Machine learning methods in computational cancer biology


Molecular data from cancer tumours is characterized by the fact that the number of measured features is in the tens of thousands, while the number of samples is a few hundred at best. This mismatch necessitates the development of new algorithms for sparse regression and sparse classification with an eye towards cancer applications. Another aspect of… (More)
DOI: 10.1016/j.arcontrol.2017.03.007