Development of a Machine Learning Classifier for Brain Tumors Diagnosis Based on DNA Methylation Profile

Background: More than 150 types of brain tumors have been documented. Accurate diagnosis is important for making appropriate therapeutic decisions in treating the diseases. The goal of this study is to develop a DNA methylation profile-based classifier to accurately identify various kinds of brain tumors.Methods: Thirteen datasets of DNA methylation profiles were downloaded from the Gene Expression Omnibus (GEO) database, of which GSE90496 and GSE109379 were used as the training set and the validation set, respectively, and the remaining 11 sets were used as the independent test set. The random forest algorithm was used to select the CpG sites based on the importance of the features and a multilayer perceptron (MLP) model was trained to classify the samples. Deconvolution with the debCAM package was used to explore the cellular composition difference among tumors.Results: From training datasets with 2,801 samples, 396,568 CpG sites were retained after preprocessing, of which 767 were selected as the modeling features. A three-layer MLP model was developed, which consists of 1,320 nodes in the hidden layer, to predict the histological types of brain tumors. The prediction accuracy is 99.2, 87.0, and 96.58%, respectively, on the training, validation and test sets. The results of deconvolution analysis showed that the cell proportions of different tumor subtypes were different, and it is approximately enough to distinguish different tumor entities.Conclusion: We developed a classifier that is robust for the classification of central nervous system tumors, and tried to analyze the reasons for the classification performance.

Download Full-text

Genome-wide DNA methylation profile of early-onset endometrial cancer: its correlation with genetic aberrations and comparison with late-onset endometrial cancer

Carcinogenesis ◽

10.1093/carcin/bgz046 ◽

2019 ◽

Vol 40 (5) ◽

pp. 611-623 ◽

Cited By ~ 7

Author(s):

Takeshi Makabe ◽

Eri Arai ◽

Takuro Hirano ◽

Nanako Ito ◽

Yukihiro Fukamachi ◽

...

Keyword(s):

Dna Methylation ◽

Endometrial Cancer ◽

Early Onset ◽

Late Onset ◽

Methylation Profile ◽

Cancer Tissue ◽

Cpg Sites ◽

Genome Wide ◽

Dna Methylation Profile ◽

Endometrioid Endometrial Cancer

Abstract The present study was performed to clarify the significance of DNA methylation alterations during endometrial carcinogenesis. Genome-wide DNA methylation analysis and targeted sequencing of tumor-related genes were performed using the Infinium MethylationEPIC BeadChip and the Ion AmpliSeq Cancer Hotspot Panel v2, respectively, for 31 samples of normal control endometrial tissue from patients without endometrial cancer and 81 samples of endometrial cancer tissue. Principal component analysis revealed that tumor samples had a DNA methylation profile distinct from that of control samples. Gene Ontology enrichment analysis revealed significant differences of DNA methylation at 1034 CpG sites between early-onset endometrioid endometrial cancer (EE) tissue (patients aged ≤40 years) and late-onset endometrioid endometrial cancer (LE) tissue, which were accumulated among ‘transcriptional factors’. Mutations of the CTNNB1 gene or DNA methylation alterations of genes participating in Wnt signaling were frequent in EEs, whereas genetic and epigenetic alterations of fibroblast growth factor signaling genes were observed in LEs. Unsupervised hierarchical clustering grouped EE samples in Cluster EA (n = 22) and samples in Cluster EB (n = 12). Clinicopathologically less aggressive tumors tended to be accumulated in Cluster EB, and DNA methylation levels of 18 genes including HOXA9, HOXD10 and SOX11 were associated with differences in such aggressiveness between the two clusters. We identified 11 marker CpG sites that discriminated EB samples from EA samples with 100% sensitivity and specificity. These data indicate that genetically and epigenetically different pathways may participate in the development of EEs and LEs, and that DNA methylation profiling may help predict tumors that are less aggressive and amenable to fertility preservation treatment.

Download Full-text

Systematic underestimation of the epigenetic clock and age acceleration in older subjects

Genome Biology ◽

10.1186/s13059-019-1810-4 ◽

2019 ◽

Vol 20 (1) ◽

Cited By ~ 11

Author(s):

Louis Y. El Khoury ◽

Tyler Gorrie-Stone ◽

Melissa Smart ◽

Amanda Hughes ◽

Yanchun Bao ◽

...

Keyword(s):

Dna Methylation ◽

Older People ◽

Methylation Profile ◽

Epigenetic Clock ◽

Association Tests ◽

Cpg Sites ◽

Multiple Datasets ◽

Dna Methylation Profile ◽

Age Dependent ◽

Older Subjects

Abstract Background The Horvath epigenetic clock is widely used. It predicts age quite well from 353 CpG sites in the DNA methylation profile in unknown samples and has been used to calculate “age acceleration” in various tissues and environments. Results The model systematically underestimates age in tissues from older people. This is seen in all examined tissues but most strongly in the cerebellum and is consistently observed in multiple datasets. Age acceleration is thus age-dependent, and this can lead to spurious associations. The current literature includes examples of association tests with age acceleration calculated in a wide variety of ways. Conclusions The concept of an epigenetic clock is compelling, but caution should be taken in interpreting associations with age acceleration. Association tests of age acceleration should include age as a covariate.

Download Full-text

Integrated analysis of DNA methylation profile in HLA-G gene and imaging in coronary heart disease

European Heart Journal ◽

10.1093/ehjci/ehaa946.1255 ◽

2020 ◽

Vol 41 (Supplement_2) ◽

Author(s):

G Benincasa ◽

C Schiano ◽

T Infante ◽

M Franzese ◽

R Casale ◽

...

Keyword(s):

Dna Methylation ◽

Coronary Heart Disease ◽

Heart Disease ◽

Cpg Island ◽

Methylation Profile ◽

Integrated Analysis ◽

Funding Source ◽

Relevant Parameter ◽

Cardiac Computed Tomography Angiography ◽

Dna Methylation Profile

Abstract Aims Immune endothelial inflammation, underlie coronary heart disease (CHD) related phenotypes, could provide new insight into the pathobiology of the disease. We investigated DNA methylation level of the unique CpG island of HLA-G gene in CHD patients and evaluated the correlation with cardiac computed tomography angiography (CCTA) features. Methods Thirty-two patients that underwent CCTA for suspected CHD were enrolled for this study. Obstructive CHD group included fourteen patients, in which there was a stenosis greater than or equal to 50% in one or more of the major coronary arteries detected; whereas subjects with Calcium (Ca) Score=0, uninjured coronaries and with no obstructive CHD were considered as control subjects (Ctrls) (n=18). For both groups, DNA methylation profile of the whole 5'UTR-CpG island of HLA-G was measured. The plasma soluble HLA-G (sHLA-G) levels were detected in all subjects by specific ELISA assay. Statistical analysis was performed using R software. Results For the first time, our study reported that 1) a significant hypomethylation characterized three specific fragments (B, C and F) of the 5'UTR-CpG island (p=0.05) of HLA-G gene in CHD patients compared to Ctrl group; 2) hypomethylation level of one specific fragment positively correlated with coronary Ca score, a relevant parameter of CCTA (p<0.05) between two groups. Conclusions Our results showed that reduced levels of circulating HLA-G molecules could derive from epigenetic marks inducing hypomethylation of specific regions into 5'UTR-CpG island of HLA-G gene in CHD patients with obstructive coronary stenosis vs non critical stenosis group. Funding Acknowledgement Type of funding source: Public grant(s) – National budget only. Main funding source(s): Italian Minister of Health

Download Full-text

DNA methylation patterns identify subgroups of pancreatic neuroendocrine tumors with clinical association

Communications Biology ◽

10.1038/s42003-020-01469-0 ◽

2021 ◽

Vol 4 (1) ◽

Author(s):

Vanessa Lakis ◽

◽

Rita T. Lawlor ◽

Felicity Newell ◽

Ann-Marie Patch ◽

...

Keyword(s):

Dna Methylation ◽

Neuroendocrine Tumors ◽

Methylation Profile ◽

Pancreatic Neuroendocrine Tumors ◽

Wild Type ◽

Genomic Information ◽

Chromosome 11 ◽

Dna Methylation Profile ◽

Methylation Patterns ◽

Recurrent Patterns

AbstractHere we report the DNA methylation profile of 84 sporadic pancreatic neuroendocrine tumors (PanNETs) with associated clinical and genomic information. We identified three subgroups of PanNETs, termed T1, T2 and T3, with distinct patterns of methylation. The T1 subgroup was enriched for functional tumors and ATRX, DAXX and MEN1 wild-type genotypes. The T2 subgroup contained tumors with mutations in ATRX, DAXX and MEN1 and recurrent patterns of chromosomal losses in half of the genome with no association between regions with recurrent loss and methylation levels. T2 tumors were larger and had lower methylation in the MGMT gene body, which showed positive correlation with gene expression. The T3 subgroup harboured mutations in MEN1 with recurrent loss of chromosome 11, was enriched for grade G1 tumors and showed histological parameters associated with better prognosis. Our results suggest a role for methylation in both driving tumorigenesis and potentially stratifying prognosis in PanNETs.

Download Full-text

DNA methylation profile of genes involved in inflammation and autoimmunity correlates with vascular function in morbidly obese adults

Epigenetics ◽

10.1080/15592294.2021.1876285 ◽

2021 ◽

pp. 1-17

Author(s):

Mohamed M. Ali ◽

Dina Naquiallah ◽

Maryam Qureshi ◽

Mohammed Imaduddin Mirza ◽

Chandra Hassan ◽

...

Keyword(s):

Dna Methylation ◽

Vascular Function ◽

Methylation Profile ◽

Morbidly Obese ◽

Obese Adults ◽

Dna Methylation Profile

Download Full-text

Overlapping DNA methylation profile between placentas with trisomy 16 and early-onset preeclampsia

Placenta ◽

10.1016/j.placenta.2014.01.001 ◽

2014 ◽

Vol 35 (3) ◽

pp. 216-222 ◽

Cited By ~ 16

Author(s):

J.D. Blair ◽

S. Langlois ◽

D.E. McFadden ◽

W.P. Robinson

Keyword(s):

Dna Methylation ◽

Early Onset ◽

Methylation Profile ◽

Trisomy 16 ◽

Dna Methylation Profile ◽

Early Onset Preeclampsia

Download Full-text

Active BRAF-V600E is the key player in generation of a sessile serrated polyp-specific DNA methylation profile

PLoS ONE ◽

10.1371/journal.pone.0192499 ◽

2018 ◽

Vol 13 (3) ◽

pp. e0192499 ◽

Cited By ~ 4

Author(s):

Somaye Dehghanizadeh ◽

Vahid Khoddami ◽

Timothy L. Mosbruger ◽

Sue S. Hammoud ◽

Kornelia Edes ◽

...

Keyword(s):

Dna Methylation ◽

Methylation Profile ◽

Braf V600e ◽

Serrated Polyp ◽

Dna Methylation Profile

Download Full-text

Methylome and transcriptome analyses of soybean response to bean pyralid larvae

BMC Genomics ◽

10.1186/s12864-021-08140-w ◽

2021 ◽

Vol 22 (1) ◽

Author(s):

Wei-Ying Zeng ◽

Yu-Rong Tan ◽

Sheng-Feng Long ◽

Zu-Dong Sun ◽

Zhen-Guang Lai ◽

...

Keyword(s):

Dna Methylation ◽

Protein Biosynthesis ◽

Cell Structure ◽

Methylation Profile ◽

Primary Metabolism ◽

Global Methylation ◽

Genome Wide ◽

Differentially Methylated Genes ◽

Dna Methylation Profile ◽

Soybean Resistance

Abstract Background Bean pyralid is one of the major leaf-feeding insects that affect soybean crops. DNA methylation can control the networks of gene expressions, and it plays an important role in responses to biotic stress. However, at present the genome-wide DNA methylation profile of the soybean resistance to bean pyralid has not been reported so far. Results Using whole-genome bisulfite sequencing (WGBS) and RNA-sequencing (RNA-seq), we analyzed the highly resistant material (Gantai-2-2, HRK) and highly susceptible material (Wan82–178, HSK), under bean pyralid larvae feeding 0 h and 48 h, to clarify the molecular mechanism of the soybean resistance and explore its insect-resistant genes. We identified 2194, 6872, 39,704 and 40,018 differentially methylated regions (DMRs), as well as 497, 1594, 9596 and 9554 differentially methylated genes (DMGs) in the HRK0/HRK48, HSK0/HSK48, HSK0/HRK0 and HSK48/HRK48 comparisons, respectively. Through the analysis of global methylation and transcription, 265 differentially expressed genes (DEGs) were negatively correlated with DMGs, there were 34, 49, 141 and 116 negatively correlated genes in the HRK0/HRK48, HSK0/HSK48, HSK0/HRK0 and HSK48/HRK48, respectively. The MapMan cluster analysis showed that 114 negatively correlated genes were clustered in 24 pathways, such as protein biosynthesis and modification; primary metabolism; secondary metabolism; cell cycle, cell structure and component; RNA biosynthesis and processing, and so on. Moreover, CRK40; CRK62; STK; MAPK9; L-type lectin-domain containing receptor kinase VIII.2; CesA; CSI1; fimbrin-1; KIN-14B; KIN-14 N; KIN-4A; cytochrome P450 81E8; BEE1; ERF; bHLH25; bHLH79; GATA26, were likely regulatory genes involved in the soybean responses to bean pyralid larvae. Finally, 5 DMRs were further validated that the genome-wide DNA data were reliable through PS-PCR and 5 DEGs were confirmed the relationship between DNA methylation and gene expression by qRT-PCR. The results showed an excellent agreement with deep sequencing. Conclusions Genome-wide DNA methylation profile of soybean response to bean pyralid was obtained for the first time. Several specific DMGs which participated in protein kinase, cell and organelle, flavonoid biosynthesis and transcription factor were further identified to be likely associated with soybean response to bean pyralid. Our data will provide better understanding of DNA methylation alteration and their potential role in soybean insect resistance.

Download Full-text

Chicken cecal DNA methylome alteration in the response to Salmonella enterica serovar Enteritidis inoculation

10.21203/rs.3.rs-20344/v2 ◽

2020 ◽

Author(s):

Yuanmei Wang ◽

Liying Liu ◽

Min Li ◽

Lili Lin ◽

Pengcheng Su ◽

...

Keyword(s):

Dna Methylation ◽

Signaling Pathway ◽

Salmonella Enterica ◽

Methylation Profile ◽

Control Group ◽

Poultry Production ◽

Salmonella Enterica Serovar Enteritidis ◽

Genome Wide ◽

Differentially Methylated Genes ◽

Dna Methylation Profile

Abstract Background: Salmonella enterica serovar Enteritidis (SE) is one of the pathogenic bacteria, which affects poultry production and poses a severe threat to public health. Chicken meat and eggs are the main sources of human salmonellosis. DNA methylation is involved in regulatory processes including gene expression, chromatin structure and genomic imprinting. To understand the methylation regulation in the response to SE inoculation in chicken, the genome-wide DNA methylation profile following SE inoculation was analyzed through whole-genome bisulfite sequencing in the current study.Results: There were 185,362,463 clean reads and 126,098,724 unique reads in the control group, and 180,530,750 clean Reads and 126,782,896 unique reads in the inoculated group. The methylation density in the gene body was higher than that in the upstream and downstream regions of the gene. There were 8,946 differentially methylated genes (3,639 hypo-methylated genes, 5,307 hyper-methylated genes) obtained between inoculated and control groups. Methylated genes were mainly enriched in immune-related Gene Ontology (GO) terms and metabolic process terms. Cytokine-cytokine receptor interaction, TGF-beta signaling pathway, FoxO signaling pathway, Wnt signaling pathway and several metabolism-related pathways were significantly enriched. The density of differentially methylated cytosines in miRNAs was the highest. HOX genes were widely methylated.Conclusions: The genome-wide DNA methylation profile in the response to SE inoculation in chicken was analyzed. SE inoculation promoted the DNA methylation in the chicken cecum and caused methylation alteration in immune- and metabolic- related genes. Wnt signal pathway, miRNAs and HOX gene family may play crucial roles in the methylation regulation of SE inoculation in chicken. The findings herein will deepen the understanding of epigenetic regulation in the response to SE inoculation in chicken.

Download Full-text