Characterization of Hormone Receptor and HER2 Status in Breast Cancer Using Mass Spectrometry Imaging.

Immunohistochemical evaluation of estrogen receptor, progesterone receptor, and human epidermal growth factor receptor-2 status stratify the different subtypes of breast cancer and define the treatment course. Triple-negative breast cancer (TNBC), which does not register receptor overexpression, is often associated with worse patient prognosis. Mass spectrometry imaging transcribes the molecular content of tissue specimens without requiring additional tags or preliminary analysis of the samples, being therefore an excellent methodology for an unbiased determination of tissue constituents, in particular tumor markers. In this study, the proteomic content of 1191 human breast cancer samples was characterized by mass spectrometry imaging and the epithelial regions were employed to train and test machine-learning models to characterize the individual receptor status and to classify TNBC. The classification models presented yielded high accuracies for estrogen and progesterone receptors and over 95% accuracy for classification of TNBC. Analysis of the molecular features revealed that vimentin overexpression is associated with TNBC, supported by immunohistochemistry validation, revealing a new potential target for diagnosis and treatment.

MALDI-MSI: A Powerful Approach to Understand Primary Pancreatic Ductal Adenocarcinoma and Metastases.

Cancer-related deaths are very commonly attributed to complications from metastases to neighboring as well as distant organs. Dissociate response in the treatment of pancreatic adenocarcinoma is one of the main causes of low treatment success and low survival rates. This behavior could not be explained by transcriptomics or genomics; however, differences in the composition at the protein level could be observed. We have characterized the proteomic composition of primary pancreatic adenocarcinoma and distant metastasis directly in human tissue samples, utilizing mass spectrometry imaging. The mass spectrometry data was used to train and validate machine learning models that could distinguish both tissue entities with an accuracy above 90%. Model validation on samples from another collection yielded a correct classification of both entities. Tentative identification of the discriminative molecular features showed that collagen fragments (COL1A1, COL1A2, and COL3A1) play a fundamental role in tumor development. From the analysis of the receiver operating characteristic, we could further advance some potential targets, such as histone and histone variations, that could provide a better understanding of tumor development, and consequently, more effective treatments.

Multicenter Evaluation of Tissue Classification by Matrix-Assisted Laser Desorption/Ionization Mass Spectrometry Imaging.

Many studies have demonstrated that tissue phenotyping (tissue typing) based on mass spectrometric imaging data is possible; however, comprehensive studies assessing variation and classifier transferability are largely lacking. This study evaluated the generalization of tissue classification based on Matrix Assisted Laser Desorption/Ionization (MALDI) mass spectrometric imaging (MSI) across measurements performed at different sites. Sections of a tissue microarray (TMA) consisting of different formalin-fixed and paraffin-embedded (FFPE) human tissue samples from different tumor entities (leiomyoma, seminoma, mantle cell lymphoma, melanoma, breast cancer, and squamous cell carcinoma of the lung) were prepared and measured by MALDI-MSI at different sites using a standard protocol (SOP). Technical variation was deliberately introduced on two separate measurements via a different sample preparation protocol and a MALDI Time of Flight mass spectrometer that was not tuned to optimal performance. Using standard data preprocessing, a classification accuracy of 91.4% per pixel was achieved for intrasite classifications. When applying a leave-one-site-out cross-validation strategy, accuracy per pixel over sites was 78.6% for the SOP-compliant data sets and as low as 36.1% for the mistuned instrument data set. Data preprocessing designed to remove technical variation while retaining biological information substantially increased classification accuracy for all data sets with SOP-compliant data sets improved to 94.3%. In particular, classification accuracy of the mistuned instrument data set improved to 81.3% and from 67.0% to 87.8% per pixel for the non-SOP-compliant data set. We demonstrate that MALDI-MSI-based tissue classification is possible across sites when applying histological annotation and an optimized data preprocessing pipeline to improve generalization of classifications over technical variation and increasing overall robustness.

The Impact of Histological Annotations for Accurate Tissue Classification Using Mass Spectrometry Imaging.

Knowing the precise location of analytes in the tissue has the potential to provide information about the organs' function and predict its behavior. It is especially powerful when used in diagnosis and prognosis prediction of pathologies, such as cancer. Spatial proteomics, in particular mass spectrometry imaging, together with machine learning approaches, has been proven to be a very helpful tool in answering some histopathology conundrums. To gain accurate information about the tissue, there is a need to build robust classification models. We have investigated the impact of histological annotation on the classification accuracy of different tumor tissues. Intrinsic tissue heterogeneity directly impacts the efficacy of the annotations, having a more pronounced effect on more heterogeneous tissues, as pancreatic ductal adenocarcinoma, where the impact is over 20% in accuracy. On the other hand, in more homogeneous samples, such as kidney tumors, histological annotations have a slenderer impact on the classification accuracy.