scholarly journals Diagnostic classification based on DNA methylation profiles using sequential machine learning approaches

2021 ◽  
Author(s):  
M. W. Wojewodzic ◽  
J. P. Lavender
Keyword(s):  
Machine Learning ◽  
Dna Methylation ◽  
Machine Learning Algorithms ◽  
Aberrant Methylation ◽  
Learning Approaches ◽  
Tissue Samples ◽  
Non Invasive ◽  
Genome Wide ◽  
Cancer Types ◽  
Methylation Patterns

AbstractAberrant methylation patterns in human DNA have great potential for the discovery of novel diagnostic and disease progression biomarkers. In this paper, we used machine learning algorithms to identify promising methylation sites for diagnosing cancerous tissue and to classify patients based on methylation values at these sites.We used genome-wide DNA methylation patterns from both cancerous and normal tissue samples, obtained from the Genomic Data Commons consortium and trialled our methods on three types of urological cancer. A decision tree was used to identify the methylation sites most useful for diagnosis.The identified locations were then used to train a neural network to classify samples as either cancerous or non-cancerous. Using this two-step approach we found strong indicative biomarker panels for each of the three cancer types.These methods could likely be translated to other cancers and improved by using non-invasive liquid methods such as blood instead of biopsy tissue.

scholarly journals Diagnostic classification based on DNA methylation profiles using sequential machine learning approaches.

2021 ◽  
Author(s):  
Marcin W. Wojewodzic ◽  
Jan P. Lavender
Keyword(s):  
Machine Learning ◽  
Dna Methylation ◽  
Machine Learning Algorithms ◽  
Aberrant Methylation ◽  
Learning Approaches ◽  
Tissue Samples ◽  
Non Invasive ◽  
Genome Wide ◽  
Cancer Types ◽  
Methylation Patterns

Abstract Aberrant methylation patterns in human DNA have great potential for the discovery of novel diagnostic and disease progression biomarkers. In this paper, we used machine learning algorithms to identify promising methylation sites for diagnosing cancerous tissue and to classify patients based on methylation values at these sites. We used genome-wide DNA methylation patterns from both cancerous and normal tissue samples, obtained from the Genomic Data Commons consortium and trialled our methods on three types of urological cancer. A decision tree was used to identify the methylation sites most useful for diagnosis. The identified locations were then used to train a neural network to classify samples as either cancerous or non-cancerous. Using this two-step approach we found strong indicative biomarker panels for each of the three cancer types. These methods could likely be translated to other cancers and improved by using non-invasive liquid methods such as blood instead of biopsy tissue.

scholarly journals Significant associations between driver gene mutations and DNA methylation alterations across many cancer types

2017 ◽  
Author(s):  
Yun-Ching Chen ◽  
Valer Gotea ◽  
Gennady Margolin ◽  
Laura Elnitski
Keyword(s):  
Gene Expression ◽  
Dna Methylation ◽  
Thyroid Cancer ◽  
Gene Mutations ◽  
Driver Gene ◽  
Driver Genes ◽  
Cancer Subtypes ◽  
Genome Wide ◽  
Cancer Types ◽  
Methylation Patterns

AbstractRecent evidence shows that mutations in several driver genes can cause aberrant methylation patterns, a hallmark of cancer. In light of these findings, we hypothesized that the landscapes of tumor genomes and epigenomes are tightly interconnected. We measured this relationship using principal component analyses and methylation-mutation associations applied at the nucleotide level and with respect to genome-wide trends. We found a few mutated driver genes were associated with genome-wide patterns of aberrant hypomethylation or CpG island hypermethylation in specific cancer types. We identified associations between 737 mutated driver genes and site-specific methylation changes. Moreover, using these mutation-methylation associations, we were able to distinguish between two uterine and two thyroid cancer subtypes. The driver gene mutation-associated methylation differences between the thyroid cancer subtypes were linked to differential gene expression in JAK-STAT signaling, NADPH oxidation, and other cancer-related pathways. These results establish that driver-gene mutations are associated with methylation alterations capable of shaping regulatory network functions. In addition, the methodology presented here can be used to subdivide tumors into more homogeneous subsets corresponding to their underlying molecular characteristics, which could improve treatment efficacy.Author summaryMutations that alter the function of driver genes by changing DNA nucleotides have been recognized as a key player in cancer progression. Recent evidence showed that DNA methylation, a molecular signature that is used for controlling gene expression and that consists of cytosine residues with attached methyl groups in the context of CG dinucleotides, is also highly dysregulated in cancer and contributes to carcinogenesis. However, whether those methylation alterations correspond to mutated driver genes in cancer remains unclear. In this study, we analyzed 4,302 tumors from 18 cancer types and demonstrated that driver gene mutations are inherently connected with the aberrant DNA methylation landscape in cancer. We showed that those driver gene-associated methylation patterns can classify heterogeneous tumors in a cancer type into homogeneous subtypes and have the potential to influence the genes that contribute to tumor growth. This finding could help us to better understand the fundamental connection between driver gene mutations and DNA methylation alterations in cancer and to further improve the cancer treatment.

scholarly journals Pioneer transcription factors are associated with the modulation of DNA methylation patterns across cancers

2021 ◽  
Author(s):  
Roza Berhanu Lemma ◽  
Thomas Fleischer ◽  
Emily Martinsen ◽  
Vessela N Kristensen ◽  
Ragnhild Eskeland ◽  
...  
Keyword(s):  
Gene Expression ◽  
Dna Methylation ◽  
Transcription Factors ◽  
Gene Expression Regulation ◽  
De Novo ◽  
Aberrant Methylation ◽  
Cancer Types ◽  
Aberrant Dna Methylation ◽  
Methylation Patterns ◽  
Mcf 7

Methylation of cytosines on DNA is a prominent modification associated with gene expression regulation. Aberrant DNA methylation patterns have recurrently been linked to dysregulation of the regulatory program in cancer cells. To shed light on the underlying molecular mechanism driving this process, we hypothesized that aberrant methylation patterns could be controlled by the binding of specific transcription factors (TFs) across cancer types. By combining DNA methylation arrays and gene expression data with TF binding sites (TFBSs), we explored the interplay between TF binding and DNA methylation in 19 cancer cohorts. We performed emQTL (expression-methylation quantitative trait loci) analyses in each cohort and identified 13 TFs whose expression levels are correlated with local DNA methylation patterns around their binding site in at least 2 cancer types. The 13 TFs are mainly associated with local demethylation and are enriched for pioneer function, suggesting a specific role for these TFs in modulating chromatin structure and transcription in cancer patients. Furthermore, we confirmed that de novo methylation is precluded across cancers at CpGs lying in genomic regions enriched for TF-binding signatures associated with SP1, CTCF, NRF1, GABPA, KLF9, and/or YY1. The modulation of DNA methylation associated with TF binding was observed at cis-regulatory regions controlling immune- and cancer-associated pathways, corroborating that the emQTL signals were derived from both cancer and tumour-infiltrating cells. As a case example, we experimentally confirmed that FOXA1 knock-down is associated with higher methylation in regions bound by FOXA1 in breast cancer MCF-7 cells. Finally, we reported physical interactions between FOXA1 with TET1 and TET2 at physiological levels in MCF-7 cells, adding further support for FOXA1 attracting TET1 and TET2 to induce local demethylation in cancer.

scholarly journals Systematic Investigation of DNA Methylation Associated With Platinum Chemotherapy Resistance Across 13 Cancer Types

2021 ◽  
Vol 12 ◽  
Author(s):  
Ruizheng Sun ◽  
Chao Du ◽  
Jiaxin Li ◽  
Yanhong Zhou ◽  
Wei Xiong ◽  
...  
Keyword(s):  
Dna Methylation ◽  
Systematic Investigation ◽  
Support Vector ◽  
Platinum Resistance ◽  
Chemotherapy Response ◽  
Aberrant Methylation ◽  
Cancer Type ◽  
Cancer Types ◽  
Methylation Patterns ◽  
Platinum Chemotherapy

Background: Platinum resistance poses a significant problem for oncology clinicians. As a result, the role of epigenetics and DNA methylation in platinum-based chemoresistance has gained increasing attention from researchers in recent years. A systematic investigation of aberrant methylation patterns related to platinum resistance across various cancer types is urgently needed.Methods: We analyzed the platinum chemotherapy response-related methylation patterns from different perspectives of 618 patients across 13 cancer types and integrated transcriptional and clinical data. Spearman’s test was used to evaluate the correlation between methylation and gene expression. Cox analysis, the Kaplan-Meier method, and log-rank tests were performed to identify potential risk biomarkers based on differentially methylated positions (DMPs) and compare survival based on DMP values. Support vector machines and receiver operating characteristic curves were used to identify the platinum-response predictive DMPs.Results: A total of 3,703 DMPs (p value < 0.001 and absolute delta beta >0.10) were identified, and the DMP numbers of each cancer type varied. A total of 39.83% of DMPs were hypermethylated and 60.17% were hypomethylated in platinum-resistant patients. Among them, 405 DMPs (Benjamini and Hochberg adjusted p value < 0.05) were found to be associated with prognosis in tumor patients treated with platinum-based regimens, and 664 DMPs displayed the potential to predict platinum chemotherapy response. In addition, we defined six DNA DMPs consisting of four gene members (mesothelin, protein kinase cAMP-dependent type II regulatory subunit beta, msh homeobox 1, and par-6 family cell polarity regulator alpha) that may have favorable prognostic and predictive values for platinum chemotherapy.Conclusion: The methylation-transcription axis exists and participates in the complex biological mechanism of platinum resistance in various cancers. Six DMPs and four associated genes may have the potential to serve as promising epigenetic biomarkers for platinum-based chemotherapy and guide clinical selection of optimal treatment.

scholarly journals Epigenome Chaos: Stochastic and Deterministic DNA Methylation Events Drive Cancer Evolution

Cancers ◽  
2021 ◽  
Vol 13 (8) ◽  
pp. 1800
Author(s):  
Giusi Russo ◽  
Alfonso Tramontano ◽  
Ilaria Iodice ◽  
Lorenzo Chiariotti ◽  
Antonio Pezone
Keyword(s):  
Dna Methylation ◽  
Tumor Heterogeneity ◽  
Tumor Evolution ◽  
Aberrant Methylation ◽  
Epigenetic Alterations ◽  
Cancer Evolution ◽  
Cancer Types ◽  
Chromatin Proteins ◽  
Aberrant Dna Methylation ◽  
Methylation Patterns

Cancer evolution is associated with genomic instability and epigenetic alterations, which contribute to the inter and intra tumor heterogeneity, making genetic markers not accurate to monitor tumor evolution. Epigenetic changes, aberrant DNA methylation and modifications of chromatin proteins, determine the “epigenome chaos”, which means that the changes of epigenetic traits are randomly generated, but strongly selected by deterministic events. Disordered changes of DNA methylation profiles are the hallmarks of all cancer types, but it is not clear if aberrant methylation is the cause or the consequence of cancer evolution. Critical points to address are the profound epigenetic intra- and inter-tumor heterogeneity and the nature of the heterogeneity of the methylation patterns in each single cell in the tumor population. To analyze the methylation heterogeneity of tumors, new technological and informatic tools have been developed. This review discusses the state of the art of DNA methylation analysis and new approaches to reduce or solve the complexity of methylated alleles in DNA or cell populations.

scholarly journals Prognostic DNA methylation patterns in cytogenetically normal acute myeloid leukemia are predefined by stem cell chromatin marks

Blood ◽  
2011 ◽  
Vol 118 (20) ◽  
pp. 5573-5582 ◽  
Author(s):  
Stefan Deneberg ◽  
Philippe Guardiola ◽  
Andreas Lennartsson ◽  
Ying Qu ◽  
Verena Gaidzik ◽  
...  
Keyword(s):  
Dna Methylation ◽  
Acute Myeloid Leukemia ◽  
Odds Ratio ◽  
Myeloid Leukemia ◽  
Negative Impact ◽  
Prognostic Impact ◽  
Aberrant Methylation ◽  
Genome Wide ◽  
Methylation Patterns ◽  
Acute Myeloid

Abstract Cytogenetically normal acute myeloid leukemia (CN-AML) compose between 40% and 50% of all adult acute myeloid leukemia (AML) cases. In this clinically diverse group, molecular aberrations, such as FLT3-ITD, NPM1, and CEBPA mutations, recently have added to the prognostic accuracy. Aberrant DNA methylation is a hallmark of cancer, including AML. We investigated in total 118 CN-AML samples in a test and a validation cohort for genome-wide promoter DNA methylation with Illumina Methylation Bead arrays and compared them with normal myeloid precursors and global gene expression. IDH and NPM1 mutations were associated with different methylation patterns (P = .0004 and .04, respectively). Genome-wide methylation levels were elevated in IDH-mutated samples (P = .006). We observed a negative impact of DNA methylation on transcription. Genes targeted by Polycomb group (PcG) proteins and genes associated with bivalent histone marks in stem cells showed increased aberrant methylation in AML (P < .0001). Furthermore, high methylation levels of PcG target genes were independently associated with better progression-free survival (odds ratio = 0.47, P = .01) and overall survival (odds ratio = 0.36, P = .001). In summary, genome-wide methylation patterns show preferential methylation of PcG targets with prognostic impact in CN-AML.

scholarly journals Genome wide DNA methylation analysis of alveolar capillary dysplasia lung tissue reveals aberrant methylation of genes involved in development including the FOXF1 locus

2021 ◽  
Vol 13 (1) ◽  
Author(s):  
Evelien Slot ◽  
Ruben Boers ◽  
Joachim Boers ◽  
Wilfred F. J. van IJcken ◽  
Dick Tibboel ◽  
...  
Keyword(s):  
Dna Methylation ◽  
Lung Tissue ◽  
Pulmonary Veins ◽  
Genomic Alteration ◽  
Aberrant Methylation ◽  
Coding Region ◽  
Alveolar Capillary Dysplasia ◽  
Genome Wide ◽  
Methylation Patterns ◽  
Alveolar Capillary

Abstract Background Alveolar capillary dysplasia with or without misalignment of the pulmonary veins (ACD/MPV) is a lethal congenital lung disorder associated with a variety of heterozygous genomic alterations in the FOXF1 gene or its 60 kb enhancer. Cases without a genomic alteration in the FOXF1 locus have been described as well. The mechanisms responsible for FOXF1 haploinsufficiency and the cause of ACD/MPV in patients without a genomic FOXF1 variant are poorly understood, complicating the search for potential therapeutic targets for ACD/MPV. To investigate the contribution of aberrant DNA methylation, genome wide methylation patterns of ACD/MPV lung tissues were compared with methylation patterns of control lung tissues using the recently developed technique Methylated DNA sequencing (MeD-seq). Results Eight ACD/MPV lung tissue samples and three control samples were sequenced and their mutual comparison resulted in identification of 319 differentially methylated regions (DMRs) genome wide, involving 115 protein coding genes. The potentially upregulated genes were significantly enriched in developmental signalling pathways, whereas potentially downregulated genes were mainly enriched in O-linked glycosylation. In patients with a large maternal deletion encompassing the 60 kb FOXF1 enhancer, DNA methylation patterns in this FOXF1 enhancer were not significantly different compared to controls. However, two hypermethylated regions were detected in the 60 kb FOXF1 enhancer of patients harbouring a FOXF1 point mutation. Lastly, a large hypermethylated region overlapping the first FOXF1 exon was found in one of the ACD/MPV patients without a known pathogenic FOXF1 variation. Conclusion This is the first study providing genome wide methylation data on lung tissue of ACD/MPV patients. DNA methylation analyses in the FOXF1 locus excludes maternal imprinting of the 60 kb FOXF1 enhancer. Hypermethylation at the 60 kb FOXF1 enhancer might contribute to FOXF1 haploinsufficiency caused by heterozygous mutations in the FOXF1 coding region. Interestingly, DNA methylation analyses of patients without a genomic FOXF1 variant suggest that abnormal hypermethylation of exon 1 might play a role in some ACD/MPV in patients.

Prediction of K562 Cells Functional Inhibitors Based on Machine Learning Approaches

2020 ◽  
Vol 25 (40) ◽  
pp. 4296-4302 ◽  
Author(s):  
Yuan Zhang ◽  
Zhenyan Han ◽  
Qian Gao ◽  
Xiaoyi Bai ◽  
Chi Zhang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Inclusion Bodies ◽  
Cross Validation ◽  
Independent Set ◽  
K562 Cells ◽  
Machine Learning Algorithms ◽  
Learning Approaches ◽  
Validation Test ◽  
Excess Number ◽  
Fold Cross Validation

Background: β thalassemia is a common monogenic genetic disease that is very harmful to human health. The disease arises is due to the deletion of or defects in β-globin, which reduces synthesis of the β-globin chain, resulting in a relatively excess number of α-chains. The formation of inclusion bodies deposited on the cell membrane causes a decrease in the ability of red blood cells to deform and a group of hereditary haemolytic diseases caused by massive destruction in the spleen. Methods: In this work, machine learning algorithms were employed to build a prediction model for inhibitors against K562 based on 117 inhibitors and 190 non-inhibitors. Results: The overall accuracy (ACC) of a 10-fold cross-validation test and an independent set test using Adaboost were 83.1% and 78.0%, respectively, surpassing Bayes Net, Random Forest, Random Tree, C4.5, SVM, KNN and Bagging. Conclusion: This study indicated that Adaboost could be applied to build a learning model in the prediction of inhibitors against K526 cells.

scholarly journals Multi-species and multi-tissue methylation clocks for age estimation in toothed whales and dolphins

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Todd R. Robeck ◽  
Zhe Fei ◽  
Ake T. Lu ◽  
Amin Haghani ◽  
Eve Jourdain ◽  
...  
Keyword(s):  
Dna Methylation ◽  
Age Estimation ◽  
Species Conservation ◽  
Genome Wide ◽  
Epigenetic Aging ◽  
Highly Correlated ◽  
Methylation Patterns ◽  
Cg Dinucleotides ◽  
Free Ranging ◽  
Unique Species

AbstractThe development of a precise blood or skin tissue DNA Epigenetic Aging Clock for Odontocete (OEAC) would solve current age estimation inaccuracies for wild odontocetes. Therefore, we determined genome-wide DNA methylation profiles using a custom array (HorvathMammalMethyl40) across skin and blood samples (n = 446) from known age animals representing nine odontocete species within 4 phylogenetic families to identify age associated CG dinucleotides (CpGs). The top CpGs were used to create a cross-validated OEAC clock which was highly correlated for individuals (r = 0.94) and for unique species (median r = 0.93). Finally, we applied the OEAC for estimating the age and sex of 22 wild Norwegian killer whales. DNA methylation patterns of age associated CpGs are highly conserved across odontocetes. These similarities allowed us to develop an odontocete epigenetic aging clock (OEAC) which can be used for species conservation efforts by provide a mechanism for estimating the age of free ranging odontocetes from either blood or skin samples.

Sign in / Sign up

Export Citation Format

Share Document