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

Deep Learning with Neuroimaging and Genomics in Alzheimer's Disease

A growing body of evidence currently proposes that deep learning approaches can serve as an essential cornerstone for the diagnosis and prediction of Alzheimer's disease (AD). In light of the latest advancements in neuroimaging and genomics, numerous deep learning models are being exploited to distinguish AD from normal controls and/or to distinguish AD from mild cognitive impairment in recent research studies. In this review, we focus on the latest developments for AD prediction using deep learning techniques in cooperation with the principles of neuroimaging and genomics. First, we narrate various investigations that make use of deep learning algorithms to establish AD prediction using genomics or neuroimaging data. Particularly, we delineate relevant integrative neuroimaging genomics investigations that leverage deep learning methods to forecast AD on the basis of incorporating both neuroimaging and genomics data. Moreover, we outline the limitations as regards to the recent AD investigations of deep learning with neuroimaging and genomics. Finally, we depict a discussion of challenges and directions for future research. The main novelty of this work is that we summarize the major points of these investigations and scrutinize the similarities and differences among these investigations.

Prediction of Probable Major Depressive Disorder in the Taiwan Biobank: An Integrated Machine Learning and Genome-Wide Analysis Approach

In light of recent advancements in machine learning, personalized medicine using predictive algorithms serves as an essential paradigmatic methodology. Our goal was to explore an integrated machine learning and genome-wide analysis approach which targets the prediction of probable major depressive disorder (MDD) using 9828 individuals in the Taiwan Biobank. In our analysis, we reported a genome-wide significant association with probable MDD that has not been previously identified: FBN1 on chromosome 15. Furthermore, we pinpointed 17 single nucleotide polymorphisms (SNPs) which show evidence of both associations with probable MDD and potential roles as expression quantitative trait loci (eQTLs). To predict the status of probable MDD, we established prediction models with random undersampling and synthetic minority oversampling using 17 eQTL SNPs and eight clinical variables. We utilized five state-of-the-art models: logistic ridge regression, support vector machine, C4.5 decision tree, LogitBoost, and random forests. Our data revealed that random forests had the highest performance (area under curve = 0.8905 ± 0.0088; repeated 10-fold cross-validation) among the predictive algorithms to infer complex correlations between biomarkers and probable MDD. Our study suggests that an integrated machine learning and genome-wide analysis approach may offer an advantageous method to establish bioinformatics tools for discriminating MDD patients from healthy controls.

The promise of machine learning in predicting treatment outcomes in psychiatry

For many years, psychiatrists have tried to understand factors involved in response to medications or psychotherapies, in order to personalize their treatment choices. There is now a broad and growing interest in the idea that we can develop models to personalize treatment decisions using new statistical approaches from the field of machine learning and applying them to larger volumes of data. In this pursuit, there has been a paradigm shift away from experimental studies to confirm or refute specific hypotheses towards a focus on the overall explanatory power of a predictive model when tested on new, unseen datasets. In this paper, we review key studies using machine learning to predict treatment outcomes in psychiatry, ranging from medications and psychotherapies to digital interventions and neurobiological treatments. Next, we focus on some new sources of data that are being used for the development of predictive models based on machine learning, such as electronic health records, smartphone and social media data, and on the potential utility of data from genetics, electrophysiology, neuroimaging and cognitive testing. Finally, we discuss how far the field has come towards implementing prediction tools in real-world clinical practice. Relatively few retrospective studies to-date include appropriate external validation procedures, and there are even fewer prospective studies testing the clinical feasibility and effectiveness of predictive models. Applications of machine learning in psychiatry face some of the same ethical challenges posed by these techniques in other areas of medicine or computer science, which we discuss here. In short, machine learning is a nascent but important approach to improve the effectiveness of mental health care, and several prospective clinical studies suggest that it may be working already.

Prediction of repeated-dose intravenous ketamine response in major depressive disorder using the GWAS-based machine learning approach

Major depressive disorder (MDD) is one of the most common psychiatric disorders. Various clinical studies have shown that the N-methyl-D-aspartate (NMDA) receptor antagonist ketamine has rapid, robust, and sustained antidepressant effects. However, given the concerns about the adverse effects of ketamine on patients, it would be important to identify a set of biomarkers that could be used to predict clinical outcomes for its treatment. A total of 83 MDD patients received treatment with six ketamine infusions for up to 2 weeks and were classified into "responders" or "non-responders" based on an average change in the HAMD score >50% from baseline. A nested cross-validation approach was applied to prevent information leakage and overestimation of model performance. The initial dataset was divided randomly into training and test sets in a nested six-fold cross-validation. We first performed genome-wide logistic regression to find potentially significant variants related to treatment response and then selected the top SNPs based on the genetic association results using the random forests algorithm. Subsequently, six machine learning models were employed to construct prediction models by using ten-fold cross-validation. A series of model comparisons showed that the best performing fold was characterized by accuracy of 0.85, precision of 0.75, and a sensitivity of 1.00 with the support vector machine algorithm. Together, these findings demonstrated that the machine learning approach can predict the treatment outcomes of multiple ketamine infusions on the basis of the genotyping information of each participant.

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.

Na+ leak-current channel (NALCN) at the junction of motor and neuropsychiatric symptoms in Parkinson's disease

Parkinson's disease (PD) is a debilitating movement disorder often accompanied by neuropsychiatric symptoms that stem from the loss of dopaminergic function in the basal ganglia and altered neurotransmission more generally. Akinesia, postural instability, tremors and frozen gait constitute the major motor disturbances, whereas neuropsychiatric symptoms include altered circadian rhythms, disordered sleep, depression, psychosis and cognitive impairment. Evidence is emerging that the motor and neuropsychiatric symptoms may share etiologic factors. Calcium/ion channels (CACNA1C, NALCN), synaptic proteins (SYNJ1) and neuronal RNA-binding proteins (RBFOX1) are among the risk genes that are common to PD and various psychiatric disorders. The Na⁺ leak-current channel (NALCN) is the focus of this review because it has been implicated in dystonia, regulation of movement, cognitive impairment, sleep and circadian rhythms. It regulates the resting membrane potential in neurons, mediates pace-making activity, participates in synaptic vesicle recycling and is functionally co-localized to the endoplasmic reticulum (ER)-several of the major processes adversely affected in PD. Here, we summarize the literature on mechanisms and pathways that connect the motor and neuropsychiatric symptoms of PD with a focus on recurring relationships to the NALCN. It is hoped that the various connections outlined here will stimulate further discussion, suggest additional areas for exploration and ultimately inspire novel treatment strategies.

Endocannabinoid Gene × Gene Interaction Association to Alcohol Use Disorder in Two Adolescent Cohorts

Genetic markers of the endocannabinoid system have been linked to a variety of addiction-related behaviors that extend beyond cannabis use. In the current study we investigate the relationship between endocannabinoid (eCB) genetic markers and alcohol use disorder (AUD) in European adolescents (14-18 years old) followed in the IMAGEN study (n = 2,051) and explore replication in a cohort of North American adolescents from Canadian Saguenay Youth Study (SYS) (n = 772). Case-control status is represented by a score of more than 7 on the Alcohol Use Disorder Identification Test (AUDIT). First a set-based test method was used to examine if a relationship between the eCB system and AUDIT case/control status exists at the gene level. Using only SNPs that are both independent and significantly associated to case-control status, we perform Fisher's exact test to determine SNP level odds ratios in relation to case-control status and then perform logistic regressions as post-hoc analysis, while considering various covariates. Generalized multifactor dimensionality reduction (GMDR) was used to analyze the most robust SNP×SNP interaction of the five eCB genes with positive AUDIT screen. While no gene-sets were significantly associated to AUDIT scores after correction for multiple tests, in the case/control analysis, 7 SNPs were significantly associated with AUDIT scores of > 7 (p < 0.05; OR<1). Two SNPs remain significant after correction by false discovery rate (FDR): rs9343525 in CNR1 (pcorrected =0.042, OR = 0.73) and rs507961 in MGLL (pcorrected = 0.043, OR = 0.78). Logistic regression showed that both rs9353525 (CNR1) and rs507961 (MGLL) remained significantly associated with positive AUDIT screens (p < 0.01; OR < 1) after correction for multiple covariables and interaction of covariable × SNP. This result was not replicated in the SYS cohort. The GMDR model revealed a significant three-SNP interaction (p = 0.006) involving rs484061 (MGLL), rs4963307 (DAGLA), and rs7766029 (CNR1) predicted case-control status, after correcting for multiple covariables in the IMAGEN sample. A binomial logistic regression of the combination of these three SNPs by phenotype in the SYS cohort showed a result in the same direction as seen in the IMAGEN cohort (BETA = 0.501, p = 0.06). While preliminary, the present study suggests that the eCB system may play a role in the development of AUD in adolescents.

Predicting the risk of drug-drug interactions in psychiatric hospitals: a retrospective longitudinal pharmacovigilance study

OBJECTIVES

The aim was to use routine data available at a patient's admission to the hospital to predict polypharmacy and drug-drug interactions (DDI) and to evaluate the prediction performance with regard to its usefulness to support the efficient management of benefits and risks of drug prescriptions.

DESIGN

Retrospective, longitudinal study.

SETTING

We used data from a large multicentred pharmacovigilance project carried out in eight psychiatric hospitals in Hesse, Germany.

PARTICIPANTS

Inpatient episodes consecutively discharged between 1 October 2017 and 30 September 2018 (year 1) or 1 January 2019 and 31 December 2019 (year 2).

OUTCOME MEASURES

The proportion of rightly classified hospital episodes.

METHODS

We used gradient boosting to predict respective outcomes. We tested the performance of our final models in unseen patients from another calendar year and separated the study sites used for training from the study sites used for performance testing.

RESULTS

A total of 53 909 episodes were included in the study. The models' performance, as measured by the area under the receiver operating characteristic, was 'excellent' (0.83) and 'acceptable' (0.72) compared with common benchmarks for the prediction of polypharmacy and DDI, respectively. Both models were substantially better than a naive prediction based solely on basic diagnostic grouping.

CONCLUSION

This study has shown that polypharmacy and DDI can be predicted from routine data at patient admission. These predictions could support an efficient management of benefits and risks of hospital prescriptions, for instance by including pharmaceutical supervision early after admission for patients at risk before pharmacological treatment is established.

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.

Precision psychiatry in clinical practice

The treatment of depression represents a major challenge for healthcare systems and choosing among the many available drugs without objective guidance criteria is an error-prone process. Recently, pharmacogenetic biomarkers entered in prescribing guidelines, giving clinicians the possibility to use this additional tool to guide prescription and improve therapeutic outcomes. This marked an important step towards precision psychiatry, which aim is to integrate biological and environmental information to personalise treatments. Only genetic variants in cytochrome enzymes are endorsed by prescribing guidelines, but in the future polygenic predictors of treatment outcomes may be translated into the clinic. The integration of genetics with other relevant information (e.g., concomitant diseases and treatments, drug plasma levels) could be managed in a standardised way through ad hoc software. The overcoming of the current obstacles (e.g., staff training, genotyping and informatics facilities) can lead to a broad implementation of precision psychiatry and represent a revolution for psychiatric care.Key pointsPrecision psychiatry aims to integrate biological and environmental information to personalise treatments and complement clinical judgementPharmacogenetic biomarkers in cytochrome genes were included in prescribing guidelines and represented an important step towards precision psychiatryTherapeutic drug monitoring is an important and cost-effective tool which should be integrated with genetic testing and clinical evaluation in order to optimise pharmacotherapyOther individual factors relevant to pharmacotherapy response (e.g., individual's symptom profile, concomitant diseases) can be integrated with genetic information through artificial intelligence to provide treatment recommendationsThe creation of pharmacogenetic services within healthcare systems is a challenging and multi-step process, education of health professionals, promotion by institutions and regulatory bodies, economic and ethical barriers are the main issues.

Improved cancer biomarkers identification using network-constrained infinite latent feature selection

Identifying biomarkers that are associated with different types of cancer is an important goal in the field of bioinformatics. Different researcher groups have analyzed the expression profiles of many genes and found some certain genetic patterns that can promote the improvement of targeted therapies, but the significance of some genes is still ambiguous. More reliable and effective biomarkers identification methods are then needed to detect candidate cancer-related genes. In this paper, we proposed a novel method that combines the infinite latent feature selection (ILFS) method with the functional interaction (FIs) network to rank the biomarkers. We applied the proposed method to the expression data of five cancer types. The experiments indicated that our network-constrained ILFS (NCILFS) provides an improved prediction of the diagnosis of the samples and locates many more known oncogenes than the original ILFS and some other existing methods. We also performed functional enrichment analysis by inspecting the over-represented gene ontology (GO) biological process (BP) terms and applying the gene set enrichment analysis (GSEA) method on selected biomarkers for each feature selection method. The enrichments analysis reports show that our network-constraint ILFS can produce more biologically significant gene sets than other methods. The results suggest that network-constrained ILFS can identify cancer-related genes with a higher discriminative power and biological significance.

Prediction of response to anti-vascular endothelial growth factor treatment in diabetic macular oedema using an optical coherence tomography-based machine learning method

PURPOSE

To predict the anti-vascular endothelial growth factor (VEGF) therapeutic response of diabetic macular oedema (DME) patients from optical coherence tomography (OCT) at the initiation stage of treatment using a machine learning-based self-explainable system.

METHODS

A total of 712 DME patients were included and classified into poor and good responder groups according to central macular thickness decrease after three consecutive injections. Machine learning models were constructed to make predictions based on related features extracted automatically using deep learning algorithms from OCT scans at baseline. Five-fold cross-validation was applied to optimize and evaluate the models. The model with the best performance was then compared with two ophthalmologists. Feature importance was further investigated, and a Wilcoxon rank-sum test was performed to assess the difference of a single feature between two groups.

RESULTS

Of 712 patients, 294 were poor responders and 418 were good responders. The best performance for the prediction task was achieved by random forest (RF), with sensitivity, specificity and area under the receiver operating characteristic curve of 0.900, 0.851 and 0.923. Ophthalmologist 1 and ophthalmologist 2 reached sensitivity of 0.775 and 0.750, and specificity of 0.716 and 0.821, respectively. The sum of hyperreflective dots was found to be the most relevant feature for prediction.

CONCLUSION

An RF classifier was constructed to predict the treatment response of anti-VEGF from OCT images of DME patients with high accuracy. The algorithm contributes to predicting treatment requirements in advance and provides an optimal individualized therapeutic regimen.

The Tuberculosis-Depression Syndemic and Evolution of Pharmaceutical Therapeutics: From Ancient Times to the Future

The interplay between tuberculosis and depression has been problematic since the humoralists. Over the centuries similarities in disease management have transpired. With the advent of isoniazid chemotherapy, transformation of tuberculosis patients from morbidly depressive to euphoric was noted. Isoniazid was thereafter widely prescribed for depression: hepatotoxicity ending its use as an antidepressant in 1961. Isoniazid monotherapy led to the emergence of drug resistant tuberculosis, stimulating new drug development. Vastly increased investment into antidepressants ensued thereafter while investment in new drugs for tuberculosis lagged. In the 21st century, both diseases independently contribute significantly to global disease burdens: renewed convergence and the resultant syndemic is detrimental to both patient groups. Ending the global tuberculosis epidemic and decreasing the burden of depression and will require multidisciplinary, patient-centered approaches that consider this combined co-morbidity. The emerging era of big data for health, digital interventions and novel and repurposed compounds promise new ways to treat both diseases and manage the syndemic, but absence of clinical structures to support these innovations may derail the treatment programs for both. New policies are urgently required optimizing use of the current advances in healthcare available in the digital era, to ensure that patient-centered care takes cognizance of both diseases.

A Deep Learning Algorithm to Predict Hazardous Drinkers and the Severity of Alcohol-Related Problems Using K-NHANES

Purpose: The number of patients with alcohol-related problems is steadily increasing. A large-scale survey of alcohol-related problems has been conducted. However, studies that predict hazardous drinkers and identify which factors contribute to the prediction are limited. Thus, the purpose of this study was to predict hazardous drinkers and the severity of alcohol-related problems of patients using a deep learning algorithm based on a large-scale survey data. Materials and Methods: Datasets of National Health and Nutrition Examination Survey of South Korea (K-NHANES), a nationally representative survey for the entire South Korean population, were used to train deep learning and conventional machine learning algorithms. Datasets from 69,187 and 45,672 participants were used to predict hazardous drinkers and the severity of alcohol-related problems, respectively. Based on the degree of contribution of each variable to deep learning, it was possible to determine which variable contributed significantly to the prediction of hazardous drinkers. Results: Deep learning showed the higher performance than conventional machine learning algorithms. It predicted hazardous drinkers with an AUC (Area under the receiver operating characteristic curve) of 0.870 (Logistic regression: 0.858, Linear SVM: 0.849, Random forest classifier: 0.810, K-nearest neighbors: 0.740). Among 325 variables for predicting hazardous drinkers, energy intake was a factor showing the greatest contribution to the prediction, followed by carbohydrate intake. Participants were classified into Zone I, Zone II, Zone III, and Zone IV based on the degree of alcohol-related problems, showing AUCs of 0.881, 0.774, 0.853, and 0.879, respectively. Conclusion: Hazardous drinking groups could be effectively predicted and individuals could be classified according to the degree of alcohol-related problems using a deep learning algorithm. This algorithm could be used to screen people who need treatment for alcohol-related problems among the general population or hospital visitors.

Deep learning for brain disorders: from data processing to disease treatment

In order to reach precision medicine and improve patients' quality of life, machine learning is increasingly used in medicine. Brain disorders are often complex and heterogeneous, and several modalities such as demographic, clinical, imaging, genetics and environmental data have been studied to improve their understanding. Deep learning, a subpart of machine learning, provides complex algorithms that can learn from such various data. It has become state of the art in numerous fields, including computer vision and natural language processing, and is also growingly applied in medicine. In this article, we review the use of deep learning for brain disorders. More specifically, we identify the main applications, the concerned disorders and the types of architectures and data used. Finally, we provide guidelines to bridge the gap between research studies and clinical routine.

Defining phenotypes of long-term lithium and valproate response, including combination therapy: a modified application of the Alda scale in patients with bipolar disorders

BACKGROUND

When evaluating the long-term treatment response to mood stabilizers using the Alda scale, mood stabilizer combination therapy is typically considered a confounding factor, and patients receiving combination therapy are excluded from the analysis. However, this may result in bias if those under combination therapy are worse treatment responders. This study aims to explore whether the Alda scale is applicable to patients taking lithium and valproate combination therapy. We compared long-term treatment response in patients receiving monotherapy and combination therapy of the two drugs, and investigated clinical correlates of the responses to each drug.

METHODS

The study subjects consisted of 102 patients with bipolar I (BD-I) or bipolar II (BD-II) disorder who had been undergoing maintenance treatment with lithium and/or valproate for more than 2 years at a single specialized bipolar disorder clinic. Long-term treatment response was measured using the Alda scale and compared among the lithium monotherapy group, the valproate monotherapy group, and the mood stabilizer combination group. Clinical correlates of long-term treatment response were evaluated in lithium users and valproate users separately.

RESULTS

There were no significant differences in terms of baseline illness characteristics among groups. The combination group showed the worst treatment response for all the response measurements applied. This group also had the higher rate of 'poor responder' with a statistically significant difference compared to valproate group. Older age at onset and (hypo)manic episode at onset showed significant positive associations with total Alda score in lithium users, while comorbid anxiety disorders, obsessive-compulsive disorder and mixed episode showed significant negative associations in valproate users.

CONCLUSIONS

The combination group had poorer long-term treatment response but did not show distinct clinical characteristics compared to the monotherapy groups. When exploring the long-term effects of mood stabilizers, excluding patients undergoing combination treatment could result in bias because they may represent a poor response group. The long-term treatment responses of lithium and valproate had different clinical correlates.

Pathogenic Single Nucleotide Polymorphisms on Autophagy-Related Genes

In recent years, the study of single nucleotide polymorphisms (SNPs) has gained increasing importance in biomedical research, as they can either be at the molecular origin of a determined disorder or directly affect the efficiency of a given treatment. In this regard, sequence variations in genes involved in pro-survival cellular pathways are commonly associated with pathologies, as the alteration of these routes compromises cellular homeostasis. This is the case of autophagy, an evolutionarily conserved pathway that counteracts extracellular and intracellular stressors by mediating the turnover of cytosolic components through lysosomal degradation. Accordingly, autophagy dysregulation has been extensively described in a wide range of human pathologies, including cancer, neurodegeneration, or inflammatory alterations. Thus, it is not surprising that pathogenic gene variants in genes encoding crucial effectors of the autophagosome/lysosome axis are increasingly being identified. In this review, we present a comprehensive list of clinically relevant SNPs in autophagy-related genes, highlighting the scope and relevance of autophagy alterations in human disease.

Candidate Strategies for Development of a Rapid-Acting Antidepressant Class That Does Not Result in Neuropsychiatric Adverse Effects: Prevention of Ketamine-Induced Neuropsychiatric Adverse Reactions

Non-competitive N-methyl-D-aspartate/glutamate receptor (NMDAR) antagonism has been considered to play important roles in the pathophysiology of schizophrenia. In spite of severe neuropsychiatric adverse effects, esketamine (racemic enantiomer of ketamine) has been approved for the treatment of conventional monoaminergic antidepressant-resistant depression. Furthermore, ketamine improves anhedonia, suicidal ideation and bipolar depression, for which conventional monoaminergic antidepressants are not fully effective. Therefore, ketamine has been accepted, with rigorous restrictions, in psychiatry as a new class of antidepressant. Notably, the dosage of ketamine for antidepressive action is comparable to the dose that can generate schizophrenia-like psychotic symptoms. Furthermore, the psychotropic effects of ketamine precede the antidepressant effects. The maintenance of the antidepressive efficacy of ketamine often requires repeated administration; however, repeated ketamine intake leads to abuse and is consistently associated with long-lasting memory-associated deficits. According to the dissociative anaesthetic feature of ketamine, it exerts broad acute influences on cognition/perception. To evaluate the therapeutic validation of ketamine across clinical contexts, including its advantages and disadvantages, psychiatry should systematically assess the safety and efficacy of either short- and long-term ketamine treatments, in terms of both acute and chronic outcomes. Here, we describe the clinical evidence of NMDAR antagonists, and then the temporal mechanisms of schizophrenia-like and antidepressant-like effects of the NMDAR antagonist, ketamine. The underlying pharmacological rodent studies will also be discussed.

Machine learning for precision medicine

Precision medicine is an emerging approach to clinical research and patient care that focuses on understanding and treating disease by integrating multi-modal or multi-omics data from an individual to make patient-tailored decisions. With the large and complex datasets generated using precision medicine diagnostic approaches, novel techniques to process and understand these complex data were needed. At the same time, computer science has progressed rapidly to develop techniques that enable the storage, processing, and analysis of these complex datasets, a feat that traditional statistics and early computing technologies could not accomplish. Machine learning, a branch of artificial intelligence, is a computer science methodology that aims to identify complex patterns in data that can be used to make predictions or classifications on new unseen data or for advanced exploratory data analysis. Machine learning analysis of precision medicine's multi-modal data allows for broad analysis of large datasets and ultimately a greater understanding of human health and disease. This review focuses on machine learning utilization for precision medicine's "big data", in the context of genetics, genomics, and beyond.

Prediction of Antidepressant Treatment Response and Remission Using an Ensemble Machine Learning Framework

In the wake of recent advances in machine learning research, the study of pharmacogenomics using predictive algorithms serves as a new paradigmatic application. In this work, our goal was to explore an ensemble machine learning approach which aims to predict probable antidepressant treatment response and remission in major depressive disorder (MDD). To discover the status of antidepressant treatments, we established an ensemble predictive model with a feature selection algorithm resulting from the analysis of genetic variants and clinical variables of 421 patients who were treated with selective serotonin reuptake inhibitors. We also compared our ensemble machine learning framework with other state-of-the-art models including multi-layer feedforward neural networks (MFNNs), logistic regression, support vector machine, C4.5 decision tree, naïve Bayes, and random forests. Our data revealed that the ensemble predictive algorithm with feature selection (using fewer biomarkers) performed comparably to other predictive algorithms (such as MFNNs and logistic regression) to derive the perplexing relationship between biomarkers and the status of antidepressant treatments. Our study demonstrates that the ensemble machine learning framework may present a useful technique to create bioinformatics tools for discriminating non-responders from responders prior to antidepressant treatments.

Relevant Applications of Generative Adversarial Networks in Drug Design and Discovery: Molecular De Novo Design, Dimensionality Reduction, and De Novo Peptide and Protein Design

A growing body of evidence now suggests that artificial intelligence and machine learning techniques can serve as an indispensable foundation for the process of drug design and discovery. In light of latest advancements in computing technologies, deep learning algorithms are being created during the development of clinically useful drugs for treatment of a number of diseases. In this review, we focus on the latest developments for three particular arenas in drug design and discovery research using deep learning approaches, such as generative adversarial network (GAN) frameworks. Firstly, we review drug design and discovery studies that leverage various GAN techniques to assess one main application such as molecular de novo design in drug design and discovery. In addition, we describe various GAN models to fulfill the dimension reduction task of single-cell data in the preclinical stage of the drug development pipeline. Furthermore, we depict several studies in de novo peptide and protein design using GAN frameworks. Moreover, we outline the limitations in regard to the previous drug design and discovery studies using GAN models. Finally, we present a discussion of directions and challenges for future research.

Brain NMDA Receptors in Schizophrenia and Depression

N-methyl-D-aspartate (NMDA) receptor antagonists such as phencyclidine (PCP), dizocilpine (MK-801) and ketamine have long been considered a model of schizophrenia, both in animals and humans. However, ketamine has been recently approved for treatment-resistant depression, although with severe restrictions. Interestingly, the dosage in both conditions is similar, and positive symptoms of schizophrenia appear before antidepressant effects emerge. Here, we describe the temporal mechanisms implicated in schizophrenia-like and antidepressant-like effects of NMDA blockade in rats, and postulate that such effects may indicate that NMDA receptor antagonists induce similar mechanistic effects, and only the basal pre-drug state of the organism delimitates the overall outcome. Hence, blockade of NMDA receptors in depressive-like status can lead to amelioration or remission of symptoms, whereas healthy individuals develop psychotic symptoms and schizophrenia patients show an exacerbation of these symptoms after the administration of NMDA receptor antagonists.

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.

Sensitivity and specificity evaluation of multiple neurodegenerative proteins for Creutzfeldt-Jakob disease diagnosis using a deep-learning approach

The diagnosis of sporadic Creutzfeldt-Jakob disease (sCJD) can only be confirmed by abnormal protease-resistant prion protein accumulation in post-mortem brain tissue. The relationships between sCJD and cerebrospinal fluid (CSF) proteins such as 14–3-3, tau, and α-synuclein (a-syn) have been investigated for their potential value in pre-mortem diagnosis. Recently, deep-learning (DL) methods have attracted attention in neurodegenerative disease research. We established DL-aided pre-mortem diagnostic methods for CJD using multiple CSF biomarkers to improve their discriminatory sensitivity and specificity. Enzyme-linked immunosorbent assays were performed on phospho-tau (p-tau), total-tau (t-tau), a-syn, and β-amyloid (1–42), and western blot analysis was performed for 14–3-3 protein from CSF samples of 49 sCJD and 256 non-CJD Korean patients, respectively. The deep neural network structure comprised one input, five hidden, and one output layers, with 20, 40, 30, 20 and 12 hidden unit numbers per hidden layer, respectively. The best performing DL model demonstrated 90.38% accuracy, 83.33% sensitivity, and 92.5% specificity for the three-protein combination of t-tau, p-tau, and a-syn, and all other patients in a separate CSF set (n = 15) with other neuronal diseases were correctly predicted to not have CJD. Thus, DL-aided pre-mortem diagnosis may provide a suitable tool for discriminating CJD patients from non-CJD patients.

Deep learning in mental health outcome research: a scoping review

Mental illnesses, such as depression, are highly prevalent and have been shown to impact an individual's physical health. Recently, artificial intelligence (AI) methods have been introduced to assist mental health providers, including psychiatrists and psychologists, for decision-making based on patients' historical data (e.g., medical records, behavioral data, social media usage, etc.). Deep learning (DL), as one of the most recent generation of AI technologies, has demonstrated superior performance in many real-world applications ranging from computer vision to healthcare. The goal of this study is to review existing research on applications of DL algorithms in mental health outcome research. Specifically, we first briefly overview the state-of-the-art DL techniques. Then we review the literature relevant to DL applications in mental health outcomes. According to the application scenarios, we categorize these relevant articles into four groups: diagnosis and prognosis based on clinical data, analysis of genetics and genomics data for understanding mental health conditions, vocal and visual expression data analysis for disease detection, and estimation of risk of mental illness using social media data. Finally, we discuss challenges in using DL algorithms to improve our understanding of mental health conditions and suggest several promising directions for their applications in improving mental health diagnosis and treatment.

Low expression of NCALD is associated with chemotherapy resistance and poor prognosis in epithelial ovarian cancer

Background

Low expression of NCALD(neurocalcin delta) in peripheral blood of ovarian cancer patients predicts poor prognosis. However, the molecular mechanism of NCALD in ovarian cancer and its relationship with chemotherapy outcomes is unclear. The aim of this study was to investigate the potential signaling pathways of NCALD and to evaluate its ability to predict chemotherapy outcomes and prognosis.

Methods

High-throughput RNA sequencing data were downloaded from TCGA. GSEA explored the potential signaling pathways of NCALD. The expression of NCALD in chemotherapy sensitive and chemotherapy resistant ovarian cancer patients was detected by TCGA data and clinical samples. ROC analysis confirmed the ability of NCALD to predict chemotherapy outcomes. The association between NCALD expression and prognosis in ovarian cancer patients was assessed using Kaplan-Meier plotter.

Results

In patients with NCALD overexpression, genes expression related to ERK1 / 2 signaling pathway, NF-kappaB signaling pathway, TGF-β signaling pathway and immune response pathway was increased, especially ERK1 / 2 signaling pathway. The expression of NCALD in chemoresistant patients was significantly lower than chemosensitive patients. In TCGA data and immunohistochemical samples, the AUC of NCALD expression predicting chemotherapy outcome was 0.59 and 0.64, respectively. In clinical samples, low expression of NCALD was associated with poor OS and PFS.

Conclusions

NCALD may activate the ERK1 / 2 signaling pathway in ovarian cancer. As a new biomarker of chemotherapy sensitivity, NCALD was significantly down-regulated in chemotherapy resistance ovarian cancer patients. Low expression of NCALD in ovarian cancer is associated with poor OS and PFS. In the future, further research will be needed on the potential mechanism and clinical application value of NCALD in ovarian cancer.

Personalized Psychiatry and Depression: The Role of Sociodemographic and Clinical Variables

Despite several pharmacological options, the clinical outcomes of major depressive disorder (MDD) are often unsatisfactory. Personalized psychiatry attempts to tailor therapeutic interventions according to each patient's unique profile and characteristics. This approach can be a crucial strategy in improving pharmacological outcomes in MDD and overcoming trial-and-error treatment choices. In this narrative review, we evaluate whether sociodemographic (i.e., gender, age, race/ethnicity, and socioeconomic status) and clinical [i.e., body mass index (BMI), severity of depressive symptoms, and symptom profiles] variables that are easily assessable in clinical practice may help clinicians to optimize the selection of antidepressant treatment for each patient with MDD at the early stages of the disorder. We found that several variables were associated with poorer outcomes for all antidepressants. However, only preliminary associations were found between some clinical variables (i.e., BMI, anhedonia, and MDD with melancholic/atypical features) and possible benefits with some specific antidepressants. Finally, in clinical practice, the assessment of sociodemographic and clinical variables considered in our review can be valuable for early identification of depressed individuals at high risk for poor responses to antidepressants, but there are not enough data on which to ground any reliable selection of specific antidepressant class or compounds. Recent advances in computational resources, such as machine learning techniques, which are able to integrate multiple potential predictors, such as individual/ clinical variables, biomarkers, and genetic factors, may offer future reliable tools to guide personalized antidepressant choice for each patient with MDD.

C2H2-Type Zinc Finger Proteins in Brain Development, Neurodevelopmental, and Other Neuropsychiatric Disorders: Systematic Literature-Based Analysis

Neurodevelopmental disorders (NDDs) are multifaceted pathologic conditions manifested with intellectual disability, autistic features, psychiatric problems, motor dysfunction, and/or genetic/chromosomal abnormalities. They are associated with skewed neurogenesis and brain development, in part through dysfunction of the neural stem cells (NSCs) where abnormal transcriptional regulation on key genes play significant roles. Recent accumulated evidence highlights C₂H₂-type zinc finger proteins (C₂H₂-ZNFs), the largest transcription factor family in humans, as important targets for the pathologic processes associated with NDDs. In this review, we identified their significant accumulation (74 C₂H₂-ZNFs: ~10% of all human member proteins) in brain physiology and pathology. Specifically, we discuss their physiologic contribution to brain development, particularly focusing on their actions in NSCs. We then explain their pathologic implications in various forms of NDDs, such as morphological brain abnormalities, intellectual disabilities, and psychiatric disorders. We found an important tendency that poly-ZNFs and KRAB-ZNFs tend to be involved in the diseases that compromise gross brain structure and human-specific higher-order functions, respectively. This may be consistent with their characteristic appearance in the course of species evolution and corresponding contribution to these brain activities.

Predicting patient outcomes in psychiatric hospitals with routine data: a machine learning approach

BACKGROUND

A common problem in machine learning applications is availability of data at the point of decision making. The aim of the present study was to use routine data readily available at admission to predict aspects relevant to the organization of psychiatric hospital care. A further aim was to compare the results of a machine learning approach with those obtained through a traditional method and those obtained through a naive baseline classifier.

METHODS

The study included consecutively discharged patients between 1st of January 2017 and 31st of December 2018 from nine psychiatric hospitals in Hesse, Germany. We compared the predictive performance achieved by stochastic gradient boosting (GBM) with multiple logistic regression and a naive baseline classifier. We tested the performance of our final models on unseen patients from another calendar year and from different hospitals.

RESULTS

The study included 45,388 inpatient episodes. The models' performance, as measured by the area under the Receiver Operating Characteristic curve, varied strongly between the predicted outcomes, with relatively high performance in the prediction of coercive treatment (area under the curve: 0.83) and 1:1 observations (0.80) and relatively poor performance in the prediction of short length of stay (0.69) and non-response to treatment (0.65). The GBM performed slightly better than logistic regression. Both approaches were substantially better than a naive prediction based solely on basic diagnostic grouping.

CONCLUSION

The present study has shown that administrative routine data can be used to predict aspects relevant to the organisation of psychiatric hospital care. Future research should investigate the predictive performance that is necessary to provide effective assistance in clinical practice for the benefit of both staff and patients.

A polygenic predictor of treatment-resistant depression using whole exome sequencing and genome-wide genotyping

Treatment-resistant depression (TRD) occurs in ~30% of patients with major depressive disorder (MDD) but the genetics of TRD was previously poorly investigated. Whole exome sequencing and genome-wide genotyping were available in 1209 MDD patients after quality control. Antidepressant response was compared to non-response to one treatment and non-response to two or more treatments (TRD). Differences in the risk of carrying damaging variants were tested. A score expressing the burden of variants in genes and pathways was calculated weighting each variant for its functional (Eigen) score and frequency. Gene-based and pathway-based scores were used to develop predictive models of TRD and non-response using gradient boosting in 70% of the sample (training) which were tested in the remaining 30% (testing), evaluating also the addition of clinical predictors. Independent replication was tested in STAR*D and GENDEP using exome array-based data. TRD and non-responders did not show higher risk to carry damaging variants compared to responders. Genes/pathways associated with TRD included those modulating cell survival and proliferation, neurodegeneration, and immune response. Genetic models showed significant prediction of TRD vs. response and they were improved by the addition of clinical predictors, but they were not significantly better than clinical predictors alone. Replication results were driven by clinical factors, except for a model developed in subjects treated with serotonergic antidepressants, which showed a clear improvement in prediction at the extremes of the genetic score distribution in STAR*D. These results suggested relevant biological mechanisms implicated in TRD and a new methodological approach to the prediction of TRD.

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.

Analysis of Features Selected by a Deep Learning Model for Differential Treatment Selection in Depression

Background: Deep learning has utility in predicting differential antidepressant treatment response among patients with major depressive disorder, yet there remains a paucity of research describing how to interpret deep learning models in a clinically or etiologically meaningful way. In this paper, we describe methods for analyzing deep learning models of clinical and demographic psychiatric data, using our recent work on a deep learning model of STAR*D and CO-MED remission prediction.

Methods: Our deep learning analysis with STAR*D and CO-MED yielded four models that predicted response to the four treatments used across the two datasets. Here, we use classical statistics and simple data representations to improve interpretability of the features output by our deep learning model and provide finer grained understanding of their clinical and etiological significance. Specifically, we use representations derived from our model to yield features predicting both treatment non-response and differential treatment response to four standard antidepressants, and use linear regression and t-tests to address questions about the contribution of trauma, education, and somatic symptoms to our models.

Results: Traditional statistics were able to probe the input features of our deep learning models, reproducing results from previous research, while providing novel insights into depression causes and treatments. We found that specific features were predictive of treatment response, and were able to break these down by treatment and non-response categories; that specific trauma indices were differentially predictive of baseline depression severity; that somatic symptoms were significantly different between males and females, and that education and low income proved important psycho-social stressors associated with depression.

Conclusion: Traditional statistics can augment interpretation of deep learning models. Such interpretation can lend us new hypotheses about depression and contribute to building causal models of etiology and prognosis. We discuss dataset-specific effects and ideal clinical samples for machine learning analysis aimed at improving tools to assist in optimizing treatment.

Genetic Intersections of Language and Neuropsychiatric Conditions

PURPOSE OF REVIEW

To better understand the shared basis of language and mental health, this review examines the behavioral and neurobiological features of aberrant language in five major neuropsychiatric conditions. Special attention is paid to genes implicated in both language and neuropsychiatric disorders, as they reveal biological domains likely to underpin the processes controlling both.

RECENT FINDINGS

Abnormal language and communication are common manifestations of neuropsychiatric conditions, and children with impaired language are more likely to develop psychiatric disorders than their peers. Major themes in the genetics of both language and psychiatry include master transcriptional regulators, like FOXP2; key developmental regulators, like AUTS2; and mediators of neurotransmission, like GRIN2A and CACNA1C.

Gene-Environment Interactions and Role of Epigenetics in Anxiety Disorders

Several environmental risk factors such as early adverse childhood experiences, stress, and stressful life events are associated with anxiety disorders. Current approaches such as epigenetics and gene-environment interactions were used to identify candidate biomarkers for anxiety disorders to assess determinants of disease. In this chapter, in relation to gene-environment interactions, a variety of association studies regarding anxiety disorders were surveyed. We then showed supporting results from recent association studies such as human studies and animal models in terms of the epigenetic contribution to disease susceptibility to anxiety disorders. At last, future directions and limitations are highlighted. With the advances in multi-omics technologies, innovative ideas regarding disease prevention and drug responsiveness in anxiety disorders require further research in epigenetics and gene-environment interactions.

Nell-1 Is a Key Functional Modulator in Osteochondrogenesis and Beyond

Neural EGFL-like 1 (Nell-1) is a well-studied osteogenic factor that has comparable osteogenic potency with the Food and Drug Administration-approved bone morphogenic protein 2 (BMP-2). In this review, which aims to summarize the advanced Nell-1 research in the past 10 y, we start with the correlation of structural and functional relevance of the Nell-1 protein with the identification of a specific receptor of Nell-1, contactin-associated protein-like 4 (Cntnap4), for osteogenesis. The indispensable role of Nell-1 in normal craniofacial and appendicular skeletal development and growth was also defined by using the newly developed tissue-specific Nell-1 knockout mouse lines in addition to the existing transgenic mouse models. With the achievements on Nell-1's osteogenic therapeutic evaluations from multiple preclinical animal models for local and systemic bone regeneration, the synergistic effect of Nell-1 with BMP-2 on osteogenesis, as well as the advantages of Nell-1 as an osteogenic protein with antiadipogenic, anti-inflammatory, and provascularized characteristics over BMP-2 in bone tissue engineering, is highlighted, which lays the groundwork for the clinical trial approval of Nell-1. At the molecular level, besides the mitogen-activated protein kinase (MAPK) signaling pathway, we emphasize the significant involvement of the Wnt/β-catenin pathway as well as the key regulatory molecules Runt-related transcription factor 2 (Runx2) in Nell-1-induced osteogenesis. In addition, the involvement of Nell-1 in chondrogenesis and its relevant pathologies have been revealed with the participation of the nuclear factor of activated T cells 1 (Nfatc1), Runx3, and Indian hedgehog (Ihh) signaling pathways, although the mechanistic insights of Nell-1's osteochondrogenic property will be continuously evolving. With this perspective, we elucidate some emerging and novel functional properties of Nell-1 in oral-dental and neural tissues that will be the frontiers of future Nell-1 studies beyond the context of bone and cartilage. As such, the therapeutic potential of Nell-1 continues to evolve and grow with continuous pursuit.

Association and Interaction Effects of Interleukin-12 Related Genes and Physical Activity on Cognitive Aging in Old Adults in the Taiwanese Population

Evidence suggests that the neuro-inflammation mechanisms associated with interleukin-12 (IL-12) may be linked to Alzheimer's diseases and cognitive aging. In this study, we speculate that single nucleotide polymorphisms (SNPs) in IL-12-associated genes, such as IL12A, IL12B, IL12RB1, and IL12RB2 genes, could be associated with cognitive aging individually and/or via complicated interactions in the elder Taiwanese population. There were totally 3,730 Taiwanese individuals with age ≥60 years from the Taiwan Biobank. Mini-Mental State Examination (MMSE) was analyzed for all participants. We employed MMSE scores to assess cognitive functions. Our analysis revealed that the IL12A gene (including rs116910715, rs78902931, and rs78569420), the IL12B gene (including rs730691), and the IL12RB2 gene (including rs3790558, rs4655538, rs75699623, and rs1874396) were associated with cognitive aging. Among these SNPs, the association with the IL12RB2 rs3790558 SNP remained significant after performing Bonferroni correction (P = 6.87 × 10⁻⁴). Additionally, we found that interactions between the IL12A and IL12RB2 genes influenced cognitive aging (P = 0.022). Finally, we pinpointed the effects of interactions between IL12A, IL12B, and IL12RB2 with physical activity (P < 0.001, = 0.002, and < 0.001, respectively). Our study suggests that the IL-12-associated genes may contribute to susceptibility to cognitive aging independently as well as through gene-gene and gene-physical activity interactions.

Biomarkers in aggression

Aggressive behavior exerts an enormous impact on society remaining among the main causes of worldwide premature death. Effective primary interventions, relying on predictive models of aggression that show adequate sensitivity and specificity are currently lacking. One strategy to increase the accuracy and precision of prediction would be to include biological data in the predictive models. Clearly, to be included in such models, biological markers should be reliably associated with the specific trait under study (i.e., diagnostic biomarkers). Aggression, however, is phenotypically highly heterogeneous, an element that has hindered the identification of reliable biomarkers. However, current research is trying to overcome these challenges by focusing on more homogenous aggression subtypes and/or by studying large sample size of aggressive individuals. Further advance is coming by bioinformatics approaches that are allowing the integration of inter-species biological data as well as the development of predictive algorithms able to discriminate subjects on the basis of the propensity toward aggressive behavior. In this review we first present a brief summary of the available evidence on neuroimaging of aggression. We will then treat extensively the data on genetic determinants, including those from hypothesis-free genome-wide association studies (GWAS) and candidate gene studies. Transcriptomic and neurochemical biomarkers will then be reviewed, and we will dedicate a section on the role of metabolomics in aggression. Finally, we will discuss how biomarkers can inform the development of new pharmacological tools as well as increase the efficacy of preventive strategies.

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.

Pharmacogenetics and Depression: A Critical Perspective

Depression leads the higher personal and socio-economical burden within psychiatric disorders. Despite the fact that over 40 antidepressants (ADs) are available, suboptimal response still poses a major challenge and is thought to be partially a result of genetic variation. Pharmacogenetics studies the effects of genetic variants on treatment outcomes with the aim of providing tailored treatments, thereby maximizing efficacy and tolerability. After two decades of pharmacogenetic research, variants in genes coding for the cytochromes involved in ADs metabolism (CYP2D6 and CYP2C19) are now considered biomarkers with sufficient scientific support for clinical application, despite the lack of conclusive cost/effectiveness evidence. The effect of variants in genes modulating ADs mechanisms of action (pharmacodynamics) is still controversial, because of the much higher complexity of ADs pharmacodynamics compared to ADs metabolism. Considerable progress has been made since the era of candidate gene studies: the genomic revolution has made possible to assess genetic variance on an unprecedented scale, throughout the whole genome, and to analyze the cumulative effect of different variants. The results have revealed key information on the biological mechanisms mediating ADs effect and identified hypothetical new pharmacological targets. They also paved the way for future availability of polygenic pharmacogenetic panels to predict treatment outcome, which are expected to explain much higher variance in ADs response compared to CYP2D6 and CYP2C19 only. As the demand and availability of AD pharmacogenetic testing is projected to increase, it is important for clinicians to keep abreast of this evolving area to facilitate informed discussions with their patients.

Genetic Associations between Voltage-Gated Calcium Channels and Psychiatric Disorders

Psychiatric disorders are mental, behavioral or emotional disorders. These conditions are prevalent, one in four adults suffer from any type of psychiatric disorders world-wide. It has always been observed that psychiatric disorders have a genetic component, however, new methods to sequence full genomes of large cohorts have identified with high precision genetic risk loci for these conditions. Psychiatric disorders include, but are not limited to, bipolar disorder, schizophrenia, autism spectrum disorder, anxiety disorders, major depressive disorder, and attention-deficit and hyperactivity disorder. Several risk loci for psychiatric disorders fall within genes that encode for voltage-gated calcium channels (CaVs). Calcium entering through CaVs is crucial for multiple neuronal processes. In this review, we will summarize recent findings that link CaVs and their auxiliary subunits to psychiatric disorders. First, we will provide a general overview of CaVs structure, classification, function, expression and pharmacology. Next, we will summarize tools to study risk loci associated with psychiatric disorders. We will examine functional studies of risk variations in CaV genes when available. Finally, we will review pharmacological evidence of the use of CaV modulators to treat psychiatric disorders. Our review will be of interest for those studying pathophysiological aspects of CaVs.

Pharmacogenomics-Driven Prediction of Antidepressant Treatment Outcomes: A Machine-Learning Approach With Multi-trial Replication

We set out to determine whether machine learning–based algorithms that included functionally validated pharmacogenomic biomarkers joined with clinical measures could predict selective serotonin reuptake inhibitor (SSRI) remission/response in patients with major depressive disorder (MDD). We studied 1,030 white outpatients with MDD treated with citalopram/escitalopram in the Mayo Clinic Pharmacogenomics Research Network Antidepressant Medication Pharmacogenomic Study (PGRN‐AMPS; n = 398), Sequenced Treatment Alternatives to Relieve Depression (STAR*D; n = 467), and International SSRI Pharmacogenomics Consortium (ISPC; n = 165) trials. A genomewide association study for PGRN‐AMPS plasma metabolites associated with SSRI response (serotonin) and baseline MDD severity (kynurenine) identified single nucleotide polymorphisms (SNPs) in DEFB1,ERICH3,AHR, and TSPAN5 that we tested as predictors. Supervised machine‐learning methods trained using SNPs and total baseline depression scores predicted remission and response at 8 weeks with area under the receiver operating curve (AUC) > 0.7 (P < 0.04) in PGRN‐AMPS patients, with comparable prediction accuracies > 69% (P ≤ 0.07) in STAR*D and ISPC. These results demonstrate that machine learning can achieve accurate and, importantly, replicable prediction of SSRI therapy response using total baseline depression severity combined with pharmacogenomic biomarkers.

Polymorphisms of the DNA repair gene EXO1 modulate cognitive aging in old adults in a Taiwanese population

Evidence indicates that the age-related neuropathological mechanisms associated with DNA repair genes may contribute to cognitive aging and Alzheimer's disease. In this study, we hypothesize that single nucleotide polymorphisms (SNPs) within 155 DNA repair genes may be linked to cognitive aging independently and/or through complex interactions in an older Taiwanese population. A total of 3,730 Taiwanese subjects aged over 60 years from the Taiwan Biobank were analyzed. Mini-Mental State Examination (MMSE) was administered to all subjects, and MMSE scores were used to measure cognitive functions. Our data showed that out of 1,652 SNPs, the rs1776181 (P = 1.47 × 10^-5), rs1776177 (P = 8.42 × 10^-7), rs1635510 (P = 7.97 × 10^-6), and rs2526698 (P = 7.06 × 10^-6) SNPs in the EXO1 gene were associated with cognitive aging. The association with these SNP remained significant after performing Bonferroni correction. Additionally, we found that interactions between the EXO1 and RAD51C genes influenced cognitive aging (P = 0.002). Finally, we pinpointed the influence of interactions between EXO1 and physical activity (P < 0.001) as well as between DCLRE1C and physical activity (P < 0.001). Our study indicated that DNA repair genes may contribute to susceptibility in cognitive aging independently as well as through gene-gene and gene-physical interactions.

Translating cancer genomics into precision medicine with artificial intelligence: applications, challenges and future perspectives

In the field of cancer genomics, the broad availability of genetic information offered by next-generation sequencing technologies and rapid growth in biomedical publication has led to the advent of the big-data era. Integration of artificial intelligence (AI) approaches such as machine learning, deep learning, and natural language processing (NLP) to tackle the challenges of scalability and high dimensionality of data and to transform big data into clinically actionable knowledge is expanding and becoming the foundation of precision medicine. In this paper, we review the current status and future directions of AI application in cancer genomics within the context of workflows to integrate genomic analysis for precision cancer care. The existing solutions of AI and their limitations in cancer genetic testing and diagnostics such as variant calling and interpretation are critically analyzed. Publicly available tools or algorithms for key NLP technologies in the literature mining for evidence-based clinical recommendations are reviewed and compared. In addition, the present paper highlights the challenges to AI adoption in digital healthcare with regard to data requirements, algorithmic transparency, reproducibility, and real-world assessment, and discusses the importance of preparing patients and physicians for modern digitized healthcare. We believe that AI will remain the main driver to healthcare transformation toward precision medicine, yet the unprecedented challenges posed should be addressed to ensure safety and beneficial impact to healthcare.

Development of Neuroimaging-Based Biomarkers in Psychiatry

This chapter presents an overview of accumulating neuroimaging data with emphasis on translational potential. The subject will be described in the context of three disease states, i.e., schizophrenia, bipolar disorder, and major depressive disorder, and for three clinical goals, i.e., disease risk assessment, subtyping, and treatment decision.

Precision pharmacotherapy: psychiatry's future direction in preventing, diagnosing, and treating mental disorders

Mental disorders account for around one-third of disability worldwide and cause enormous personal and societal burden. Current pharmacotherapies and nonpharmacotherapies do help many patients, but there are still high rates of partial or no response, delayed effect, and unfavorable adverse effects. The current diagnostic taxonomy of mental disorders by the Diagnostic and Statistical Manual of Mental Disorders and the International Classification of Diseases relies on presenting signs and symptoms, but does not reflect evidence from neurobiological and behavioral systems. However, in the last decades, the understanding of biological mechanisms underlying mental disorders has grown and can be used for the development of precision medicine, that is, to deliver a patient-tailored individual treatment. Precision medicine may incorporate genetic variants contributing to the mental disorder and the response to pharmacotherapies, but also consider gene ¥ environment interactions, blood-based markers, neuropsychological tests, data from electronic health records, early life adversity, stressful life events, and very proximal factors such as lifestyle, nutrition, and sport. Methods such as artificial intelligence and the underlying machine learning and deep learning approaches provide the framework to stratify patients, initiate specific tailored treatments and thus increase response rates, reduce adverse effects and medical errors. In conclusion, precision medicine uses measurable health parameters to identify individuals at risk of a mental disorder, to improve the diagnostic process and to deliver a patient-tailored treatment.

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.