A primer on the use of machine learning to distil knowledge from data in biological psychiatry.

Applications of machine learning in the biomedical sciences are growing rapidly. This growth has been spurred by diverse cross-institutional and interdisciplinary collaborations, public availability of large datasets, an increase in the accessibility of analytic routines, and the availability of powerful computing resources. With this increased access and exposure to machine learning comes a responsibility for education and a deeper understanding of its bases and bounds, borne equally by data scientists seeking to ply their analytic wares in medical research and by biomedical scientists seeking to harness such methods to glean knowledge from data. This article provides an accessible and critical review of machine learning for a biomedically informed audience, as well as its applications in psychiatry. The review covers definitions and expositions of commonly used machine learning methods, and historical trends of their use in psychiatry. We also provide a set of standards, namely Guidelines for REporting Machine Learning Investigations in Neuropsychiatry (GREMLIN), for designing and reporting studies that use machine learning as a primary data-analysis approach. Lastly, we propose the establishment of the Machine Learning in Psychiatry (MLPsych) Consortium, enumerate its objectives, and identify areas of opportunity for future applications of machine learning in biological psychiatry. This review serves as a cautiously optimistic primer on machine learning for those on the precipice as they prepare to dive into the field, either as methodological practitioners or well-informed consumers.

A review of neuroeconomic gameplay in psychiatric disorders.

Abnormalities in social interaction are a common feature of several psychiatric disorders, aligning with the recent move towards using Research Domain Criteria (RDoC) to describe disorders in terms of observable behaviours rather than using specific diagnoses. Neuroeconomic games are an effective measure of social decision-making that can be adapted for use in neuroimaging, allowing investigation of the biological basis for behaviour. This review summarises findings of neuroeconomic gameplay studies in Axis 1 psychiatric disorders and advocates the use of these games as measures of the RDoC Affiliation and Attachment, Reward Responsiveness, Reward Learning and Reward Valuation constructs. Although research on neuroeconomic gameplay is in its infancy, consistencies have been observed across disorders, particularly in terms of impaired integration of social and cognitive information, avoidance of negative social interactions and reduced reward sensitivity, as well as a reduction in activity in brain regions associated with processing and responding to social information.

A major role for common genetic variation in anxiety disorders.

Anxiety disorders are common, complex psychiatric disorders with twin heritabilities of 30-60%. We conducted a genome-wide association study of Lifetime Anxiety Disorder (ncase = 25 453, ncontrol = 58 113) and an additional analysis of Current Anxiety Symptoms (ncase = 19 012, ncontrol = 58 113). The liability scale common variant heritability estimate for Lifetime Anxiety Disorder was 26%, and for Current Anxiety Symptoms was 31%. Five novel genome-wide significant loci were identified including an intergenic region on chromosome 9 that has previously been associated with neuroticism, and a locus overlapping the BDNF receptor gene, NTRK2. Anxiety showed significant positive genetic correlations with depression and insomnia as well as coronary artery disease, mirroring findings from epidemiological studies. We conclude that common genetic variation accounts for a substantive proportion of the genetic architecture underlying anxiety.

Using tree-based methods for detection of gene-gene interactions in the presence of a polygenic signal: simulation study with application to educational attainment in the Generation Scotland Cohort Study.

Motivation: The genomic architecture of human complex diseases is thought to be attributable to single markers, polygenic components and epistatic components. No study has examined the ability of tree-based methods to detect epistasis in the presence of a polygenic signal. We sought to apply decision tree-based methods, C5.0 and logic regression, to detect epistasis under several simulated conditions, varying strength of interaction and linkage disequilibrium (LD) structure. We then applied the same methods to the phenotype of educational attainment in a large population cohort. Results: LD pruning improved the power and reduced the type I error. C5.0 had a conservative type I error rate whereas logic regression had a type I error rate that exceeded 5%. Despite the more conservative type I error, C5.0 was observed to have higher power than logic regression across several conditions. In the presence of a polygenic signal, power was generally reduced. Applying both methods on educational attainment in a large population cohort yielded numerous interacting SNPs; notably a SNP in RCAN3 which is associated with reading and spelling and a SNP in NPAS3, a neurodevelopmental gene. Availability and implementation: All methods used are implemented and freely available in R. Supplementary information: Supplementary data are available at Bioinformatics online.

Genome-wide association study of antidepressant treatment resistance in a population-based cohort using health service prescription data and meta-analysis with GENDEP.

Antidepressants demonstrate modest response rates in the treatment of major depressive disorder (MDD). Despite previous genome-wide association studies (GWAS) of antidepressant treatment response, the underlying genetic factors are unknown. Using prescription data in a population and family-based cohort (Generation Scotland: Scottish Family Health Study; GS:SFHS), we sought to define a measure of (a) antidepressant treatment resistance and (b) stages of antidepressant resistance by inferring antidepressant switching as non-response to treatment. GWAS were conducted separately for antidepressant treatment resistance in GS:SFHS and the Genome-based Therapeutic Drugs for Depression (GENDEP) study and then meta-analysed (meta-analysis n = 4213, cases = 358). For stages of antidepressant resistance, a GWAS on GS:SFHS only was performed (n = 3452). Additionally, we conducted gene-set enrichment, polygenic risk scoring (PRS) and genetic correlation analysis. We did not identify any significant loci, genes or gene sets associated with antidepressant treatment resistance or stages of resistance. Significant positive genetic correlations of antidepressant treatment resistance and stages of resistance with neuroticism, psychological distress, schizotypy and mood disorder traits were identified. These findings suggest that larger sample sizes are needed to identify the genetic architecture of antidepressant treatment response, and that population-based observational studies may provide a tractable approach to achieving the necessary statistical power.

An examination of the language construct in NIMH's research domain criteria: Time for reconceptualization!

The National Institute of Mental Health's Research Domain Criteria (RDoC) Initiative "calls for the development of new ways of classifying psychopathology based on dimensions of observable behavior." As a result of this ambitious initiative, language has been identified as an independent construct in the RDoC matrix. In this article, we frame language within an evolutionary and neuropsychological context and discuss some of the limitations to the current measurements of language. Findings from genomics and the neuroimaging of performance during language tasks are discussed in relation to serious mental illness and within the context of caveats regarding measuring language. Indeed, the data collection and analysis methods employed to assay language have been both aided and constrained by the available technologies, methodologies, and conceptual definitions. Consequently, different fields of language research show inconsistent definitions of language that have become increasingly broad over time. Individually, they have also shown significant improvements in conceptual resolution, as well as in experimental and analytic techniques. More recently, language research has embraced collaborations across disciplines, notably neuroscience, cognitive science, and computational linguistics and has ultimately re-defined classical ideas of language. As we move forward, the new models of language with their remarkably multifaceted constructs force a re-examination of the NIMH RDoC conceptualization of language and thus the neuroscience and genetics underlying this concept. © 2016 The Authors. American Journal of Medical Genetics Part B: Neuropsychiatric Genetics Published by Wiley Periodicals, Inc.

Letter to the editor: on the stability and ranking of predictors from random forest variable importance measures.

A recent study examined the stability of rankings from random forests using two variable importance measures (mean decrease accuracy (MDA) and mean decrease Gini (MDG)) and concluded that rankings based on the MDG were more robust than MDA. However, studies examining data-specific characteristics on ranking stability have been few. Rankings based on the MDG measure showed sensitivity to within-predictor correlation and differences in category frequencies, even when the number of categories was held constant, and thus may produce spurious results. The MDA measure was robust to these data characteristics. Further, under strong within-predictor correlation, MDG rankings were less stable than those using MDA.

Genetic variation in AKT1 is linked to dopamine-associated prefrontal cortical structure and function in humans.

AKT1-dependent molecular pathways control diverse aspects of cellular development and adaptation, including interactions with neuronal dopaminergic signaling. If AKT1 has an impact on dopaminergic signaling, then genetic variation in AKT1 would be associated with brain phenotypes related to cortical dopaminergic function. Here, we provide evidence that a coding variation in AKT1 that affects protein expression in human B lymphoblasts influenced several brain measures related to dopaminergic function. Cognitive performance linked to frontostriatal circuitry, prefrontal physiology during executive function, and frontostriatal gray-matter volume on MRI were altered in subjects with the AKT1 variation. Moreover, on neuroimaging measures with a main effect of the AKT1 genotype, there was significant epistasis with a functional polymorphism (Val158Met) in catechol-O-methyltransferase [COMT], a gene that indexes cortical synaptic dopamine. This genetic interaction was consistent with the putative role of AKT1 in dopaminergic signaling. Supportive of an earlier tentative association of AKT1 with schizophrenia, we also found that this AKT1 variant was associated with risk for schizophrenia. These data implicate AKT1 in modulating human prefrontal-striatal structure and function and suggest that the mechanism of this effect may be coupled to dopaminergic signaling and relevant to the expression of psychosis.

Functional polymorphisms in PRODH are associated with risk and protection for schizophrenia and fronto-striatal structure and function.

PRODH, encoding proline oxidase (POX), has been associated with schizophrenia through linkage, association, and the 22q11 deletion syndrome (Velo-Cardio-Facial syndrome). Here, we show in a family-based sample that functional polymorphisms in PRODH are associated with schizophrenia, with protective and risk alleles having opposite effects on POX activity. Using a multimodal imaging genetics approach, we demonstrate that haplotypes constructed from these risk and protective functional polymorphisms have dissociable correlations with structure, function, and connectivity of striatum and prefrontal cortex, impacting critical circuitry implicated in the pathophysiology of schizophrenia. Specifically, the schizophrenia risk haplotype was associated with decreased striatal volume and increased striatal-frontal functional connectivity, while the protective haplotype was associated with decreased striatal-frontal functional connectivity. Our findings suggest a role for functional genetic variation in POX on neostriatal-frontal circuits mediating risk and protection for schizophrenia.

The evolutionarily conserved G protein-coupled receptor SREB2/GPR85 influences brain size, behavior, and vulnerability to schizophrenia.

The G protein-coupled receptor (GPCR) family is highly diversified and involved in many forms of information processing. SREB2 (GPR85) is the most conserved GPCR throughout vertebrate evolution and is expressed abundantly in brain structures exhibiting high levels of plasticity, e.g., the hippocampal dentate gyrus. Here, we show that SREB2 is involved in determining brain size, modulating diverse behaviors, and potentially in vulnerability to schizophrenia. Mild overexpression of SREB2 caused significant brain weight reduction and ventricular enlargement in transgenic (Tg) mice as well as behavioral abnormalities mirroring psychiatric disorders, e.g., decreased social interaction, abnormal sensorimotor gating, and impaired memory. SREB2 KO mice showed a reciprocal phenotype, a significant increase in brain weight accompanying a trend toward enhanced memory without apparent other behavioral abnormalities. In both Tg and KO mice, no gross malformation of brain structures was observed. Because of phenotypic overlap between SREB2 Tg mice and schizophrenia, we sought a possible link between the two. Minor alleles of two SREB2 SNPs, located in intron 2 and in the 3' UTR, were overtransmitted to schizophrenia patients in a family-based sample and showed an allele load association with reduced hippocampal gray matter volume in patients. Our data implicate SREB2 as a potential risk factor for psychiatric disorders and its pathway as a target for psychiatric therapy.

The behaviour of random forest permutation-based variable importance measures under predictor correlation.

BACKGROUND: Random forests (RF) have been increasingly used in applications such as genome-wide association and microarray studies where predictor correlation is frequently observed. Recent works on permutation-based variable importance measures (VIMs) used in RF have come to apparently contradictory conclusions. We present an extended simulation study to synthesize results. RESULTS: In the case when both predictor correlation was present and predictors were associated with the outcome (HA), the unconditional RF VIM attributed a higher share of importance to correlated predictors, while under the null hypothesis that no predictors are associated with the outcome (H0) the unconditional RF VIM was unbiased. Conditional VIMs showed a decrease in VIM values for correlated predictors versus the unconditional VIMs under HA and was unbiased under H0. Scaled VIMs were clearly biased under HA and H0. CONCLUSIONS: Unconditional unscaled VIMs are a computationally tractable choice for large datasets and are unbiased under the null hypothesis. Whether the observed increased VIMs for correlated predictors may be considered a "bias" - because they do not directly reflect the coefficients in the generating model - or if it is a beneficial attribute of these VIMs is dependent on the application. For example, in genetic association studies, where correlation between markers may help to localize the functionally relevant variant, the increased importance of correlated predictors may be an advantage. On the other hand, we show examples where this increased importance may result in spurious signals.

Evidence of statistical epistasis between DISC1, CIT and NDEL1 impacting risk for schizophrenia: biological validation with functional neuroimaging.

The etiology of schizophrenia likely involves genetic interactions. DISC1, a promising candidate susceptibility gene, encodes a protein which interacts with many other proteins, including CIT, NDEL1, NDE1, FEZ1 and PAFAH1B1, some of which also have been associated with psychosis. We tested for epistasis between these genes in a schizophrenia case-control study using machine learning algorithms (MLAs: random forest, generalized boosted regression andMonteCarlo logic regression). Convergence of MLAs revealed a subset of seven SNPs that were subjected to 2-SNP interaction modeling using likelihood ratio tests for nested unconditional logistic regression models. Of the 7C2 = 21 interactions, four were significant at the α = 0.05 level: DISC1 rs1411771-CIT rs10744743 OR = 3.07 (1.37, 6.98) p = 0.007; CIT rs3847960-CIT rs203332 OR = 2.90 (1.45, 5.79) p = 0.003; CIT rs3847960-CIT rs440299 OR = 2.16 (1.04, 4.46) p = 0.038; one survived Bonferroni correction (NDEL1 rs4791707-CIT rs10744743 OR = 4.44 (2.22, 8.88) p = 0.00013). Three of four interactions were validated via functional magnetic resonance imaging (fMRI) in an independent sample of healthy controls; risk associated alleles at both SNPs predicted prefrontal cortical inefficiency during the N-back task, a schizophrenia-linked intermediate biological phenotype: rs3847960-rs440299; rs1411771-rs10744743, rs4791707-rs10744743 (SPM5 p < 0.05, corrected), although we were unable to statistically replicate the interactions in other clinical samples. Interestingly, the CIT SNPs are proximal to exons that encode theDISC1 interaction domain. In addition, the 3' UTR DISC1 rs1411771 is predicted to be an exonic splicing enhancer and the NDEL1 SNP is ~3,000 bp from the exon encoding the region of NDEL1 that interacts with the DISC1 protein, giving a plausible biological basis for epistasis signals validated by fMRI.

Predictor correlation impacts machine learning algorithms: implications for genomic studies.

MOTIVATION: The advent of high-throughput genomics has produced studies with large numbers of predictors (e.g. genome-wide association, microarray studies). Machine learning algorithms (MLAs) are a computationally efficient way to identify phenotype-associated variables in high-dimensional data. There are important results from mathematical theory and numerous practical results documenting their value. One attractive feature of MLAs is that many operate in a fully multivariate environment, allowing for small-importance variables to be included when they act cooperatively. However, certain properties of MLAs under conditions common in genomic-related data have not been well-studied--in particular, correlations among predictors pose a problem. RESULTS: Using extensive simulation, we showed considering correlation within predictors is crucial in making valid inferences using variable importance measures (VIMs) from three MLAs: random forest (RF), conditional inference forest (CIF) and Monte Carlo logic regression (MCLR). Using a case-control illustration, we showed that the RF VIMs--even permutation-based--were less able to detect association than other algorithms at effect sizes encountered in complex disease studies. This reduction occurred when 'causal' predictors were correlated with other predictors, and was sharpest when RF tree building used the Gini index. Indeed, RF Gini VIMs are biased under correlation, dependent on predictor correlation strength/number and over-trained to random fluctuations in data when tree terminal node size was small. Permutation-based VIM distributions were less variable for correlated predictors and are unbiased, thus may be preferred when predictors are correlated. MLAs are a powerful tool for high-dimensional data analysis, but well-considered use of algorithms is necessary to draw valid conclusions. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

The role of polygenic risk score gene-set analysis in the context of the omnigenic model of schizophrenia.

A recent development in the genetic architecture of schizophrenia suggested that an omnigenic model may underlie the risk for this disorder. The aim of our study was to use polygenic profile scoring to quantitatively assess whether a number of experimentally derived sets would contribute to the disorder above and beyond the omnigenic effect. Using the PGC2 secondary analysis schizophrenia case-control cohort (N = 29,125 cases and 34,836 controls), a robust polygenic signal was observed from gene sets based on TCF4, FMR1, upregulation from MIR137 and downregulation from CHD8. Additional analyses revealed a constant floor effect in the amount of variance explained, consistent with the omnigenic model. Thus, we report that putative core gene sets showed a significant effect above and beyond the floor effect that might be linked with the underlying omnigenic background. In addition, we demonstrate a method to quantify the contribution of specific gene sets within the omnigenic context.

Pharmaco-epidemiology of antidepressant exposure in a UK cohort record-linkage study.

OBJECTIVES: Antidepressants are the most commonly prescribed psychiatric medication but concern has been raised about significant increases in their usage in high income countries. We aimed to quantify antidepressant prevalence, incidence, adherence and predictors of use in the adult population. METHODS: The study record-linked administrative prescribing and morbidity data to the Generation Scotland cohort ( N = 11,052), between 2009 and 2016. Prevalence and incidence of any antidepressant use was determined. Antidepressant adherence was measured using Proportion of Days Covered and Medication Possession Ratio. Time-to-event analysis for incident antidepressant use within 5 years of Generation Scotland: Scottish Family Health Study (GS:SFHS) recruitment was performed to reveal patient-level predictors of use. RESULTS: Almost one-third (28.0%, 95%CI 26.9-29.1) of the adults in our sample were prescribed at least one antidepressant in the 5-year period 2012-2016. There was a 36.2% increase in annual prevalence between 2010 and 2016. Incidence was 2.4(2.1-2.7)% per year. The majority of antidepressant episodes (57.6%) were greater than 9 months duration and adherence was generally high (69.0% with Proportion of Days Covered >80%). Predictors of new antidepressant use included history of affective disorder, being female, physical comorbidities, higher neuroticism scores, and lower cognitive function scores. CONCLUSIONS: Antidepressant prevalence is greater than previously reported but incidence remains relatively stable. We found the majority of antidepressant episodes to be of relatively long duration with good estimated adherence. Our study supports the hypothesis that increased long-term use among existing (and returning) users, along with wider ranges of indications for antidepressants, has significantly increased the prevalence of these medications.

Catmap: case-control and TDT meta-analysis package.

BACKGROUND: Risk for complex disease is thought to be controlled by multiple genetic risk factors, each with small individual effects. Meta-analyses of several independent studies may be helpful to increase the ability to detect association when effect sizes are modest. Although many software options are available for meta-analysis of genetic case-control data, no currently available software implements the method described by Kazeem and Farrall (2005), which combines data from independent family-based and case-control studies. RESULTS: I introduce the package catmap for the R statistical computing environment that implements fixed- and random-effects pooled estimates for case-control and transmission disequilibrium methods, allowing for the use of genetic association data across study types. In addition, catmap may be used to create forest and funnel plots and to perform sensitivity analysis and cumulative meta-analysis. catmap is available from the Comprehensive R Archive Network http://www.r-project.org. CONCLUSION: catmap allows researchers to synthesize data to assess evidence for association in studies of genetic polymorphisms, facilitating the use of pooled data analyses which may increase power to detect moderate genetic associations.

snp.plotter: an R-based SNP/haplotype association and linkage disequilibrium plotting package.

UNLABELLED: snp.plotter is a newly developed R package which produces high-quality plots of results from genetic association studies. The main features of the package include options to display a linkage disequilibrium (LD) plot below the P-value plot using either the r2 or D' LD metric, to set the X-axis to equal spacing or to use the physical map of markers, and to specify plot labels, colors, symbols and LD heatmap color scheme. snp.plotter can plot single SNP and/or haplotype data and simultaneously plot multiple sets of results. R is a free software environment for statistical computing and graphics available for most platforms. The proposed package provides a simple way to convey both association and LD information in a single appealing graphic for genetic association studies. AVAILABILITY: Downloadable R package and example datasets are available at http://cbdb.nimh.nih.gov/~kristin/snp.plotter.html and http://www.r-project.org.

Phenotypic and genetic analysis of cognitive performance in Major Depressive Disorder in the Generation Scotland: Scottish Family Health Study.

Lower performances in cognitive ability in individuals with Major Depressive Disorder (MDD) have been observed on multiple occasions. Understanding cognitive performance in MDD could provide a wider insight in the aetiology of MDD as a whole. Using a large, well characterised cohort (N = 7012), we tested for: differences in cognitive performance by MDD status and a gene (single SNP or polygenic score) by MDD interaction effect on cognitive performance. Linear regression was used to assess the association between cognitive performance and MDD status in a case-control, single-episode-recurrent MDD and control-recurrent MDD study design. Test scores on verbal declarative memory, executive functioning, vocabulary, and processing speed were examined. Cognitive performance measures showing a significant difference between groups were subsequently analysed for genetic associations. Those with recurrent MDD have lower processing speed versus controls and single-episode MDD (ß = -2.44, p = 3.6 × 10-04; ß = -2.86, p = 1.8 × 10-03, respectively). There were significantly higher vocabulary scores in MDD cases versus controls (ß = 0.79, p = 2.0 × 10-06), and for recurrent MDD versus controls (ß = 0.95, p = 5.8 × 10-05). Observed differences could not be linked to significant single-locus associations. Polygenic scores created from a processing speed meta-analysis GWAS explained 1% of variation in processing speed performance in the single-episode versus recurrent MDD study (p = 1.7 × 10-03) and 0.5% of variation in the control versus recurrent MDD study (p = 1.6 × 10-10). Individuals with recurrent MDD showed lower processing speed and executive function while showing higher vocabulary performance. Within MDD, persons with recurrent episodes show lower processing speed and executive function scores relative to individuals experiencing a single episode.

Data science for mental health: a UK perspective on a global challenge.

Data science uses computer science and statistics to extract new knowledge from high-dimensional datasets (ie, those with many different variables and data types). Mental health research, diagnosis, and treatment could benefit from data science that uses cohort studies, genomics, and routine health-care and administrative data. The UK is well placed to trial these approaches through robust NHS-linked data science projects, such as the UK Biobank, Generation Scotland, and the Clinical Record Interactive Search (CRIS) programme. Data science has great potential as a low-cost, high-return catalyst for improved mental health recognition, understanding, support, and outcomes. Lessons learnt from such studies could have global implications.

Diabetes mellitus and subsite-specific colorectal cancer risks in the Iowa Women's Health Study.

OBJECTIVE: Controversy remains regarding the association between type 2 diabetes mellitus (DM) and colorectal cancer (CRC) risk. To clarify and extend the existing data, we prospectively evaluated the association between self-reported type 2 DM (onset at >30 years of age) and incident CRC, overall and by anatomic subsite, among postmenopausal women in the Iowa Women's Health Study (n = 35,230). METHODS: After 14 years of follow-up, a total of 870 incident CRC cases were identified through annual linkage to the Iowa Cancer Registry. DM was analyzed as reported at baseline and as a time-dependent variable using information obtained during follow-up. CRC risks were estimated using Cox proportional hazards regression models. RESULTS: After adjusting for age, body mass index and other potential confounding variables, the relative risk (RR) for women with DM versus women without DM was modestly increased at 1.4 [95% confidence interval (95% CI), 1.1-1.8]. By anatomic subsite, the RR for proximal colon cancer was statistically significantly increased (RR, 1.9; 95% CI, 1.3-2.6), whereas the RRs for distal colon (RR, 1.1; 95% CI, 0.6-1.8) and rectal cancer (RR, 0.8; 95% CI, 0.4-1.6) were not statistically different from unity. Analyses that included DM ascertained at baseline and follow-up yielded similar results. CONCLUSION: In this large, prospective study of postmenopausal women, the association between DM and incident CRC was found to be subsite specific. If confirmed by others, this finding implies that CRC prevention strategies among type 2 DM patients should include examination of the proximal colon.