Artificial Intelligence for epigenetics: towards personalized medicine

2020 ◽  
Vol 27 ◽  
Author(s):  
Giulia De Riso ◽  
Sergio Cocozza
Keyword(s):  
Biological Sciences ◽  
Artificial Intelligence ◽  
Personalized Medicine ◽  
Molecular Mechanisms ◽  
Genomic Sequence ◽  
Health Care Interventions ◽  
Genome Wide ◽  
Genetic And Environmental Factors ◽  
Opening Up ◽  
Omic Data

: Epigenetics is a field of biological sciences focused on the study of reversible, heritable changes in gene function not due to modifications of the genomic sequence. These changes are the result of a complex cross-talk between several molecular mechanisms, that is in turn orchestrated by genetic and environmental factors. The epigenetic profile captures the unique regulatory landscape and the exposure to environmental stimuli of an individual. It thus constitutes a valuable reservoir of information for personalized medicine, which is aimed at customizing health-care interventions based on the unique characteristics of each individual. Nowadays, the complex milieu of epigenomic marks can be studied at the genome-wide level thanks to massive, highthroughput technologies. This new experimental approach is opening up new and interesting knowledge perspectives. However, the analysis of these complex omic data requires to face important analytic issues. Artificial Intelligence, and in particular Machine Learning, are emerging as powerful resources to decipher epigenomic data. In this review, we will first describe the most used ML approaches in epigenomics. We then will recapitulate some of the recent applications of ML to epigenomic analysis. Finally, we will provide some examples of how the ML approach to epigenetic data can be useful for personalized medicine.

scholarly journals Artificial intelligence, physiological genomics, and precision medicine

2018 ◽  
Vol 50 (4) ◽  
pp. 237-243 ◽  
Author(s):  
Anna Marie Williams ◽  
Yong Liu ◽  
Kevin R. Regner ◽  
Fabrice Jotterand ◽  
Pengyuan Liu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Big Data ◽  
Precision Medicine ◽  
Ethical Issues ◽  
Genomic Sequence ◽  
Sequence Data ◽  
Common Diseases ◽  
Powerful Approach ◽  
Genetic And Environmental Factors ◽  
Analytical Approaches

Big data are a major driver in the development of precision medicine. Efficient analysis methods are needed to transform big data into clinically-actionable knowledge. To accomplish this, many researchers are turning toward machine learning (ML), an approach of artificial intelligence (AI) that utilizes modern algorithms to give computers the ability to learn. Much of the effort to advance ML for precision medicine has been focused on the development and implementation of algorithms and the generation of ever larger quantities of genomic sequence data and electronic health records. However, relevance and accuracy of the data are as important as quantity of data in the advancement of ML for precision medicine. For common diseases, physiological genomic readouts in disease-applicable tissues may be an effective surrogate to measure the effect of genetic and environmental factors and their interactions that underlie disease development and progression. Disease-applicable tissue may be difficult to obtain, but there are important exceptions such as kidney needle biopsy specimens. As AI continues to advance, new analytical approaches, including those that go beyond data correlation, need to be developed and ethical issues of AI need to be addressed. Physiological genomic readouts in disease-relevant tissues, combined with advanced AI, can be a powerful approach for precision medicine for common diseases.

Artificial Intelligence-Driven Designer Drug Combinations: From Drug Development to Personalized Medicine

2018 ◽  
Vol 24 (1) ◽  
pp. 124-125
Author(s):  
Masturah Bte Mohd Abdul Rashid ◽  
Edward Kai-Hua Chow
Keyword(s):  
Artificial Intelligence ◽  
Personalized Medicine ◽  
Translational Medicine ◽  
Molecular Mechanisms ◽  
Disease Model ◽  
Drug Combinations ◽  
Designer Drug ◽  
Great Promise ◽  
Specific Patient ◽  
And Personalized Medicine

Artificial intelligence holds great promise in transforming how drugs are designed and patients are treated. In a study recently published in Science Translational Medicine, a unique artificial intelligence platform makes efficient use of small experimental datasets to design new drug combinations as well as identify the best drug combinations for specific patient samples. This quadratic phenotypic optimization platform (QPOP) does not rely on previous assumptions of molecular mechanisms of disease, but rather uses system-specific experimental data to determine the best drug combinations for a specific disease model or a patient sample. In this commentary, we explore how QPOP was applied toward multiple myeloma in the study. We also discuss how this study demonstrates the potential for applications of QPOP toward improving therapeutic regimen design and personalized medicine.

The Role of the Endothelium in Premature Atherosclerosis: Molecular Mechanisms

2020 ◽  
Vol 27 (7) ◽  
pp. 1041-1051 ◽  
Author(s):  
Michael Spartalis ◽  
Eleftherios Spartalis ◽  
Antonios Athanasiou ◽  
Stavroula A. Paschou ◽  
Christos Kontogiannis ◽  
...  
Keyword(s):  
Molecular Mechanisms ◽  
Low Density Lipoprotein ◽  
Critical Role ◽  
Density Lipoprotein ◽  
Number Of Genes ◽  
Causes Of Mortality ◽  
Artery Disease ◽  
Genetic And Environmental Factors ◽  
Made In

Atherosclerotic disease is still one of the leading causes of mortality. Atherosclerosis is a complex progressive and systematic artery disease that involves the intima of the large and middle artery vessels. The inflammation has a key role in the pathophysiological process of the disease and the infiltration of the intima from monocytes, macrophages and T-lymphocytes combined with endothelial dysfunction and accumulated oxidized low-density lipoprotein (LDL) are the main findings of atherogenesis. The development of atherosclerosis involves multiple genetic and environmental factors. Although a large number of genes, genetic polymorphisms, and susceptible loci have been identified in chromosomal regions associated with atherosclerosis, it is the epigenetic process that regulates the chromosomal organization and genetic expression that plays a critical role in the pathogenesis of atherosclerosis. Despite the positive progress made in understanding the pathogenesis of atherosclerosis, the knowledge about the disease remains scarce.

scholarly journals Genetic analysis of amyotrophic lateral sclerosis identifies contributing pathways and cell types

2021 ◽  
Vol 7 (3) ◽  
pp. eabd9036
Author(s):  
Sara Saez-Atienzar ◽  
Sara Bandres-Ciga ◽  
Rebekah G. Langston ◽  
Jonggeol J. Kim ◽  
Shing Wan Choi ◽  
...  
Keyword(s):  
Amyotrophic Lateral Sclerosis ◽  
Membrane Trafficking ◽  
Molecular Mechanisms ◽  
Cell Types ◽  
Polygenic Risk Score ◽  
Genome Wide ◽  
Genome Wide Data ◽  
Data Driven Approach ◽  
Single Nucleus ◽  
Lateral Sclerosis

Despite the considerable progress in unraveling the genetic causes of amyotrophic lateral sclerosis (ALS), we do not fully understand the molecular mechanisms underlying the disease. We analyzed genome-wide data involving 78,500 individuals using a polygenic risk score approach to identify the biological pathways and cell types involved in ALS. This data-driven approach identified multiple aspects of the biology underlying the disease that resolved into broader themes, namely, neuron projection morphogenesis, membrane trafficking, and signal transduction mediated by ribonucleotides. We also found that genomic risk in ALS maps consistently to GABAergic interneurons and oligodendrocytes, as confirmed in human single-nucleus RNA-seq data. Using two-sample Mendelian randomization, we nominated six differentially expressed genes (ATG16L2, ACSL5, MAP1LC3A, MAPKAPK3, PLXNB2, and SCFD1) within the significant pathways as relevant to ALS. We conclude that the disparate genetic etiologies of this fatal neurological disease converge on a smaller number of final common pathways and cell types.

scholarly journals Genome-Wide Mapping of Histone H3 Lysine 4 Trimethylation (H3K4me3) and Its Involvement in Fatty Acid Biosynthesis in Sunflower Developing Seeds

Plants ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 706
Author(s):  
Antonio J. Moreno-Pérez ◽  
Raquel Martins-Noguerol ◽  
Cristina DeAndrés-Gil ◽  
Mónica Venegas-Calerón ◽  
Rosario Sánchez ◽  
...  
Keyword(s):  
Fatty Acid ◽  
Chromatin Remodeling ◽  
Molecular Mechanisms ◽  
Acid Metabolism ◽  
Fatty Acid Biosynthesis ◽  
Acid Synthesis ◽  
Sunflower Seeds ◽  
Acid Biosynthesis ◽  
Functional Regions ◽  
Genome Wide

Histone modifications are of paramount importance during plant development. Investigating chromatin remodeling in developing oilseeds sheds light on the molecular mechanisms controlling fatty acid metabolism and facilitates the identification of new functional regions in oil crop genomes. The present study characterizes the epigenetic modifications H3K4me3 in relationship with the expression of fatty acid-related genes and transcription factors in developing sunflower seeds. Two master transcriptional regulators identified in this analysis, VIV1 (homologous to Arabidopsis ABI3) and FUS3, cooperate in the regulation of WRINKLED 1, a transcriptional factor regulating glycolysis, and fatty acid synthesis in developing oilseeds.

scholarly journals Genome-wide association study suggests that variation at the RCOR1 locus is associated with tinnitus in UK Biobank

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Helena R. R. Wells ◽  
Fatin N. Zainul Abidin ◽  
Maxim B. Freidin ◽  
Frances M. K. Williams ◽  
Sally J. Dawson
Keyword(s):  
Association Study ◽  
Molecular Mechanisms ◽  
Genome Wide Association Study ◽  
Genome Wide Association ◽  
Uk Biobank ◽  
Significance Threshold ◽  
Genome Wide ◽  
Final Sample ◽  
Close Proximity ◽  
Repressor Complex

AbstractTinnitus is a prevalent condition in which perception of sound occurs without an external stimulus. It is often associated with pre-existing hearing loss or noise-induced damage to the auditory system. In some individuals it occurs frequently or even continuously and leads to considerable distress and difficulty sleeping. There is little knowledge of the molecular mechanisms involved in tinnitus which has hindered the development of treatments. Evidence suggests that tinnitus has a heritable component although previous genetic studies have not established specific risk factors. From a total of 172,608 UK Biobank participants who answered questions on tinnitus we performed a case–control genome-wide association study for self-reported tinnitus. Final sample size used in association analysis was N = 91,424. Three variants in close proximity to the RCOR1 gene reached genome wide significance: rs4906228 (p = 1.7E−08), rs4900545 (p = 1.8E−08) and 14:103042287_CT_C (p = 3.50E−08). RCOR1 encodes REST Corepressor 1, a component of a co-repressor complex involved in repressing neuronal gene expression in non-neuronal cells. Eleven other independent genetic loci reached a suggestive significance threshold of p < 1E−06.

scholarly journals Cerebrospinal fluid metabolomics identifies 19 brain-related phenotype associations

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Daniel J. Panyard ◽  
Kyeong Mo Kim ◽  
Burcu F. Darst ◽  
Yuetiva K. Deming ◽  
Xiaoyuan Zhong ◽  
...  
Keyword(s):  
Cerebrospinal Fluid ◽  
Drug Targets ◽  
Large Scale ◽  
Prediction Models ◽  
Genome Wide Association ◽  
Large Samples ◽  
Genome Wide ◽  
Metabolomic Data ◽  
Related Phenotype ◽  
Omic Data

AbstractThe study of metabolomics and disease has enabled the discovery of new risk factors, diagnostic markers, and drug targets. For neurological and psychiatric phenotypes, the cerebrospinal fluid (CSF) is of particular importance. However, the CSF metabolome is difficult to study on a large scale due to the relative complexity of the procedure needed to collect the fluid. Here, we present a metabolome-wide association study (MWAS), which uses genetic and metabolomic data to impute metabolites into large samples with genome-wide association summary statistics. We conduct a metabolome-wide, genome-wide association analysis with 338 CSF metabolites, identifying 16 genotype-metabolite associations (metabolite quantitative trait loci, or mQTLs). We then build prediction models for all available CSF metabolites and test for associations with 27 neurological and psychiatric phenotypes, identifying 19 significant CSF metabolite-phenotype associations. Our results demonstrate the feasibility of MWAS to study omic data in scarce sample types.

scholarly journals Developmental cannabidiol exposure increases anxiety and modifies genome-wide brain DNA methylation in adult female mice

2021 ◽  
Vol 13 (1) ◽  
Author(s):  
Nicole M. Wanner ◽  
Mathia Colwell ◽  
Chelsea Drown ◽  
Christopher Faulk
Keyword(s):  
Dna Methylation ◽  
Molecular Mechanisms ◽  
Coat Color ◽  
Brain Regions ◽  
Functional Enrichment ◽  
Positive Effects ◽  
Genome Wide ◽  
Nulliparous Female ◽  
The Impact ◽  
The Brain

Abstract Background Use of cannabidiol (CBD), the primary non-psychoactive compound found in cannabis, has recently risen dramatically, while relatively little is known about the underlying molecular mechanisms of its effects. Previous work indicates that direct CBD exposure strongly impacts the brain, with anxiolytic, antidepressant, antipsychotic, and other effects being observed in animal and human studies. The epigenome, particularly DNA methylation, is responsive to environmental input and can direct persistent patterns of gene regulation impacting phenotype. Epigenetic perturbation is particularly impactful during embryogenesis, when exogenous exposures can disrupt critical resetting of epigenetic marks and impart phenotypic effects lasting into adulthood. The impact of prenatal CBD exposure has not been evaluated; however, studies using the psychomimetic cannabinoid Δ9-tetrahydrocannabinol (THC) have identified detrimental effects on psychological outcomes in developmentally exposed adult offspring. We hypothesized that developmental CBD exposure would have similar negative effects on behavior mediated in part by the epigenome. Nulliparous female wild-type Agouti viable yellow (Avy) mice were exposed to 20 mg/kg CBD or vehicle daily from two weeks prior to mating through gestation and lactation. Coat color shifts, a readout of DNA methylation at the Agouti locus in this strain, were measured in F1 Avy/a offspring. Young adult F1 a/a offspring were then subjected to tests of working spatial memory and anxiety/compulsive behavior. Reduced-representation bisulfite sequencing was performed on both F0 and F1 cerebral cortex and F1 hippocampus to identify genome-wide changes in DNA methylation for direct and developmental exposure, respectively. Results F1 offspring exposed to CBD during development exhibited increased anxiety and improved memory behavior in a sex-specific manner. Further, while no significant coat color shift was observed in Avy/a offspring, thousands of differentially methylated loci (DMLs) were identified in both brain regions with functional enrichment for neurogenesis, substance use phenotypes, and other psychologically relevant terms. Conclusions These findings demonstrate for the first time that despite positive effects of direct exposure, developmental CBD is associated with mixed behavioral outcomes and perturbation of the brain epigenome.

scholarly journals Stable DNMT3L overexpression in SH-SY5Y neurons recreates a facet of the genome-wide Down syndrome DNA methylation signature

2021 ◽  
Vol 14 (1) ◽  
Author(s):  
Benjamin I. Laufer ◽  
J. Antonio Gomez ◽  
Julia M. Jianu ◽  
Janine M. LaSalle
Keyword(s):  
Dna Methylation ◽  
Down Syndrome ◽  
Neuronal Differentiation ◽  
Molecular Mechanisms ◽  
Cpg Island ◽  
Differential Methylation ◽  
Chromosome 21 ◽  
Pairwise Comparisons ◽  
Genome Wide ◽  
A Genome

Abstract Background Down syndrome (DS) is characterized by a genome-wide profile of differential DNA methylation that is skewed towards hypermethylation in most tissues, including brain, and includes pan-tissue differential methylation. The molecular mechanisms involve the overexpression of genes related to DNA methylation on chromosome 21. Here, we stably overexpressed the chromosome 21 gene DNA methyltransferase 3L (DNMT3L) in the human SH-SY5Y neuroblastoma cell line and assayed DNA methylation at over 26 million CpGs by whole genome bisulfite sequencing (WGBS) at three different developmental phases (undifferentiated, differentiating, and differentiated). Results DNMT3L overexpression resulted in global CpG and CpG island hypermethylation as well as thousands of differentially methylated regions (DMRs). The DNMT3L DMRs were skewed towards hypermethylation and mapped to genes involved in neurodevelopment, cellular signaling, and gene regulation. Consensus DNMT3L DMRs showed that cell lines clustered by genotype and then differentiation phase, demonstrating sets of common genes affected across neuronal differentiation. The hypermethylated DNMT3L DMRs from all pairwise comparisons were enriched for regions of bivalent chromatin marked by H3K4me3 as well as differentially methylated sites from previous DS studies of diverse tissues. In contrast, the hypomethylated DNMT3L DMRs from all pairwise comparisons displayed a tissue-specific profile enriched for regions of heterochromatin marked by H3K9me3 during embryonic development. Conclusions Taken together, these results support a mechanism whereby regions of bivalent chromatin that lose H3K4me3 during neuronal differentiation are targeted by excess DNMT3L and become hypermethylated. Overall, these findings demonstrate that DNMT3L overexpression during neurodevelopment recreates a facet of the genome-wide DS DNA methylation signature by targeting known genes and gene clusters that display pan-tissue differential methylation in DS.

Sign in / Sign up

Export Citation Format

Share Document