Dataset Information

Whole slide images reflect DNA methylation patterns of human tumors.

ABSTRACT: DNA methylation is an important epigenetic mechanism regulating gene expression and its role in carcinogenesis has been extensively studied. High-throughput DNA methylation assays have been used broadly in cancer research. Histopathology images are commonly obtained in cancer treatment, given that tissue sampling remains the clinical gold-standard for diagnosis. In this work, we investigate the interaction between cancer histopathology images and DNA methylation profiles to provide a better understanding of tumor pathobiology at the epigenetic level. We demonstrate that classical machine learning algorithms can associate the DNA methylation profiles of cancer samples with morphometric features extracted from whole slide images. Furthermore, grouping the genes into methylation clusters greatly improves the performance of the models. The well-predicted genes are enriched in key pathways in carcinogenesis including hypoxia in glioma and angiogenesis in renal cell carcinoma. Our results provide new insights into the link between histopathological and molecular data.

SUBMITTER: Zheng H

PROVIDER: S-EPMC7064513 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Whole slide images reflect DNA methylation patterns of human tumors.

Zheng Hong H Momeni Alexandre A Cedoz Pierre-Louis PL Vogel Hannes H Gevaert Olivier O

NPJ genomic medicine 20200310

DNA methylation is an important epigenetic mechanism regulating gene expression and its role in carcinogenesis has been extensively studied. High-throughput DNA methylation assays have been used broadly in cancer research. Histopathology images are commonly obtained in cancer treatment, given that tissue sampling remains the clinical gold-standard for diagnosis. In this work, we investigate the interaction between cancer histopathology images and DNA methylation profiles to provide a better unde ...[more]

PMID: 32194984

Similar Datasets

Project description:ObjectiveObesity is driven by modifiable lifestyle factors whose effects may be mediated by epigenetics. Therefore, we investigated lifestyle effects on blood DNA methylation in participants of the LIFE-Adult study, a well-characterised population-based cohort from Germany.Research design and methodsLifestyle scores (LS) based on diet, physical activity, smoking and alcohol intake were calculated in 4107 participants of the LIFE-Adult study. Fifty subjects with an extremely healthy lifestyle and 50 with an extremely unhealthy lifestyle (5th and 95th percentiles LS) were selected for genome-wide DNA methylation analysis in blood samples employing Illumina Infinium® Methylation EPIC BeadChip system technology.ResultsDifferences in DNA methylation patterns between body mass index groups (<25 vs. >30 kg/m2 ) were rather marginal compared to inter-lifestyle differences (0 vs. 145 differentially methylated positions [DMPs]), which identified 4682 differentially methylated regions (DMRs; false discovery rate [FDR <5%) annotated to 4426 unique genes. A DMR annotated to the glutamine-fructose-6-phosphate transaminase 2 (GFPT2) locus showed the strongest hypomethylation (∼6.9%), and one annotated to glutamate rich 1 (ERICH1) showed the strongest hypermethylation (∼5.4%) in healthy compared to unhealthy lifestyle individuals. Intersection analysis showed that diet, physical activity, smoking and alcohol intake equally contributed to the observed differences, which affected, among others, pathways related to glutamatergic synapses (adj. p < .01) and axon guidance (adj. p < .05). We showed that methylation age correlates with chronological age and waist-to-hip ratio with lower DNA methylation age (DNAmAge) acceleration distances in participants with healthy lifestyles. Finally, two identified top DMPs for the alanyl aminopeptidase (ANPEP) locus also showed the strongest expression quantitative trait methylation in blood.ConclusionsDNA methylation patterns help discriminate individuals with a healthy versus unhealthy lifestyle, which may mask subtle methylation differences derived from obesity.

Project description:ObjectiveDigital pathology is today a widely used technology, and the digitalization of microscopic slides into whole slide images (WSIs) allows the use of machine learning algorithms as a tool in the diagnostic process. In recent years, "deep learning" algorithms for image analysis have been applied to digital pathology with great success. The training of these algorithms requires a large volume of high-quality images and image annotations. These large image collections are a potent source of information, and to use and share the information, standardization of the content through a consistent terminology is essential. The aim of this project was to develop a pilot dataset of exhaustive annotated WSI of normal and abnormal human tissue and link the annotations to appropriate ontological information.Materials and methodsSeveral biomedical ontologies and controlled vocabularies were investigated with the aim of selecting the most suitable ontology for this project. The selection criteria required an ontology that covered anatomical locations, histological subcompartments, histopathologic diagnoses, histopathologic terms, and generic terms such as normal, abnormal, and artifact. WSIs of normal and abnormal tissue from 50 colon resections and 69 skin excisions, diagnosed 2015-2016 at the Department of Clinical Pathology in Linköping, were randomly collected. These images were manually and exhaustively annotated at the level of major subcompartments, including normal or abnormal findings and artifacts.ResultsSystemized nomenclature of medicine clinical terms (SNOMED CT) was chosen, and the annotations were linked to its codes and terms. Two hundred WSI were collected and annotated, resulting in 17,497 annotations, covering a total area of 302.19 cm2, equivalent to 107,7 gigapixels. Ninety-five unique SNOMED CT codes were used. The time taken to annotate a WSI varied from 45 s to over 360 min, a total time of approximately 360 h.ConclusionThis work resulted in a dataset of 200 exhaustive annotated WSIs of normal and abnormal tissue from the colon and skin, and it has informed plans to build a comprehensive library of annotated WSIs. SNOMED CT was found to be the best ontology for annotation labeling. This project also demonstrates the need for future development of annotation tools in order to make the annotation process more efficient.

Dataset Information

Whole slide images reflect DNA methylation patterns of human tumors.

Publications

Whole slide images reflect DNA methylation patterns of human tumors.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets