Augmentation of Physician Assessments with Multi-Omics Enhances Predictability of Drug Response: A Case Study of Major Depressive Disorder

Comprehensive multi-omics profiling identifies novel molecular subtypes of pancreatic ductal adenocarcinoma

Pancreatic cancer, a highly fatal malignancy, is predicted to rank as the second leading cause of cancer-related death in the next decade. This highlights the urgent need for new insights into personalized diagnosis and treatment. Although molecular subtypes of pancreatic cancer were well established in genomics and transcriptomics, few known molecular classifications are translated to guide clinical strategies and require a paradigm shift. Notably, chronically developing and continuously improving high-throughput technologies and systems serve as an important driving force to further portray the molecular landscape of pancreatic cancer in terms of epigenomics, proteomics, metabonomics, and metagenomics. Therefore, a more comprehensive understanding of molecular classifications at multiple levels using an integrated multi-omics approach holds great promise to exploit more potential therapeutic options. In this review, we recapitulated the molecular spectrum from different omics levels, discussed various subtypes on multi-omics means to move one step forward towards bench-to-beside translation of pancreatic cancer with clinical impact, and proposed some methodological and scientific challenges in store.

Pharmacogenomic augmented machine learning in electronic health record alerts: A health system-wide usability survey of clinicians

Pharmacogenomic (PGx) biomarkers integrated using machine learning can be embedded within the electronic health record (EHR) to provide clinicians with individualized predictions of drug treatment outcomes. Currently, however, drug alerts in the EHR are largely generic (not patient-specific) and contribute to increased clinician stress and burnout. Improving the usability of PGx alerts is an urgent need. Therefore, this work aimed to identify principles for optimal PGx alert design through a health-system-wide, mixed-methods study. Clinicians representing multiple practices and care settings (N = 1062) in urban, rural, and underserved regions were invited to complete an electronic survey comparing the usability of three drug alerts for citalopram, as a case study. Alert 1 contained a generic warning of pharmacogenomic effects on citalopram metabolism. Alerts 2 and 3 provided patient-specific predictions of citalopram efficacy with varying depth of information. Primary outcomes included the System's Usability Scale score (0-100 points) of each alert, the perceived impact of each alert on stress and decision-making, and clinicians' suggestions for alert improvement. Secondary outcomes included the assessment of alert preference by clinician age, practice type, and geographic setting. Qualitative information was captured to provide context to quantitative information. The final cohort comprised 305 geographically and clinically diverse clinicians. A simplified, individualized alert (Alert 2) was perceived as beneficial for decision-making and stress compared with a more detailed version (Alert 3) and the generic alert (Alert 1) regardless of age, practice type, or geographic setting. Findings emphasize the need for clinician-guided design of PGx alerts in the era of digital medicine.

Machine Learning Predicts Conversion from Normal Aging to Mild Cognitive Impairment Using Medical History, APOE Genotype, and Neuropsychological Assessment

Background

Identifying individuals at risk for mild cognitive impairment (MCI) is of urgent clinical need.

Objective

This study aimed to determine whether machine learning approaches could harness longitudinal neuropsychology measures, medical data, and APOEɛ4 genotype to identify individuals at risk of MCI 1 to 2 years prior to diagnosis.

Methods

Data from 676 individuals who participated in the 'APOE in the Predisposition to, Protection from and Prevention of Alzheimer's Disease' longitudinal study (N = 66 who converted to MCI) were utilized in supervised machine learning algorithms to predict conversion to MCI.

Results

A random forest algorithm predicted conversion 1-2 years prior to diagnosis with 97% accuracy (p = 0.0026). The global minima (each individual's lowest score) of memory measures from the 'Rey Auditory Verbal Learning Test' and the 'Selective Reminding Test' were the strongest predictors.

Conclusions

This study demonstrates the feasibility of using machine learning to identify individuals likely to convert from normal cognition to MCI.

Dealing with dimensionality: the application of machine learning to multi-omics data

MOTIVATION

Machine learning (ML) methods are motivated by the need to automate information extraction from large datasets in order to support human users in data-driven tasks. This is an attractive approach for integrative joint analysis of vast amounts of omics data produced in next generation sequencing and other -omics assays. A systematic assessment of the current literature can help to identify key trends and potential gaps in methodology and applications. We surveyed the literature on ML multi-omic data integration and quantitatively explored the goals, techniques and data involved in this field. We were particularly interested in examining how researchers use ML to deal with the volume and complexity of these datasets.

RESULTS

Our main finding is that the methods used are those that address the challenges of datasets with few samples and many features. Dimensionality reduction methods are used to reduce the feature count alongside models that can also appropriately handle relatively few samples. Popular techniques include autoencoders, random forests and support vector machines. We also found that the field is heavily influenced by the use of The Cancer Genome Atlas dataset, which is accessible and contains many diverse experiments.

AVAILABILITY AND IMPLEMENTATION

All data and processing scripts are available at this GitLab repository: https://gitlab.com/polavieja_lab/ml_multi-omics_review/ or in Zenodo: https://doi.org/10.5281/zenodo.7361807.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Methodological and Quality Flaws in the Use of Artificial Intelligence in Mental Health Research: Systematic Review

BACKGROUND

Artificial intelligence (AI) is giving rise to a revolution in medicine and health care. Mental health conditions are highly prevalent in many countries, and the COVID-19 pandemic has increased the risk of further erosion of the mental well-being in the population. Therefore, it is relevant to assess the current status of the application of AI toward mental health research to inform about trends, gaps, opportunities, and challenges.

OBJECTIVE

This study aims to perform a systematic overview of AI applications in mental health in terms of methodologies, data, outcomes, performance, and quality.

METHODS

A systematic search in PubMed, Scopus, IEEE Xplore, and Cochrane databases was conducted to collect records of use cases of AI for mental health disorder studies from January 2016 to November 2021. Records were screened for eligibility if they were a practical implementation of AI in clinical trials involving mental health conditions. Records of AI study cases were evaluated and categorized by the International Classification of Diseases 11th Revision (ICD-11). Data related to trial settings, collection methodology, features, outcomes, and model development and evaluation were extracted following the CHARMS (Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies) guideline. Further, evaluation of risk of bias is provided.

RESULTS

A total of 429 nonduplicated records were retrieved from the databases and 129 were included for a full assessment-18 of which were manually added. The distribution of AI applications in mental health was found unbalanced between ICD-11 mental health categories. Predominant categories were Depressive disorders (n=70) and Schizophrenia or other primary psychotic disorders (n=26). Most interventions were based on randomized controlled trials (n=62), followed by prospective cohorts (n=24) among observational studies. AI was typically applied to evaluate quality of treatments (n=44) or stratify patients into subgroups and clusters (n=31). Models usually applied a combination of questionnaires and scales to assess symptom severity using electronic health records (n=49) as well as medical images (n=33). Quality assessment revealed important flaws in the process of AI application and data preprocessing pipelines. One-third of the studies (n=56) did not report any preprocessing or data preparation. One-fifth of the models were developed by comparing several methods (n=35) without assessing their suitability in advance and a small proportion reported external validation (n=21). Only 1 paper reported a second assessment of a previous AI model. Risk of bias and transparent reporting yielded low scores due to a poor reporting of the strategy for adjusting hyperparameters, coefficients, and the explainability of the models. International collaboration was anecdotal (n=17) and data and developed models mostly remained private (n=126).

CONCLUSIONS

These significant shortcomings, alongside the lack of information to ensure reproducibility and transparency, are indicative of the challenges that AI in mental health needs to face before contributing to a solid base for knowledge generation and for being a support tool in mental health management.

Multi-omics data integration methods and their applications in psychiatric disorders

To study mental illness and health, in the past researchers have often broken down their complexity into individual subsystems (e.g., genomics, transcriptomics, proteomics, clinical data) and explored the components independently. Technological advancements and decreasing costs of high throughput sequencing has led to an unprecedented increase in data generation. Furthermore, over the years it has become increasingly clear that these subsystems do not act in isolation but instead interact with each other to drive mental illness and health. Consequently, individual subsystems are now analysed jointly to promote a holistic understanding of the underlying biological complexity of health and disease. Complementing the increasing data availability, current research is geared towards developing novel methods that can efficiently combine the information rich multi-omics data to discover biologically meaningful biomarkers for diagnosis, treatment, and prognosis. However, clinical translation of the research is still challenging. In this review, we summarise conventional and state-of-the-art statistical and machine learning approaches for discovery of biomarker, diagnosis, as well as outcome and treatment response prediction through integrating multi-omics and clinical data. In addition, we describe the role of biological model systems and in silico multi-omics model designs in clinical translation of psychiatric research from bench to bedside. Finally, we discuss the current challenges and explore the application of multi-omics integration in future psychiatric research. The review provides a structured overview and latest updates in the field of multi-omics in psychiatry.

Multi-omic modeling of antidepressant response implicates dynamic immune and inflammatory changes in individuals who respond to treatment

BACKGROUND

Major depressive disorder (MDD) is a leading cause of disability worldwide, and is commonly treated with antidepressant drugs (AD). Although effective, many patients fail to respond to AD treatment, and accordingly identifying factors that can predict AD response would greatly improve treatment outcomes. In this study, we developed a machine learning tool to integrate multi-omic datasets (gene expression, DNA methylation, and genotyping) to identify biomarker profiles associated with AD response in a cohort of individuals with MDD.

MATERIALS AND METHODS

Individuals with MDD (N = 111) were treated for 8 weeks with antidepressants and were separated into responders and non-responders based on the Montgomery-Åsberg Depression Rating Scale (MADRS). Using peripheral blood samples, we performed RNA-sequencing, assessed DNA methylation using the Illumina EPIC array, and performed genotyping using the Illumina PsychArray. To address this rich multi-omic dataset with high dimensional features, we developed integrative Geneset-Embedded non-negative Matrix factorization (iGEM), a non-negative matrix factorization (NMF) based model, supplemented with auxiliary information regarding gene sets and gene-methylation relationships. In particular, we factorize the subjects by features (i.e., gene expression or DNA methylation) into subjects-by-factors and factors-by-features. We define the factors as the meta-phenotypes as they represent integrated composite scores of the molecular measurements for each subject.

RESULTS

Using our model, we identified a number of meta-phenotypes which were related to AD response. By integrating geneset information into the model, we were able to relate these meta-phenotypes to biological processes, including a meta-phenotype related to immune and inflammatory functions as well as other genes related to depression or AD response. The meta-phenotype identified several genes including immune interleukin 1 receptor like 1 (IL1RL1) and interleukin 5 receptor (IL5) subunit alpha (IL5RA), AKT/PIK3 pathway related phosphoinositide-3-kinase regulatory subunit 6 (PIK3R6), and sphingomyelin phosphodiesterase 3 (SMPD3), which has been identified as a target of AD treatment.

CONCLUSIONS

The derived meta-phenotypes and associated biological functions represent both biomarkers to predict response, as well as potential new treatment targets. Our method is applicable to other diseases with multi-omic data, and the software is open source and available on Github (https://github.com/li-lab-mcgill/iGEM).

Network science approach elucidates integrative genomic-metabolomic signature of antidepressant response and lifetime history of attempted suicide in adults with major depressive disorder

Background: Individuals with major depressive disorder (MDD) and a lifetime history of attempted suicide demonstrate lower antidepressant response rates than those without a prior suicide attempt. Identifying biomarkers of antidepressant response and lifetime history of attempted suicide may help augment pharmacotherapy selection and improve the objectivity of suicide risk assessments. Towards this goal, this study sought to use network science approaches to establish a multi-omics (genomic and metabolomic) signature of antidepressant response and lifetime history of attempted suicide in adults with MDD. Methods: Single nucleotide variants (SNVs) which associated with suicide attempt(s) in the literature were identified and then integrated with a) p180-assayed metabolites collected prior to antidepressant pharmacotherapy and b) a binary measure of antidepressant response at 8 weeks of treatment using penalized regression-based networks in 245 'Pharmacogenomics Research Network Antidepressant Medication Study (PGRN-AMPS)' and 103 'Combining Medications to Enhance Depression Outcomes (CO-MED)' patients with major depressive disorder. This approach enabled characterization and comparison of biological profiles and associated antidepressant treatment outcomes of those with (N = 46) and without (N = 302) a self-reported lifetime history of suicide attempt. Results: 351 SNVs were associated with suicide attempt(s) in the literature. Intronic SNVs in the circadian genes CLOCK and ARNTL (encoding the CLOCK:BMAL1 heterodimer) were amongst the top network analysis features to differentiate patients with and without a prior suicide attempt. CLOCK and ARNTL differed in their correlations with plasma phosphatidylcholines, kynurenine, amino acids, and carnitines between groups. CLOCK and ARNTL-associated phosphatidylcholines showed a positive correlation with antidepressant response in individuals without a prior suicide attempt which was not observed in the group with a prior suicide attempt. Conclusion: Results provide evidence for a disturbance between CLOCK:BMAL1 circadian processes and circulating phosphatidylcholines, kynurenine, amino acids, and carnitines in individuals with MDD who have attempted suicide. This disturbance may provide mechanistic insights for differential antidepressant pharmacotherapy outcomes between patients with MDD with versus without a lifetime history of attempted suicide. Future investigations of CLOCK:BMAL1 metabolic regulation in the context of suicide attempts may help move towards biologically-augmented pharmacotherapy selection and stratification of suicide risk for subgroups of patients with MDD and a lifetime history of attempted suicide.

Role of Omics in Migraine Research and Management: A Narrative Review

Migraine is a neurological disorder defined by episodic attacks of chronic pain associated with nausea, photophobia, and phonophobia. It is known to be a complex disease with several environmental and genetic factors contributing to its susceptibility. Risk factors for migraine include head or neck injury (Arnold, Cephalalgia 38(1):1-211, 2018). Stress and high temperature are known to trigger migraine, while sleep disorders and anxiety are considered to be the comorbid conditions with migraine. Studies have reported various biomarkers, including genetic variants, proteins, and metabolites implicated in migraine's pathophysiology. Using the "omics" approach, which deals with genetics, transcriptomics, proteomics, and metabolomics, more specific biomarkers for various migraine can be identified. On account of its multifactorial nature, migraine is an ideal study model focusing on integrated omics approaches, including genomics, transcriptomics, proteomics, and metabolomics. The current review has been compiled with an aim to focus on the genomic alterations especially involved in the regulation of glutamatergic neurotransmission, cortical excitability, ion channels, solute carrier proteins, or receptors; their expression in migraine patients and also specific proteins and metabolites, including some inflammatory biomarkers that might represent the migraine phenotype at the molecular level. The systems biology approach holds the promise to understand the pathophysiology of the disease at length and also to identify the specific therapeutic targets for novel interventions.

Improving Pain Assessment Using Vital Signs and Pain Medication for Patients With Sickle Cell Disease: Retrospective Study

BACKGROUND

Sickle cell disease (SCD) is the most common inherited blood disorder affecting millions of people worldwide. Most patients with SCD experience repeated, unpredictable episodes of severe pain. These pain episodes are the leading cause of emergency department visits among patients with SCD and may last for several weeks. Arguably, the most challenging aspect of treating pain episodes in SCD is assessing and interpreting a patient's pain intensity level.

OBJECTIVE

This study aims to learn deep feature representations of subjective pain trajectories using objective physiological signals collected from electronic health records.

METHODS

This study used electronic health record data collected from 496 Duke University Medical Center participants over 5 consecutive years. Each record contained measures for 6 vital signs and the patient's self-reported pain score, with an ordinal range from 0 (no pain) to 10 (severe and unbearable pain). We also extracted 3 features related to medication: medication type, medication status (given or applied, or missed or removed or due), and total medication dosage (mg/mL). We used variational autoencoders for representation learning and designed machine learning classification algorithms to build pain prediction models. We evaluated our results using an accuracy and confusion matrix and visualized the qualitative data representations.

RESULTS

We designed a classification model using raw data and deep representational learning to predict subjective pain scores with average accuracies of 82.8%, 70.6%, 49.3%, and 47.4% for 2-point, 4-point, 6-point, and 11-point pain ratings, respectively. We observed that random forest classification models trained on deep represented features outperformed models trained on unrepresented data for all pain rating scales. We observed that at varying Likert scales, our models performed better when provided with medication data along with vital signs data. We visualized the data representations to understand the underlying latent representations, indicating neighboring representations for similar pain scores with a higher resolution of pain ratings.

CONCLUSIONS

Our results demonstrate that medication information (the type of medication, total medication dosage, and whether the medication was given or missed) can significantly improve subjective pain prediction modeling compared with modeling with only vital signs. This study shows promise in data-driven estimated pain scores that will help clinicians with additional information about the patient's condition, in addition to the patient's self-reported pain scores.

Multi-Omics Characterization of Early- and Adult-Onset Major Depressive Disorder

Age at depressive onset (AAO) corresponds to unique symptomatology and clinical outcomes. Integration of genome-wide association study (GWAS) results with additional “omic” measures to evaluate AAO has not been reported and may reveal novel markers of susceptibility and/or resistance to major depressive disorder (MDD). To address this gap, we integrated genomics with metabolomics using data-driven network analysis to characterize and differentiate MDD based on AAO. This study first performed two GWAS for AAO as a continuous trait in (a) 486 adults from the Pharmacogenomic Research Network-Antidepressant Medication Pharmacogenomic Study (PGRN-AMPS), and (b) 295 adults from the Combining Medications to Enhance Depression Outcomes (CO-MED) study. Variants from top signals were integrated with 153 p180-assayed metabolites to establish multi-omics network characterizations of early (<age 18) and adult-onset depression. The most significant variant (p = 8.77 × 10−8) localized to an intron of SAMD3. In silico functional annotation of top signals (p < 1 × 10−5) demonstrated gene expression enrichment in the brain and during embryonic development. Network analysis identified differential associations between four variants (in/near INTU, FAT1, CNTN6, and TM9SF2) and plasma metabolites (phosphatidylcholines, carnitines, biogenic amines, and amino acids) in early- compared with adult-onset MDD. Multi-omics integration identified differential biosignatures of early- and adult-onset MDD. These biosignatures call for future studies to follow participants from childhood through adulthood and collect repeated -omics and neuroimaging measures to validate and deeply characterize the biomarkers of susceptibility and/or resistance to MDD development.

Deep Learning Classification of Breast Cancer Tissue from Terahertz Imaging Through Wavelet Synchro-Squeezed Transformation and Transfer Learning

Terahertz imaging and spectroscopy is an exciting technology that has the potential to provide insights in medical imaging. Prior research has leveraged statistical inference to classify tissue regions from terahertz images. To date, these approaches have shown that the segmentation problem is challenging for images of fresh tissue and for tumors that have invaded muscular regions. Artificial intelligence, particularly machine learning and deep learning, has been shown to improve performance in some medical imaging challenges. This paper builds on that literature by modifying a set of deep learning approaches to the challenge of classifying tissue regions of images captured by terahertz imaging and spectroscopy of freshly excised murine xenograft tissue. Our approach is to preprocess the images through a wavelet synchronous-squeezed transformation (WSST) to convert time-sequential terahertz data of each THz pixel to a spectrogram. Spectrograms are used as input tensors to a deep convolution neural network for pixel-wise classification. Based on the classification result of each pixel, a cancer tissue segmentation map is achieved. In experimentation, we adopt leave-one-sample-out cross-validation strategy, and evaluate our chosen networks and results using multiple metrics such as accuracy, precision, intersection, and size. The results from this experimentation demonstrate improvement in classification accuracy compared to statistical methods, an improvement to segmentation between muscle and cancerous regions in xenograft tumors, and identify areas to improve the imaging and classification methodology.

Multi-omics driven predictions of response to acute phase combination antidepressant therapy: a machine learning approach with cross-trial replication

Combination antidepressant pharmacotherapies are frequently used to treat major depressive disorder (MDD). However, there is no evidence that machine learning approaches combining multi-omics measures (e.g., genomics and plasma metabolomics) can achieve clinically meaningful predictions of outcomes to combination pharmacotherapy. This study examined data from 264 MDD outpatients treated with citalopram or escitalopram in the Mayo Clinic Pharmacogenomics Research Network Antidepressant Medication Pharmacogenomic Study (PGRN-AMPS) and 111 MDD outpatients treated with combination pharmacotherapies in the Combined Medications to Enhance Outcomes of Antidepressant Therapy (CO-MED) study to predict response to combination antidepressant therapies. To assess whether metabolomics with functionally validated single-nucleotide polymorphisms (SNPs) improves predictability over metabolomics alone, models were trained/tested with and without SNPs. Models trained with PGRN-AMPS' and CO-MED's escitalopram/citalopram patients predicted response in CO-MED's combination pharmacotherapy patients with accuracies of 76.6% (p < 0.01; AUC: 0.85) without and 77.5% (p < 0.01; AUC: 0.86) with SNPs. Then, models trained solely with PGRN-AMPS' escitalopram/citalopram patients predicted response in CO-MED's combination pharmacotherapy patients with accuracies of 75.3% (p < 0.05; AUC: 0.84) without and 77.5% (p < 0.01; AUC: 0.86) with SNPs, demonstrating cross-trial replication of predictions. Plasma hydroxylated sphingomyelins were prominent predictors of treatment outcomes. To explore the relationship between SNPs and hydroxylated sphingomyelins, we conducted multi-omics integration network analysis. Sphingomyelins clustered with SNPs and metabolites related to monoamine neurotransmission, suggesting a potential functional relationship. These results suggest that integrating specific metabolites and SNPs achieves accurate predictions of treatment response across classes of antidepressants. Finally, these results motivate functional investigation into how sphingomyelins might influence MDD pathophysiology, antidepressant response, or both.

Prediction of short-term antidepressant response using probabilistic graphical models with replication across multiple drugs and treatment settings

Heterogeneity in the clinical presentation of major depressive disorder and response to antidepressants limits clinicians' ability to accurately predict a specific patient's eventual response to therapy. Validated depressive symptom profiles may be an important tool for identifying poor outcomes early in the course of treatment. To derive these symptom profiles, we first examined data from 947 depressed subjects treated with selective serotonin reuptake inhibitors (SSRIs) to delineate the heterogeneity of antidepressant response using probabilistic graphical models (PGMs). We then used unsupervised machine learning to identify specific depressive symptoms and thresholds of improvement that were predictive of antidepressant response by 4 weeks for a patient to achieve remission, response, or nonresponse by 8 weeks. Four depressive symptoms (depressed mood, guilt feelings and delusion, work and activities and psychic anxiety) and specific thresholds of change in each at 4 weeks predicted eventual outcome at 8 weeks to SSRI therapy with an average accuracy of 77% (p = 5.5E-08). The same four symptoms and prognostic thresholds derived from patients treated with SSRIs correctly predicted outcomes in 72% (p = 1.25E-05) of 1996 patients treated with other antidepressants in both inpatient and outpatient settings in independent publicly-available datasets. These predictive accuracies were higher than the accuracy of 53% for predicting SSRI response achieved using approaches that (i) incorporated only baseline clinical and sociodemographic factors, or (ii) used 4-week nonresponse status to predict likely outcomes at 8 weeks. The present findings suggest that PGMs providing interpretable predictions have the potential to enhance clinical treatment of depression and reduce the time burden associated with trials of ineffective antidepressants. Prospective trials examining this approach are forthcoming.

Temporal and spectral unmixing of photoacoustic signals by deep learning

Improving the imaging speed of multi-parametric photoacoustic microscopy (PAM) is essential to leveraging its impact in biomedicine. However, to avoid temporal overlap, the A-line rate is limited by the acoustic speed in biological tissues to a few megahertz. Moreover, to achieve high-speed PAM of the oxygen saturation of hemoglobin, the stimulated Raman scattering effect in optical fibers has been widely used to generate 558 nm from a commercial 532 nm laser for dual-wavelength excitation. However, the fiber length for effective wavelength conversion is typically short, corresponding to a small time delay that leads to a significant overlap of the A-lines acquired at the two wavelengths. Increasing the fiber length extends the time interval but limits the pulse energy at 558 nm. In this Letter, we report a conditional generative adversarial network-based approach that enables temporal unmixing of photoacoustic A-line signals with an interval as short as ${\sim}{38}\;{\rm ns}$, breaking the physical limit on the A-line rate. Moreover, this deep learning approach allows the use of multi-spectral laser pulses for PAM excitation, addressing the insufficient energy of monochromatic laser pulses. This technique lays the foundation for ultrahigh-speed multi-parametric PAM.

Pharmacometabonomics: data processing and statistical analysis

Individual variations in drug efficacy, side effects and adverse drug reactions are still challenging that cannot be ignored in drug research and development. The aim of pharmacometabonomics is to better understand the pharmacokinetic properties of drugs and monitor the drug effects on specific metabolic pathways. Here, we systematically reviewed the recent technological advances in pharmacometabonomics for better understanding the pathophysiological mechanisms of diseases as well as the metabolic effects of drugs on bodies. First, the advantages and disadvantages of all mainstream analytical techniques were compared. Second, many data processing strategies including filtering, missing value imputation, quality control-based correction, transformation, normalization together with the methods implemented in each step were discussed. Third, various feature selection and feature extraction algorithms commonly applied in pharmacometabonomics were described. Finally, the databases that facilitate current pharmacometabonomics were collected and discussed. All in all, this review provided guidance for researchers engaged in pharmacometabonomics and metabolomics, and it would promote the wide application of metabolomics in drug research and personalized medicine.

Prospects for personalization of depression treatment with genome sequencing

The effectiveness of antidepressants in the treatment of major depressive disorder varies considerably between patients. With these interindividual differences and a number of antidepressants to choose from, the first choice of treatment often fails to produce improvement in the patient's condition. A substantial part of the variation in response to antidepressants can be explained by genetic factors. Accordingly, variants related to drug metabolism in two pharmacogenes, CYP2D6 and CYP2C19, have already been translated into guidelines for antidepressant prescriptions. The role of variants in other genes that influence antidepressant responses is not yet understood. Furthermore, rare and individual variants account for a substantial part of genetic differences in antidepressant efficacy. Recent years have brought a tremendous increase in the accessibility of genome sequencing in terms of data availability and its clinical use. In this review, we summarize recent developments and current issues in the personalization of major depressive disorder treatment through pharmacogenomics.

Selective Serotonin Reuptake Inhibitor Pharmaco-Omics: Mechanisms and Prediction

Selective serotonin reuptake inhibitors (SSRIs) are a standard of care for the pharmacotherapy of patients suffering from Major Depressive Disorder (MDD). However, only one-half to two-thirds of MDD patients respond to SSRI therapy. Recently, a "multiple omics" research strategy was applied to identify genetic differences between patients who did and did not respond to SSRI therapy. As a first step, plasma metabolites were assayed using samples from the 803 patients in the PGRN-AMPS SSRI MDD trial. The metabolomics data were then used to "inform" genomics by performing a genome-wide association study (GWAS) for plasma concentrations of the metabolite most highly associated with clinical response, serotonin (5-HT). Two genome-wide or near genome-wide significant single nucleotide polymorphism (SNP) signals were identified, one that mapped near the TSPAN5 gene and another across the ERICH3 gene, both genes that are highly expressed in the brain. Knocking down TSPAN5 and ERICH3 resulted in decreased 5-HT concentrations in neuroblastoma cell culture media and decreased expression of enzymes involved in 5-HT biosynthesis and metabolism. Functional genomic studies demonstrated that ERICH3 was involved in clathrin-mediated vesicle formation and TSPAN5 was an ethanol-responsive gene that may be a marker for response to acamprosate pharmacotherapy of alcohol use disorder (AUD), a neuropsychiatric disorder highly co-morbid with MDD. In parallel studies, kynurenine was the plasma metabolite most highly associated with MDD symptom severity and application of a metabolomics-informed pharmacogenomics approach identified DEFB1 and AHR as genes associated with variation in plasma kynurenine levels. Both genes also contributed to kynurenine-related inflammatory pathways. Finally, a multiply replicated predictive algorithm for SSRI clinical response with a balanced predictive accuracy of 76% (compared with 56% for clinical data alone) was developed by including the SNPs in TSPAN5, ERICH3, DEFB1 and AHR. In summary, application of a multiple omics research strategy that used metabolomics to inform genomics, followed by functional genomic studies, identified novel genes that influenced monoamine biology and made it possible to develop a predictive algorithm for SSRI clinical outcomes in MDD. A similar pharmaco-omic research strategy might be broadly applicable for the study of other neuropsychiatric diseases and their drug therapy.

Exploring the Role of Gut Microbiota in Major Depressive Disorder and in Treatment Resistance to Antidepressants

Major depressive disorder (MDD) is a common severe psychiatric illness, exhibiting sub-optimal response to existing pharmacological treatments. Although its etiopathogenesis is still not completely understood, recent findings suggest that an altered composition of the gut microbiota might play a role. Here we aimed to explore potential differences in the composition of the gut microbiota between patients with MDD and healthy controls (HC) and to identify possible signatures of treatment response by analyzing two groups of MDD patients characterized as treatment-resistant (TR) or responders (R) to antidepressants. Stool samples were collected from 34 MDD patients (8 TR, 19 R and 7 untreated) and 20 HC. Microbiota was characterized using the 16S metagenomic approach. A penalized logistic regression analysis algorithm was applied to identify bacterial populations that best discriminate the diagnostic groups. Statistically significant differences were identified for the families of Paenibacillaceae and Flavobacteriaceaea, for the genus Fenollaria, and the species Flintibacter butyricus, Christensenella timonensis, and Eisenbergiella massiliensis among others. The phyla Proteobacteria, Tenericutes and the family Peptostreptococcaceae were more abundant in TR, whereas the phylum Actinobacteria was enriched in R patients. Moreover, a number of bacteria only characterized the microbiota of TR patients, and many others were only detected in R. Our results confirm that dysbiosis is a hallmark of MDD and suggest that microbiota of TR patients significantly differs from responders to antidepressants. This finding further supports the relevance of an altered composition of the gut microbiota in the etiopathogenesis of MDD, suggesting a role in response to antidepressants.

Machine learning approach to predict medication overuse in migraine patients

Machine learning (ML) is largely used to develop automatic predictors in migraine classification but automatic predictors for medication overuse (MO) in migraine are still in their infancy. Thus, to understand the benefits of ML in MO prediction, we explored an automated predictor to estimate MO risk in migraine. To achieve this objective, a study was designed to analyze the performance of a customized ML-based decision support system that combines support vector machines and Random Optimization (RO-MO). We used RO-MO to extract prognostic information from demographic, clinical and biochemical data. Using a dataset of 777 consecutive migraine patients we derived a set of predictors with discriminatory power for MO higher than that observed for baseline SVM. The best four were incorporated into the final RO-MO decision support system and risk evaluation on a five-level stratification was performed. ROC analysis resulted in a c-statistic of 0.83 with a sensitivity and specificity of 0.69 and 0.87, respectively, and an accuracy of 0.87 when MO was predicted by at least three RO-MO models. Logistic regression analysis confirmed that the derived RO-MO system could effectively predict MO with ORs of 5.7 and 21.0 for patients classified as probably (3 predictors positive), or definitely at risk of MO (4 predictors positive), respectively. In conclusion, a combination of ML and RO - taking into consideration clinical/biochemical features, drug exposure and lifestyle - might represent a valuable approach to MO prediction in migraine and holds the potential for improving model precision through weighting the relative importance of attributes.

In search of pathobiological endotypes: a systems approach to early rheumatoid arthritis

INTRODUCTION

Rheumatoid arthritis (RA) is a chronic, systemic autoimmune disease. Early referral and treatment are key to the effective management of the disease. This makes imperative the identification of biomarkers and of pathobiological endotypes.

AREAS COVERED

This review describes recent efforts to integrate large-scale datasets for the identification of disease endotypes for precision medicine in early, seropositive RA. We conducted a search for systems and multi-omics papers in early RA patients through to 1 January 2020. We reviewed investigations of multiple technologies such as transcriptomic, proteomic and metabolomic platforms as well as extensive clinical datasets. We outline progress made and describe some of the advantages and limitations of current computational and statistical methods.

EXPERT OPINION

The search for pathobiological endotypes in early RA is rapidly developing. While currently, studies tend to be small, reliant upon new technologies and unproven analytical tools, as the technology becomes cheaper and more reliable, and the properties of analytical tools for the integration of cross-platform biology become better understood, it seems likely that better biomarkers of disease, remission and response to individual therapies will emerge.

Metabolomics and Multi-Omics Integration: A Survey of Computational Methods and Resources

As researchers are increasingly able to collect data on a large scale from multiple clinical and omics modalities, multi-omics integration is becoming a critical component of metabolomics research. This introduces a need for increased understanding by the metabolomics researcher of computational and statistical analysis methods relevant to multi-omics studies. In this review, we discuss common types of analyses performed in multi-omics studies and the computational and statistical methods that can be used for each type of analysis. We pinpoint the caveats and considerations for analysis methods, including required parameters, sample size and data distribution requirements, sources of a priori knowledge, and techniques for the evaluation of model accuracy. Finally, for the types of analyses discussed, we provide examples of the applications of corresponding methods to clinical and basic research. We intend that our review may be used as a guide for metabolomics researchers to choose effective techniques for multi-omics analyses relevant to their field of study.

Variant discovery using next-generation sequencing and its future role in pharmacogenetics

Next-generation sequencing (NGS) has enabled the discovery of a multitude of novel and mostly rare variants in pharmacogenes that may alter a patient’s therapeutic response to drugs. In addition to single nucleotide variants, structural variation affecting the number of copies of whole genes or parts of genes can be detected. While current guidelines concerning clinical implementation mostly act upon well-documented, common single nucleotide variants to guide dosing or drug selection, in silico and large-scale functional assessment of rare variant effects on protein function are at the forefront of pharmacogenetic research to facilitate their clinical integration. Here, we discuss the role of NGS in variant discovery, paving the way for more comprehensive genotype-guided pharmacotherapy that can translate to improved clinical care.

Challenges and Future Prospects of Precision Medicine in Psychiatry

Precision medicine is increasingly recognized as a promising approach to improve disease treatment, taking into consideration the individual clinical and biological characteristics shared by specific subgroups of patients. In specific fields such as oncology and hematology, precision medicine has already started to be implemented in the clinical setting and molecular testing is routinely used to select treatments with higher efficacy and reduced adverse effects. The application of precision medicine in psychiatry is still in its early phases. However, there are already examples of predictive models based on clinical data or combinations of clinical, neuroimaging and biological data. While the power of single clinical predictors would remain inadequate if analyzed only with traditional statistical approaches, these predictors are now increasingly used to impute machine learning models that can have adequate accuracy even in the presence of relatively small sample size. These models have started to be applied to disentangle relevant clinical questions that could lead to a more effective management of psychiatric disorders, such as prediction of response to the mood stabilizer lithium, resistance to antidepressants in major depressive disorder or stratification of the risk and outcome prediction in schizophrenia. In this narrative review, we summarized the most important findings in precision medicine in psychiatry based on studies that constructed machine learning models using clinical, neuroimaging and/or biological data. Limitations and barriers to the implementation of precision psychiatry in the clinical setting, as well as possible solutions and future perspectives, will be presented.

Multi-omics Data Integration, Interpretation, and Its Application

To study complex biological processes holistically, it is imperative to take an integrative approach that combines multi-omics data to highlight the interrelationships of the involved biomolecules and their functions. With the advent of high-throughput techniques and availability of multi-omics data generated from a large set of samples, several promising tools and methods have been developed for data integration and interpretation. In this review, we collected the tools and methods that adopt integrative approach to analyze multiple omics data and summarized their ability to address applications such as disease subtyping, biomarker prediction, and deriving insights into the data. We provide the methodology, use-cases, and limitations of these tools; brief account of multi-omics data repositories and visualization portals; and challenges associated with multi-omics data integration.

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.

Global Evolution of Research in Artificial Intelligence in Health and Medicine: A Bibliometric Study

The increasing application of Artificial Intelligence (AI) in health and medicine has attracted a great deal of research interest in recent decades. This study aims to provide a global and historical picture of research concerning AI in health and medicine. A total of 27,451 papers that were published between 1977 and 2018 (84.6% were dated 2008⁻2018) were retrieved from the Web of Science platform. The descriptive analysis examined the publication volume, and authors and countries collaboration. A global network of authors' keywords and content analysis of related scientific literature highlighted major techniques, including Robotic, Machine learning, Artificial neural network, Artificial intelligence, Natural language process, and their most frequent applications in Clinical Prediction and Treatment. The number of cancer-related publications was the highest, followed by Heart Diseases and Stroke, Vision impairment, Alzheimer's, and Depression. Moreover, the shortage in the research of AI application to some high burden diseases suggests future directions in AI research. This study offers a first and comprehensive picture of the global efforts directed towards this increasingly important and prolific field of research and suggests the development of global and national protocols and regulations on the justification and adaptation of medical AI products.