Markov Random Fields and Mass Spectra Discrimination
This work addresses the need for biologically interpretable cancer diagnosis tools for medical researchers and clinicians, though it is incremental as it builds on existing mass spectrometry techniques with a new modeling approach.
The authors tackled the problem of automated discrimination between cancer types or stages from mass spectra, which often results in uninterpretable 'black-box' classifiers, by developing new signature discovery algorithms that produce interpretable signatures based on selected biomarkers, validated on six benchmark tasks for colorectal and ovarian cancer patients.
For mass spectra acquired from cancer patients by MALDI or SELDI techniques, automated discrimination between cancer types or stages has often been implemented by machine learnings. These techniques typically generate "black-box" classifiers, which are difficult to interpret biologically. We develop new and efficient signature discovery algorithms leading to interpretable signatures combining the discriminating power of explicitly selected small groups of biomarkers, identified by their m/z ratios. Our approach is based on rigorous stochastic modeling of "homogeneous" datasets of mass spectra by a versatile class of parameterized Markov Random Fields. We present detailed algorithms validated by precise theoretical results. We also outline the successful tests of our approach to generate efficient explicit signatures for six benchmark discrimination tasks, based on mass spectra acquired from colorectal cancer patients, as well as from ovarian cancer patients.