Application of artificial neural networks to investigate one-carbon metabolism in Alzheimer's disease and healthy matched individuals

Mitochondrial One-Carbon Metabolism and Alzheimer's Disease

Mitochondrial one-carbon metabolism provides carbon units to several pathways, including nucleic acid synthesis, mitochondrial metabolism, amino acid metabolism, and methylation reactions. Late-onset Alzheimer's disease is the most common age-related neurodegenerative disease, characterised by impaired energy metabolism, and is potentially linked to mitochondrial bioenergetics. Here, we discuss the intersection between the molecular pathways linked to both mitochondrial one-carbon metabolism and Alzheimer's disease. We propose that enhancing one-carbon metabolism could promote the metabolic processes that help brain cells cope with Alzheimer's disease-related injuries. We also highlight potential therapeutic avenues to leverage one-carbon metabolism to delay Alzheimer's disease pathology.

Genetic variants of folate metabolism and the risk of multiple sclerosis

BACKGROUND AND AIMS

Multiple sclerosis (MS) is a chronic inflammatory disease of the central nervous system (CNS) of unknown cause. Alterations in one-carbon metabolism have impact in the pathophysiology by genetic susceptibility to MS and increased the risk of MS. The aim of this study was to investigate the contribution of the gene polymorphism on Methylenetetrahydrofolate Reductase (MTHFR), Methionine Synthase Reductase (MTRR), Methionine Synthase (MTR) enzymes and of the essential factors (homocysteine, Hcy; cysteine, Cys; and vitamin B12, VitB12) in folate metabolism.

METHODS

Eligible MS patients (n = 147) and health controls (n = 127) were participated. The gene polymorphisms were analyzed by Polymerase Chain Reaction-Restriction Fragment Length Polymorphism (PCR-RFLP) and the levels of plasma Hcy, Cys and VitB12 were measured by Enzyme Linked Immunuabsorbent Assay (ELISA).

RESULTS AND CONCLUSION

Our results showed that the levels of Hcy and VitB12 were lower and the levels of Cys were higher in MS compared to controls. The observation of high Cys values in all 3 gene polymorphisms suggests that the transsulfiration pathway of Hcy is directed towards Cys formation since the methionine synthesis pathway does not work. We could not find any association with all gene polymorphisms with the risk of MS. The T allele of MTHFR C677T and G allele of MTR A2756G are risk factors for serum Cys level on MS. As for MTR A2756G, serum vitB12 was observed in MS patients with G allele.

Artificial neural networks reveal sex differences in gene methylation, and connections between maternal risk factors and symptom severity in autism spectrum disorder

Aim and methods: Artificial neural networks were used to unravel connections among blood gene methylation levels, sex, maternal risk factors and symptom severity evaluated using the Autism Diagnostic Observation Schedule 2 (ADOS-2) score in 58 children with autism spectrum disorder (ASD). Results: Methylation levels of MECP2, HTR1A and OXTR genes were connected to females, and those of EN2, BCL2 and RELN genes to males. High gestational weight gain, lack of folic acid supplements, advanced maternal age, preterm birth, low birthweight and living in rural context were the best predictors of a high ADOS-2 score. Conclusion: Artificial neural networks revealed links among ASD maternal risk factors, symptom severity, gene methylation levels and sex differences in methylation that warrant further investigation in ASD.

The Application of Artificial Intelligence in the Genetic Study of Alzheimer's Disease

Alzheimer's disease (AD) is a neurodegenerative disease in which genetic factors contribute approximately 70% of etiological effects. Studies have found many significant genetic and environmental factors, but the pathogenesis of AD is still unclear. With the application of microarray and next-generation sequencing technologies, research using genetic data has shown explosive growth. In addition to conventional statistical methods for the processing of these data, artificial intelligence (AI) technology shows obvious advantages in analyzing such complex projects. This article first briefly reviews the application of AI technology in medicine and the current status of genetic research in AD. Then, a comprehensive review is focused on the application of AI in the genetic research of AD, including the diagnosis and prognosis of AD based on genetic data, the analysis of genetic variation, gene expression profile, gene-gene interaction in AD, and genetic analysis of AD based on a knowledge base. Although many studies have yielded some meaningful results, they are still in a preliminary stage. The main shortcomings include the limitations of the databases, failing to take advantage of AI to conduct a systematic biology analysis of multilevel databases, and lack of a theoretical framework for the analysis results. Finally, we outlook the direction of future development. It is crucial to develop high quality, comprehensive, large sample size, data sharing resources; a multi-level system biology AI analysis strategy is one of the development directions, and computational creativity may play a role in theory model building, verification, and designing new intervention protocols for AD.

Plasma Homocysteine and Polymorphisms of Genes Involved in Folate Metabolism Correlate with DNMT1 Gene Methylation Levels

DNA methyltransferase 1 (DNMT1) is responsible for the maintenance of DNA methylation patterns during cell division. Several human diseases are characterized by impaired DNMT1 gene methylation, but less is known about the factors that regulate DNMT1 promoter methylation levels. Dietary folates and related B-vitamins are essential micronutrients for DNA methylation processes, and we performed the present study to investigate the contribution of circulating folate, vitamin B12, homocysteine, and common polymorphisms in folate pathway genes to the DNMT1 gene methylation levels. We investigated DNMT1 gene methylation levels in peripheral blood DNA samples from 215 healthy individuals. All the DNA samples were genotyped for MTHFR 677C > T (rs1801133) and 1298A > C (rs1801131), MTRR 66A > G (rs1801394), MTR 2756A > G (rs1805087), SLC19A1 (RFC1) 80G > A (rs1051266), TYMS 28-bp tandem repeats (rs34743033) and 1494 6-bp insertion/deletion (indel) (rs34489327), DNMT3A -448A > G (rs1550117), and DNMT3B -149C > T (rs2424913) polymorphisms. Circulating homocysteine, folate, and vitamin B12 levels were available from 158 of the recruited individuals. We observed an inverse correlation between plasma homocysteine and DNMT1 methylation levels. Furthermore, both MTR rs1805087 and TYMS rs34743033 polymorphisms showed a statistically significant effect on DNMT1 methylation levels. The present study revealed several correlations between the folate metabolic pathway and DNMT1 promoter methylation that could be of relevance for those disorders characterized by altered DNA methylation.

Directional Relationship Between Vitamin D Status and Prediabetes: A New Approach from Artificial Neural Network in a Cohort of Workers with Overweight-Obesity

Objective: Despite the increasing literature on the association of diabetes with inflammation, cardiovascular risk, and vitamin D (25(OH)D) concentrations, strong evidence on the direction of causality among these factors is still lacking. This gap could be addressed by means of artificial neural networks (ANN) analysis.Methods: Retrospective observational study was carried out by means of an innovative data mining analysis-known as auto-contractive map (AutoCM)-and semantic mapping followed by Activation and Competition System on data of workers referring to an occupational-health outpatient clinic. Parameters analyzed included weight, height, waist circumference, body mass index (BMI), percentage of fat mass, glucose, insulin, glycated hemoglobin (HbA1c), creatinine, total cholesterol, low- and high-density lipoprotein cholesterol, triglycerides, uric acid, fibrinogen, homocysteine, C-reactive protein (CRP), diastolic and systolic blood pressure, and 25(OH)D.Results: The study included 309 workers. Of these, 23.6% were overweight, 40.5% were classified into the first class of obesity, 23.3% were in the second class, and 12.6% were in the third class (BMI > 40 kg/m ). All mean biochemical values were in normal range, except for total cholesterol, low- and high-density lipoprotein cholesterol, CRP, and 25(OH)D. HbA1c was between 39 and 46 mmol/mol in 51.78%. 25(OH)D levels were sufficient in only 12.6%. Highest inverse correlation for hyperglycemia onset was with BMI and waist circumference, suggesting a protective role of 25(OH)D against their increase. AutoCM processing and the semantic map evidenced direct association of 25(OH)D with high link strength (0.99) to low CRP levels and low high-density lipoprotein cholesterol levels. Low 25(OH)D led to changes in glucose, which affected metabolic syndrome biomarkers, first of which was homeostatic model assessment index and blood glucose, but not 25(OH)D.Conclusions: The use of ANN suggests a key role of 25(OH)D respect to all considered metabolic parameters in the development of diabetes and evidences a causation between low 25(OH)D and high glucose concentrations.

Association of Polymorphisms in Genes Involved in One-Carbon Metabolism with MTHFR Methylation Levels

Methylenetetrahydrofolate reductase (MTHFR) is a pivotal enzyme in the one-carbon metabolism, a metabolic pathway required for DNA synthesis and methylation reactions. MTHFR hypermethylation, resulting in reduced gene expression, can contribute to several human disorders, but little is still known about the factors that regulate MTHFR methylation levels. We performed the present study to investigate if common polymorphisms in one-carbon metabolism genes contribute to MTHFR methylation levels. MTHFR methylation was assessed in peripheral blood DNA samples from 206 healthy subjects with methylation-sensitive high-resolution melting (MS-HRM); genotyping was performed for MTHFR 677C>T (rs1801133) and 1298A>C (rs1801131), MTRR 66A>G (rs1801394), MTR 2756A>G (rs1805087), SLC19A1 (RFC1) 80G>A (rs1051266), TYMS 28-bp tandem repeats (rs34743033) and 1494 6-bp ins/del (rs34489327), DNMT3A -448A>G (rs1550117), and DNMT3B -149C>T (rs2424913) polymorphisms. We observed a statistically significant effect of the DNMT3B -149C>T polymorphism on mean MTHFR methylation levels, and particularly CT and TT carriers showed increased methylation levels than CC carriers. The present study revealed an association between a functional polymorphism of DNMT3B and MTHFR methylation levels that could be of relevance in those disorders, such as inborn defects, metabolic disorders and cancer, that have been linked to impaired DNA methylation.

The Methylenetetrahydrofolate Reductase C677T Polymorphism and Risk for Late-Onset Alzheimer's disease: Further Evidence in an Italian Multicenter Study

BACKGROUND

A functional polymorphism in the methylenetetrahydrofolate reductase (MTHFR) gene, namely C677T (rs1801133), results in increased Hcy levels and has been associated with risk of late-onset Alzheimer's disease (LOAD). Many investigators reported association between rs1801133 and LOAD risk in Asian populations and in carriers of the apolipoprotein E (APOE) ɛ4 allele, but recent meta-analyses suggest a contribution also in other populations, including Caucasians and/or northern Africans.

OBJECTIVE

To further address this issue, we performed a relatively large case-control study, including 581 LOAD patients and 468 matched controls of Italian origin. APOE data were available for a subgroup of almost 600 subjects.

METHODS

Genotyping for rs1801133 was performed with PCR-RFLP techniques.

RESULTS

In the total population, the MTHFR 677T allele (OR = 1.20; 95% CI = 1.01-1.43) and carriers of the MTHFR 677T allele (CT+TT versus CC: OR = 1.34; 95% CI = 1.03-1.73) resulted in increased LOAD risk. Similarly, in APOEɛ4 carriers, we observed an increased frequency of MTHFR 677CT carriers (CT versus CC: OR = 2.82; 95% CI = 1.25-6.32). Very interestingly, also in non-APOEɛ4 carriers, both MTHFR 677T allele (OR = 1.38; 95% CI = 1.03-1.85) and MTHFR 677TT genotype (OR = 2.08; 95% CI = 1.11-3.90) were associated with LOAD. All these associations survived after corrections for age, gender, and multiple testing.

CONCLUSIONS

The present results suggest that the MTHFR C677T polymorphism is likely a LOAD risk factor in our cohort, either in APOEɛ4 or in non-APOEɛ4 carriers.

Boosting backpropagation algorithm by stimulus-sampling: Application in computer-aided medical diagnosis

Neural networks (NNs), in general, and multi-layer perceptron (MLP), in particular, represent one of the most efficient classifiers among the machine learning (ML) algorithms. Inspired by the stimulus-sampling paradigm, it is plausible to assume that the association of stimuli with the neurons in the output layer of a MLP can increase its performance. The stimulus-sampling process is assumed memoryless (Markovian), in the sense that the choice of a particular stimulus at a certain step, conditioned by the whole prior evolution of the learning process, depends only on the network's answer at the previous step. This paper proposes a novel learning technique, by enhancing the standard backpropagation algorithm performance with the aid of a stimulus-sampling procedure applied to the output neurons. The network uses the observable behavior that varies throughout the training process by stimulating the correct answers through corresponding rewards/penalties assigned to the output neurons. The proposed model has been applied in computer-aided medical diagnosis using five real-life breast cancer, colon cancer, diabetes, thyroid, and fetal heartbeat databases. The statistical comparison to well-established ML algorithms proved beyond doubt its efficiency and robustness.

Artificial Neural Networks Link One-Carbon Metabolism to Gene-Promoter Methylation in Alzheimer's Disease

BACKGROUND

There is increasing interest in DNA methylation studies in Alzheimer's disease (AD), but little is still known concerning the relationship between gene-promoter methylation and circulating biomarkers of one-carbon metabolism in patients.

OBJECTIVE

To detect the connections among circulating folate, homocysteine (hcy) and vitamin B12 levels and promoter methylation levels of PSEN1, BACE1, DNMT1, DNMT3A, DNMT3B, and MTHFR genes in blood DNA.

METHODS

We applied a data mining system called Auto Contractive Map to an existing database of 100 AD and 100 control individuals.

RESULTS

Low vitamin B12 was linked to the AD condition, to low folates, and to high hcy. Low PSEN1 methylation was linked to low folate levels as well as to low promoter methylation of BACE1 and DNMTs genes. Low hcy was linked to controls, to high folates and vitamin B12, as well as to high methylation levels of most of the studied genes.

CONCLUSIONS

The present pilot study suggests that promoter methylation levels of the studied genes are linked to circulating levels of folates, hcy, and vitamin B12.

Folic Acid Alters Methylation Profile of JAK-STAT and Long-Term Depression Signaling Pathways in Alzheimer's Disease Models

Dementia has emerged as a major societal issue because of the worldwide aging population and the absence of any effective treatment. DNA methylation is an epigenetic mechanism that evidently plays a role in Alzheimer's disease (AD). Folate acts through one-carbon metabolism to support the methylation of multiple substrates including DNA. We aimed to test the hypothesis that folic acid supplementation alters DNA methylation profiles in AD models. Mouse Neuro-2a cells expressing human APP695 (N2a-APP cells) were incubated with folic acid (2.8-20 μmol/L). AD transgenic mice were fed either folate-deficient or control diets and gavaged daily with water or folic acid (600 μg/kg). Gene methylation profiles were determined by methylated DNA immunoprecipitation-DNA microarray (MeDIP-chip). Differentially methylated regions (DMRs) were determined by Quantitative Differentially Methylated Regions analysis, and differentially methylated genes (DMGs) carrying at least three DMRs were selected for pathway analysis. Folic acid up-regulated DNA methylation levels in N2a-APP cells and AD transgenic mouse brains. Functional network analysis of folic acid-induced DMGs in these AD models revealed subnetworks composed of 24 focus genes in the janus kinase-signal transducer and activator of transcription (JAK-STAT) signaling pathway and 12 focus genes in the long-term depression (LTD) signaling pathway. In conclusion, these results revealed a role for folic acid in the JAK-STAT and LTD signaling pathways which may be relevant to AD pathogenesis. This novel finding may stimulate reinvestigation of folic acid supplementation as a prophylactic or therapeutic treatment for AD.

Application of Genetic Algorithm to Predict Optimal Sowing Region and Timing for Kentucky Bluegrass in China

Temperature is a predominant environmental factor affecting grass germination and distribution. Various thermal-germination models for prediction of grass seed germination have been reported, in which the relationship between temperature and germination were defined with kernel functions, such as quadratic or quintic function. However, their prediction accuracies warrant further improvements. The purpose of this study is to evaluate the relative prediction accuracies of genetic algorithm (GA) models, which are automatically parameterized with observed germination data. The seeds of five P. pratensis (Kentucky bluegrass, KB) cultivars were germinated under 36 day/night temperature regimes ranging from 5/5 to 40/40 °C with 5 °C increments. Results showed that optimal germination percentages of all five tested KB cultivars were observed under a fluctuating temperature regime of 20/25 °C. Meanwhile, the constant temperature regimes (e.g., 5/5, 10/10, 15/15 °C, etc.) suppressed the germination of all five cultivars. Furthermore, the back propagation artificial neural network (BP-ANN) algorithm was integrated to optimize temperature-germination response models from these observed germination data. It was found that integrations of GA-BP-ANN (back propagation aided genetic algorithm artificial neural network) significantly reduced the Root Mean Square Error (RMSE) values from 0.21~0.23 to 0.02~0.09. In an effort to provide a more reliable prediction of optimum sowing time for the tested KB cultivars in various regions in the country, the optimized GA-BP-ANN models were applied to map spatial and temporal germination percentages of blue grass cultivars in China. Our results demonstrate that the GA-BP-ANN model is a convenient and reliable option for constructing thermal-germination response models since it automates model parameterization and has excellent prediction accuracy.

Polymorphic variation in the epigenetic gene DNMT3B modulates the environmental impact on cognitive ability: a twin study

BACKGROUND

Though cognitive abilities in adulthood are largely influenced by individual genetic background, they have also been shown to be importantly influenced by environmental factors. Some of these influences are mediated by epigenetic mechanisms. Accordingly, polymorphic variants in the epigenetic gene DNMT3B have been linked to neurocognitive performance. Since monozygotic (MZ) twins may show larger or smaller intrapair phenotypic differences depending on whether their genetic background is more or less sensitive to environmental factors, a twin design was implemented to determine if particular polymorphisms in the DNMT3B gene may be linked to a better (worse) response to enriched (deprived) environmental factors.

METHODS

Applying the variability gene methodology in a sample of 54 healthy MZ twin pairs (108 individuals) with no lifetime history of psychopathology, two DNMT3B polymorphisms were analyzed in relation to their intrapair differences for either intellectual quotient (IQ) or working memory performance.

RESULTS

MZ twin pairs with the CC genotype for rs406193 SNP showed statistically significant larger intrapair differences in IQ than CT pairs.

CONCLUSIONS

Results suggest that DNMT3B polymorphisms may explain variability in the IQ response to either enriched or impoverished environmental conditions. Accordingly, the applied methodology is shown as a potentially valuable tool for determining genetic markers of cognitive plasticity. Further research is needed to confirm this specific result and to expand on other putative genetic markers of environmental sensitivity.

Application of artificial neural networks to link genetic and environmental factors to DNA methylation in colorectal cancer

AIMS

We applied artificial neural networks (ANNs) to understand the connections among polymorphisms of genes involved in folate metabolism, clinico-pathological features and promoter methylation levels of MLH1, APC, CDKN2A(INK4A), MGMT and RASSF1A in 83 sporadic colorectal cancer (CRC) tissues, and to link dietary and lifestyle factors with gene promoter methylation.

MATERIALS & METHODS

Promoter methylation was assessed by means of methylation-sensitive high-resolution melting and genotyping by PCR-RFLP technique. Data were analyzed with the Auto Contractive Map, a special kind of ANN able to define the strength of the association of each variable with all the others and to visually show the map of the main connections.

RESULTS

We observed a strong connection between the low methylation levels of the five CRC genes and the MTR 2756AA genotype. Several other connections were revealed, including those between dietary and lifestyle factors and the methylation levels of CRC genes.

CONCLUSION

ANNs revealed the complexity of the interconnections among factors linked to DNA methylation in CRC.

A pilot study evaluating the contribution of SLC19A1 (RFC-1) 80G>a polymorphism to Alzheimer's disease in Italian Caucasians

Alzheimer's disease (AD) is the most common neurodegenerative disorder and the primary form of dementia in the elderly. Polymorphisms of genes involved in folate metabolism have been frequently suggested as risk factors for sporadic AD. A common c.80G>A polymorphism (rs1051266) in the gene coding for the reduced folate carrier (SLC19A1 gene, commonly known as RFC-1 gene) was investigated as AD risk factor in Asian populations, yielding conflicting results. We screened a Caucasian population of Italian origin composed of 192 sporadic AD patients and 186 healthy matched controls, for the presence of the RFC-1 c.80G>A polymorphism, and searched for correlation with circulating levels of folate, homocysteine, and vitamin B12. No difference in the distribution of allele and genotype frequencies was observed between AD patients and controls. No correlation was observed among the genotypes generated by the RFC-1 c.80G>A polymorphism and circulating levels of folate, homocysteine, and vitamin B12 either in the whole cohort of subjects or after stratification into clinical subtypes. Present results do not support a role for the RFC-1 c.80G>A polymorphism as independent risk factor for sporadic AD in Italian Caucasians.

Plasma metabolite profiles of Alzheimer's disease and mild cognitive impairment

Previous studies have demonstrated altered metabolites in samples of Alzheimer's disease (AD) patients. However, the sample size from many of them is relatively small and the metabolites are relatively limited. Here we applied a comprehensive platform using ultraperformance liquid chromatography-time-of-flight mass spectrometry and gas chromatography-time-of-flight mass spectrometry to analyze plasma samples from AD patients, amnestic mild cognitive impairment (aMCI) patients, and normal controls. A biomarker panel consisting of six plasma metabolites (arachidonic acid, N,N-dimethylglycine, thymine, glutamine, glutamic acid, and cytidine) was identified to discriminate AD patients from normal control. Another panel of five plasma metabolites (thymine, arachidonic acid, 2-aminoadipic acid, N,N-dimethylglycine, and 5,8-tetradecadienoic acid) was able to differentiate aMCI patients from control subjects. Both biomarker panels had good agreements with clinical diagnosis. The 2 panels of metabolite markers were all involved in fatty acid metabolism, one-carbon metabolism, amino acid metabolism, and nucleic acid metabolism. Additionally, no altered metabolites were found among the patients at different stages, as well as among those on anticholinesterase medication and those without anticholinesterase medication. These findings provide a comprehensive global plasma metabolite profiling and may contribute to making early diagnosis as well as understanding the pathogenic mechanism of AD and aMCI.