Browse
Submit Data
Databases
API
Help

Dataset Information

28 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Cancer Tissue Classification Using Supervised Machine Learning Applied to MALDI Mass Spectrometry Imaging.

ABSTRACT: Matrix assisted laser desorption/ionization mass spectrometry imaging (MALDI MSI) can determine the spatial distribution of analytes such as protein distributions in a tissue section according to their mass-to-charge ratio. Here, we explored the clinical potential of machine learning (ML) applied to MALDI MSI data for cancer diagnostic classification using tissue microarrays (TMAs) on 302 colorectal (CRC) and 257 endometrial cancer (EC)) patients. ML based on deep neural networks discriminated colorectal tumour from normal tissue with an overall accuracy of 98% in balanced cross-validation (98.2% sensitivity and 98.6% specificity). Moreover, our machine learning approach predicted the presence of lymph node metastasis (LNM) for primary tumours of EC with an accuracy of 80% (90% sensitivity and 69% specificity). Our results demonstrate the capability of MALDI MSI for complementing classic histopathological examination for cancer diagnostic applications.

SUBMITTER: Mittal P

PROVIDER: S-EPMC8582378 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Cancer tissue classification using supervised machine learning applied to MALDI mass spectrometry imaging

Project description:With the current clinical available technologies, not all cancers are staged accurately. Because of this a large percentage of patients are misclassified before treatment, leading to under or over treatment. Therefore, a classification system based on the molecular feature is required to deter-mine the tumour behavior and metastatic potential. Here, we have shown the diagnostic potential of MALDI MSI using supervised machine learning approach in distinguishing cancerous colorectal tissue from normal with an overall accuracy of 98%. Also, shown is the capability of the technique in predicting the presence of metastasis in endometrial cancer with an overall accuracy of 80%. The development of such a model can help in determining the optimum treatment for cancerous pa-tients, reduce morbidity and better patient outcome.

2022-02-17 | PXD025594 | Pride

Stretched tissue mounting for MALDI mass spectrometry imaging.

Project description:Matrix-assisted laser desorption/ionization (MALDI) mass spectrometry imaging (MSI) combines information-rich chemical detection with spatial localization of analytes. For a given instrumental platform and analyte class, the data acquired can represent a compromise between analyte extraction and spatial information. Here, we introduce an improvement to the spatial resolution achievable with MALDI MSI conducted with standard mass spectrometric systems that also reduces analyte migration during matrix application. Tissue is placed directly on a stretchable membrane that, when stretched, fragments the tissue into micrometer-sized pieces. Scanning electron microscopy analysis shows that this process produces fairly homogeneous distributions of small tissue fragments separated and surrounded by areas of hydrophobic membrane surface. MALDI matrix is then applied by either a robotic microspotter or an artist's airbrush. Rat spinal cord samples imaged with an instrumental resolution of 50-250 ?m demonstrate lipid distributions with a 5-fold high spatial resolution (a 25-fold increase in pixel density) after stretching compared to tissues that were not stretched.

| S-EPMC3229305 | biostudies-literature

Supervised machine learning in the mass spectrometry laboratory: A tutorial.

Project description:As the demand for laboratory testing by mass spectrometry increases, so does the need for automated methods for data analysis. Clinical mass spectrometry (MS) data is particularly well-suited for machine learning (ML) methods, which deal nicely with structured and discrete data elements. The alignment of these two fields offers a promising synergy that can be used to optimize workflows, improve result quality, and enhance our understanding of high-dimensional datasets and their inherent relationship with disease. In recent years, there has been an increasing number of publications that examine the capabilities of ML-based software in the context of chromatography and MS. However, given the historically distant nature between the fields of clinical chemistry and computer science, there is an opportunity to improve technological literacy of ML-based software within the clinical laboratory scientist community. To this end, we present a basic overview of ML and a tutorial of an ML-based experiment using a previously published MS dataset. The purpose of this paper is to describe the fundamental principles of supervised ML, outline the steps that are classically involved in an ML-based experiment, and discuss the purpose of good ML practice in the context of a binary MS classification problem.

| S-EPMC8692990 | biostudies-literature

Morphometric Cell Classification for Single-Cell MALDI-Mass Spectrometry Imaging.

Project description:The large-scale and label-free molecular characterization of single cells in their natural tissue habitat remains a major challenge in molecular biology. We present a method that integrates morphometric image analysis to delineate and classify individual cells with their single-cell-specific molecular profiles. This approach provides a new means to study spatial biological processes such as cancer field effects and the relationship between morphometric and molecular features.

| S-EPMC7540554 | biostudies-literature

High resolution MALDI imaging mass spectrometry of retinal tissue lipids.

Project description:Matrix assisted laser desorption ionization imaging mass spectrometry (MALDI IMS) has the ability to provide an enormous amount of information on the abundances and spatial distributions of molecules within biological tissues. The rapid progress in the development of this technology significantly improves our ability to analyze smaller and smaller areas and features within tissues. The mammalian eye has evolved over millions of years to become an essential asset for survival, providing important sensory input of an organism's surroundings. The highly complex sensory retina of the eye is comprised of numerous cell types organized into specific layers with varying dimensions, the thinnest of which is the 10 ?m retinal pigment epithelium (RPE). This single cell layer and the photoreceptor layer contain the complex biochemical machinery required to convert photons of light into electrical signals that are transported to the brain by axons of retinal ganglion cells. Diseases of the retina, including age-related macular degeneration (AMD), retinitis pigmentosa, and diabetic retinopathy, occur when the functions of these cells are interrupted by molecular processes that are not fully understood. In this report, we demonstrate the use of high spatial resolution MALDI IMS and FT-ICR tandem mass spectrometry in the Abca4(-/-) knockout mouse model of Stargardt disease, a juvenile onset form of macular degeneration. The spatial distributions and identity of lipid and retinoid metabolites are shown to be unique to specific retinal cell layers.

| S-EPMC4180438 | biostudies-literature

Extracellular Matrix Imaging of Breast Tissue Pathologies by MALDI-Imaging Mass Spectrometry.

Project description:PURPOSE:A new method accessing proteins from extracellular matrix by imaging mass spectrometry (ECM IMS) has been recently reported. ECM IMS is evaluated for use in exploring breast tissue pathologies. EXPERIMENTAL DESIGN:A tissue microarray (TMA) is analyzed that has 176 cores of biopsies and lumpectomies spanning breast pathologies of inflammation, hyperplasia, fibroadenoma, invasive ductal carcinoma, and invasive lobular carcinoma and normal adjacent to tumor (NAT). NAT is compared to subtypes by area under the receiver operating curve (ROC) >0.7. A lumpectomy is also characterized for collagen organization by microscopy and stromal protein distribution by IMS. LC-based high-resolution accurate mass (HRAM) proteomics is used to identify proteins from the lumpectomy. RESULTS:TMA analysis shows distinct spectral signatures reflecting a heterogeneous tissue microenvironment. Ninety-four peaks show an ROC > 0.7 compared to NAT; NAT has overall higher intensities. Lumpectomy analysis by IMS visualizes a complex central tumor region with distal tumor regions. A total of 39 stromal proteins are identified by HRAM LC-based proteomics. Accurate mass matches between image data and LC-based proteomics demonstrate a heterogeneous collagen type environment in the central tumor. CONCLUSIONS:Data portray the heterogeneous stromal microenvironment of breast pathologies, including alteration of multiple collagen-type patterns. ECM IMS is a promising new tool for investigating the stromal microenvironment of breast tissue including cancer.

| S-EPMC6730639 | biostudies-literature

Cancer tissue classification using machine learning applied to MALDI MSI and high resolution H&E stained images

Project description:Aim is to identify a panel of m/z markers for the early detection of colorectal cancer (CRC). Identification of a molecular pattern that can distinguish the primary tumours of colorectal cancer with lymph node metastasis compared to those without. Materials and Methods: Using MALDI MSI data, we developed and validated a machine learning model that can be used for early screening of CRC. Our model yields high sensitivity and specificity in distinguishing normal tissue from the cancerous. Model described here, can be a used in clinical labs for early diagnosis of colorectal cancer

2022-02-15 | PXD019662 | Pride

Cancer tissue classification using machine learning applied to MALDI MSI and high resolution H&E stained images

Project description:Aim is to identify a panel of m/z markers for the early detection of colorectal cancer (CRC). Identification of a molecular pattern that can distin- guish the primary tumours of colorectal cancer with lymph node metastasis compared to those without. Materials and Methods: Using MALDI MSI data, we developed and validated a machine learning model that can be used for early screening of CRC. Results: Our model yields high sensitivity and speci- ficity in distinguishing normal tissue from the cancerous. Model described here, can be a used in clinical labs for early diagnosis of colorectal cancer

2022-02-15 | PXD019666 | Pride

Self-supervised clustering of mass spectrometry imaging data using contrastive learning.

Project description:Mass spectrometry imaging (MSI) is widely used for the label-free molecular mapping of biological samples. The identification of co-localized molecules in MSI data is crucial to the understanding of biochemical pathways. One of key challenges in molecular colocalization is that complex MSI data are too large for manual annotation but too small for training deep neural networks. Herein, we introduce a self-supervised clustering approach based on contrastive learning, which shows an excellent performance in clustering of MSI data. We train a deep convolutional neural network (CNN) using MSI data from a single experiment without manual annotations to effectively learn high-level spatial features from ion images and classify them based on molecular colocalizations. We demonstrate that contrastive learning generates ion image representations that form well-resolved clusters. Subsequent self-labeling is used to fine-tune both the CNN encoder and linear classifier based on confidently classified ion images. This new approach enables autonomous and high-throughput identification of co-localized species in MSI data, which will dramatically expand the application of spatial lipidomics, metabolomics, and proteomics in biological research.

| S-EPMC8694357 | biostudies-literature

Single-Cell Classification Using Mass Spectrometry through Interpretable Machine Learning.

Project description:The brain consists of organized ensembles of cells that exhibit distinct morphologies, cellular connectivity, and dynamic biochemistries that control the executive functions of an organism. However, the relationships between chemical heterogeneity, cell function, and phenotype are not always understood. Recent advancements in matrix-assisted laser desorption/ionization mass spectrometry have enabled the high-throughput, multiplexed chemical analysis of single cells, capable of resolving hundreds of molecules in each mass spectrum. We developed a machine learning workflow to classify single cells according to their mass spectra based on cell groups of interest (GOI), e.g., neurons vs astrocytes. Three data sets from various cell groups were acquired on three different mass spectrometer platforms representing thousands of individual cell spectra that were collected and used to validate the single cell classification workflow. The trained models achieved >80% classification accuracy and were subjected to the recently developed instance-based model interpretation framework, SHapley Additive exPlanations (SHAP), which locally assigns feature importance for each single-cell spectrum. SHAP values were used for both local and global interpretations of our data sets, preserving the chemical heterogeneity uncovered by the single-cell analysis while offering the ability to perform supervised analysis. The top contributing mass features to each of the GOI were ranked and selected using mean absolute SHAP values, highlighting the features that are specific to the defined GOI. Our approach provides insight into discriminating the chemical profiles of the single cells through interpretable machine learning, facilitating downstream analysis and validation.

| S-EPMC7374983 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data