Multimodal Lung Cancer Subtyping Using Deep Learning Neural Networks on Whole Slide Tissue Images and MALDI MSI.

Artificial intelligence (AI) has shown potential for facilitating the detection and classification of tumors. In patients with non-small cell lung cancer, distinguishing between the most common subtypes, adenocarcinoma (ADC) and squamous cell carcinoma (SqCC), is crucial for the development of an effective treatment plan. This task, however, may still present challenges in clinical routine. We propose a two-modality, AI-based classification algorithm to detect and subtype tumor areas, which combines information from matrix-assisted laser desorption/ionization (MALDI) mass spectrometry imaging (MSI) data and digital microscopy whole slide images (WSIs) of lung tissue sections. The method consists of first detecting areas with high tumor cell content by performing a segmentation of the hematoxylin and eosin-stained (H&E-stained) WSIs, and subsequently classifying the tumor areas based on the corresponding MALDI MSI data. We trained the algorithm on six tissue microarrays (TMAs) with tumor samples from N = 232 patients and used 14 additional whole sections for validation and model selection. Classification accuracy was evaluated on a test dataset with another 16 whole sections. The algorithm accurately detected and classified tumor areas, yielding a test accuracy of 94.7% on spectrum level, and correctly classified 15 of 16 test sections. When an additional quality control criterion was introduced, a 100% test accuracy was achieved on sections that passed the quality control (14 of 16). The presented method provides a step further towards the inclusion of AI and MALDI MSI data into clinical routine and has the potential to reduce the pathologist's work load. A careful analysis of the results revealed specific challenges to be considered when training neural networks on data from lung cancer tissue.

Robust subtyping of non-small cell lung cancer whole sections through MALDI mass spectrometry imaging.

Subtyping of the most common non-small cell lung cancer (NSCLC) tumor types adenocarcinoma (ADC) and squamous cell carcinoma (SqCC) is still a challenge in the clinical routine and a correct diagnosis is crucial for an adequate therapy selection. Matrix-assisted laser desorption/ionization (MALDI) mass spectrometry imaging (MSI) has shown potential for NSCLC subtyping but is subject to strong technical variability and has only been applied to tissue samples assembled in tissue microarrays (TMAs). To our knowledge, a successful transfer of a classifier from TMAs to whole sections, which are generated in the standard clinical routine, has not been presented in the literature as of yet. We introduce a classification algorithm using extensive preprocessing and a classifier (either a neural network or a linear discriminant analysis (LDA)) to robustly classify whole sections of ADC and SqCC lung tissue. The classifiers were trained on TMAs and validated and tested on whole sections. Vital for a successful application on whole sections is the extensive preprocessing and the use of whole sections for hyperparameter selection. The classification system with the neural network/LDA results in 99.0%/98.3% test accuracy on spectra level and 100.0%/100.0% test accuracy on whole section level, respectively, and, therefore, provides a powerful tool to support the pathologist's decision making process. The presented method is a step further towards a clinical application of MALDI MSI and artificial intelligence for subtyping of NSCLC tissue sections.

Deeply Supervised UNet for Semantic Segmentation to Assist Dermatopathological Assessment of Basal Cell Carcinoma.

Accurate and fast assessment of resection margins is an essential part of a dermatopathologist's clinical routine. In this work, we successfully develop a deep learning method to assist the dermatopathologists by marking critical regions that have a high probability of exhibiting pathological features in whole slide images (WSI). We focus on detecting basal cell carcinoma (BCC) through semantic segmentation using several models based on the UNet architecture. The study includes 650 WSI with 3443 tissue sections in total. Two clinical dermatopathologists annotated the data, marking tumor tissues' exact location on 100 WSI. The rest of the data, with ground-truth sectionwise labels, are used to further validate and test the models. We analyze two different encoders for the first part of the UNet network and two additional training strategies: (a) deep supervision, (b) linear combination of decoder outputs, and obtain some interpretations about what the network's decoder does in each case. The best model achieves over 96%, accuracy, sensitivity, and specificity on the Test set.

Cross-Normalization of MALDI Mass Spectrometry Imaging Data Improves Site-to-Site Reproducibility.

Matrix-assisted laser desorption/ionization mass spectrometry imaging (MALDI MSI) is an established tool for the investigation of formalin-fixed paraffin-embedded (FFPE) tissue samples and shows a high potential for applications in clinical research and histopathological tissue classification. However, the applicability of this method to serial clinical and pharmacological studies is often hampered by inevitable technical variation and limited reproducibility. We present a novel spectral cross-normalization algorithm that differs from the existing normalization methods in two aspects: (a) it is based on estimating the full statistical distribution of spectral intensities and (b) it involves applying a non-linear, mass-dependent intensity transformation to align this distribution with a reference distribution. This method is combined with a model-driven resampling step that is specifically designed for data from MALDI imaging of tryptic peptides. This method was performed on two sets of tissue samples: a single human teratoma sample and a collection of five tissue microarrays (TMAs) of breast and ovarian tumor tissue samples (N = 241 patients). The MALDI MSI data was acquired in two labs using multiple protocols, allowing us to investigate different inter-lab and cross-protocol scenarios, thus covering a wide range of technical variations. Our results suggest that the proposed cross-normalization significantly reduces such batch effects not only in inter-sample and inter-lab comparisons but also in cross-protocol scenarios. This demonstrates the feasibility of cross-normalization and joint data analysis even under conditions where preparation and acquisition protocols themselves are subject to variation.

Using the Chemical Noise Background in MALDI Mass Spectrometry Imaging for Mass Alignment and Calibration.

Matrix-assisted laser desorption/ionization mass spectrometry imaging (MALDI MSI) is an established tool for the investigation of formalin fixed paraffin embedded (FFPE) tissue samples and shows a high potential for applications in clinical research and histopathological diagnosis. The applicability and accuracy of this method, however, heavily depends on the quality of the acquired data, and in particular mass misalignment in axial time-of-flight (TOF) MSI continues to be a serious issue. We present a mass alignment and recalibration method that is specifically designed to operate on MALDI peptide imaging data. The proposed method exploits statistical properties of the characteristic chemical noise background observed in peptide imaging experiments. By comparing these properties to a theoretical peptide mass model, the effective mass shift of each spectrum is estimated and corrected. The method was evaluated on a cohort of 31 FFPE tissue samples, pursuing a statistical validation approach to estimate both the reduction of relative misalignment, as well as the increase in absolute mass accuracy. Our results suggest that a relative mass precision of approximately 5 ppm and an absolute accuracy of approximately 20 ppm are achievable using our method.

Neratinib protects pancreatic beta cells in diabetes.

The loss of functional insulin-producing ß-cells is a hallmark of diabetes. Mammalian sterile 20-like kinase 1 (MST1) is a key regulator of pancreatic ß-cell death and dysfunction; its deficiency restores functional ß-cells and normoglycemia. The identification of MST1 inhibitors represents a promising approach for a ß-cell-protective diabetes therapy. Here, we identify neratinib, an FDA-approved drug targeting HER2/EGFR dual kinases, as a potent MST1 inhibitor, which improves ß-cell survival under multiple diabetogenic conditions in human islets and INS-1E cells. In a pre-clinical study, neratinib attenuates hyperglycemia and improves ß-cell function, survival and ß-cell mass in type 1 (streptozotocin) and type 2 (obese Leprdb/db) diabetic mouse models. In summary, neratinib is a previously unrecognized inhibitor of MST1 and represents a potential ß-cell-protective drug with proof-of-concept in vitro in human islets and in vivo in rodent models of both type 1 and type 2 diabetes.

Targeted Feature Extraction in MALDI Mass Spectrometry Imaging to Discriminate Proteomic Profiles of Breast and Ovarian Cancer.

PURPOSE: To develop a mass spectrometry imaging (MSI) based workflow for extracting m/z values related to putative protein biomarkers and using these for reliable tumor classification. EXPERIMENTAL DESIGN: Given a list of putative breast and ovarian cancer biomarker proteins, a set of related m/z values are extracted from heterogeneous MSI datasets derived from formalin-fixed paraffin-embedded tissue material. Based on these features, a linear discriminant analysis classification model is trained to discriminate the two tumor types. RESULTS: It is shown that the discriminative power of classification models based on the extracted features is increased compared to the automatic training approach, especially when classifiers are applied to spectral data acquired under different conditions (instrument, preparation, laboratory). CONCLUSIONS AND CLINICAL RELEVANCE: Robust classification models not confounded by technical variation between MSI measurements are obtained. This supports the assumption that the classification of the respective tumor types is based on biological rather than technical differences, and that the selected features are related to the proteomic profiles of the tumor types under consideration.

3D MALDI mass spectrometry imaging reveals specific localization of long-chain acylcarnitines within a 10-day time window of spinal cord injury.

We report, for the first time, the detection and specific localization of long-chain acylcarnitines (LC ACs) along the lesion margins in an experimental model of spinal cord injury (SCI) using 3D mass spectrometry imaging (MSI). Acylcarnitines palmitoylcarnitine (AC(16:0)), palmitoleoylcarnitine (AC(16:1)), elaidic carnitine (AC(18:1)) and tetradecanoylcarnitine (AC(14:1)) were detected as early as 3 days post injury, and were present along the lesion margins 7 and 10 days after SCI induced by balloon compression technique in the rat. 3D MSI revealed the heterogeneous distribution of these lipids across the injured spinal cord, appearing well-defined at the lesion margins rostral to the lesion center, and becoming widespread and less confined to the margins at the region located caudally. The assigned acylcarnitines co-localize with resident microglia/macrophages detected along the lesion margins by immunofluorescence. Given the reported pro-inflammatory role of these acylcarnitines, their specific spatial localization along the lesion margin could hint at their potential pathophysiological roles in the progression of SCI.

Proteomic Analysis of the Spatio-temporal Based Molecular Kinetics of Acute Spinal Cord Injury Identifies a Time- and Segment-specific Window for Effective Tissue Repair.

Spinal cord injury (SCI) represents a major debilitating health issue with a direct socioeconomic burden on the public and private sectors worldwide. Although several studies have been conducted to identify the molecular progression of injury sequel due from the lesion site, still the exact underlying mechanisms and pathways of injury development have not been fully elucidated. In this work, based on OMICs, 3D matrix-assisted laser desorption ionization (MALDI) imaging, cytokines arrays, confocal imaging we established for the first time that molecular and cellular processes occurring after SCI are altered between the lesion proximity, i.e. rostral and caudal segments nearby the lesion (R1-C1) whereas segments distant from R1-C1, i.e. R2-C2 and R3-C3 levels coexpressed factors implicated in neurogenesis. Delay in T regulators recruitment between R1 and C1 favor discrepancies between the two segments. This is also reinforced by presence of neurites outgrowth inhibitors in C1, absent in R1. Moreover, the presence of immunoglobulins (IgGs) in neurons at the lesion site at 3 days, validated by mass spectrometry, may present additional factor that contributes to limited regeneration. Treatment in vivo with anti-CD20 one hour after SCI did not improve locomotor function and decrease IgG expression. These results open the door of a novel view of the SCI treatment by considering the C1 as the therapeutic target.

Benchmark datasets for 3D MALDI- and DESI-imaging mass spectrometry.

BACKGROUND: Three-dimensional (3D) imaging mass spectrometry (MS) is an analytical chemistry technique for the 3D molecular analysis of a tissue specimen, entire organ, or microbial colonies on an agar plate. 3D-imaging MS has unique advantages over existing 3D imaging techniques, offers novel perspectives for understanding the spatial organization of biological processes, and has growing potential to be introduced into routine use in both biology and medicine. Owing to the sheer quantity of data generated, the visualization, analysis, and interpretation of 3D imaging MS data remain a significant challenge. Bioinformatics research in this field is hampered by the lack of publicly available benchmark datasets needed to evaluate and compare algorithms. FINDINGS: High-quality 3D imaging MS datasets from different biological systems at several labs were acquired, supplied with overview images and scripts demonstrating how to read them, and deposited into MetaboLights, an open repository for metabolomics data. 3D imaging MS data were collected from five samples using two types of 3D imaging MS. 3D matrix-assisted laser desorption/ionization imaging (MALDI) MS data were collected from murine pancreas, murine kidney, human oral squamous cell carcinoma, and interacting microbial colonies cultured in Petri dishes. 3D desorption electrospray ionization (DESI) imaging MS data were collected from a human colorectal adenocarcinoma. CONCLUSIONS: With the aim to stimulate computational research in the field of computational 3D imaging MS, selected high-quality 3D imaging MS datasets are provided that could be used by algorithm developers as benchmark datasets.

Histomolecular interpretation of pleomorphic adenomas of the salivary gland by matrix-assisted laser desorption ionization imaging and spatial segmentation.

BACKGROUND: Despite efforts in localization of key proteins using immunohistochemistry, the complex proteomic composition of pleomorphic adenomas has not yet been characterized. Matrix-assisted laser desorption/ionization imaging mass spectrometry (MALDI imaging) allows label-free and spatially resolved detection of hundreds of proteins directly from tissue sections and of histomorphological regions by finding colocalized molecular signals. Spatial segmentation of MALDI imaging data is an algorithmic method for finding regions of similar proteomic composition as functionally similar regions. METHODS: We investigated 2 pleomorphic adenomas by applying spatial segmentation to the MALDI imaging data of tissue sections. RESULTS: The spatial segmentation subdivided the tissue in a good accordance with the tissue histology. Numerous molecular signals colocalized with histologically defined tissue regions were found. CONCLUSION: Our study highlights the cellular transdifferentiation within the pleomorphic adenoma. It could be shown that spatial segmentation of MALDI imaging data is a promising approach in the emerging field of digital histological analysis and characterization of tumors.

Comparative genome analysis of Burkholderia phytofirmans PsJN reveals a wide spectrum of endophytic lifestyles based on interaction strategies with host plants.

Burkholderia phytofirmans PsJN is a naturally occurring plant-associated bacterial endophyte that effectively colonizes a wide range of plants and stimulates their growth and vitality. Here we analyze whole genomes, of PsJN and of eight other endophytic bacteria. This study illustrates that a wide spectrum of endophytic life styles exists. Although we postulate the existence of typical endophytic traits, no unique gene cluster could be exclusively linked to the endophytic lifestyle. Furthermore, our study revealed a high genetic diversity among bacterial endophytes as reflected in their genotypic and phenotypic features. B. phytofirmans PsJN is in many aspects outstanding among the selected endophytes. It has the biggest genome consisting of two chromosomes and one plasmid, well-equipped with genes for the degradation of complex organic compounds and detoxification, e.g., 24 glutathione-S-transferase (GST) genes. Furthermore, strain PsJN has a high number of cell surface signaling and secretion systems and harbors the 3-OH-PAME quorum-sensing system that coordinates the switch of free-living to the symbiotic lifestyle in the plant-pathogen R. solanacearum. The ability of B. phytofirmans PsJN to successfully colonize such a wide variety of plant species might be based on its large genome harboring a broad range of physiological functions.

Environmental factors affecting the expression of pilAB as well as the proteome and transcriptome of the grass endophyte Azoarcus sp. strain BH72.

BACKGROUND: Bacterial communication is involved in regulation of cellular mechanisms such as metabolic processes, microbe-host interactions or biofilm formation. In the nitrogen-fixing model endophyte of grasses Azoarcus sp. strain BH72, known cell-cell signaling systems have not been identified; however, the pilA gene encoding the structural protein of type IV pili that are essential for plant colonization appears to be regulated in a population density-dependent manner. METHODOLOGY/PRINCIPAL FINDINGS: Our data suggest that pilAB expression is affected by population density, independent of autoinducers typical for gram-negative bacteria, likely depending on unknown secreted molecule(s) that can be produced by different bacterial species. We used transcriptomic and proteomic approaches to identify target genes and proteins differentially regulated in conditioned supernatants in comparison to standard growth conditions. Around 8% of the 3992 protein-coding genes of Azoarcus sp. and 18% of the detected proteins were differentially regulated. Regulatory proteins and transcription factors among the regulated proteins indicated a complex hierarchy. Differentially regulated genes and proteins were involved in processes such as type IV pili formation and regulation, metal and nutrient transport, energy metabolism, and unknown functions mediated by hypothetical proteins. Four of the newly discovered target genes were further analyzed and in general they showed regulation patterns similar to pilAB. The expression of one of them was shown to be induced in plant roots. CONCLUSION/SIGNIFICANCE: This study is the first global approach to initiate characterization of cell density-dependent gene regulation mediated by soluble molecule(s) in the model endophyte Azoarcus sp. strain BH72. Our data suggest that the putative signaling molecule(s) are also produced by other Proteobacteria and might thus be used for interspecies communication. This study provides the foundation for the development of robust reporter systems for Azoarcus sp. to analyze mechanisms and molecules involved in the population-dependent gene expression in this endophyte in future.