadoop other than the fact that the cluster is likely using it for file storage.
Use of this site constitutes acceptance of our User Agreement and Privacy Policy.
If you want to write the code to do it, then pretty much anything is possible :)