Alterations in cell metabolism, including changes in lipid composition occurring during malignancy, are well characterized for various tumor types. However, a significant part of studies that deal with brain tumors have been performed using cell cultures and animal models. Here, we present a dataset of 124 high-resolution negative ionization mode lipid profiles of human brain tumors resected during neurosurgery. The dataset is supplemented with 38 non-tumor pathological brain tissue samples resected during elective surgery. The change in lipid composition alterations of brain tumors enables the possibility of discriminating between malignant and healthy tissues with the implementation of ambient mass spectrometry. On the other hand, the collection of clinical samples allows the comparison of the metabolism alteration patterns in animal models or in vitro models with natural tumor samples ex vivo. The presented dataset is intended to be a data sample for bioinformaticians to test various data analysis techniques with ambient mass spectrometry profiles, or to be a source of clinically relevant data for lipidomic research in oncology.
Mass spectrometry fingerprinting combined with multidimensional data analysis has been proposed in surgery to determine if a biopsy sample is a tumor. In the specific case of brain tumors, it is complicated to obtain control samples, leading to model overfitting due to unbalanced sample cohorts. Usually, classifiers are trained using a single measurement regime, most notably single ion polarity, but mass range and spectral resolution could also be varied. It is known that lipid groups differ significantly in their ability to produce positive or negative ions; hence, using only one polarity significantly restricts the chemical space available for sample discrimination purposes. In this work, we have developed an approach employing mass spectrometry data obtained by eight different regimes of measurement simultaneously. Regime-specific classifiers are trained, then a mixture of experts techniques based on voting or mean probability is used to aggregate predictions of all trained classifiers and assign a class to the whole sample. The aggregated classifiers have shown a much better performance than any of the single-regime classifiers and help significantly reduce the effect of an unbalanced dataset without any augmentation.
The automatic processing of high-dimensional mass spectrometry data is required for the clinical implementation of ambient ionization molecular profiling methods. However, complex algorithms required for the analysis of peak-rich spectra are sensitive to the quality of the input data. Therefore, an objective and quantitative indicator, insensitive to the conditions of the experiment, is currently in high demand for the automated treatment of mass spectrometric data. In this work, we demonstrate the utility of the Shapley value as an indicator of the quality of the individual mass spectrum in the classification task for human brain tumor tissue discrimination. The Shapley values are calculated on the training set of glioblastoma and nontumor pathological tissues spectra and used as feedback to create a random forest regression model to estimate the contributions for all spectra of each specimen. As a result, it is shown that the implementation of Shapley values significantly accelerates the data analysis of negative mode mass spectrometry data alongside simultaneous improving the regression models’ accuracy.
About Me
PhD student at Moscow Institute of Physics and Technology
PhD student at Moscow Institute of Physics and Technology