Transcriptomics and machine learning to advance schizophrenia genetics: A case-control study using post-mortem brain data.

BACKGROUND AND OBJECTIVE: Alterations of the expression of a variety of genes have been reported in patients with schizophrenia (SCZ). Moreover, machine learning (ML) analysis of gene expression microarray data has shown promising preliminary results in the study of SCZ. Our objective was to evaluate the performance of ML in classifying SCZ cases and controls based on gene expression microarray data from the dorsolateral prefrontal cortex. METHODS: We apply a state-of-the-art ML algorithm (XGBoost) to train and evaluate a classification model using 201 SCZ cases and 278 controls. We utilized 10-fold cross-validation for model selection, and a held-out testing set to evaluate the model. The performance metric utilizes to evaluate classification performance was the area under the receiver-operator characteristics curve (AUC). RESULTS: We report an average AUC on 10-fold cross-validation of 0.76 and an AUC of 0.76 on testing data, not used during training. Analysis of the rolling balanced classification accuracy from high to low prediction confidence levels showed that the most certain subset of predictions ranged between 80-90%. The ML model utilized 182 gene expression probes. Further improvement to classification performance was observed when applying an automated ML strategy on the 182 features, which achieved an AUC of 0.79 on the same testing data. We found literature evidence linking all of the top ten ML ranked genes to SCZ. Furthermore, we leveraged information from the full set of microarray gene expressions available via univariate differential gene expression analysis. We then prioritized differentially expressed gene sets using the piano gene set analysis package. We augmented the ranking of the prioritized gene sets with genes from the complex multivariate ML model using hypergeometric tests to identify more robust gene sets. We identified two significant Gene Ontology molecular function gene sets: "oxidoreductase activity, acting on the CH-NH2 group of donors" and "integrin binding." Lastly, we present candidate treatments for SCZ based on findings from our study CONCLUSIONS: Overall, we observed above-chance performance from ML classification of SCZ cases and controls based on brain gene expression microarray data, and found that ML analysis of gene expressions could further our understanding of the pathophysiology of SCZ and help identify novel treatments.

Machine learning and bioinformatic analysis of brain and blood mRNA profiles in major depressive disorder: A case-control study.

This study analyzed gene expression messenger RNA data, from cases with major depressive disorder (MDD) and controls, using supervised machine learning (ML). We built on the methodology of prior studies to obtain more generalizable/reproducible results. First, we obtained a classifier trained on gene expression data from the dorsolateral prefrontal cortex of post-mortem MDD cases (n = 126) and controls (n = 103). An average area-under-the-receiver-operating-characteristics-curve (AUC) from 10-fold cross-validation of 0.72 was noted, compared to an average AUC of 0.55 for a baseline classifier (p = .0048). The classifier achieved an AUC of 0.76 on a previously unused testing-set. We also performed external validation using DLPFC gene expression values from an independent cohort of matched MDD cases (n = 29) and controls (n = 29), obtained from Affymetrix microarray (vs. Illumina microarray for the original cohort) (AUC: 0.62). We highlighted gene sets differentially expressed in MDD that were enriched for genes identified by the ML algorithm. Next, we assessed the ML classification performance in blood-based microarray gene expression data from MDD cases (n = 1,581) and controls (n = 369). We observed a mean AUC of 0.64 on 10-fold cross-validation, which was significantly above baseline (p = .0020). Similar performance was observed on the testing-set (AUC: 0.61). Finally, we analyzed the classification performance in covariates subgroups. We identified an interesting interaction between smoking and recall performance in MDD case prediction (58% accurate predictions in cases who are smokers vs. 43% accurate predictions in cases who are non-smokers). Overall, our results suggest that ML in combination with gene expression data and covariates could further our understanding of the pathophysiology in MDD.

Machine Learning Analysis of Blood microRNA Data in Major Depression: A Case-Control Study for Biomarker Discovery.

BACKGROUND: There is a lack of reliable biomarkers for major depressive disorder (MDD) in clinical practice. However, several studies have shown an association between alterations in microRNA levels and MDD, albeit none of them has taken advantage of machine learning (ML). METHOD: Supervised and unsupervised ML were applied to blood microRNA expression profiles from a MDD case-control dataset (n = 168) to distinguish between (1) case vs control status, (2) MDD severity levels defined based on the Montgomery-Asberg Depression Rating Scale, and (3) antidepressant responders vs nonresponders. RESULTS: MDD cases were distinguishable from healthy controls with an area-under-the receiver-operating characteristic curve (AUC) of 0.97 on testing data. High- vs low-severity cases were distinguishable with an AUC of 0.63. Unsupervised clustering of patients, before supervised ML analysis of each cluster for MDD severity, improved the performance of the classifiers (AUC of 0.70 for cluster 1 and 0.76 for cluster 2). Antidepressant responders could not be successfully separated from nonresponders, even after patient stratification by unsupervised clustering. However, permutation testing of the top microRNA, identified by the ML model trained to distinguish responders vs nonresponders in each of the 2 clusters, showed an association with antidepressant response. Each of these microRNA markers was only significant when comparing responders vs nonresponders of the corresponding cluster, but not using the heterogeneous unclustered patient set. CONCLUSIONS: Supervised and unsupervised ML analysis of microRNA may lead to robust biomarkers for monitoring clinical evolution and for more timely assessment of treatment in MDD patients.

Machine learning analysis of exome trios to contrast the genomic architecture of autism and schizophrenia.

BACKGROUND: Machine learning (ML) algorithms and methods offer great tools to analyze large complex genomic datasets. Our goal was to compare the genomic architecture of schizophrenia (SCZ) and autism spectrum disorder (ASD) using ML. METHODS: In this paper, we used regularized gradient boosted machines to analyze whole-exome sequencing (WES) data from individuals SCZ and ASD in order to identify important distinguishing genetic features. We further demonstrated a method of gene clustering to highlight which subsets of genes identified by the ML algorithm are mutated concurrently in affected individuals and are central to each disease (i.e., ASD vs. SCZ "hub" genes). RESULTS: In summary, after correcting for population structure, we found that SCZ and ASD cases could be successfully separated based on genetic information, with 86-88% accuracy on the testing dataset. Through bioinformatic analysis, we explored if combinations of genes concurrently mutated in patients with the same condition ("hub" genes) belong to specific pathways. Several themes were found to be associated with ASD, including calcium ion transmembrane transport, immune system/inflammation, synapse organization, and retinoid metabolic process. Moreover, ion transmembrane transport, neurotransmitter transport, and microtubule/cytoskeleton processes were highlighted for SCZ. CONCLUSIONS: Our manuscript introduces a novel comparative approach for studying the genetic architecture of genetically related diseases with complex inheritance and highlights genetic similarities and differences between ASD and SCZ.

Balance Problems, Paralysis, and Angina as Clinical Markers for Severity in Major Depression.

Major depressive disorder (MDD) is a heterogeneous disorder. Our hypothesis is that neurological symptoms correlate with the severity of MDD symptoms. One hundred eighty-four outpatients with MDD completed a self-report questionnaire on past and present medical history. Patients were divided into three roughly equal depression severity levels based on scores from the APA Severity Measure for Depression-Adult (n = 66, 58, 60, for low, medium, high severity, respectively). We saw a significant and gradual increase in the frequency of "muscular paralysis" (1.5-5.2-16.7%) and "balance problems" (21.2-36.2-46.6%) from low to medium to high severity groups. We repeated the analysis using only the two most extreme severity categories: low severity (66 samples) vs. high severity (60 samples). High severity patients were also found to experience more "angina" symptoms than low severity patients (27.3 vs. 50%). The three significant clinical variables identified were introduced into a binary logistic regression model as the independent variables with high or low severity as the dependent variable. Both "muscular paralysis" and "balance problems" were significantly associated with increased severity of depression (odds ratio of 13.5 and 2.9, respectively), while "angina" was associated with an increase in severity with an odds ratio of 2.0, albeit not significantly. We show that neurological exam or clinical history could be useful biomarkers for depression severity. Our findings, if replicated, could lead to a simple clinical scale administered regularly for monitoring patients with MDD.

Are MEDLINE searches sufficient for systematic reviews and meta-analyses of the diagnostic accuracy of depression screening tools? A review of meta-analyses.

OBJECTIVE: Database searches for studies of diagnostic test accuracy are notoriously difficult to filter, highly resource-intensive, and a potential barrier to quality evidence synthesis. We examined published meta-analyses of depression screening tool accuracy to evaluate the (1) proportion of included primary studies found in any online database in the original meta-analyses that were indexed in MEDLINE; (2) the proportion of patients from MEDLINE-indexed studies; and (3) the proportion of depression cases from studies indexed in MEDLINE. METHODS: MEDLINE and PsycINFO were searched from January 1, 2005 through October 31, 2014 for meta-analyses in any language on the accuracy of depression screening tools. RESULTS: We identified 16 eligible meta-analyses that included 398 primary study citations, which had been identified via an online database in the original meta-analyses, including 257 unique citations and 234 unique patient samples. The 234 unique patient samples included 69,957 total patients and 11,867 depression cases. Of these, 220 samples (94%) were from studies indexed in MEDLINE, including 97% of all patients and 96% of all depression cases. When applying a peer-reviewed search strategy in MEDLINE, 91% of all samples, 96% of patients and 95% of depression cases were retrieved. Results were similar for total and unique citations. CONCLUSIONS: Restricting searches to MEDLINE may capture almost all eligible studies, patients and depression cases. Although not examined in the present study, MEDLINE may not be indexed as quickly as other databases. Thus, MEDLINE searches should be complemented by date-limited searches of other databases for recent citations.

A pentaherbs capsule as a treatment option for atopic dermatitis in children: an open-labeled case series.

Traditional Chinese Medicine (TCM) has been used in patients with atopic dermatitis (AD), but its therapeutic effects are debatable. We evaluated the clinical and biochemical effects of a TCM capsule (PentaHerbs capsule) in children with AD. After a run-in period of 4 weeks, children old enough to manage oral medication were admitted and their disease severity was evaluated by the SCORing Atopic Dermatitis (SCORAD) index. Blood was obtained for complete blood count, total and allergen-specific immunoglobulin E (IgE), biochemical studies and inflammatory markers of AD severity [serum cutaneous T cell-attracting chemokine (CTACK), macrophage-derived chemokine (MDC), thymus and activation-regulated chemokine (TARC) and eosinophil cationic protein (ECP)] prior to, and after 3 months of, TCM use. Three PentaHerbs capsules twice a day were prescribed for 4 months. Patients were followed monthly to ensure compliance, and SCORAD scores were obtained at each visit. Five boys and four girls participated in the study. All patients had detectable food or inhalant-specific IgE in serum. There was significant improvement in the overall and component SCORAD scores. There were no significant differences between the pre- and post-treatment values of the serum CTACK, MDC, TARC and ECP levels but CTACK showed a decreasing trend (p = 0.069). No clinical or biochemical evidence of any adverse drug reaction was observed during the study period. The PentaHerbs capsules were well tolerated by the children and apparent beneficial effects were noted clinically. A larger, randomized placebo-controlled study is required to confirm the efficacy of this formulation for AD.