Differential DNA methylation of steatosis and non-alcoholic fatty liver disease in adolescence.

BACKGROUND AND AIMS: Epigenetic modifications are associated with hepatic fat accumulation and non-alcoholic fatty liver disease (NAFLD). However, few epigenetic modifications directly implicated in such processes have been identified during adolescence, a critical developmental window where physiological changes could influence future disease trajectory. To investigate the association between DNA methylation and NAFLD in adolescence, we undertook discovery and validation of novel methylation marks, alongside replication of previously reported marks. APPROACH AND RESULTS: We performed a DNA methylation epigenome-wide association study (EWAS) on DNA from whole blood from 707 Raine Study adolescents phenotyped for steatosis score and NAFLD by ultrasound at age 17. Next, we performed pyrosequencing validation of loci within the most 100 strongly associated differentially methylated CpG sites (dmCpGs) for which ≥ 2 probes per gene remained significant across four statistical models with a nominal p value < 0.007. EWAS identified dmCpGs related to three genes (ANK1, MIR10a, PTPRN2) that met our criteria for pyrosequencing. Of the dmCpGs and surrounding loci that were pyrosequenced (ANK1 n = 6, MIR10a n = 7, PTPRN2 n = 3), three dmCpGs in ANK1 and two in MIR10a were significantly associated with NAFLD in adolescence. After adjustment for waist circumference only dmCpGs in ANK1 remained significant. These ANK1 CpGs were also associated with γ-glutamyl transferase and alanine aminotransferase concentrations. Three of twenty-two differentially methylated dmCpGs previously associated with adult NAFLD were associated with NAFLD in adolescence (all adjusted p < 2.3 × 10-3). CONCLUSIONS: We identified novel DNA methylation loci associated with NAFLD and serum liver biochemistry markers during adolescence, implicating putative dmCpG/gene regulatory pathways and providing insights for future mechanistic studies.

Adiposity associated DNA methylation signatures in adolescents are related to leptin and perinatal factors.

Epigenetics links perinatal influences with later obesity. We identifed differentially methylated CpG (dmCpG) loci measured at 17 years associated with concurrent adiposity measures and examined whether these were associated with hsCRP, adipokines, and early life environmental factors. Genome-wide DNA methylation from 1192 Raine Study participants at 17 years, identified 29 dmCpGs (Bonferroni corrected p < 1.06E-07) associated with body mass index (BMI), 10 with waist circumference (WC) and 9 with subcutaneous fat thickness. DmCpGs within Ras Association (RalGDS/AF-6), Pleckstrin Homology Domains 1 (RAPH1), Musashi RNA-Binding Protein 2 (MSI2), and solute carrier family 25 member 10 (SLC25A10) are associated with both BMI and WC. Validation by pyrosequencing confirmed these associations and showed that MSI2 , SLC25A10 , and RAPH1 methylation was positively associated with serum leptin. These were  also associated with the early environment; MSI2 methylation (ß = 0.81, p = 0.0004) was associated with pregnancy maternal smoking, SLC25A10 (CpG2 ß = 0.12, p = 0.002) with pre- and early pregnancy BMI, and RAPH1 (ß = -1.49, p = 0.036) with gestational weight gain. Adjusting for perinatal factors, methylation of the dmCpGs within MSI2, RAPH1, and SLC25A10 independently predicted BMI, accounting for 24% of variance. MSI2 methylation was additionally associated with BMI over time (17 years old ß = 0.026, p = 0.0025; 20 years old ß = 0.027, p = 0.0029) and between generations (mother ß = 0.044, p = 7.5e-04). Overall findings suggest that DNA methylation in MSI2, RAPH1, and SLC25A10 in blood may be robust markers, mediating through early life factors.

Machine learning and clinical epigenetics: a review of challenges for diagnosis and classification.

BACKGROUND: Machine learning is a sub-field of artificial intelligence, which utilises large data sets to make predictions for future events. Although most algorithms used in machine learning were developed as far back as the 1950s, the advent of big data in combination with dramatically increased computing power has spurred renewed interest in this technology over the last two decades. MAIN BODY: Within the medical field, machine learning is promising in the development of assistive clinical tools for detection of e.g. cancers and prediction of disease. Recent advances in deep learning technologies, a sub-discipline of machine learning that requires less user input but more data and processing power, has provided even greater promise in assisting physicians to achieve accurate diagnoses. Within the fields of genetics and its sub-field epigenetics, both prime examples of complex data, machine learning methods are on the rise, as the field of personalised medicine is aiming for treatment of the individual based on their genetic and epigenetic profiles. CONCLUSION: We now have an ever-growing number of reported epigenetic alterations in disease, and this offers a chance to increase sensitivity and specificity of future diagnostics and therapies. Currently, there are limited studies using machine learning applied to epigenetics. They pertain to a wide variety of disease states and have used mostly supervised machine learning methods.