DNA Methylation Markers for Pan-Cancer Prediction by Deep Learning

Machine learning algorithms and biomarkers identification for pancreatic cancer diagnosis using multi-omics data integration

PURPOSE

Pancreatic cancer is a lethal type of cancer with most of the cases being diagnosed in an advanced stage and poor prognosis. Developing new diagnostic and prognostic markers for pancreatic cancer can significantly improve early detection and patient outcomes. These biomarkers can potentially revolutionize medical practice by enabling personalized, more effective, targeted treatments, ultimately improving patient outcomes.

METHODS

The search strategy was developed following PRISMA guidelines. A comprehensive search was performed across four electronic databases: PubMed, Scopus, EMBASE, and Web of Science, covering all English publications up to September 2022. The Newcastle-Ottawa Scale (NOS) was utilized to assess bias, categorizing studies as "good," "fair," or "poor" quality based on their NOS scores. Descriptive statistics for all included studies were compiled and reviewed, along with the NOS scores for each study to indicate their quality assessment.

RESULTS

Our results showed that SVM and RF are the most widely used algorithms in machine learning and data analysis, particularly for biomarker identification. SVM, a supervised learning algorithm, is employed for both classification and regression by mapping data points in high-dimensional space to identify the optimal separating hyperplane between classes.

CONCLUSIONS

The application of machine-learning algorithms in the search for novel biomarkers in pancreatic cancer represents a significant advancement in the field. By harnessing the power of artificial intelligence, researchers are poised to make strides towards earlier detection and more effective treatment, ultimately improving patient outcomes in this challenging disease.

Enhancing insights into diseases through horizontal gene transfer event detection from gut microbiome

Horizontal gene transfer (HGT) phenomena pervade the gut microbiome and significantly impact human health. Yet, no current method can accurately identify complete HGT events, including the transferred sequence and the associated deletion and insertion breakpoints from shotgun metagenomic data. Here, we develop LocalHGT, which facilitates the reliable and swift detection of complete HGT events from shotgun metagenomic data, delivering an accuracy of 99.4%-verified by Nanopore data-across 200 gut microbiome samples, and achieving an average F1 score of 0.99 on 100 simulated data. LocalHGT enables a systematic characterization of HGT events within the human gut microbiome across 2098 samples, revealing that multiple recipient genome sites can become targets of a transferred sequence, microhomology is enriched in HGT breakpoint junctions (P-value = 3.3e-58), and HGTs can function as host-specific fingerprints indicated by the significantly higher HGT similarity of intra-personal temporal samples than inter-personal samples (P-value = 4.3e-303). Crucially, HGTs showed potential contributions to colorectal cancer (CRC) and acute diarrhoea, as evidenced by the enrichment of the butyrate metabolism pathway (P-value = 3.8e-17) and the shigellosis pathway (P-value = 5.9e-13) in the respective associated HGTs. Furthermore, differential HGTs demonstrated promise as biomarkers for predicting various diseases. Integrating HGTs into a CRC prediction model achieved an AUC of 0.87.

Mapping Knowledge Landscapes and Emerging Trends in AI for Dementia Biomarkers: Bibliometric and Visualization Analysis

BACKGROUND

With the rise of artificial intelligence (AI) in the field of dementia biomarker research, exploring its current developmental trends and research focuses has become increasingly important. This study, using literature data mining, analyzes and assesses the key contributions and development scale of AI in dementia biomarker research.

OBJECTIVE

The aim of this study was to comprehensively evaluate the current state, hot topics, and future trends of AI in dementia biomarker research globally.

METHODS

This study thoroughly analyzed the literature in the application of AI to dementia biomarkers across various dimensions, such as publication volume, authors, institutions, journals, and countries, based on the Web of Science Core Collection. In addition, scales, trends, and potential connections between AI and biomarkers were extracted and deeply analyzed through multiple expert panels.

RESULTS

To date, the field includes 1070 publications across 362 journals, involving 74 countries and 1793 major research institutions, with a total of 6455 researchers. Notably, 69.41% (994/1432) of the researchers ceased their studies before 2019. The most prevalent algorithms used are support vector machines, random forests, and neural networks. Current research frequently focuses on biomarkers such as imaging biomarkers, cerebrospinal fluid biomarkers, genetic biomarkers, and blood biomarkers. Recent advances have highlighted significant discoveries in biomarkers related to imaging, genetics, and blood, with growth in studies on digital and ophthalmic biomarkers.

CONCLUSIONS

The field is currently in a phase of stable development, receiving widespread attention from numerous countries, institutions, and researchers worldwide. Despite this, stable clusters of collaborative research have yet to be established, and there is a pressing need to enhance interdisciplinary collaboration. Algorithm development has shown prominence, especially the application of support vector machines and neural networks in imaging studies. Looking forward, newly discovered biomarkers are expected to undergo further validation, and new types, such as digital biomarkers, will garner increased research interest and attention.

Early detection and diagnosis of cancer with interpretable machine learning to uncover cancer-specific DNA methylation patterns

Cancer, a collection of more than two hundred different diseases, remains a leading cause of morbidity and mortality worldwide. Usually detected at the advanced stages of disease, metastatic cancer accounts for 90% of cancer-associated deaths. Therefore, the early detection of cancer, combined with current therapies, would have a significant impact on survival and treatment of various cancer types. Epigenetic changes such as DNA methylation are some of the early events underlying carcinogenesis. Here, we report on an interpretable machine learning model that can classify 13 cancer types as well as non-cancer tissue samples using only DNA methylome data, with 98.2% accuracy. We utilize the features identified by this model to develop EMethylNET, a robust model consisting of an XGBoost model that provides information to a deep neural network that can generalize to independent data sets. We also demonstrate that the methylation-associated genomic loci detected by the classifier are associated with genes, pathways and networks involved in cancer, providing insights into the epigenomic regulation of carcinogenesis.

Deep learning and machine learning approaches to classify stomach distant metastatic tumors using DNA methylation profiles

Distant metastasis of cancer is a significant contributor to cancer-related complications, and early identification of unidentified stomach adenocarcinoma is crucial for a positive prognosis. Changes inDNA methylation are being increasingly recognized as a crucial factor in predicting cancer progression. Within this research, we developed machine learning and deep learning models for distinguishing distant metastasis in samples of stomach adenocarcinoma based on DNA methylation profile. Employing deep neural networks (DNN), support vector machines (SVM), random forest (RF), Naive Bayes (NB) and decision tree (DT), and models for forecasting distant metastasis in stomach adenocarcinoma. The results show that the performance of DNN is better than that of other models, AUC and AUPR achieving 99.9 % and 99.5 % respectively. Additionally, a weighted random sampling technique was utilized to address the issue of imbalanced datasets, enabling the identification of crucial methylation markers associated with functionally significant genes in stomach distant metastasis tumors with greater performance.

Artificial Intelligence-Enabled Prostate Cancer Diagnosis and Prognosis: Current State and Future Implications

In this modern era of digital pathology, artificial intelligence (AI)-based diagnostics for prostate cancer has become a hot topic. Multiple retrospective studies have demonstrated the benefits of AI-based diagnostic solutions for prostate cancer that includes improved prostate cancer detection, quantification, grading, interobserver concordance, cost and time savings, and a potential to reduce pathologists' workload and enhance pathology laboratory workflow. One of the major milestones is the Food and Drug Administration approval of Paige prostate AI for a second review of prostate cancer diagnosed using core needle biopsies. However, implementation of these AI tools for routine prostate cancer diagnostics is still lacking. Some of the limiting factors include costly digital pathology workflow, lack of regulatory guidelines for deployment of AI, and lack of prospective studies demonstrating the actual benefits of AI algorithms. Apart from diagnosis, AI algorithms have the potential to uncover novel insights into understanding the biology of prostate cancer and enable better risk stratification, and prognostication. This article includes an in-depth review of the current state of AI for prostate cancer diagnosis and highlights the future prospects of AI in prostate pathology for improved patient care.

Discovery of novel DNA methylation biomarker panels for the diagnosis and differentiation between common adenocarcinomas and their liver metastases

Differentiation between adenocarcinomas is sometimes challenging. The promising avenue for discovering new biomarkers lies in bioinformatics using DNA methylation analysis. Utilizing a 2853-sample identification dataset and a 782-sample independent verification dataset, we have identified diagnostic DNA methylation biomarkers that are hypermethylated in cancer and differentiate between breast invasive carcinoma, cholangiocarcinoma, colorectal cancer, hepatocellular carcinoma, lung adenocarcinoma, pancreatic adenocarcinoma and stomach adenocarcinoma. The best panels for cancer type exhibit sensitivity of 77.8-95.9%, a specificity of 92.7-97.5% for tumors, a specificity of 91.5-97.7% for tumors and normal tissues and a diagnostic accuracy of 85.3-96.4%. We have shown that the results can be extended from the primary cancers to their liver metastases, as the best panels diagnose and differentiate between pancreatic adenocarcinoma liver metastases and breast invasive carcinoma liver metastases with a sensitivity and specificity of 83.3-100% and a diagnostic accuracy of 86.8-91.9%. Moreover, the panels could detect hypermethylation of selected regions in the cell-free DNA of patients with liver metastases. At the same time, these were unmethylated in the cell-free DNA of healthy donors, confirming their applicability for liquid biopsies.

Toward Explainable Artificial Intelligence for Precision Pathology

The rapid development of precision medicine in recent years has started to challenge diagnostic pathology with respect to its ability to analyze histological images and increasingly large molecular profiling data in a quantitative, integrative, and standardized way. Artificial intelligence (AI) and, more precisely, deep learning technologies have recently demonstrated the potential to facilitate complex data analysis tasks, including clinical, histological, and molecular data for disease classification; tissue biomarker quantification; and clinical outcome prediction. This review provides a general introduction to AI and describes recent developments with a focus on applications in diagnostic pathology and beyond. We explain limitations including the black-box character of conventional AI and describe solutions to make machine learning decisions more transparent with so-called explainable AI. The purpose of the review is to foster a mutual understanding of both the biomedical and the AI side. To that end, in addition to providing an overview of the relevant foundations in pathology and machine learning, we present worked-through examples for a better practical understanding of what AI can achieve and how it should be done.

Artificial intelligence and allied subsets in early detection and preclusion of gynecological cancers

Gynecological cancers including breast, cervical, ovarian, uterine, and vaginal, pose the greatest threat to world health, with early identification being crucial to patient outcomes and survival rates. The application of machine learning (ML) and artificial intelligence (AI) approaches to the study of gynecological cancer has shown potential to revolutionize cancer detection and diagnosis. The current review outlines the significant advancements, obstacles, and prospects brought about by AI and ML technologies in the timely identification and accurate diagnosis of different types of gynecological cancers. The AI-powered technologies can use genomic data to discover genetic alterations and biomarkers linked to a particular form of gynecologic cancer, assisting in the creation of targeted treatments. Furthermore, it has been shown that the potential benefits of AI and ML technologies in gynecologic tumors can greatly increase the accuracy and efficacy of cancer diagnosis, reduce diagnostic delays, and possibly eliminate the need for needless invasive operations. In conclusion, the review focused on the integrative part of AI and ML based tools and techniques in the early detection and exclusion of various cancer types; together with a collaborative coordination between research clinicians, data scientists, and regulatory authorities, which is suggested to realize the full potential of AI and ML in gynecologic cancer care.

Application of deep learning in cancer epigenetics through DNA methylation analysis

DNA methylation is a fundamental epigenetic modification involved in various biological processes and diseases. Analysis of DNA methylation data at a genome-wide and high-throughput level can provide insights into diseases influenced by epigenetics, such as cancer. Recent technological advances have led to the development of high-throughput approaches, such as genome-scale profiling, that allow for computational analysis of epigenetics. Deep learning (DL) methods are essential in facilitating computational studies in epigenetics for DNA methylation analysis. In this systematic review, we assessed the various applications of DL applied to DNA methylation data or multi-omics data to discover cancer biomarkers, perform classification, imputation and survival analysis. The review first introduces state-of-the-art DL architectures and highlights their usefulness in addressing challenges related to cancer epigenetics. Finally, the review discusses potential limitations and future research directions in this field.

The Development of Immunotherapy for the Treatment of Recurrent Glioblastoma

Recurrent glioblastoma (rGBM) is a highly aggressive form of brain cancer that poses a significant challenge for treatment in neuro-oncology, and the survival status of patients after relapse usually means rapid deterioration, thus becoming the leading cause of death among patients. In recent years, immunotherapy has emerged as a promising strategy for the treatment of recurrent glioblastoma by stimulating the body's immune system to recognize and attack cancer cells, which could be used in combination with other treatments such as surgery, radiation, and chemotherapy to improve outcomes for patients with recurrent glioblastoma. This therapy combines several key methods such as the use of monoclonal antibodies, chimeric antigen receptor T cell (CAR-T) therapy, checkpoint inhibitors, oncolytic viral therapy cancer vaccines, and combination strategies. In this review, we mainly document the latest immunotherapies for the treatment of glioblastoma and especially focus on rGBM.

Advances in methylation analysis of liquid biopsy in early cancer detection of colorectal and lung cancer

Methylation patterns in cell-free DNA (cfDNA) have emerged as a promising genomic feature for detecting the presence of cancer and determining its origin. The purpose of this study was to evaluate the diagnostic performance of methylation-sensitive restriction enzyme digestion followed by sequencing (MRE-Seq) using cfDNA, and to investigate the cancer signal origin (CSO) of the cancer using a deep neural network (DNN) analyses for liquid biopsy of colorectal and lung cancer. We developed a selective MRE-Seq method with DNN learning-based prediction model using demethylated-sequence-depth patterns from 63,266 CpG sites using SacII enzyme digestion. A total of 191 patients with stage I-IV cancers (95 lung cancers and 96 colorectal cancers) and 126 noncancer participants were enrolled in this study. Our study showed an area under the receiver operating characteristic curve (AUC) of 0.978 with a sensitivity of 78.1% for colorectal cancer, and an AUC of 0.956 with a sensitivity of 66.3% for lung cancer, both at a specificity of 99.2%. For colorectal cancer, sensitivities for stages I-IV ranged from 76.2 to 83.3% while for lung cancer, sensitivities for stages I-IV ranged from 44.4 to 78.9%, both again at a specificity of 99.2%. The CSO model's true-positive rates were 94.4% and 89.9% for colorectal and lung cancers, respectively. The MRE-Seq was found to be a useful method for detecting global hypomethylation patterns in liquid biopsy samples and accurately diagnosing colorectal and lung cancers, as well as determining CSO of the cancer using DNN analysis.Trial registration: This trial was registered at ClinicalTrials.gov (registration number: NCT04253509) for lung cancer on 5 February 2020, https://clinicaltrials.gov/ct2/show/NCT04253509 . Colorectal cancer samples were retrospectively registered at CRIS (Clinical Research Information Service, registration number: KCT0008037) on 23 December 2022, https://cris.nih.go.kr , https://who.init/ictrp . Healthy control samples were retrospectively registered.

Accurate prediction of pan-cancer types using machine learning with minimal number of DNA methylation sites

DNA methylation analysis has been applied to determine the primary site of cancer; however, robust and accurate prediction of cancer types with a minimum number of sites is still a significant scientific challenge. To build an accurate and robust cancer type prediction tool with a minimum number of DNA methylation sites, we internally benchmarked different DNA methylation site selection and ranking procedures, as well as different classification models. We used The Cancer Genome Atlas dataset (26 cancer types with 8296 samples) to train and test models and used an independent dataset (17 cancer types with 2738 samples) for model validation. A deep neural network model using a combined feature selection procedure (named MethyDeep) can predict 26 cancer types using 30 methylation sites with superior performance compared with the known methods for both primary and metastatic cancers in independent validation datasets. In conclusion, MethyDeep is an accurate and robust cancer type predictor with the minimum number of DNA methylation sites; it could help the cost-effective clarification of cancer of unknown primary patients and the liquid biopsy-based early screening of cancers.

AttOmics: attention-based architecture for diagnosis and prognosis from omics data

MOTIVATION

The increasing availability of high-throughput omics data allows for considering a new medicine centered on individual patients. Precision medicine relies on exploiting these high-throughput data with machine-learning models, especially the ones based on deep-learning approaches, to improve diagnosis. Due to the high-dimensional small-sample nature of omics data, current deep-learning models end up with many parameters and have to be fitted with a limited training set. Furthermore, interactions between molecular entities inside an omics profile are not patient specific but are the same for all patients.

RESULTS

In this article, we propose AttOmics, a new deep-learning architecture based on the self-attention mechanism. First, we decompose each omics profile into a set of groups, where each group contains related features. Then, by applying the self-attention mechanism to the set of groups, we can capture the different interactions specific to a patient. The results of different experiments carried out in this article show that our model can accurately predict the phenotype of a patient with fewer parameters than deep neural networks. Visualizing the attention maps can provide new insights into the essential groups for a particular phenotype.

AVAILABILITY AND IMPLEMENTATION

The code and data are available at https://forge.ibisc.univ-evry.fr/abeaude/AttOmics. TCGA data can be downloaded from the Genomic Data Commons Data Portal.

The transcriptional risk scores for kidney renal clear cell carcinoma using XGBoost and multiple omics data

Most kidney cancers are kidney renal clear cell carcinoma (KIRC) that is a main cause of cancer-related deaths. Polygenic risk score (PRS) is a weighted linear combination of phenotypic related alleles on the genome that can be used to assess KIRC risk. However, standalone SNP data as input to the PRS model may not provide satisfactory result. Therefore, Transcriptional risk scores (TRS) based on multi-omics data and machine learning models were proposed to assess the risk of KIRC. First, we collected four types of multi-omics data (DNA methylation, miRNA, mRNA and lncRNA) of KIRC patients from the TCGA database. Subsequently, a novel TRS method utilizing multiple omics data and XGBoost model was developed. Finally, we performed prevalence analysis and prognosis prediction to evaluate the utility of the TRS generated by our method. Our TRS methods exhibited better predictive performance than the linear models and other machine learning models. Furthermore, the prediction accuracy of combined TRS model was higher than that of single-omics TRS model. The KM curves showed that TRS was a valid prognostic indicator for cancer staging. Our proposed method extended the current definition of TRS from standalone SNP data to multi-omics data and was superior to the linear models and other machine learning models, which may provide a useful implement for diagnostic and prognostic prediction of KIRC.

AD-Syn-Net: systematic identification of Alzheimer's disease-associated mutation and co-mutation vulnerabilities via deep learning

Alzheimer's disease (AD) is one of the most challenging neurodegenerative diseases because of its complicated and progressive mechanisms, and multiple risk factors. Increasing research evidence demonstrates that genetics may be a key factor responsible for the occurrence of the disease. Although previous reports identified quite a few AD-associated genes, they were mostly limited owing to patient sample size and selection bias. There is a lack of comprehensive research aimed to identify AD-associated risk mutations systematically. To address this challenge, we hereby construct a large-scale AD mutation and co-mutation framework ('AD-Syn-Net'), and propose deep learning models named Deep-SMCI and Deep-CMCI configured with fully connected layers that are capable of predicting cognitive impairment of subjects effectively based on genetic mutation and co-mutation profiles. Next, we apply the customized frameworks to data sets to evaluate the importance scores of the mutations and identified mutation effectors and co-mutation combination vulnerabilities contributing to cognitive impairment. Furthermore, we evaluate the influence of mutation pairs on the network architecture to dissect the genetic organization of AD and identify novel co-mutations that could be responsible for dementia, laying a solid foundation for proposing future targeted therapy for AD precision medicine. Our deep learning model codes are available open access here: https://github.com/Pan-Bio/AD-mutation-effectors.

Shifting the Cancer Screening Paradigm: The Rising Potential of Blood-Based Multi-Cancer Early Detection Tests

Cancer remains a leading cause of death worldwide, partly owing to late detection which entails limited and often ineffective therapeutic options. Most cancers lack validated screening procedures, and the ones available disclose several drawbacks, leading to low patient compliance and unnecessary workups, adding up the costs to healthcare systems. Hence, there is a great need for innovative, accurate, and minimally invasive tools for early cancer detection. In recent years, multi-cancer early detection (MCED) tests emerged as a promising screening tool, combining molecular analysis of tumor-related markers present in body fluids with artificial intelligence to simultaneously detect a variety of cancers and further discriminate the underlying cancer type. Herein, we aim to provide a highlight of the variety of strategies currently under development concerning MCED, as well as the major factors which are preventing clinical implementation. Although MCED tests depict great potential for clinical application, large-scale clinical validation studies are still lacking.

Rise of Deep Learning Clinical Applications and Challenges in Omics Data: A Systematic Review

This research aims to review and evaluate the most relevant scientific studies about deep learning (DL) models in the omics field. It also aims to realize the potential of DL techniques in omics data analysis fully by demonstrating this potential and identifying the key challenges that must be addressed. Numerous elements are essential for comprehending numerous studies by surveying the existing literature. For example, the clinical applications and datasets from the literature are essential elements. The published literature highlights the difficulties encountered by other researchers. In addition to looking for other studies, such as guidelines, comparative studies, and review papers, a systematic approach is used to search all relevant publications on omics and DL using different keyword variants. From 2018 to 2022, the search procedure was conducted on four Internet search engines: IEEE Xplore, Web of Science, ScienceDirect, and PubMed. These indexes were chosen because they offer enough coverage and linkages to numerous papers in the biological field. A total of 65 articles were added to the final list. The inclusion and exclusion criteria were specified. Of the 65 publications, 42 are clinical applications of DL in omics data. Furthermore, 16 out of 65 articles comprised the review publications based on single- and multi-omics data from the proposed taxonomy. Finally, only a small number of articles (7/65) were included in papers focusing on comparative analysis and guidelines. The use of DL in studying omics data presented several obstacles related to DL itself, preprocessing procedures, datasets, model validation, and testbed applications. Numerous relevant investigations were performed to address these issues. Unlike other review papers, our study distinctly reflects different observations on omics with DL model areas. We believe that the result of this study can be a useful guideline for practitioners who look for a comprehensive view of the role of DL in omics data analysis.

AI-DrugNet: A network-based deep learning model for drug repurposing and combination therapy in neurological disorders

Discovering effective therapies is difficult for neurological and developmental disorders in that disease progression is often associated with a complex and interactive mechanism. Over the past few decades, few drugs have been identified for treating Alzheimer's disease (AD), especially for impacting the causes of cell death in AD. Although drug repurposing is gaining more success in developing therapeutic efficacy for complex diseases such as common cancer, the complications behind AD require further study. Here, we developed a novel prediction framework based on deep learning to identify potential repurposed drug therapies for AD, and more importantly, our framework is broadly applicable and may generalize to identifying potential drug combinations in other diseases. Our prediction framework is as follows: we first built a drug-target pair (DTP) network based on multiple drug features and target features, as well as the associations between DTP nodes where drug-target pairs are the DTP nodes and the associations between DTP nodes are represented as the edges in the AD disease network; furthermore, we incorporated the drug-target feature from the DTP network and the relationship information between drug-drug, target-target, drug-target within and outside of drug-target pairs, representing each drug-combination as a quartet to generate corresponding integrated features; finally, we developed an AI-based Drug discovery Network (AI-DrugNet), which exhibits robust predictive performance. The implementation of our network model help identify potential repurposed and combination drug options that may serve to treat AD and other diseases.

Methylation biomarkers for early cancer detection and diagnosis: Current and future perspectives

The increase in recent scientific studies on cancer biomarkers has brought great new insights into the field. Moreover, novel technological breakthroughs such as long read sequencing and microarrays have enabled high throughput profiling of many biomarkers, while advances in bioinformatic tools have made the possibility of developing highly reliable and accurate biomarkers a reality. These changes triggered renewed interest in biomarker research and provided tremendous opportunities for enhancing cancer management and improving early disease detection. DNA methylation alterations are known to accompany and contribute to carcinogenesis, making them promising biomarkers for cancer, namely due to their stability, frequency and accessibility in bodily fluids. The advent of newer minimally invasive experimental methods such as liquid biopsies provide the perfect setting for methylation-based biomarker development and application. Despite their huge potential, accurate and robust biomarkers for the conclusive diagnosis of most cancer types are still not routinely used, hence a strong need for sustained research in this field is still needed. This review provides a brief exposition of current methylation biomarkers for cancer diagnosis and early detection, including markers already in clinical use as well as various upcoming ones. It also outlines how recent big data and novel technologies will revolutionise the next generation of cancer tests in supplementing or replacing currently existing invasive techniques.

Comparative epigenomics by machine learning approach for neuroblastoma

BACKGROUND

Neuroblastoma (NB) is the second most common pediatric solid tumor. Because the number of genetic mutations found in tumors are small, even in some patients with unfavorable NB, epigenetic variation is expected to play an important role in NB progression. DNA methylation is a major epigenetic mechanism, and its relationship with NB prognosis has been a concern. One limitation with the analysis of variation in DNA methylation is the lack of a suitable analytical model. Therefore, in this study, we performed a random forest (RF) analysis of the DNA methylome data of NB from multiple databases.

RESULTS

RF is a popular machine learning model owing to its simplicity, intuitiveness, and computational cost. RF analysis identified novel intermediate-risk patient groups with characteristic DNA methylation patterns within the low-risk group. Feature selection analysis based on probe annotation revealed that enhancer-annotated regions had strong predictive power, particularly for MYCN-amplified NBs. We developed a gene-based analytical model to identify candidate genes related to disease progression, such as PRDM8 and FAM13A-AS1. RF analysis revealed sufficient predictive power compared to other machine learning models.

CONCLUSIONS

RF is a useful tool for DNA methylome analysis in cancer epigenetic studies, and has potential to identify a novel cancer-related genes.

DNA Methylation Analysis Reveals Distinct Patterns in Satellite Cell-Derived Myogenic Progenitor Cells of Subjects with Spastic Cerebral Palsy

Spastic type cerebral palsy (CP) is a complex neuromuscular disorder that involves altered skeletal muscle microanatomy and growth, but little is known about the mechanisms contributing to muscle pathophysiology and dysfunction. Traditional genomic approaches have provided limited insight regarding disease onset and severity, but recent epigenomic studies indicate that DNA methylation patterns can be altered in CP. Here, we examined whether a diagnosis of spastic CP is associated with intrinsic DNA methylation differences in myoblasts and myotubes derived from muscle resident stem cell populations (satellite cells; SCs). Twelve subjects were enrolled (6 CP; 6 control) with informed consent/assent. Skeletal muscle biopsies were obtained during orthopedic surgeries, and SCs were isolated and cultured to establish patient-specific myoblast cell lines capable of proliferation and differentiation in culture. DNA methylation analyses indicated significant differences at 525 individual CpG sites in proliferating SC-derived myoblasts (MB) and 1774 CpG sites in differentiating SC-derived myotubes (MT). Of these, 79 CpG sites were common in both culture types. The distribution of differentially methylated 1 Mbp chromosomal segments indicated distinct regional hypo- and hyper-methylation patterns, and significant enrichment of differentially methylated sites on chromosomes 12, 13, 14, 15, 18, and 20. Average methylation load across 2000 bp regions flanking transcriptional start sites was significantly different in 3 genes in MBs, and 10 genes in MTs. SC derived MBs isolated from study participants with spastic CP exhibited fundamental differences in DNA methylation compared to controls at multiple levels of organization that may reveal new targets for studies of mechanisms contributing to muscle dysregulation in spastic CP.

Application of Deep Learning to IVC Filter Detection from CT Scans

IVC filters (IVCF) perform an important function in select patients that have venous blood clots. However, they are usually intended to be temporary, and significant delay in removal can have negative health consequences for the patient. Currently, all Interventional Radiology (IR) practices are tasked with tracking patients in whom IVCF are placed. Due to their small size and location deep within the abdomen it is common for patients to forget that they have an IVCF. Therefore, there is a significant delay for a new healthcare provider to become aware of the presence of a filter. Patients may have an abdominopelvic CT scan for many reasons and, fortunately, IVCF are clearly visible on these scans. In this research a deep learning model capable of segmenting IVCF from CT scan slices along the axial plane is developed. The model achieved a Dice score of 0.82 for training over 372 CT scan slices. The segmentation model is then integrated with a prediction algorithm capable of flagging an entire CT scan as having IVCF. The prediction algorithm utilizing the segmentation model achieved a 92.22% accuracy at detecting IVCF in the scans.

A Deep Survival EWAS approach estimating risk profile based on pre-diagnostic DNA methylation: An application to breast cancer time to diagnosis

Previous studies for cancer biomarker discovery based on pre-diagnostic blood DNA methylation (DNAm) profiles, either ignore the explicit modeling of the Time To Diagnosis (TTD), or provide inconsistent results. This lack of consistency is likely due to the limitations of standard EWAS approaches, that model the effect of DNAm at CpG sites on TTD independently. In this work, we aim to identify blood DNAm profiles associated with TTD, with the aim to improve the reliability of the results, as well as their biological meaningfulness. We argue that a global approach to estimate CpG sites effect profile should capture the complex (potentially non-linear) relationships interplaying between sites. To prove our concept, we develop a new Deep Learning-based approach assessing the relevance of individual CpG Islands (i.e., assigning a weight to each site) in determining TTD while modeling their combined effect in a survival analysis scenario. The algorithm combines a tailored sampling procedure with DNAm sites agglomeration, deep non-linear survival modeling and SHapley Additive exPlanations (SHAP) values estimation to aid robustness of the derived effects profile. The proposed approach deals with the common complexities arising from epidemiological studies, such as small sample size, noise, and low signal-to-noise ratio of blood-derived DNAm. We apply our approach to a prospective case-control study on breast cancer nested in the EPIC Italy cohort and we perform weighted gene-set enrichment analyses to demonstrate the biological meaningfulness of the obtained results. We compared the results of Deep Survival EWAS with those of a traditional EWAS approach, demonstrating that our method performs better than the standard approach in identifying biologically relevant pathways.

Blood-derived DNAm profiles could be exploited as new biomarkers for cancer risk stratification and possibly, early detection. This is of particular interest since blood is a convenient tissue to assay for constitutional methylation and its collection is non-invasive. Exploiting pre-diagnostic blood DNAm data opens the further opportunity to investigate the association of DNAm at baseline on cancer risk, modeling the relationship between sites’ methylation and the Time to Diagnosis. Previous studies mostly provide inconsistent results likely due to the limitations of standard EWAS approaches, that model the effect of DNAm at CpG sites on TTD independently. In this work we argue that an approach to estimate single CpG sites’ effect while modeling their combined effect on the survival outcome is needed, and we claim that such approach should capture the complex (potentially non-linear) relationships interplaying between sites. We prove this concept by developing a novel approach to analyze a prospective case-control study on breast cancer nested in the EPIC Italy cohort. A weighted gene set enrichment analysis confirms that our approach outperforms standard EWAS in identifying biologically meaningful pathways.

Application of Feature Selection and Deep Learning for Cancer Prediction Using DNA Methylation Markers

DNA methylation is a process that can affect gene accessibility and therefore gene expression. In this study, a machine learning pipeline is proposed for the prediction of breast cancer and the identification of significant genes that contribute to the prediction. The current study utilized breast cancer methylation data from The Cancer Genome Atlas (TCGA), specifically the TCGA-BRCA dataset. Feature engineering techniques have been utilized to reduce data volume and make deep learning scalable. A comparative analysis of the proposed approach on Illumina 27K and 450K methylation data reveals that deep learning methodologies for cancer prediction can be coupled with feature selection models to enhance prediction accuracy. Prediction using 450K methylation markers can be accomplished in less than 13 s with an accuracy of 98.75%. Of the list of 685 genes in the feature selected 27K dataset, 578 were mapped to Ensemble Gene IDs. This reduced set was significantly (FDR < 0.05) enriched in five biological processes and one molecular function. Of the list of 1572 genes in the feature selected 450K data set, 1290 were mapped to Ensemble Gene IDs. This reduced set was significantly (FDR < 0.05) enriched in 95 biological processes and 17 molecular functions. Seven oncogene/tumor suppressor genes were common between the 27K and 450K feature selected gene sets. These genes were RTN4IP1, MYO18B, ANP32A, BRF1, SETBP1, NTRK1, and IGF2R. Our bioinformatics deep learning workflow, incorporating imputation and data balancing methods, is able to identify important methylation markers related to functionally important genes in breast cancer with high accuracy compared to deep learning or statistical models alone.

The construction of transcriptional risk scores for breast cancer based on lightGBM and multiple omics data

BACKGROUND

Polygenic risk score (PRS) can evaluate the individual-level genetic risk of breast cancer. However, standalone single nucleotide polymorphisms (SNP) data used for PRS may not provide satisfactory prediction accuracy. Additionally, current PRS models based on linear regression have insufficient power to leverage non-linear effects from thousands of associated SNPs. Here, we proposed a transcriptional risk score (TRS) based on multiple omics data to estimate the risk of breast cancer.

METHODS

The multiple omics data and clinical data of breast invasive carcinoma (BRCA) were collected from the cancer genome atlas (TCGA) and the gene expression omnibus (GEO). First, we developed a novel TRS model for BRCA utilizing single omic data and LightGBM algorithm. Subsequently, we built a combination model of TRS derived from each omic data to further improve the prediction accuracy. Finally, we performed association analysis and prognosis prediction to evaluate the utility of the TRS generated by our method.

RESULTS

The proposed TRS model achieved better predictive performance than the linear models and other ML methods in single omic dataset. An independent validation dataset also verified the effectiveness of our model. Moreover, the combination of the TRS can efficiently strengthen prediction accuracy. The analysis of prevalence and the associations of the TRS with phenotypes including case-control and cancer stage indicated that the risk of breast cancer increases with the increases of TRS. The survival analysis also suggested that TRS for the cancer stage is an effective prognostic metric of breast cancer patients.

CONCLUSIONS

Our proposed TRS model expanded the current definition of PRS from standalone SNP data to multiple omics data and outperformed the linear models, which may provide a powerful tool for diagnostic and prognostic prediction of breast cancer.

Benchmarking DNA Methylation Analysis of 14 Alignment Algorithms for Whole Genome Bisulfite Sequencing in Mammals

Whole genome bisulfite sequencing (WGBS) is an essential technique for methylome studies. Although a series of tools have been developed to overcome the mapping challenges caused by bisulfite treatment, the latest available tools have not been evaluated on the performance of reads mapping as well as on biological insights in multiple mammals. Herein, based on the real and simulated WGBS data of 14.77 billion reads, we undertook 936 mappings to benchmark and evaluate 14 wildly utilized alignment algorithms from reads mapping to biological interpretation in humans, cattle and pigs: Bwa-meth, BSBolt, BSMAP, Walt, Abismal, Batmeth2, Hisat_3n, Hisat_3n_repeat, Bismark-bwt2-e2e, Bismark-his2, BSSeeker2-bwt, BSSeeker2-soap2, BSSeeker2-bwt2-e2e and BSSeeker2-bwt2-local. Specifically, Bwa-meth, BSBolt, BSMAP, Bismark-bwt2-e2e and Walt exhibited higher uniquely mapped reads, mapped precision, recall and F1 score than other nine alignment algorithms, and the influences of distinct alignment algorithms on the methylomes varied considerably at the numbers and methylation levels of CpG sites, the calling of differentially methylated CpGs (DMCs) and regions (DMRs). Moreover, we reported that BSMAP showed the highest accuracy at the detection of CpG coordinates and methylation levels, the calling of DMCs, DMRs, DMR-related genes and signaling pathways. These results suggested that careful selection of algorithms to profile the genome-wide DNA methylation is required, and our works provided investigators with useful information on the choice of alignment algorithms to effectively improve the DNA methylation detection accuracy in mammals.

i-Modern: Integrated multi-omics network model identifies potential therapeutic targets in glioma by deep learning with interpretability

Effective and precise classification of glioma patients for their disease risks is critical to improving early diagnosis and patient survival. In the recent past, a significant amount of multi-omics data derived from cancer patients has emerged. However, a robust framework for integrating multi-omics data types to efficiently and precisely subgroup glioma patients and predict survival prognosis is still lacking. In addition, effective therapeutic targets for treating glioma patients with poor prognoses are in dire need. To begin to resolve this difficulty, we developed i-Modern, an integrated Multi-omics deep learning network method, and optimized a sophisticated computational model in gliomas that can accurately stratify patients based on their prognosis. We built a survival-associated predictive framework integrating transcription profile, miRNA expression, somatic mutations, copy number variation (CNV), DNA methylation, and protein expression. This framework achieved promising performance in distinguishing high-risk glioma patients from those with good prognoses. Furthermore, we constructed multiple fully connected neural networks that are trained on prioritized multi-omics signatures or even only potential single-omics signatures, based on our customized scoring system. Together, the landmark multi-omics signatures we identified may serve as potential therapeutic targets in gliomas.

Multi-omics to characterize the functional relationships of R-loops with epigenetic modifications, RNAPII transcription and gene expression

Abnormal accumulation of R-loops results in replication stress, genome instability, chromatin alterations and gene silencing. Little research has been done to characterize functional relationships among R-loops, histone marks, RNA polymerase II (RNAPII) transcription and gene regulation. We built extremely randomized trees (ETs) models to predict the genome-wide R-loops using RNAPII and multiple histone modifications chromatin immunoprecipitation (ChIP)-seq, DNase-seq, Global Run-On sequencing (GRO-seq) and R-loop profiling data. We compared the performance of ET models to multiple machine learning approaches, and the proposed ET models achieved the best and extremely robust performances. Epigenetic profiles are highly predictive of R-loops genome-widely and they are strongly associated with R-loop formation. In addition, the presence of R-loops is significantly correlated with RNAPII transcription activity, H3K4me3 and open chromatin around the transcription start site, and H3K9me1 and H3K9me3 around the transcription termination site. RNAPII pausing defects were correlated with 5′R-loops accumulation, and transcriptional termination defects and read-throughs were correlated with 3′R-loops accumulation. Furthermore, we found driver genes with 5′R-loops and RNAPII pausing defects express significantly higher and genes with 3′R-loops and read-through transcription express significantly lower than genes without R-loops. These driver genes are enriched with chromosomal instability, Hippo–Merlin signaling Dysregulation, DNA damage response and TGF-β pathways, indicating R-loops accumulating at the 5′ end of genes play oncogenic roles, whereas at the 3′ end of genes play tumor-suppressive roles in tumorigenesis.

Predicting High Blood Pressure Using DNA Methylome-Based Machine Learning Models

DNA methylation modification plays a vital role in the pathophysiology of high blood pressure (BP). Herein, we applied three machine learning (ML) algorithms including deep learning (DL), support vector machine, and random forest for detecting high BP using DNA methylome data. Peripheral blood samples of 50 elderly individuals were collected three times at three visits for DNA methylome profiling. Participants who had a history of hypertension and/or current high BP measure were considered to have high BP. The whole dataset was randomly divided to conduct a nested five-group cross-validation for prediction performance. Data in each outer training set were independently normalized using a min–max scaler, reduced dimensionality using principal component analysis, then fed into three predictive algorithms. Of the three ML algorithms, DL achieved the best performance (AUPRC = 0.65, AUROC = 0.73, accuracy = 0.69, and F1-score = 0.73). To confirm the reliability of using DNA methylome as a biomarker for high BP, we constructed mixed-effects models and found that 61,694 methylation sites located in 15,523 intragenic regions and 16,754 intergenic regions were significantly associated with BP measures. Our proposed models pioneered the methodology of applying ML and DNA methylome data for early detection of high BP in clinical practices.

Pan-cancer methylome analysis for cancer diagnosis and classification of cancer cell of origin

The accurate and early diagnosis and classification of cancer origin from either tissue or liquid biopsy is crucial for selecting the appropriate treatment and reducing cancer-related mortality. Here, we established the CAncer Cell-of-Origin (CACO) methylation panel using the methylation data of the 28 types of cancer in The Cancer Genome Atlas (7950 patients and 707 normal controls) as well as healthy whole blood samples (95 subjects). We showed that the CACO methylation panel had high diagnostic potential with high sensitivity and specificity in the discovery (maximum AUC = 0.998) and validation (maximum AUC = 1.000) cohorts. Moreover, we confirmed that the CACO methylation panel could identify the cancer cell type of origin using the methylation profile from liquid as well as tissue biopsy, including primary, metastatic, and multiregional cancer samples and cancer of unknown primary, independent of the methylation analysis platform and specimen preparation method. Together, the CACO methylation panel can be a powerful tool for the classification and diagnosis of cancer.

Neural Network Aided Detection of Huntington Disease

Huntington Disease (HD) is a degenerative neurological disease that causes a significant impact on the quality of life of the patient and eventually death. In this paper we present an approach to create a biomarker using as an input DNA CpG methylation data to identify HD patients. DNA CpG methylation is a well-known epigenetic marker for disease state. Technological advances have made it possible to quickly analyze hundreds of thousands of CpGs. This large amount of information might introduce noise as potentially not all DNA CpG methylation levels will be related to the presence of the illness. In this paper, we were able to reduce the number of CpGs considered from hundreds of thousands to 237 using a non-linear approach. It will be shown that using only these 237 CpGs and non-linear techniques such as artificial neural networks makes it possible to accurately differentiate between control and HD patients. An underlying assumption in this paper is that there are no indications suggesting that the process is linear and therefore non-linear techniques, such as artificial neural networks, are a valid tool to analyze this complex disease. The proposed approach is able to accurately distinguish between control and HD patients using DNA CpG methylation data as an input and non-linear forecasting techniques. It should be noted that the dataset analyzed is relatively small. However, the results seem relatively consistent and the analysis can be repeated with larger data-sets as they become available.

The Role of Artificial Intelligence in Early Cancer Diagnosis

Improving the proportion of patients diagnosed with early-stage cancer is a key priority of the World Health Organisation. In many tumour groups, screening programmes have led to improvements in survival, but patient selection and risk stratification are key challenges. In addition, there are concerns about limited diagnostic workforces, particularly in light of the COVID-19 pandemic, placing a strain on pathology and radiology services. In this review, we discuss how artificial intelligence algorithms could assist clinicians in (1) screening asymptomatic patients at risk of cancer, (2) investigating and triaging symptomatic patients, and (3) more effectively diagnosing cancer recurrence. We provide an overview of the main artificial intelligence approaches, including historical models such as logistic regression, as well as deep learning and neural networks, and highlight their early diagnosis applications. Many data types are suitable for computational analysis, including electronic healthcare records, diagnostic images, pathology slides and peripheral blood, and we provide examples of how these data can be utilised to diagnose cancer. We also discuss the potential clinical implications for artificial intelligence algorithms, including an overview of models currently used in clinical practice. Finally, we discuss the potential limitations and pitfalls, including ethical concerns, resource demands, data security and reporting standards.

Recent Advances in Device Engineering and Computational Analysis for Characterization of Cell-Released Cancer Biomarkers

During cancer progression, tumors shed different biomarkers into the bloodstream, including circulating tumor cells (CTCs), extracellular vesicles (EVs), circulating cell-free DNA (cfDNA), and circulating tumor DNA (ctDNA). The analysis of these biomarkers in the blood, known as 'liquid biopsy' (LB), is a promising approach for early cancer detection and treatment monitoring, and more recently, as a means for cancer therapy. Previous reviews have discussed the role of CTCs and ctDNA in cancer progression; however, ctDNA and EVs are rapidly evolving with technological advancements and computational analysis and are the subject of enormous recent studies in cancer biomarkers. In this review, first, we introduce these cell-released cancer biomarkers and briefly discuss their clinical significance in cancer diagnosis and treatment monitoring. Second, we present conventional and novel approaches for the isolation, profiling, and characterization of these markers. We then investigate the mathematical and in silico models that are developed to investigate the function of ctDNA and EVs in cancer progression. We convey our views on what is needed to pave the way to translate the emerging technologies and models into the clinic and make the case that optimized next-generation techniques and models are needed to precisely evaluate the clinical relevance of these LB markers.

Genome-wide DNA methylation profiling and identification of potential pan-cancer and tumor-specific biomarkers

DNA methylation alterations have already been linked to cancer, and their usefulness for therapy and diagnosis has encouraged research into the human epigenome. Several biomarker studies have focused on identifying cancer types individually, yet common cancer and multi-cancer markers are still underexplored. We used The Cancer Genome Atlas (TCGA) to investigate genome-wide methylation profiles of 14 different cancer types and developed a three-step computational approach to select candidate biomarker CpG sites. In total, 1,991 pan-cancer and between 75 and 1,803 cancer-specific differentially methylated CpG sites were discovered. Differentially methylated blocks and regions were also discovered for the first time on such a large-scale. Through a three-step computational approach, a combination of four pan-cancer CpG markers was identified from these sites and externally validated (AUC = 0.90), maintaining comparable performance across tumor stages. Additionally, 20 tumor-specific CpG markers were identified and made up the final type-specific prediction model, which could accurately differentiate tumor types (AUC = 0.87-0.99). Our study highlights the power of the methylome as a rich source of cancer biomarkers, and the signatures we identified provide a new resource for understanding cancer mechanisms on the wider genomic scale with strong applicability in the context of new minimally invasive cancer detection assays.

Machine Learning in Epigenomics: Insights into Cancer Biology and Medicine

The recent deluge of genome-wide technologies for the mapping of the epigenome and resulting data in cancer samples has provided the opportunity for gaining insights into and understanding the roles of epigenetic processes in cancer. However, the complexity, high-dimensionality, sparsity, and noise associated with these data pose challenges for extensive integrative analyses. Machine Learning (ML) algorithms are particularly suited for epigenomic data analyses due to their flexibility and ability to learn underlying hidden structures. We will discuss four overlapping but distinct major categories under ML: dimensionality reduction, unsupervised methods, supervised methods, and deep learning (DL). We review the preferred use cases of these algorithms in analyses of cancer epigenomics data with the hope to provide an overview of how ML approaches can be used to explore fundamental questions on the roles of epigenome in cancer biology and medicine.

Deep Learning for Human Disease Detection, Subtype Classification, and Treatment Response Prediction Using Epigenomic Data

Deep learning (DL) is a distinct class of machine learning that has achieved first-class performance in many fields of study. For epigenomics, the application of DL to assist physicians and scientists in human disease-relevant prediction tasks has been relatively unexplored until very recently. In this article, we critically review published studies that employed DL models to predict disease detection, subtype classification, and treatment responses, using epigenomic data. A comprehensive search on PubMed, Scopus, Web of Science, Google Scholar, and arXiv.org was performed following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Among 1140 initially identified publications, we included 22 articles in our review. DNA methylation and RNA-sequencing data are most frequently used to train the predictive models. The reviewed models achieved a high accuracy ranged from 88.3% to 100.0% for disease detection tasks, from 69.5% to 97.8% for subtype classification tasks, and from 80.0% to 93.0% for treatment response prediction tasks. We generated a workflow to develop a predictive model that encompasses all steps from first defining human disease-related tasks to finally evaluating model performance. DL holds promise for transforming epigenomic big data into valuable knowledge that will enhance the development of translational epigenomics.

Deep Learning in Cancer Diagnosis and Prognosis Prediction: A Minireview on Challenges, Recent Trends, and Future Directions

Deep learning (DL) is a branch of machine learning and artificial intelligence that has been applied to many areas in different domains such as health care and drug design. Cancer prognosis estimates the ultimate fate of a cancer subject and provides survival estimation of the subjects. An accurate and timely diagnostic and prognostic decision will greatly benefit cancer subjects. DL has emerged as a technology of choice due to the availability of high computational resources. The main components in a standard computer-aided design (CAD) system are preprocessing, feature recognition, extraction and selection, categorization, and performance assessment. Reduction of costs associated with sequencing systems offers a myriad of opportunities for building precise models for cancer diagnosis and prognosis prediction. In this survey, we provided a summary of current works where DL has helped to determine the best models for the cancer diagnosis and prognosis prediction tasks. DL is a generic model requiring minimal data manipulations and achieves better results while working with enormous volumes of data. Aims are to scrutinize the influence of DL systems using histopathology images, present a summary of state-of-the-art DL methods, and give directions to future researchers to refine the existing methods.

Machine Learning in Oncology: What Should Clinicians Know?

The volume and complexity of scientific and clinical data in oncology have grown markedly over recent years, including but not limited to the realms of electronic health data, radiographic and histologic data, and genomics. This growth holds promise for a deeper understanding of malignancy and, accordingly, more personalized and effective oncologic care. Such goals require, however, the development of new methods to fully make use of the wealth of available data. Improvements in computer processing power and algorithm development have positioned machine learning, a branch of artificial intelligence, to play a prominent role in oncology research and practice. This review provides an overview of the basics of machine learning and highlights current progress and challenges in applying this technology to cancer diagnosis, prognosis, and treatment recommendations, including a discussion of current takeaways for clinicians.

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

Epigenetic 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.

Pan-Cancer Genome-Wide DNA Methylation Analyses Revealed That Hypermethylation Influences 3D Architecture and Gene Expression Dysregulation in HOXA Locus During Carcinogenesis of Cancers

DNA methylation dysregulation during carcinogenesis has been widely discussed in recent years. However, the pan-cancer DNA methylation biomarkers and corresponding biological mechanisms were seldom investigated. We identified differentially methylated sites and regions from 5,056 The Cancer Genome Atlas (TCGA) samples across 10 cancer types and then validated the findings using 48 manually annotated datasets consisting of 3,394 samples across nine cancer types from Gene Expression Omnibus (GEO). All samples’ DNA methylation profile was evaluated with Illumina 450K microarray to narrow down the batch effect. Nine regions were identified as commonly differentially methylated regions across cancers in TCGA and GEO cohorts. Among these regions, a DNA fragment consisting of ∼1,400 bp detected inside the HOXA locus instead of the boundary may relate to the co-expression attenuation of genes inside the locus during carcinogenesis. We further analyzed the 3D DNA interaction profile by the publicly accessible Hi-C database. Consistently, the HOXA locus in normal cell lines compromised isolated topological domains while merging to the domain nearby in cancer cell lines. In conclusion, the dysregulation of the HOXA locus provides a novel insight into pan-cancer carcinogenesis.

A New Epigenetic Model to Stratify Glioma Patients According to Their Immunosuppressive State

Gliomas are the most common primary neoplasm of the central nervous system. A promising frontier in the definition of glioma prognosis and treatment is represented by epigenetics. Furthermore, in this study, we developed a machine learning classification model based on epigenetic data (CpG probes) to separate patients according to their state of immunosuppression. We considered 573 cases of low-grade glioma (LGG) and glioblastoma (GBM) from The Cancer Genome Atlas (TCGA). First, from gene expression data, we derived a novel binary indicator to flag patients with a favorable immune state. Then, based on previous studies, we selected the genes related to the immune state of tumor microenvironment. After, we improved the selection with a data-driven procedure, based on Boruta. Finally, we tuned, trained, and evaluated both random forest and neural network classifiers on the resulting dataset. We found that a multi-layer perceptron network fed by the 338 probes selected by applying both expert choice and Boruta results in the best performance, achieving an out-of-sample accuracy of 82.8%, a Matthews correlation coefficient of 0.657, and an area under the ROC curve of 0.9. Based on the proposed model, we provided a method to stratify glioma patients according to their epigenomic state.

Artificial Intelligence and Machine Learning in Prostate Cancer Patient Management-Current Trends and Future Perspectives

Artificial intelligence (AI) is the field of computer science that aims to build smart devices performing tasks that currently require human intelligence. Through machine learning (ML), the deep learning (DL) model is teaching computers to learn by example, something that human beings are doing naturally. AI is revolutionizing healthcare. Digital pathology is becoming highly assisted by AI to help researchers in analyzing larger data sets and providing faster and more accurate diagnoses of prostate cancer lesions. When applied to diagnostic imaging, AI has shown excellent accuracy in the detection of prostate lesions as well as in the prediction of patient outcomes in terms of survival and treatment response. The enormous quantity of data coming from the prostate tumor genome requires fast, reliable and accurate computing power provided by machine learning algorithms. Radiotherapy is an essential part of the treatment of prostate cancer and it is often difficult to predict its toxicity for the patients. Artificial intelligence could have a future potential role in predicting how a patient will react to the therapy side effects. These technologies could provide doctors with better insights on how to plan radiotherapy treatment. The extension of the capabilities of surgical robots for more autonomous tasks will allow them to use information from the surgical field, recognize issues and implement the proper actions without the need for human intervention.

Epigenetic reprogramming during prostate cancer progression: A perspective from development

Conrad Waddington's theory of epigenetic landscape epitomize the process of cell fate and cellular decision-making during development. Wherein the epigenetic code maintains patterns of gene expression in pluripotent and differentiated cellular states during embryonic development and differentiation. Over the years disruption or reprogramming of the epigenetic landscape has been extensively studied in the course of cancer progression. Cellular dedifferentiation being a key hallmark of cancer allow us to take cues from the biological processes involved during development. Here, we discuss the role of epigenetic landscape and its modifiers in cell-fate determination, differentiation and prostate cancer progression. Lately, the emergence of RNA-modifications has also furthered our understanding of epigenetics in cancer. The overview of the epigenetic code regulating androgen signalling, and progression to aggressive neuroendocrine stage of PCa reinforces its gene regulatory functions during the development of prostate gland as well as cancer progression. Additionally, we also highlight the clinical implications of cancer cell epigenome, and discuss the recent advancements in the therapeutic strategies targeting the advanced stage disease.

Liquid biopsy in head and neck squamous cell carcinoma: circulating tumor cells, circulating tumor DNA, and exosomes

Introduction: Head and neck squamous cell carcinoma (HNSCC) is one of the most common cancers worldwide. Due to a lack of reliable markers, HNSCC patients are usually diagnosed at a late stage, which will lead to a worse outcome. Therefore, it is critical to improve the clinical management of cancer patients. Nowadays, the development of liquid biopsy enables a minimally invasive manner to extract molecular information from HNSCCs. Thus, this review aims to outline the clinical value of liquid biopsy in early detection, real-time monitoring, and prognostic evaluation of HNSCC. Areas covered: This comprehensive review focused on the characteristics as well as clinical applications of three liquid biopsy markers (CTCs, ctDNA, and exosomes) in HNSCC. What is more, it is promising to incorporate machine learning and 3D organoid models in the liquid biopsy of HNSCC. Expert opinion: Liquid biopsy provides a noninvasive technique to reflect the inter and intra-lesional heterogeneity through the detection of tumor cells or materials released from the primary and secondary tumors. Recently, some evolving technologies have the potential to combine with liquid biopsy to improve clinical management of HNSCC patients.

MBD2 Correlates with a Poor Prognosis and Tumor Progression in Renal Cell Carcinoma

Purpose

DNA methylation plays an important role in regulating gene expression. Methyl-CpG-binding domain (MBD) proteins recognize and bind to methylated DNA, which mediate gene silencing by the interaction with deacetylases and histone methyltransferases. MBD2 has been reported in various human cancers; however, its clinical implication and potential regulatory role in renal cell carcinoma (RCC) have not been elaborated.

Materials and Methods

In the study, we estimated the expression and prognostic value of MBD2 in RCC cell lines and tissues by Western blotting and immunohistochemistry. The associations of MBD2 expression and pathological characters and survival in RCC patients were performed using χ2 and Kaplan-Meier survival analysis, respectively. Univariate and multivariable Cox regression analyses suggested the independent predictors in RCC prognosis. The functional role of MBD2 in RCC progression was assessed by in vitro cell experiments. In addition, we identified the MBD2-mediated alterations of protein-related proliferation and EMT markers in RCC cells after MBD2 overexpression and knockdown.

Results

We found that the protein levels of MBD2 were upregulated in RCC cells and tissues. High MBD2 expression was related to TNM stage and predicted poorer survival in RCC. Enforced expression of MBD2 significantly promoted the proliferation, cycle progress, invasion and migration of RCC cells in vitro. However, downregulating MBD2 remarkably weakened the above cell functions. Mechanistically, the promotive effect of MBD2 overexpression may be regulated by its effects onp21, p53 and Cyclin D1 expression and EMT process.

Conclusion

These results indicated that MBD2confers an oncogenic function in the malignant progression of RCC. MBD2 could be served as a meaningful prognostic biomarker and a latent therapeutic target in RCC patients.

Innovating Computational Biology and Intelligent Medicine: ICIBM 2019 Special Issue

The International Association for Intelligent Biology and Medicine (IAIBM) is a nonprofit organization that promotes intelligent biology and medical science. It hosts an annual International Conference on Intelligent Biology and Medicine (ICIBM), which was established in 2012. The ICIBM 2019 was held from 9 to 11 June 2019 in Columbus, Ohio, USA. Out of the 105 original research manuscripts submitted to the conference, 18 were selected for publication in a Special Issue in Genes. The topics of the selected manuscripts cover a wide range of current topics in biomedical research including cancer informatics, transcriptomic, computational algorithms, visualization and tools, deep learning, and microbiome research. In this editorial, we briefly introduce each of the manuscripts and discuss their contribution to the advance of science and technology.

MethylNet: an automated and modular deep learning approach for DNA methylation analysis

BACKGROUND

DNA methylation (DNAm) is an epigenetic regulator of gene expression programs that can be altered by environmental exposures, aging, and in pathogenesis. Traditional analyses that associate DNAm alterations with phenotypes suffer from multiple hypothesis testing and multi-collinearity due to the high-dimensional, continuous, interacting and non-linear nature of the data. Deep learning analyses have shown much promise to study disease heterogeneity. DNAm deep learning approaches have not yet been formalized into user-friendly frameworks for execution, training, and interpreting models. Here, we describe MethylNet, a DNAm deep learning method that can construct embeddings, make predictions, generate new data, and uncover unknown heterogeneity with minimal user supervision.

RESULTS

The results of our experiments indicate that MethylNet can study cellular differences, grasp higher order information of cancer sub-types, estimate age and capture factors associated with smoking in concordance with known differences.

CONCLUSION

The ability of MethylNet to capture nonlinear interactions presents an opportunity for further study of unknown disease, cellular heterogeneity and aging processes.