Assessing Gene-Gene Interactions in Pharmacogenomics

Inference of social cognition in schizophrenia patients with neurocognitive domains and neurocognitive tests using automated machine learning

AIM

It has been suggested that single neurocognitive domain or neurocognitive test can be used to determine the overall cognitive function in schizophrenia using machine learning algorithms. It is unknown whether social cognition in schizophrenia patients can be estimated with machine learning based on neurocognitive domains or neurocognitive tests.

METHODS

To predict social cognition in schizophrenia, we applied an automated machine learning (AutoML) framework resulting from the analysis of predictive factors such as six neurocognitive domain scores and nine neurocognitive test scores of 380 schizophrenia patients in the Taiwanese population. Four clinical parameters (i.e., age, gender, subgroup, and education) were also used as predictive factors. We utilized an AutoML framework called Tree-based Pipeline Optimization Tool (TPOT) to generate predictive pipelines automatically.

RESULTS

The analysis revealed that all neurocognitive domains and tests except the reasoning and problem solving domain/test showed significant associations with social cognition. In addition, a TPOT-generated pipeline can best predict social cognition in schizophrenia using seven predictive factors, including five neurocognitive domains (i.e., speed of processing, sustained attention, working memory, verbal learning and memory, and visual learning and memory) and two clinical parameters (i.e., age and gender). This predictive pipeline consists of machine learning algorithms such as function transformers, an approximate feature map, independent component analysis, and linear regression.

CONCLUSION

The study indicates that an AutoML framework such as TPOT may provide a promising way to produce truly effective machine learning pipelines for predicting social cognition in schizophrenia using neurocognitive domains and/or neurocognitive tests.

CETP and APOA2 polymorphisms are associated with weight loss and healthy eating behavior changes in response to digital lifestyle modifications

Response to digital healthcare lifestyle modifications is highly divergent. This study aimed to examine the association between single nucleotide polymorphism (SNP) genotypes and clinical efficacy of a digital healthcare lifestyle modification. We genotyped 97 obesity-related SNPs from 45 participants aged 18-39 years, who underwent lifestyle modification via digital cognitive behavioral therapy for obesity for 8 weeks. Anthropometric, eating behavior phenotypes, and psychological measures were analyzed before and after the intervention to identify their clinical efficacy. CETP (rs9939224) SNP significantly predict "super-responders" with greater body mass index (BMI) reduction (p = 0.028; GG - 2.91%, GT - 9.94%), while APOA2 (rs5082) appeared to have some potential for predicting "poor-responders" with lower BMI reduction (p = 0.005; AA - 6.17%, AG + 2.05%, and GG + 5.11%). These SNPs was also associated with significant differences in eating behavior changes, healthy diet proportions, health diet diversity, emotional and restrained eating behavior changes. Furthermore, classification using gene-gene interactions between rs9939224 and rs5082 significantly predicted the best response, with a greater decrease in BMI (p = 0.038; - 11.45% for the best response group (CEPT GT/TT × APOA2 AA) vs. + 2.62% for the worst response group (CEPT GG × APOA2 AG/GG)). CETP and APOA2 SNPs can be used as candidate markers to predict the efficacy of digital healthcare lifestyle modifications based on genotype-based precision medicine.Trial registration: NCT03465306, ClinicalTrials.gov. Registered March, 2018.

Machine Learning and Pharmacogenomics at the Time of Precision Psychiatry

Traditional medicine and biomedical sciences are reaching a turning point because of the constantly growing impact and volume of Big Data. Machine Learning (ML) techniques and related algorithms play a central role as diagnostic, prognostic, and decision-making tools in this field. Another promising area becoming part of everyday clinical practice is personalized therapy and pharmacogenomics. Applying ML to pharmacogenomics opens new frontiers to tailored therapeutical strategies to help clinicians choose drugs with the best response and fewer side effects, operating with genetic information and combining it with the clinical profile. This systematic review aims to draw up the state-of-the-art ML applied to pharmacogenomics in psychiatry. Our research yielded fourteen papers; most were published in the last three years. The sample comprises 9,180 patients diagnosed with mood disorders, psychoses, or autism spectrum disorders. Prediction of drug response and prediction of side effects are the most frequently considered domains with the supervised ML technique, which first requires training and then testing. The random forest is the most used algorithm; it comprises several decision trees, reduces the training set's overfitting, and makes precise predictions. ML proved effective and reliable, especially when genetic and biodemographic information were integrated into the algorithm. Even though ML and pharmacogenomics are not part of everyday clinical practice yet, they will gain a unique role in the next future in improving personalized treatments in psychiatry.

Systematic Review of Pharmacogenetics of ABC and SLC Transporter Genes in Acute Myeloid Leukemia

Antineoplastic uptake by blast cells in acute myeloid leukemia (AML) could be influenced by influx and efflux transporters, especially solute carriers (SLCs) and ATP-binding cassette family (ABC) pumps. Genetic variability in SLC and ABC could produce interindividual differences in clinical outcomes. A systematic review was performed to evaluate the influence of SLC and ABC polymorphisms and their combinations on efficacy and safety in AML cohorts. Anthracycline intake was especially influenced by SLCO1B1 polymorphisms, associated with lower hepatic uptake, showing higher survival rates and toxicity in AML studies. The variant alleles of ABCB1 were related to anthracycline intracellular accumulation, increasing complete remission, survival and toxicity. Similar findings have been suggested with ABCC1 and ABCG2 polymorphisms. Polymorphisms of SLC29A1, responsible for cytarabine uptake, demonstrated significant associations with survival and response in Asian populations. Promising results were observed with SLC and ABC combinations regarding anthracycline toxicities. Knowledge of the role of transporter pharmacogenetics could explain the differences observed in drug disposition in the blast. Further studies including novel targeted therapies should be performed to determine the influence of genetic variability to individualize chemotherapy schemes.

A bagging ensemble machine learning framework to predict overall cognitive function of schizophrenia patients with cognitive domains and tests

BACKGROUND

It has been indicated that the interplay between functional outcomes and cognitive functions in schizophrenia is arbitrated by clinical symptoms, where cognitive functions are evaluated by cognitive domains and cognitive tests.

METHODS

To determine which single cognitive domain or test can best predict the overall cognitive function of schizophrenia, we established a bagging ensemble framework resulting from the analysis of factors such as 7 cognitive domain scores and 11 cognitive test scores of 302 schizophrenia patients in the Taiwanese population. We compared our bagging ensemble framework with other state-of-the-art algorithms such as multilayer feedforward neural networks, linear regression, support vector machine, and random forests.

RESULTS

The analysis revealed that among the 7 cognitive domains, the speed of processing domain can best predict the overall cognitive function in schizophrenia using our bagging ensemble framework. In addition, among the 11 cognitive tests, the visual learning and memory test can best predict the overall cognitive function in schizophrenia using our bagging ensemble framework. Finally, among the 7 cognitive domains and 11 cognitive tests, the speed of processing domain can best predict the overall cognitive function in schizophrenia using our bagging ensemble framework.

CONCLUSION

The study implicates that the bagging ensemble framework may provide an applicable approach to develop tools for forecasting overall cognitive function in schizophrenia using cognitive domains and/or cognitive tests.

Logistic ridge regression to predict bipolar disorder using mRNA expression levels in the N-methyl-D-aspartate receptor genes

BACKGROUND

It is hypothesized that demographic variables and mRNA expression levels in the N-methyl-D-aspartate receptor (NMDAR) genes can be employed as potential biomarkers to predict bipolar disorder using artificial intelligence and machine learning approaches.

METHODS

To determine bipolar status, we established a logistic ridge regression model resulting from the analysis of age, gender, and mRNA expression levels in 7 NMDAR genes in the blood of 51 bipolar patients and 139 unrelated healthy individuals in the Taiwanese population. The NMDAR genes encompasses COMT, GCAT, NRG1, PSAT1, SHMT2, SLC1A4, and SRR. We also compared our approach with various state-of-the-art algorithms such as support vector machine and C4.5 decision tree.

RESULTS

The analysis revealed that the mRNA expression levels of COMT, GCAT, NRG1, PSAT1, SHMT2, SLC1A4, and SRR were associated with bipolar disorder. Moreover, the logistic ridge regression model (area under the receiver operating characteristic curve = 0.922) performed maximally among predictive models to infer the complicated relationship between bipolar disorder and biomarkers. Additionally, the results for the age- and gender-matched cohort were similar to those of the unmatched cohort.

LIMITATIONS

The cross-sectional study design limited the predictive value.

CONCLUSION

This is the first study demonstrating that the mRNA expression levels in the NMDAR genes may be altered in patients with bipolar disorder, thereby supporting the NMDAR hypothesis of bipolar disorder. The study also indicates that the mRNA expression levels in the NMDAR genes could serve as potential biomarkers to distinguish bipolar patients from healthy controls using artificial intelligence and machine learning approaches.

Machine Learning and Deep Learning for the Pharmacogenomics of Antidepressant Treatments

A growing body of evidence now proposes that machine learning and deep learning techniques can serve as a vital foundation for the pharmacogenomics of antidepressant treatments in patients with major depressive disorder (MDD). In this review, we focus on the latest developments for pharmacogenomics research using machine learning and deep learning approaches together with neuroimaging and multi-omics data. First, we review relevant pharmacogenomics studies that leverage numerous machine learning and deep learning techniques to determine treatment prediction and potential biomarkers for antidepressant treatments in MDD. In addition, we depict some neuroimaging pharmacogenomics studies that utilize various machine learning approaches to predict antidepressant treatment outcomes in MDD based on the integration of research on pharmacogenomics and neuroimaging. Moreover, we summarize the limitations in regard to the past pharmacogenomics studies of antidepressant treatments in MDD. Finally, we outline a discussion of challenges and directions for future research. In light of latest advancements in neuroimaging and multi-omics, various genomic variants and biomarkers associated with antidepressant treatments in MDD are being identified in pharmacogenomics research by employing machine learning and deep learning algorithms.

Prediction of functional outcomes of schizophrenia with genetic biomarkers using a bagging ensemble machine learning method with feature selection

Genetic variants such as single nucleotide polymorphisms (SNPs) have been suggested as potential molecular biomarkers to predict the functional outcome of psychiatric disorders. To assess the schizophrenia’ functional outcomes such as Quality of Life Scale (QLS) and the Global Assessment of Functioning (GAF), we leveraged a bagging ensemble machine learning method with a feature selection algorithm resulting from the analysis of 11 SNPs (AKT1 rs1130233, COMT rs4680, DISC1 rs821616, DRD3 rs6280, G72 rs1421292, G72 rs2391191, 5-HT2A rs6311, MET rs2237717, MET rs41735, MET rs42336, and TPH2 rs4570625) of 302 schizophrenia patients in the Taiwanese population. We compared our bagging ensemble machine learning algorithm with other state-of-the-art models such as linear regression, support vector machine, multilayer feedforward neural networks, and random forests. The analysis reported that the bagging ensemble algorithm with feature selection outperformed other predictive algorithms to forecast the QLS functional outcome of schizophrenia by using the G72 rs2391191 and MET rs2237717 SNPs. Furthermore, the bagging ensemble algorithm with feature selection surpassed other predictive algorithms to forecast the GAF functional outcome of schizophrenia by using the AKT1 rs1130233 SNP. The study suggests that the bagging ensemble machine learning algorithm with feature selection might present an applicable approach to provide software tools for forecasting the functional outcomes of schizophrenia using molecular biomarkers.

Applying a bagging ensemble machine learning approach to predict functional outcome of schizophrenia with clinical symptoms and cognitive functions

It has been suggested that the relationship between cognitive function and functional outcome in schizophrenia is mediated by clinical symptoms, while functional outcome is assessed by the Quality of Life Scale (QLS) and the Global Assessment of Functioning (GAF) Scale. To determine the outcome assessed by QLS and GAF, we established a bagging ensemble framework with a feature selection algorithm resulting from the analysis of factors such as 3 clinical symptom scales and 11 cognitive function scores of 302 patients with schizophrenia in the Taiwanese population. We compared our bagging ensemble framework with other state-of-the-art algorithms such as multilayer feedforward neural networks, support vector machine, linear regression, and random forests. The analysis revealed that the bagging ensemble model with feature selection performed best among predictive models in predicting the QLS functional outcome by using 20-item Scale for the Assessment of Negative Symptoms (SANS20) and 17-item Hamilton Depression Rating Scale (HAMD17). Moreover, to predict the GAF outcome, the bagging ensemble model with feature selection performed best among predictive models by using SANS20 and the Positive and Negative Syndrome Scale-Positive (PANSS-Positive) subscale. The study indicates that there are synergistic effects between negative (SANS20) and depressive (HAMD17) symptoms as well as between negative and positive (PANSS-Positive) symptoms in influencing functional outcome of schizophrenia using the bagging ensemble framework with feature selection.

Impact of modular mitochondrial epistatic interactions on the evolution of human subpopulations

Investigation of human mitochondrial (mt) genome variation has been shown to provide insights to the human history and natural selection. By analyzing 24,167 human mt-genome samples, collected for five continents, we have developed a co-mutation network model to investigate characteristic human evolutionary patterns. The analysis highlighted richer co-mutating regions of the mt-genome, suggesting the presence of epistasis. Specifically, a large portion of COX genes was found to co-mutate in Asian and American populations, whereas, in African, European, and Oceanic populations, there was greater co-mutation bias in hypervariable regions. Interestingly, this study demonstrated hierarchical modularity as a crucial agent for these co-mutation networks. More profoundly, our ancestry-based co-mutation module analyses showed that mutations cluster preferentially in known mitochondrial haplogroups. Contemporary human mt-genome nucleotides most closely resembled the ancestral state, and very few of them were found to be ancestral-variants. Overall, these results demonstrated that subpopulation-based biases may favor mitochondrial gene specific epistasis.

Pharmacogenomic Biomarkers and Their Applications in Psychiatry

Realizing the promise of precision medicine in psychiatry is a laudable and beneficial endeavor, since it should markedly reduce morbidity and mortality and, in effect, alleviate the economic and social burden of psychiatric disorders. This review aims to summarize important issues on pharmacogenomics in psychiatry that have laid the foundation towards personalized pharmacotherapy and, in a broader sense, precision medicine. We present major pharmacogenomic biomarkers and their applications in a variety of psychiatric disorders, such as depression, attention-deficit/hyperactivity disorder (ADHD), narcolepsy, schizophrenia, and bipolar disorder. In addition, we extend the scope into epilepsy, since antiepileptic drugs are widely used to treat psychiatric disorders, although epilepsy is conventionally considered to be a neurological disorder.

Impact of combinations of single-nucleotide polymorphisms of anthracycline transporter genes upon the efficacy and toxicity of induction chemotherapy in acute myeloid leukemia

Anthracycline uptake could be affected by influx and efflux transporters in acute myeloid leukemia (AML). Combinations of single-nucleotide polymorphisms (SNPs) of wild-type genotype of influx transporters (SLC22A16, SLCO1B1) and homozygous variant genotypes of ABC polymorphisms (ABCB1, ABCC1, ABCC2, ABCG2) were evaluated in 225 adult de novo AML patients. No differences in complete remission were reported, but higher induction death was observed with combinations of SLCO1B1 rs4149056 and ABCB1 (triple variant haplotype, rs1128503), previously associated with ABCB1 and SLCO1B1 SNPs. Several combinations of SLCO1B1 and SLC22A16 with ABCB1 SNPs were associated with higher toxicities, including nephrotoxicity and hepatotoxicity, neutropenia, previously related to ABCB1, and a novel correlation with mucositis. Combination of SLC22A16 rs714368 and ABCG2 rs2231142 was related to cardiac toxicity, reproducing previous correlations with ABCG2. This study shows the impact of transporter polymorphisms in AML chemotherapy safety. Further prospective studies with larger populations are needed to validate these associations.

The use of technology in the subcategorisation of osteoarthritis: a Delphi study approach

Objective

This UK-wide OATech Network + consensus study utilised a Delphi approach to discern levels of awareness across an expert panel regarding the role of existing and novel technologies in osteoarthritis research. To direct future cross-disciplinary research it aimed to identify which could be adopted to subcategorise patients with osteoarthritis (OA).

Design

An online questionnaire was formulated based on technologies which might aid OA research and subcategorisation. During a two-day face-to-face meeting concordance of expert opinion was established with surveys (23 questions) before, during and at the end of the meeting (Rounds 1, 2 and 3, respectively). Experts spoke on current evidence for imaging, genomics, epigenomics, proteomics, metabolomics, biomarkers, activity monitoring, clinical engineering and machine learning relating to subcategorisation. For each round of voting, ≥80% votes led to consensus and ≤20% to exclusion of a statement.

Results

Panel members were unanimous that a combination of novel technological advances have potential to improve OA diagnostics and treatment through subcategorisation, agreeing in Rounds 1 and 2 that epigenetics, genetics, MRI, proteomics, wet biomarkers and machine learning could aid subcategorisation. Expert presentations changed participants' opinions on the value of metabolomics, activity monitoring and clinical engineering, all reaching consensus in Round 2. X-rays lost consensus between Rounds 1 and 2; clinical X-rays reached consensus in Round 3.

Conclusion

Consensus identified that 9 of the 11 technologies should be targeted towards OA subcategorisation to address existing OA research technology and knowledge gaps. These novel, rapidly evolving technologies are recommended as a focus for emergent, cross-disciplinary osteoarthritis research programmes.

An Ensemble Approach to Predict Schizophrenia Using Protein Data in the N-methyl-D-Aspartate Receptor (NMDAR) and Tryptophan Catabolic Pathways

In the wake of recent advances in artificial intelligence research, precision psychiatry using machine learning techniques represents a new paradigm. The D-amino acid oxidase (DAO) protein and its interaction partner, the D-amino acid oxidase activator (DAOA, also known as G72) protein, have been implicated as two key proteins in the N-methyl-D-aspartate receptor (NMDAR) pathway for schizophrenia. Another potential biomarker in regard to the etiology of schizophrenia is melatonin in the tryptophan catabolic pathway. To develop an ensemble boosting framework with random undersampling for determining disease status of schizophrenia, we established a prediction approach resulting from the analysis of genomic and demographic variables such as DAO levels, G72 levels, melatonin levels, age, and gender of 355 schizophrenia patients and 86 unrelated healthy individuals in the Taiwanese population. We compared our ensemble boosting framework with other state-of-the-art algorithms such as support vector machine, multilayer feedforward neural networks, logistic regression, random forests, naive Bayes, and C4.5 decision tree. The analysis revealed that the ensemble boosting model with random undersampling [area under the receiver operating characteristic curve (AUC) = 0.9242 ± 0.0652; sensitivity = 0.8580 ± 0.0770; specificity = 0.8594 ± 0.0760] performed maximally among predictive models to infer the complicated relationship between schizophrenia disease status and biomarkers. In addition, we identified a causal link between DAO and G72 protein levels in influencing schizophrenia disease status. The study indicates that the ensemble boosting framework with random undersampling may provide a suitable method to establish a tool for distinguishing schizophrenia patients from healthy controls using molecules in the NMDAR and tryptophan catabolic pathways.

Fibrate pharmacogenomics: expanding past the genome

Fibrates are a medication class prescribed for decades as 'broad-spectrum' lipid-modifying agents used to lower blood triglyceride levels and raise high-density lipoprotein cholesterol levels. Such lipid changes are associated with a decrease in cardiovascular disease, and fibrates are commonly used to reduce risk of dangerous cardiovascular outcomes. As with most drugs, it is well established that response to fibrate treatment is variable, and this variation is heritable. This has motivated the investigation of pharmacogenomic determinants of response, and multiple studies have discovered a number of genes associated with fibrate response. Similar to other complex traits, the interrogation of single nucleotide polymorphisms using candidate gene or genome-wide approaches has not revealed a substantial portion of response variation. However, recent innovations in technological platforms and advances in statistical methodologies are revolutionizing the use and integration of other 'omes' in pharmacogenomics studies. Here, we detail successes, challenges, and recent advances in fibrate pharmacogenomics.

Precision Psychiatry Applications with Pharmacogenomics: Artificial Intelligence and Machine Learning Approaches

A growing body of evidence now suggests that precision psychiatry, an interdisciplinary field of psychiatry, precision medicine, and pharmacogenomics, serves as an indispensable foundation of medical practices by offering the accurate medication with the accurate dose at the accurate time to patients with psychiatric disorders. In light of the latest advancements in artificial intelligence and machine learning techniques, numerous biomarkers and genetic loci associated with psychiatric diseases and relevant treatments are being discovered in precision psychiatry research by employing neuroimaging and multi-omics. In this review, we focus on the latest developments for precision psychiatry research using artificial intelligence and machine learning approaches, such as deep learning and neural network algorithms, together with multi-omics and neuroimaging data. Firstly, we review precision psychiatry and pharmacogenomics studies that leverage various artificial intelligence and machine learning techniques to assess treatment prediction, prognosis prediction, diagnosis prediction, and the detection of potential biomarkers. In addition, we describe potential biomarkers and genetic loci that have been discovered to be associated with psychiatric diseases and relevant treatments. Moreover, we outline the limitations in regard to the previous precision psychiatry and pharmacogenomics studies. Finally, we present a discussion of directions and challenges for future research.

Class Balanced Multifactor Dimensionality Reduction to Detect Gene-Gene Interactions

Detecting gene-gene interactions in single-nucleotide polymorphism data is vital for understanding disease susceptibility. However, existing approaches may be limited by the sample size in case-control studies. Herein, we propose a balance approach for the multifactor dimensionality reduction (BMDR) method to increase the accuracy of estimates of the prediction error rate in small samples. BMDR explicitly selects the best model by evaluating the average of prediction error rates over k-fold cross-validation without cross-validation consistency selection. In this study, we used several epistatic models with and without marginal effects under different parameter settings (heritability and minor allele frequencies) to evaluate the performance of existing approaches. Using simulated data sets, BMDR successfully detected gene-gene interactions, particularly for data sets with small sample sizes. A large data set was obtained from the Wellcome Trust Case Control Consortium, and results indicated that BMDR could effectively detect significant gene-gene interactions.

Pharmacogenomics And Hypertension: Current Insights

Hypertension is a multifactorial disease that affects approximately one billion subjects worldwide and is a major risk factor associated with cardiovascular events, including coronary heart disease and cerebrovascular accidents. Therefore, adequate blood pressure control is important to prevent these events, reducing premature mortality and disability. However, only one third of patients have the effective control of blood pressure, despite several classes of antihypertensive drugs available. These disappointing outcomes may be at least in part explained by interpatient variability in drug response due to genetic polymorphisms. To address the effects of genetic polymorphisms on blood pressure responses to the antihypertensive drug classes, studies have applied candidate genes and genome wide approaches. More recently, a third approach that considers gene-gene interactions has also been applied in hypertension pharmacogenomics. In this article, we carried out a comprehensive review of recent findings on the pharmacogenomics of antihypertensive drugs, including diuretics, β-blockers, angiotensin-converting enzyme inhibitors and angiotensin II receptor blockers, and calcium channel blockers. We also discuss the limitations and inconsistences that have been found in hypertension pharmacogenomics and the challenges to implement this valuable approach in clinical practice.

Epigenetics and Depression: An Update

OBJECTIVE

Depression is associated with various environmental risk factors such as stress, childhood maltreatment experiences, and stressful life events. Current approaches to assess the pathophysiology of depression, such as epigenetics and gene-environment (GxE) interactions, have been widely leveraged to determine plausible markers, genes, and variants for the risk of developing depression.

METHODS

We focus on the most recent developments for genomic research in epigenetics and GxE interactions.

RESULTS

In this review, we first survey a variety of association studies regarding depression with consideration of GxE interactions. We then illustrate evidence of epigenetic mechanisms such as DNA methylation, microRNAs, and histone modifications to influence depression in terms of animal models and human studies. Finally, we highlight their limitations and future directions.

CONCLUSION

In light of emerging technologies in artificial intelligence and machine learning, future research in epigenetics and GxE interactions promises to achieve novel innovations that may lead to disease prevention and future potential therapeutic treatments for depression.

Developing Predictive or Prognostic Biomarkers for Charged Particle Radiotherapy

The response to radiotherapy can vary greatly among individuals, even though advances in technology allow for the highly localized placement of therapeutic doses of radiation to a tumor. This variability in patient response to radiation is biologically driven, but the individuality of tumor and healthy tissue biology are not used to create individual treatment plans. Biomarkers of radiosensitivity, whether intrinsic or from hypoxia, would move radiation oncology from precision medicine to precise, personalized medicine. Charged particle radiotherapy allows for even greater dose conformity, but the biological advantages of charged particle radiotherapy have not yet been cultivated. The development of biomarkers that would drive biologically based clinical trials, identify patients for whom charged particles are most appropriate, or aid in particle-selection strategies could be envisioned with appropriate biomarkers. Initially, biomarkers for low-linear energy transfer (LET) radiation responses should be tested against charged particles. Biomarkers of tumor radioresistance to low-LET radiations could be used to identify patients for whom the enhanced relative biological effectiveness (RBE) of charged particles would be more effective compared with low-LET radiations and those for whom specific DNA-repair inhibitors, in combination with charged particles, may also be appropriate. Furthermore, heavy charged particles can overcome the radioresistance of hypoxic tumors when used at the appropriate LET. Biomarkers for hypoxia could identify hypoxic tumors and, in combination with imaging, define hypoxic regions of a tumor for specific ion selection. Moreover, because of the enhanced RBE for charged particles, the risk for adverse healthy tissue effects may be greater, even though charged particles have greater tumor conformality. There are many validated healthy-tissue biomarkers available to test against charged particle exposures. Lastly, newer biological techniques, as well as newer bioinformatic and computational methods, are rapidly changing the landscape for biomarker identification, validation, and clinical trial design.

Pharmacogenetics of oral antidiabetic therapy

Type 2 diabetes prevalence is still on the rise worldwide. Antidiabetic drugs are widely prescribed to patients with Type 2 diabetes. Most patients start with metformin which is mostly well tolerated. However, a high percentage of patients fail to achieve glycemic control. The effectiveness of metformin as well as most other antidiabetic drugs depends among other factors on interindividual genetic differences that are up to now ignored in the treatment of Type 2 diabetes. Interestingly, many genes influencing the effectiveness of antidiabetic drugs are Type 2 diabetes risk genes making matters worse. Here, we shed light on these interindividual genetic differences.

Effects of circadian clock genes and environmental factors on cognitive aging in old adults in a Taiwanese population

Previous animal studies have indicated associations between circadian clock genes and cognitive impairment . In this study, we assessed whether 11 circadian clockgenes are associated with cognitive aging independently and/or through complex interactions in an old Taiwanese population. We also analyzed the interactions between environmental factors and these genes in influencing cognitive aging. A total of 634 Taiwanese subjects aged over 60 years from the Taiwan Biobank were analyzed. Mini-Mental State Examinations (MMSE) were administered to all subjects, and MMSE scores were used to evaluate cognitive function. Our data showed associations between cognitive aging and single nucleotide polymorphisms (SNPs) in 4 key circadian clock genes, CLOCK rs3749473 (p = 0.0017), NPAS2 rs17655330 (p = 0.0013), RORA rs13329238 (p = 0.0009), and RORB rs10781247 (p = 7.9 × 10⁻⁵). We also found that interactions between CLOCK rs3749473, NPAS2 rs17655330, RORA rs13329238, and RORB rs10781247 affected cognitive aging (p = 0.007). Finally, we investigated the influence of interactions between CLOCK rs3749473, RORA rs13329238, and RORB rs10781247 with environmental factors such as alcohol consumption, smoking status, physical activity, and social support on cognitive aging (p = 0.002 ∼ 0.01). Our study indicates that circadian clock genes such as the CLOCK, NPAS2, RORA, and RORB genes may contribute to the risk of cognitive aging independently as well as through gene-gene and gene-environment interactions.

Association and interaction effects of Alzheimer's disease-associated genes and lifestyle on cognitive aging in older adults in a Taiwanese population

Genome-wide association studies and meta-analyses implicated that increased risk of developing Alzheimers diseases (AD) has been associated with the ABCA7, APOE, BIN1, CASS4, CD2AP, CD33, CELF1, CLU, CR1, DSG2, EPHA1, FERMT2, HLA-DRB1, HLA-DRB4, INPP5D, MEF2C, MS4A4A, MS4A4E, MS4A6E, NME8, PICALM, PLD3, PTK2B, RIN3, SLC24A4, SORL1, and ZCWPW1 genes. In this study, we assessed whether single nucleotide polymorphisms (SNPs) within these 27 AD-associatedgenes are linked with cognitive aging independently and/or through complex interactions in an older Taiwanese population. We also analyzed the interactions between lifestyle and these genes in influencing cognitive aging. A total of 634 Taiwanese subjects aged over 60 years from the Taiwan Biobank were analyzed. Mini-Mental State Examination (MMSE) scores were performed for all subjects to evaluate cognitive functions. Out of the 588 SNPs tested in this study, only the association between CASS4-rs911159 and cognitive aging persisted significantly (P = 2.2 × 10⁻⁵) after Bonferroni correction. Our data also showed a nominal association of cognitive aging with the SNPs in six more key AD-associated genes, including EPHA1-rs10952552, FERMT2-rs4901317, MEF2C-rs9293506, PLD3-rs11672825, RIN3-rs1885747, and SLC24A4-rs67063100 (P = 0.0018∼0.0097). Additionally, we found the interactions among CASS4-rs911159, EPHA-rs10952552, FERMT2-rs4901317, MEF2C-rs9293506, or SLC24A4-rs67063100 on cognitive aging (P = 0.004∼0.035). Moreover, our analysis suggested the interactions of SLC24A4-rs67063100 or MEF2C-rs9293506 with lifestyle such as alcohol consumption, smoking status, physical activity, or social support on cognitive aging (P = 0.008∼0.041). Our study indicates that the AD-associated genes may contribute to the risk of cognitive aging independently as well as through gene-gene and gene-lifestyle interactions.

A Deep Learning Approach for Predicting Antidepressant Response in Major Depression Using Clinical and Genetic Biomarkers

In the wake of recent advances in scientific research, personalized medicine using deep learning techniques represents a new paradigm. In this work, our goal was to establish deep learning models which distinguish responders from non-responders, and also to predict possible antidepressant treatment outcomes in major depressive disorder (MDD). To uncover relationships between the responsiveness of antidepressant treatment and biomarkers, we developed a deep learning prediction approach resulting from the analysis of genetic and clinical factors such as single nucleotide polymorphisms (SNPs), age, sex, baseline Hamilton Rating Scale for Depression score, depressive episodes, marital status, and suicide attempt status of MDD patients. The cohort consisted of 455 patients who were treated with selective serotonin reuptake inhibitors (treatment-response rate = 61.0%; remission rate = 33.0%). By using the SNP dataset that was original to a genome-wide association study, we selected 10 SNPs (including ABCA13 rs4917029, BNIP3 rs9419139, CACNA1E rs704329, EXOC4 rs6978272, GRIN2B rs7954376, LHFPL3 rs4352778, NELL1 rs2139423, NUAK1 rs2956406, PREX1 rs4810894, and SLIT3 rs139863958) which were associated with antidepressant treatment response. Furthermore, we pinpointed 10 SNPs (including ARNTL rs11022778, CAMK1D rs2724812, GABRB3 rs12904459, GRM8 rs35864549, NAALADL2 rs9878985, NCALD rs483986, PLA2G4A rs12046378, PROK2 rs73103153, RBFOX1 rs17134927, and ZNF536 rs77554113) in relation to remission. Then, we employed multilayer feedforward neural networks (MFNNs) containing 1-3 hidden layers and compared MFNN models with logistic regression models. Our analysis results revealed that the MFNN model with 2 hidden layers (area under the receiver operating characteristic curve (AUC) = 0.8228 ± 0.0571; sensitivity = 0.7546 ± 0.0619; specificity = 0.6922 ± 0.0765) performed maximally among predictive models to infer the complex relationship between antidepressant treatment response and biomarkers. In addition, the MFNN model with 3 hidden layers (AUC = 0.8060 ± 0.0722; sensitivity = 0.7732 ± 0.0583; specificity = 0.6623 ± 0.0853) achieved best among predictive models to predict remission. Our study indicates that the deep MFNN framework may provide a suitable method to establish a tool for distinguishing treatment responders from non-responders prior to antidepressant therapy.

Combination of G72 Genetic Variation and G72 Protein Level to Detect Schizophrenia: Machine Learning Approaches

The D-amino acid oxidase activator (DAOA, also known as G72) gene is a strong schizophrenia susceptibility gene. Higher G72 protein levels have been implicated in patients with schizophrenia. The current study aimed to differentiate patients with schizophrenia from healthy individuals using G72 single nucleotide polymorphisms (SNPs) and G72 protein levels by leveraging computational artificial intelligence and machine learning tools. A total of 149 subjects with 89 patients with schizophrenia and 60 healthy controls were recruited. Two G72 genotypes (including rs1421292 and rs2391191) and G72 protein levels were measured with the peripheral blood. We utilized three machine learning algorithms (including logistic regression, naive Bayes, and C4.5 decision tree) to build the optimal predictive model for distinguishing schizophrenia patients from healthy controls. The naive Bayes model using two factors, including G72 rs1421292 and G72 protein, appeared to be the best model for disease susceptibility (sensitivity = 0.7969, specificity = 0.9372, area under the receiver operating characteristic curve (AUC) = 0.9356). However, a model integrating G72 rs1421292 only slightly increased the discriminative power than a model with G72 protein alone (sensitivity = 0.7941, specificity = 0.9503, AUC = 0.9324). Among the three models with G72 protein alone, the naive Bayes with G72 protein alone had the best specificity (0.9503), while logistic regression with G72 protein alone was the most sensitive (0.8765). The findings remained similar after adjusting for age and gender. This study suggests that G72 protein alone, without incorporating the two G72 SNPs, may have been suitable enough to identify schizophrenia patients. We also recommend applying both naive Bayes and logistic regression models for the best specificity and sensitivity, respectively. Larger-scale studies are warranted to confirm the findings.

Transforming growth factor-β signaling pathway-associated genes SMAD2 and TGFBR2 are implicated in metabolic syndrome in a Taiwanese population

The transforming growth factor-β (TGF-β) signaling pathway and its relevant genes have been correlated with an increased risk of developing various hallmarks of metabolic syndrome (MetS). In this study, we assessed whether the TGF-β signaling pathway-associated genes of SMAD family member 2 (SMAD2), SMAD3, SMAD4, transforming growth factor beta 1 (TGFB1), TGFB2, TGFB3, transforming growth factor beta receptor 1 (TGFBR1), and TGFBR2 are associated with MetS and its individual components independently, through complex interactions, or both in a Taiwanese population. A total of 3,000 Taiwanese subjects from the Taiwan Biobank were assessed. Metabolic traits such as waist circumference, triglyceride, high-density lipoprotein cholesterol, systolic and diastolic blood pressure, and fasting glucose were measured. Our results showed a significant association of MetS with the two single nucleotide polymorphisms (SNPs) of SMAD2 rs11082639 and TGFBR2 rs3773651. The association of MetS with these SNPs remained significant after performing Bonferroni correction. Moreover, we identified the effect of SMAD2 rs11082639 on high waist circumference. We also found that an interaction between the SMAD2 rs11082639 and TGFBR2 rs3773651 SNPs influenced MetS. Our findings indicated that the TGF-β signaling pathway-associated genes of SMAD2 and TGFBR2 may contribute to the risk of MetS independently and through gene-gene interactions.

Detection of susceptibility loci on APOA5 and COLEC12 associated with metabolic syndrome using a genome-wide association study in a Taiwanese population

Background

Although the association of single nucleotide polymorphisms (SNPs) with metabolic syndrome (MetS) has been reported in various populations in several genome-wide association studies (GWAS), the data is not conclusive. In this GWAS study, we assessed whether SNPs are associated with MetS and its individual components independently and/or through complex interactions in a Taiwanese population.

Methods

A total of 10,300 Taiwanese subjects were assessed in this study. Metabolic traits such as waist circumference, triglyceride, high-density lipoprotein (HDL) cholesterol, systolic and diastolic blood pressure, and fasting glucose were measured.

Results

Our data showed an association of MetS at the genome-wide significance level (P < 8.6 x 10^-8) with two SNPs, including the rs662799 SNP in the apolipoprotein A5 (APOA5) gene and the rs16944558 SNP in the collectin subfamily member 12 (COLEC12) gene. Moreover, we identified the effect of APOA5 rs662799 on triglyceride and HDL, the effect of rs1106475 in the actin filament associated protein 1 like 2 (AFAP1L2) gene on systolic blood pressure, and the effect of rs17667932 in the mediator complex subunit 30 (MED30) gene on fasting glucose. Additionally, we found that an interaction between the APOA5 rs662799 and COLEC12 rs16944558 SNPs influenced MetS, high triglyceride, and low HDL.

Conclusions

Our study indicates that the APOA5 and COLEC12 genes may contribute to the risk of MetS and its individual components independently as well as through gene-gene interactions.

Effects of circadian clock genes and health-related behavior on metabolic syndrome in a Taiwanese population: Evidence from association and interaction analysis

Increased risk of developing metabolic syndrome (MetS) has been associated with the circadian clock genes. In this study, we assessed whether 29 circadian clock-related genes (including ADCYAP1, ARNTL, ARNTL2, BHLHE40, CLOCK, CRY1, CRY2, CSNK1D, CSNK1E, GSK3B, HCRTR2, KLF10, NFIL3, NPAS2, NR1D1, NR1D2, PER1, PER2, PER3, REV1, RORA, RORB, RORC, SENP3, SERPINE1, TIMELESS, TIPIN, VIP, and VIPR2) are associated with MetS and its individual components independently and/or through complex interactions in a Taiwanese population. We also analyzed the interactions between environmental factors and these genes in influencing MetS and its individual components. A total of 3,000 Taiwanese subjects from the Taiwan Biobank were assessed in this study. Metabolic traits such as waist circumference, triglyceride, high-density lipoprotein cholesterol, systolic and diastolic blood pressure, and fasting glucose were measured. Our data showed a nominal association of MetS with several single nucleotide polymorphisms (SNPs) in five key circadian clock genes including ARNTL, GSK3B, PER3, RORA, and RORB; but none of these SNPs persisted significantly after performing Bonferroni correction. Moreover, we identified the effect of GSK3B rs2199503 on high fasting glucose (P = 0.0002). Additionally, we found interactions among the ARNTL rs10832020, GSK3B rs2199503, PER3 rs10746473, RORA rs8034880, and RORB rs972902 SNPs influenced MetS (P < 0.001 ~ P = 0.002). Finally, we investigated the influence of interactions between ARNTL rs10832020, GSK3B rs2199503, PER3 rs10746473, and RORB rs972902 with environmental factors such as alcohol consumption, smoking status, and physical activity on MetS and its individual components (P < 0.001 ~ P = 0.002). Our study indicates that circadian clock genes such as ARNTL, GSK3B, PER3, RORA, and RORB genes may contribute to the risk of MetS independently as well as through gene-gene and gene-environment interactions.

The ADAMTS9 gene is associated with cognitive aging in the elderly in a Taiwanese population

Evidence indicates that the pathophysiologic mechanisms associated with insulin resistance may contribute to cognitive aging and Alzheimer’s diseases. In this study, we hypothesize that single nucleotide polymorphisms (SNPs) within insulin resistance-associated genes, such as the ADAM metallopeptidase with thrombospondin type 1 motif 9 (ADAMTS9), glucokinase regulator (GCKR), and peroxisome proliferator activated receptor gamma (PPARG) genes, may be linked with cognitive aging independently and/or through complex interactions in an older Taiwanese population. A total of 547 Taiwanese subjects aged over 60 years from the Taiwan Biobank were analyzed. Mini-Mental State Examinations (MMSE) were administered to all subjects, and MMSE scores were used to measure cognitive functions. Our data showed that four SNPs (rs73832338, rs9985304, rs4317088, and rs9831846) in the ADAMTS9 gene were significantly associated with cognitive aging among the subjects (P = 1.5 x 10⁻⁶ ~ 0.0002). This association remained significant after performing Bonferroni correction. Additionally, we found that interactions between the ADAMTS9 rs9985304 and ADAMTS9 rs76346246 SNPs influenced cognitive aging (P < 0.001). However, variants in the GCKR and PPARG genes had no association with cognitive aging in our study. Our study indicates that the ADAMTS9 gene may contribute to susceptibility to cognitive aging independently as well as through SNP-SNP interactions.

Machine learning and systems genomics approaches for multi-omics data

In light of recent advances in biomedical computing, big data science, and precision medicine, there is a mammoth demand for establishing algorithms in machine learning and systems genomics (MLSG), together with multi-omics data, to weigh probable phenotype-genotype relationships. Software frameworks in MLSG are extensively employed to analyze hundreds of thousands of multi-omics data by high-throughput technologies. In this study, we reviewed the MLSG software frameworks and future directions with respect to multi-omics data analysis and integration. Our review was targeted at researching recent approaches and technical solutions for the MLSG software frameworks using multi-omics platforms.

Association and interaction of APOA5, BUD13, CETP, LIPA and health-related behavior with metabolic syndrome in a Taiwanese population

Increased risk of developing metabolic syndrome (MetS) has been associated with the APOA5, APOC1, BRAP, BUD13, CETP, LIPA, LPL, PLCG1, and ZPR1 genes. In this replication study, we reassessed whether these genes are associated with MetS and its individual components independently and/or through complex interactions in a Taiwanese population. We also analyzed the interactions between environmental factors and these genes in influencing MetS and its individual components. A total of 3,000 Taiwanese subjects were assessed in this study. Metabolic traits such as waist circumference, triglyceride, high-density lipoprotein (HDL) cholesterol, systolic and diastolic blood pressure, and fasting glucose were measured. Our data showed a nominal association of MetS with the APOA5 rs662799, BUD13 rs11216129, BUD13 rs623908, CETP rs820299, and LIPA rs1412444 single nucleotide polymorphisms (SNPs). Moreover, APOA5 rs662799, BUD13 rs11216129, and BUD13 rs623908 were significantly associated with high triglyceride, low HDL, triglyceride, and HDL levels. Additionally, we found the interactions of APOA5 rs662799, BUD13 rs11216129, BUD13 rs623908, CETP rs820299, LIPA rs1412444, alcohol consumption, smoking status, or physical activity on MetS and its individual components. Our study indicates that the APOA5, BUD13, CETP, and LIPA genes may contribute to the risk of MetS independently as well as through gene-gene and gene-environment interactions.

The ENPP1 K121Q polymorphism is associated with type 2 diabetes and related metabolic phenotypes in a Taiwanese population

Increased risk of developing type 2 diabetes (T2D) has been associated with a single nucleotide polymorphism (SNP), rs1044498 (K121Q), in the ectonucleotide pyrophosphatase/phosphodiesterase 1 (ENPP1) gene, but this association is unclear among Asians. In this replication study, we reassessed whether the ENPP1 rs1044498 SNP is associated with T2D, obesity, and T2D/obesity-related metabolic traits in a Taiwanese population. A total of 1513 Taiwanese subjects were assessed in this study. The ENPP1 rs1044498 SNP was genotyped by the Taqman assay. T2D/Obesity-related quantitative traits, such as waist circumference and fasting glucose, were measured. Our data showed a significant association of the ENPP1 rs1044498 SNP with T2D (P < 0.001) among the subjects. Moreover, the ENPP1 rs1044498 SNP was significantly associated with T2D/obesity-related metabolic traits, such as waist circumference (P = 0.002) and fasting glucose (P < 0.001), among the subjects. However, we found no association of ENPP1 rs1044498 with obesity (BMI ≧ 27 kg/m(2)). Our study indicates that the ENPP1 rs1044498 SNP is associated with T2D, waist circumference, and fasting glucose in Taiwanese subjects.

Breast cancer-associated high-order SNP-SNP interaction of CXCL12/CXCR4-related genes by an improved multifactor dimensionality reduction (MDR-ER)

In association studies, the combined effects of single nucleotide polymorphism (SNP)-SNP interactions and the problem of imbalanced data between cases and controls are frequently ignored. In the present study, we used an improved multifactor dimensionality reduction (MDR) approach namely MDR-ER to detect the high order SNP‑SNP interaction in an imbalanced breast cancer data set containing seven SNPs of chemokine CXCL12/CXCR4 pathway genes. Most individual SNPs were not significantly associated with breast cancer. After MDR‑ER analysis, six significant SNP‑SNP interaction models with seven genes (highest cross‑validation consistency, 10; classification error rates, 41.3‑21.0; and prediction error rates, 47.4‑55.3) were identified. CD4 and VEGFA genes were associated in a 2‑loci interaction model (classification error rate, 41.3; prediction error rate, 47.5; odds ratio (OR), 2.069; 95% bootstrap CI, 1.40‑2.90; P=1.71E‑04) and it also appeared in all the best 2‑7‑loci models. When the loci number increased, the classification error rates and P‑values decreased. The powers in 2‑7‑loci in all models were >0.9. The minimum classification error rate of the MDR‑ER‑generated model was shown with the 7‑loci interaction model (classification error rate, 21.0; OR=15.282; 95% bootstrap CI, 9.54‑23.87; P=4.03E‑31). In the epistasis network analysis, the overall effect with breast cancer susceptibility was identified and the SNP order of impact on breast cancer was identified as follows: CD4 = VEGFA > KITLG > CXCL12 > CCR7 = MMP2 > CXCR4. In conclusion, the MDR‑ER can effectively and correctly identify the best SNP‑SNP interaction models in an imbalanced data set for breast cancer cases.

The Pro12Ala polymorphism in the peroxisome proliferator-activated receptor gamma (PPARG) gene in relation to obesity and metabolic phenotypes in a Taiwanese population

Obesity is considered as an important public health problem in the world. Although the association of a common single nucleotide polymorphism (SNP), rs1801282 (Pro12Ala), in the peroxisome proliferator-activated receptor gamma (PPARG) gene with obesity has been reported in various populations, these data are not conclusive. This study aimed to reassess whether the PPARG rs1801282 SNP is linked with obesity and obesity-related metabolic traits in a Taiwanese population. A total of 674 Taiwanese subjects with general health examinations were genotyped. The rs1801282 genotype was determined by the Taqman SNP genotyping assay. Obesity-related metabolic traits such as triglyceride, waist circumference, systolic and diastolic blood pressure, total cholesterol, and fasting glucose were measured. The PPARG rs1801282 SNP did not exhibit any significant association with obesity among the complete sample population. However, sex-stratified analyses revealed an effect on overweight in female participants where the carriers of the combined CG and GG genotypes had a higher risk to overweight than those with the CC homozygotes (OR=4.05; 95% CI=1.28-12.83; P=0.017). Compared to the carriers of CC homozygotes, BMI was significantly higher for the carriers of the combined CG and GG genotypes in the female subjects (24.4±3.7 vs. 23.5±3.8 kg/m2; P=0.033). In addition, the carriers of the CC homozygotes had a higher total cholesterol level than those with the combined CG and GG genotypes in the female subjects (197.0±37.3 vs. 180.7±33.7 mg/dl; P=0.026). Our study indicates that PPARG rs1801282 may significantly predict overweight, BMI, and total cholesterol in female but not male Taiwanese subjects.

Association of the rs6235 variant in the proprotein convertase subtilisin/kexin type 1 (PCSK1) gene with obesity and related traits in a Taiwanese population

One particularly interesting single nucleotide polymorphism (SNP), rs6235 (encoding an S690T substitution), in the proprotein convertase subtilisin/kexin type 1 (PCSK1) gene has been widely associated with obesity in several European cohorts. The present study was intended to investigate the association between the PCSK1 rs6235 SNP and the prevalence of overweight or obesity, or obesity-related metabolic traits in a Taiwanese population. A total of 964 Taiwanese subjects with general health examinations were analyzed. Our data revealed no association of PCSK1 rs6235 with the risk of obesity or overweight in the complete subjects. However, the PCSK1 rs6235 SNP exhibited a significant association with overweight among the male subjects (P=0.03), but not among the female subjects. Furthermore, the carriers of GG variant had a significantly higher waist circumference than those with the CC variant (82.5 ± 11.5 vs. 81.2 ± 10.2 cm; P=0.01) and those with the CG variant (82.5 ± 11.5 vs. 81.4 ± 10.4 cm; P=0.021). In addition, the carriers of GG variant had a higher diastolic blood pressure than those with the CC variant (81.9 ± 14.2 vs. 80.3 ± 12.9 mm Hg; P=0.023). Our study indicates that the PCSK1 rs6235 SNP may contribute to the risk of overweight in men and predict obesity-related metabolic traits such as waist circumference and diastolic blood pressure in Taiwanese subjects.

Investigation of possible epistatic interactions between GRIA2 and GRIA4 variants on clinical outcomes in patients with major depressive disorder

OBJECTIVES

To investigate the effects of glutamate receptor, ionotropic, alpha-amino-3-hydroxy-5-methyl-4-isoxazole propionate (AMPA) 2 (GRIA2) rs4260586 and glutamate receptor, ionotropic, AMPA 4 (GRIA4) rs10736648 single nucleotide polymorphisms (SNPs) on response to antidepressants in Korean patients with major depressive disorder (MDD), and to ascertain whether epistatic interactions might exist between these SNPs.

METHODS

In this retrospective analysis, patients were assessed at hospital admission and discharge using the Montgomery-Åsberg depression rating scale (MADRS). A multiple regression model was employed to investigate the effects of the two SNP variants on clinical/sociodemographic outcomes relating to MDD.

RESULTS

Out of 145 Korean patients, the presence of both GRIA2 rs4260586 and GRIA4 rs10736648 polymorphisms had no significant association with MADRS improvement scores or other clinical/sociodemographic variables.

CONCLUSIONS

These data potentially suggest a lack of epistatic interaction between GRIA2 and GRIA4 variants, regarding clinical outcomes in patients with MDD. The study was limited by small sample size, use of different antidepressants and incomplete coverage of genes under investigation. Future research should include larger patient samples treated with different antidepressants, analysis of different SNPs and/or investigation of different gene-gene interactions within the glutamatergic system.