Tumor classification with MALDI-MSI data of tissue microarrays: A case study

Abstract

A B S T R A C TWith mass spectrometry imaging (MSI) on tissue microarrays (TMAs) a large number of biomolecules can be studied for many patients at the same time, making it an attractive tool for biomarker discovery. Here we investigate whether lymph node metastasis can be predicted from MALDI-MSI data. Measurements are performed on TMAs and then filtered based on spectral intensity and the percentage of tumor cells, after which the resulting data for 122 patients is further preprocessed. We assume differences between patients with and without metastasis are expressed in a limited number of features. Two univariate feature selection methods are applied to reduce the dimensionality of the MALDI-MSI data. The selected features are then used in combination with three classifiers. The best classification scores are obtained with a decision tree classifier, which classifies about 72% of patients correctly. Almost all the predictive power comes from a single peak (m/z 718.4). The sensitivity of our classification approach, which can be generically used to search for biomarkers, is investigated using artificially modified data.

Picosecond Infrared Laser Desorption Mass Spectrometry Identifies Medulloblastoma Subgroups on Intrasurgical Timescales

“…Whether metabolic nuances provide sufficient contrast to capture grading of MB subgroups into additional subtypes (17) remains to be evaluated. In this quest, other non-ambient mass spectrometric analysis methods such as Matrix Assisted Laser Desorption Ionization Mass Spectrometry (MALDI-MS) can also be useful (44)(45)(46)(47)(48)(49). Similar to many other rapid mass spectrometry classification methods reviewed above [iKnife (28), Spider-Mass (29), MasSpec Pen (30)], PIRL-MS is likely to find utility for ex vivo and in situ/in vivo tissue examination scenario ( Supplementary Fig.…”

Emerging applications in mass spectrometry imaging; enablers and roadblocks

“…Since its development for biomolecular imaging by the Caprioli group in 1997, 1 MSI has established itself to encapsulate many bioanalytical applications, analysing a variety of samples including single-cells, three-dimensional cultures, animal tissues, whole rodents, patient microarrays and biopsies, fingermarks, and human hair. [2][3][4][5][6][7][8] Over the last decade, technical advancements in instrumentation have allowed vast improvements in MSI speed, spatial resolution and sensitivity. In addition, MSI modalities employing a wide range of ionisation sources have been developed including: matrix-assisted laser desorption ionisation (MALDI), a soft ionisation technique which employs laser energy and an absorbing matrix; secondary ionisation mass spectrometry (SIMS), using a focused primary beam of ions resulting in the analysis of secondary ions ejected from the sample surface; desorption electrospray ionisation (DESI), an ambient ionisation methodology via a solvent spray; laser ablation inductively coupled plasma (LA-ICP) involves a nanosecond-pulsed laser to the sample surface; and liquid extraction surface analysis (LESA) via direct micro-junction solvent extraction.…”

Colocalization Features for Classification of Tumors Using Desorption Electrospray Ionization Mass Spectrometry Imaging

“…Currently, the most used approach is based on extracting a “representative” spectrum for the entire MS image, which is then related to the corresponding label. 25,26 A typical choice is the mean spectrum calculated over pixels of the same tissue type. Another approach is based on selecting a random subset of pixel spectra from the tissue of interest and predicting their class.…”