Data-driven identification of prognostic tumor subpopulations using spatially mapped t-SNE of mass spectrometry imaging data

Abstract

The identification of tumor subpopulations that adversely affect patient outcomes is essential for a more targeted investigation into how tumors develop detrimental phenotypes, as well as for personalized therapy. Mass spectrometry imaging has demonstrated the ability to uncover molecular intratumor heterogeneity. The challenge has been to conduct an objective analysis of the resulting data to identify those tumor subpopulations that affect patient outcome. Here we introduce spatially mapped t-distributed stochastic neighbor embedding (t-SNE), a nonlinear visualization of the data that is able to better resolve the biomolecular intratumor heterogeneity. In an unbiased manner, t-SNE can uncover tumor subpopulations that are statistically linked to patient survival in gastric cancer and metastasis status in primary tumors of breast cancer.intratumor heterogeneity | mass spectrometry imaging | t-SNE | biomarker | cancer M ass spectrometry imaging (MSI) is a technology that simultaneously provides the spatial distribution of hundreds of biomolecules directly from tissue (1, 2). The two most common techniques, matrix-assisted laser desorption and desorption electrospray ionization, lead to minimal loss of histological information. Accordingly, the same tissue section can be histologically assessed and registered to the MSI dataset. In this manner, the mass spectral signatures of specific cell types or histopathological entities (e.g., tumor cells) can be extracted from the often highly heterogeneous tissues encountered in patient tumors (3). This high cellular specificity is behind the increasing popularity of MSI in cancer research and its proven ability to identify diagnostic and prognostic biomarkers (4).There is growing awareness that MSI also can be used to annotate tissues based on the local mass spectrometry profiles and thereby differentiate tissues/regions that are not histologically distinct. Deininger et al. (5) were the first to report that MSI may reveal the biomolecular intratumor heterogeneity associated with a tumor's clonal development. A hierarchical cluster analysis of the MSI data revealed a patchwork of molecularly distinct regions, which were postulated to reflect the tumor's clonal evolution. It was recently demonstrated that such an approach, using multivariate analysis of the MSI data to identify regions with distinct mass spectral signatures and then linking these molecularly distinct regions to patient outcome, enables the identification of tumor subpopulations that are statistically associated with poor survival and tumor metastasis (6).All methods used to date for revealing intratumor heterogeneity have been linear dimensionality-reduction techniques, but this linearity constraint focuses the results on the global characteristics of the data space at the expense of finer details (7). Accordingly, linear methods might not be sensitive to the subtle changes expected to demarcate the clonal progression of tumors, in which the molecular differences between nearly sequential subpopulations may...

Breast Cancer: Multiple Subtypes within a Tumor?

“…HI-C, ATAC-seq), mass cytometry, mass cytometry imaging, multiplexed ion beam imaging (MIBI) and multiplexed fluorescence barcoding hybridization methods are the rapidly developing modalities that could be instrumental and the technical aspects of each methodology are described in more detail in the respective reviews [60–64]. In the case of FFPE based diagnosis, mass spectrometry based techniques have been employed to spatially unravel molecularly distinct tumor subpopulations with clinically relevant attributes [65, 66]. There is also potential for integration of multiple ‘omics’ platforms, since some of these mass-spectrometric methods are also amenable to parameters such as metabolites [67].…”

Applying Machine Learning Algorithms to Segment High-Cost Patient Populations

“…Finally, we limited our study to a single approach to dimensional reduction, t-SNE. Although t-SNE has been shown to produce well-separated clusters in a variety of biomedical settings [31][32][33][34] , it is a stochastic method that relies on a number of user-specified inputs. Future work should include comparisons of t-SNE to other projection techniques, such as principal component analysis (PCA).…”

Unsupervised machine learning for exploratory data analysis in imaging mass spectrometry

“…This same workflow was used for the registration of SIMS imaging data to histology in Škrášková et al (). Furthermore, Abdelmoula et al () used t‐SNE, combined with bisecting ‐means, to study tumor heterogeneity and subpopulations in gastric and breast cancer. They used this setup to determine the number of subpopulations and assess their clinical significance.…”