Automated Biomarker Candidate Discovery in Imaging Mass Spectrometry Data Through Spatially Localized Shapley Additive Explanations

Abstract

The search for molecular species that are differentially expressed between biological states is an important step towards discovering promising biomarker candidates. In imaging mass spectrometry (IMS), performing this search manually is often impractical due to the large size and high-dimensionality of IMS datasets. Instead, we propose an interpretable machine learning workflow that automatically identifies biomarker candidates by their mass-to-charge ratios, and that quantitatively estimates their relevance to recognizing a given biological class using Shapley additive explanations (SHAP). The task of biomarker candidate discovery is translated into a feature ranking problem: given a classification model that assigns pixels to different biological classes on the basis of their mass spectra, the molecular species that the model uses as features are ranked in descending order of relative predictive importance such that the top-ranking features have a higher likelihood of being useful biomarkers. Besides providing the user with an experiment-wide measure of a molecular species biomarker potential, our workflow delivers spatially localized explanations of the classification models decision-making process in the form of a novel representation called SHAP maps. SHAP maps deliver insight into the spatial specificity of biomarker candidates by highlighting in which regions of the tissue sample each feature provides discriminative information and in which regions it does not. SHAP maps also enable one to determine whether the relationship between a biomarker candidate and a biological state of interest is correlative or anticorrelative. Our automated approach to estimating a molecular species potential for characterizing a user-provided biological class, combined with the untargeted and multiplexed nature of IMS, allows for the rapid screening of thousands of molecular species and the obtention of a broader biomarker candidate shortlist than would be possible through targeted manual assessment. Our biomarker candidate discovery workflow is demonstrated on mouse-pup and rat kidney case studies. HighlightsO_LIOur workflow automates the discovery of biomarker candidates in imaging mass spectrometry data by using state-of-the-art machine learning methodology to produce a shortlist of molecular species that are differentially expressed with regards to a user-provided biological class. C_LIO_LIA model interpretability method called Shapley additive explanations (SHAP), with observational Shapley values, enables us to quantify the local and global predictive importance of molecular species with respect to recognizing a user-provided biological class. C_LIO_LIBy providing spatially localized explanations for a classification models decision-making process, SHAP maps deliver insight into the spatial specificity of biomarker candidates and enable one to determine whether (and where) the relationship between a biomarker candidate and the class of interest is correlative or anticorrelative. C_LI