scholarly journals A deep embedded refined clustering approach for breast cancer distinction based on DNA methylation

2021 ◽  
Author(s):  
Rocío del Amor ◽  
Adrián Colomer ◽  
Carlos Monteagudo ◽  
Valery Naranjo
Keyword(s):  
Breast Cancer ◽  
Dna Methylation ◽  
Deep Learning ◽  
Dimensionality Reduction ◽  
Error Rate ◽  
Breast Tissue ◽  
Cpg Island ◽  
Learning System ◽  
Methylation Data ◽  
Tissue Samples

AbstractEpigenetic alterations have an important role in the development of several types of cancer. Epigenetic studies generate a large amount of data, which makes it essential to develop novel models capable of dealing with large-scale data. In this work, we propose a deep embedded refined clustering method for breast cancer differentiation based on DNA methylation. In concrete, the deep learning system presented here uses the levels of CpG island methylation between 0 and 1. The proposed approach is composed of two main stages. The first stage consists in the dimensionality reduction of the methylation data based on an autoencoder. The second stage is a clustering algorithm based on the soft assignment of the latent space provided by the autoencoder. The whole method is optimized through a weighted loss function composed of two terms: reconstruction and classification terms. To the best of the authors’ knowledge, no previous studies have focused on the dimensionality reduction algorithms linked to classification trained end-to-end for DNA methylation analysis. The proposed method achieves an unsupervised clustering accuracy of 0.9927 and an error rate (%) of 0.73 on 137 breast tissue samples. After a second test of the deep-learning-based method using a different methylation database, an accuracy of 0.9343 and an error rate (%) of 6.57 on 45 breast tissue samples are obtained. Based on these results, the proposed algorithm outperforms other state-of-the-art methods evaluated under the same conditions for breast cancer classification based on DNA methylation data.

scholarly journals Epigenetic clock detected a breast cancer mitosis subtype with improved immunotherapy

2021 ◽  
Author(s):  
Shipeng Shang ◽  
Xin Li ◽  
Yue Gao ◽  
Shuang Guo ◽  
Hanxiao Zhou ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Dna Methylation ◽  
Breast Tissue ◽  
Pearson Correlation ◽  
Breast Cancer Subtypes ◽  
Chronological Age ◽  
Epigenetic Clock ◽  
Methylation Data ◽  
Cancer Subtypes ◽  
Epigenetic Age

Abstract Background Epigenetic clock based on DNA methylation can estimate the epigenetic age of tissue and cell that can describe the process of aging. However, the exploration of diseases by the epigenetic clock is still an uncharted territory. Our objective was to assess the role of the epigenetic clock in breast cancer. Methods In this study, DNA methylation data of breast tissue sample was download from TCGA and GEO database. DNA methylation level of CpG sites and age of samples was calculated by using pearson correlation test. Differentially expressed genes were identified using the limma package and Kruskal-Wallis test was used for the difference between cancer subtypes. Results We developed a workflow to construct the Breast Epigenetic Clock (BEpiC) that could accurately predict the chronological age of normal breast tissue. Furthermore, the BEpiC was applied to breast cancer to identify three breast cancer subtypes (including development, homeostasis, and mitosis) by using the deviation between epigenetic age and chronological age. Interestingly, the prognosis of the three breast cancer subtypes is significantly different. In addition, the three breast cancer subtypes had distinct differences in multiple immune cells and the mitosis subtype had the highest tumor mutation burden that was used to estimate response to checkpoint inhibitors. Conclusion Our model highlights that epigenetic age of breast cancer samples had an important impact on immunotherapy. We constructed a BEpiC web server (http://bio-bigdata.hrbmu.edu.cn/BEpiC/) where users submit DNA methylation data and age information to predict the epigenetic age of breast tissue and breast cancer subtypes. Trial registration Not applicable

scholarly journals Accelerated aging in normal breast tissue of women with breast cancer

2021 ◽  
Vol 23 (1) ◽  
Author(s):  
Shoghag Panjarian ◽  
Jozef Madzo ◽  
Kelsey Keith ◽  
Carolyn M. Slater ◽  
Carmen Sapienza ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Dna Methylation ◽  
Anomaly Detection ◽  
Breast Tissue ◽  
Preventive Intervention ◽  
Normal Breast Tissue ◽  
Accelerated Aging ◽  
Normal Breast ◽  
Age Related ◽  
Unsupervised Anomaly Detection

Abstract Background DNA methylation alterations have similar patterns in normal aging tissue and in cancer. In this study, we investigated breast tissue-specific age-related DNA methylation alterations and used those methylation sites to identify individuals with outlier phenotypes. Outlier phenotype is identified by unsupervised anomaly detection algorithms and is defined by individuals who have normal tissue age-dependent DNA methylation levels that vary dramatically from the population mean. Methods We generated whole-genome DNA methylation profiles (GSE160233) on purified epithelial cells and used publicly available Infinium HumanMethylation 450K array datasets (TCGA, GSE88883, GSE69914, GSE101961, and GSE74214) for discovery and validation. Results We found that hypermethylation in normal breast tissue is the best predictor of hypermethylation in cancer. Using unsupervised anomaly detection approaches, we found that about 10% of the individuals (39/427) were outliers for DNA methylation from 6 DNA methylation datasets. We also found that there were significantly more outlier samples in normal-adjacent to cancer (24/139, 17.3%) than in normal samples (15/228, 5.2%). Additionally, we found significant differences between the predicted ages based on DNA methylation and the chronological ages among outliers and not-outliers. Additionally, we found that accelerated outliers (older predicted age) were more frequent in normal-adjacent to cancer (14/17, 82%) compared to normal samples from individuals without cancer (3/17, 18%). Furthermore, in matched samples, we found that the epigenome of the outliers in the pre-malignant tissue was as severely altered as in cancer. Conclusions A subset of patients with breast cancer has severely altered epigenomes which are characterized by accelerated aging in their normal-appearing tissue. In the future, these DNA methylation sites should be studied further such as in cell-free DNA to determine their potential use as biomarkers for early detection of malignant transformation and preventive intervention in breast cancer.

scholarly journals Age-related DNA methylation in paired normal and tumour breast tissue in Chinese breast cancer patients

Epigenetics ◽  
2020 ◽  
pp. 1-15
Author(s):  
Maeve Kiely ◽  
Lap Ah Tse ◽  
Hela Koka ◽  
Difei Wang ◽  
Priscilla Lee ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Dna Methylation ◽  
Cancer Patients ◽  
Breast Tissue ◽  
Breast Cancer Patients ◽  
Age Related

scholarly journals DNA Methylation and Breast Cancer Risk: An Epigenome-Wide Study of Normal Breast Tissue and Blood

Cancers ◽  
2020 ◽  
Vol 12 (11) ◽  
pp. 3088 ◽  
Author(s):  
Kaoutar Ennour-Idrissi ◽  
Dzevka Dragic ◽  
Elissar Issa ◽  
Annick Michaud ◽  
Sue-Ling Chang ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Dna Methylation ◽  
Breast Cancer Risk ◽  
Cancer Risk ◽  
Breast Tissue ◽  
Normal Breast Tissue ◽  
Normal Breast ◽  
Breast Epithelium ◽  
Normal Breast Epithelium ◽  
Differentially Methylated Genes

Differential DNA methylation is a potential marker of breast cancer risk. Few studies have investigated DNA methylation changes in normal breast tissue and were largely confounded by cancer field effects. To detect methylation changes in normal breast epithelium that are causally associated with breast cancer occurrence, we used a nested case–control study design based on a prospective cohort of patients diagnosed with a primary invasive hormone receptor-positive breast cancer. Twenty patients diagnosed with a contralateral breast cancer (CBC) were matched (1:1) with 20 patients who did not develop a CBC on relevant risk factors. Differentially methylated Cytosine-phosphate-Guanines (CpGs) and regions in normal breast epithelium were identified using an epigenome-wide DNA methylation assay and robust linear regressions. Analyses were replicated in two independent sets of normal breast tissue and blood. We identified 7315 CpGs (FDR < 0.05), 52 passing strict Bonferroni correction (p < 1.22 × 10−7) and 43 mapping to known genes involved in metabolic diseases with significant enrichment (p < 0.01) of pathways involving fatty acids metabolic processes. Four differentially methylated genes were detected in both site-specific and regions analyses (LHX2, TFAP2B, JAKMIP1, SEPT9), and three genes overlapped all three datasets (POM121L2, KCNQ1, CLEC4C). Once validated, the seven differentially methylated genes distinguishing women who developed and who did not develop a sporadic breast cancer could be used to enhance breast cancer risk-stratification, and allow implementation of targeted screening and preventive strategies that would ultimately improve breast cancer prognosis.

scholarly journals Extracting a biologically latent space of lung cancer epigenetics with variational autoencoders

2019 ◽  
Vol 20 (S18) ◽  
Author(s):  
Zhenxing Wang ◽  
Yadong Wang
Keyword(s):  
Lung Cancer ◽  
Dna Methylation ◽  
Deep Learning ◽  
Malignant Tumors ◽  
Methylation Data ◽  
Cancer Epigenetics ◽  
Latent Space ◽  
Unsupervised Deep Learning ◽  
Latent Representations ◽  
Model Training

Abstract Background Lung cancer is one of the most malignant tumors, causing over 1,000,000 deaths each year worldwide. Deep learning has brought success in many domains in recent years. DNA methylation, an epigenetic factor, is used for model training in many studies. There is an opportunity for deep learning methods to analyze the lung cancer epigenetic data to determine their subtypes for appropriate treatment. Results Here, we employ variational autoencoders (VAEs), an unsupervised deep learning framework, on 450K DNA methylation data of TCGA-LUAD and TCGA-LUSC to learn latent representations of the DNA methylation landscape. We extract a biologically relevant latent space of LUAD and LUSC samples. It is showed that the bivariate classifiers on the further compressed latent features could classify the subtypes accurately. Through clustering of methylation-based latent space features, we demonstrate that the VAEs can capture differential methylation patterns about subtypes of lung cancer. Conclusions VAEs can distinguish the original subtypes from manually mixed methylation data frame with the encoded features of latent space. Further applications about VAEs should focus on fine-grained subtypes identification for precision medicine.

scholarly journals Association between cadmium and breast cancer

Medicina ◽  
2008 ◽  
Vol 44 (6) ◽  
pp. 415 ◽  
Author(s):  
Loreta Strumylaitė ◽  
Algirdas Boguševičius ◽  
Stanislovas Ryselis ◽  
Darius Pranys ◽  
Lina Poškienė ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Breast Tissue ◽  
Benign Tumor ◽  
Normal Breast Tissue ◽  
Cadmium Concentration ◽  
Normal Breast ◽  
Tissue Samples ◽  
Malignant Breast Tissue ◽  
Two Samples ◽  
Malignant Breast

Cadmium is a known human lung carcinogen, although some studies indicate a link between cadmium exposure and human breast cancer. The objective of this study was to assess cadmium concentration in breast tissue samples of patients with breast cancer and benign breast tumor. Material and methods. The concentration of cadmium was determined in breast tissue samples of 21 breast cancer and 19 benign tumor patients. Two samples of breast tissue from each patient, i.e. tumor and normal tissue close to tumor, were taken for the analysis. Cadmium was determined by atomic absorption spectrometry (Perkin-Elmer, Zeeman 3030). Results. In patients with breast cancer, the mean cadmium concentration was 33.1 ng/g (95% CI, 21.9– 44.4) in malignant breast tissue and 10.4 ng/g (95% CI, 5.6–15.2) in normal breast tissue (P=0.002). In patients with benign tumor, the corresponding values were 17.5 ng/g (95% CI, 8.4–26.5) and 11.8 ng/g (95% CI, 5.1– 18.5) (P=0.3144). There was a statistically significant difference in cadmium concentration between malignant and benign breast tissues (P=0.009). Conclusion. The data obtained show that cadmium concentration is significantly higher in malignant breast tissue as compared with normal breast tissue of the same women or benign breast tissue. Further studies are necessary to determine the association between cadmium concentration in malignant breast tissue and estrogen receptor level, and smoking.

Characterization of DNA methylation of the promoters CTCF and BORIS (CTCFL) in breast and ovarian cancer.

2013 ◽  
Vol 31 (15_suppl) ◽  
pp. e22151-e22151 ◽  
Author(s):  
Ernesto Soto Reyes Solis ◽  
Daniela Morales-Espinosa ◽  
David Cantu ◽  
Gabriela Alvarado-luna ◽  
Dan Green ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Ovarian Cancer ◽  
Dna Methylation ◽  
Methylation Status ◽  
Dna Hypomethylation ◽  
Rt Pcr ◽  
Breast And Ovarian Cancer ◽  
Neoplastic Tissue ◽  
Tissue Samples ◽  
Over Expression

e22151 Background: Genetic and epigenetic alterations may promote the initiation or development of cancer. Global DNA hypomethylation and local hypermethylation have been observed, particularly in cell cycle control-associated genes, such as tumor suppressor genes like CTCF. The dissociation of CTCF is associated with hypermethylation of several promoters; its paralogue gene (BORIS) is normally expressed in testicular tissue during spermatogenesis. BORIS over-expression has been identified in multiple neoplasms such as melanoma, gynecological cancer, glioblastoma and – recently – breast cancer. The aim of this study was to characterize the methylation status of the promoter regions of CTCF and BORIS in samples from breast and ovarian cancer compared to non-neoplastic tissue, and correlate it to its expression. Methods: Tissue samples from breast and ovarian cancer, as well as healthy controls were analyzed by MS-PCR for CTCF and BORIS. BorismRNA expression was also analyzed by RT-PCR. Results: A total of 8 ovarian and 16 breast tumors, as well as 10 tumor-adjacent breast tissue samples were prospectively obtained. In non-neoplastic tissue, BORIS was found to be hypermethylated, while in ovarian tumors a loss of methylation was identified in 75% of the samples. The same phenomenon was observed in 68% of breast cancer samples when compared to non-neoplastic tissue. A correlation between loss of DNA methylation of the promoter and gene over-expression was found by RT-PCR, thus suggesting that methylation is an epigenetic phenomenon associated to the over-expression of the oncogene BORIS. The methylation analysis of CTCF did not show any differences between neoplastic and non-neoplastic tissue, suggesting that epigenetic changes mainly affect BORIS. Conclusions: Loss of methylation of the promoter region of BORIS is associated with the over-expression of the gene. No differences were found in the methylation status between healthy and neoplastic tissue for CTCF.

scholarly journals Invasive breast tumors are characterized by the presence of crystalline nanoparticles

2020 ◽  
Author(s):  
Elena Tsolaki ◽  
William Doran ◽  
Luca Magnani ◽  
Alessandro Olivo ◽  
Inge K. Herrmann ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Cancer Diagnosis ◽  
Breast Tissue ◽  
Arterial Wall ◽  
Breast Cancer Diagnosis ◽  
Malignant Tumour ◽  
Spherical Particles ◽  
Tumour Tissue ◽  
Tissue Samples

The presence of calcification in tumours has been known for decades1. Indeed, calcified breast tissue is a fundamental criterion for early breast cancer diagnosis, indicative of malignancies2, and their appearance is used to distinguish between benign and malignant in breast biopsies3,4. However, an in-depth characterization of the nature and origin of tumour tissue calcification remains elusive5–8. Here, we report the presence of nano and micron-sized spherical particles made of highly crystalline whitlockite that are exclusively found in the arterial wall of malignant invasive tumours. By applying nanoanalytical methods to healthy, benign and malignant tumour breast tissue biopsies from patients, we show that poorly crystalline apatite can be found in all breast tissue samples, whereas spherical crystalline whitlockite particles are present only in invasive cancers, mainly in areas close to the lumen of the arterial wall. Moreover, we demonstrate that the concentration of these spherical crystalline particles increases with the grade of disease, and that their size can be related to tumour type. Therefore, our results not only provide new insight into calcification of tumour tissue, but also enable a precise, yet simple route of breast cancer diagnosis and staging.

Sign in / Sign up

Export Citation Format

Share Document