Telogator: a method for reporting chromosome-specific telomere lengths from long reads.

MOTIVATION: Telomeres are the repetitive sequences found at the ends of eukaryotic chromosomes and are often thought of as a 'biological clock,' with their average length shortening during division in most cells. In addition to their association with senescence, abnormal telomere lengths are well known to be associated with multiple cancers, short telomere syndromes and as risk factors for a broad range of diseases. While a majority of methods for measuring telomere length will report average lengths across all chromosomes, it is known that aberrations in specific chromosome arms are biomarkers for certain diseases. Due to their repetitive nature, characterizing telomeres at this resolution is prohibitive for short read sequencing approaches, and is challenging still even with longer reads. RESULTS: We present Telogator: a method for reporting chromosome-specific telomere length from long read sequencing data. We demonstrate Telogator's sensitivity in detecting chromosome-specific telomere length in simulated data across a range of read lengths and error rates. Telogator is then applied to 10 germline samples, yielding a high correlation with short read methods in reporting average telomere length. In addition, we investigate common subtelomere rearrangements and identify the minimum read length required to anchor telomere/subtelomere boundaries in samples with these haplotypes. AVAILABILITY AND IMPLEMENTATION: Telogator is written in Python3 and is available at github.com/zstephens/telogator. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Predicting cholangiocarcinoma in primary sclerosing cholangitis: using artificial intelligence, clinical and laboratory data.

BACKGROUND: Primary sclerosing cholangitis (PSC) patients have a risk of developing cholangiocarcinoma (CCA). Establishing predictive models for CCA in PSC is important. METHODS: In a large cohort of 1,459 PSC patients seen at Mayo Clinic (1993-2020), we quantified the impact of clinical/laboratory variables on CCA development using univariate and multivariate Cox models and predicted CCA using statistical and artificial intelligence (AI) approaches. We explored plasma bile acid (BA) levels' predictive power of CCA (subset of 300 patients, BA cohort). RESULTS: Eight significant risk factors (false discovery rate: 20%) were identified with univariate analysis; prolonged inflammatory bowel disease (IBD) was the most important one. IBD duration, PSC duration, and total bilirubin remained significant (p < 0.05) with multivariate analysis. Clinical/laboratory variables predicted CCA with cross-validated C-indexes of 0.68-0.71 at different time points of disease, significantly better compared to commonly used PSC risk scores. Lower chenodeoxycholic acid, higher conjugated fraction of lithocholic acid and hyodeoxycholic acid, and higher ratio of cholic acid to chenodeoxycholic acid were predictive of CCA. BAs predicted CCA with a cross-validated C-index of 0.66 (std: 0.11, BA cohort), similar to clinical/laboratory variables (C-index = 0.64, std: 0.11, BA cohort). Combining BAs with clinical/laboratory variables leads to the best average C-index of 0.67 (std: 0.13, BA cohort). CONCLUSIONS: In a large PSC cohort, we identified clinical and laboratory risk factors for CCA development and demonstrated the first AI based predictive models that performed significantly better than commonly used PSC risk scores. More predictive data modalities are needed for clinical adoption of these models.

Deep learning identifies brain structures that predict cognition and explain heterogeneity in cognitive aging.

Specific brain structures (gray matter regions and white matter tracts) play a dominant role in determining cognitive decline and explain the heterogeneity in cognitive aging. Identification of these structures is crucial for screening of older adults at risk of cognitive decline. Using deep learning models augmented with a model-interpretation technique on data from 1432 Mayo Clinic Study of Aging participants, we identified a subset of brain structures that were most predictive of individualized cognitive trajectories and indicative of cognitively resilient vs. vulnerable individuals. Specifically, these structures explained why some participants were resilient to the deleterious effects of elevated brain amyloid and poor vascular health. Of these, medial temporal lobe and fornix, reflective of age and pathology-related degeneration, and corpus callosum, reflective of inter-hemispheric disconnection, accounted for 60% of the heterogeneity explained by the most predictive structures. Our results are valuable for identifying cognitively vulnerable individuals and for developing interventions for cognitive decline.

Stool microbiota are superior to saliva in distinguishing cirrhosis and hepatic encephalopathy using machine learning.

BACKGROUND & AIMS: Saliva and stool microbiota are altered in cirrhosis. Since stool is logistically difficult to collect compared to saliva, it is important to determine their relative diagnostic and prognostic capabilities. We aimed to determine the ability of stool vs. saliva microbiota to differentiate between groups based on disease severity using machine learning (ML). METHODS: Controls and outpatients with cirrhosis underwent saliva and stool microbiome analysis. Controls vs. cirrhosis and within cirrhosis (based on hepatic encephalopathy [HE], proton pump inhibitor [PPI] and rifaximin use) were classified using 4 ML techniques (random forest [RF], support vector machine, logistic regression, and gradient boosting) with AUC comparisons for stool, saliva or both sample types. Individual microbial contributions were computed using feature importance of RF and Shapley additive explanations. Finally, thresholds for including microbiota were varied between 2.5% and 10%, and core microbiome (DESeq2) analysis was performed. RESULTS: Two hundred and sixty-nine participants, including 87 controls and 182 patients with cirrhosis, of whom 57 had HE, 78 were on PPIs and 29 on rifaximin were included. Regardless of the ML model, stool microbiota had a significantly higher AUC in differentiating groups vs. saliva. Regarding individual microbiota: autochthonous taxa drove the difference between controls vs. patients with cirrhosis, oral-origin microbiota the difference between PPI users/non-users, and pathobionts and autochthonous taxa the difference between rifaximin users/non-users and patients with/without HE. These were consistent with the core microbiome analysis results. CONCLUSIONS: On ML analysis, stool microbiota composition is significantly more informative in differentiating between controls and patients with cirrhosis, and those with varying cirrhosis severity, compared to saliva. Despite logistic challenges, stool should be preferred over saliva for microbiome analysis. LAY SUMMARY: Since it is harder to collect stool than saliva, we wanted to test whether microbes from saliva were better than stool in differentiating between healthy people and those with cirrhosis and, among those with cirrhosis, those with more severe disease. Using machine learning, we found that microbes in stool were more accurate than saliva alone or in combination, therefore, stool should be preferred for analysis and collection wherever possible.

Sex is associated with differences in gut microbial composition and function in hepatic encephalopathy.

BACKGROUND & AIMS: Altered microbiota can affect the gut-liver-brain axis in cirrhosis and hepatic encephalopathy (HE), but the impact of sex on these changes is unclear. We aimed to determine differences in fecal microbiota composition/functionality between men and women with cirrhosis and HE on differing treatments. METHODS: Cross-sectional stool microbiome composition (16s rRNA sequencing) and microbial functional analyses were performed in men and women with cirrhosis, and controls. Patients with HE on rifaximin+lactulose (HE-Rif), patients with HE on lactulose only (HE-Lac) and those with cirrhosis without HE (No-HE) were compared to controls using random forest classifier. Men and women were also compared. RESULTS: A total of 761 individuals were included, 619 with cirrhosis (466 men, 153 women) and 142 controls (92 men, 50 women). Men were older and more frequently used proton pump inhibitors (PPIs), but model for end-stage liver disease score, No-HE (n = 319), HE-lac (n = 130) and HE-Rif (n = 170) proportions were similar. PPI/age-adjusted AUC of differentiation between controls vs. all cirrhosis, and controls vs. No-HE were higher within women than men, but the adjusted AUC for No-HE vs. HE-Rif was higher in men. Control vs. HE-Rif differentiation was similar across sexes. Men vs. women were different in all cirrhosis, No-HE and HE-Lac but not HE-Rif on PERMANOVA and AUC analyses. Autochthonous taxa decreased and pathobionts increased with disease progression regardless of sex. In men, Lactobacillaceae were higher in HE-Lac but decreased in HE-Rif, along with Veillonellaceae. Pathways related to glutamate and aromatic compound degradation were higher in men at all stages. Degradation of androstenedione, an estrogenic precursor, was lower in men vs. women in HE-Rif, likely enhancing feminization. CONCLUSIONS: There are differences in gut microbial function and composition between men and women with cirrhosis, which could be implicated in differential responses to HE therapies. Further studies linking these differences to sex-specific outcomes are needed. LAY SUMMARY: Patients with cirrhosis develop changes in their brain function, and men often develop feminization with disease progression. However, the interaction between sex, microbiota and disease severity is unclear. We found that as disease progressed in men, their microbial composition began to approach that observed in women, with changes in specific microbes that are associated with male hormone metabolism.

Low Predictability of Readmissions and Death Using Machine Learning in Cirrhosis.

INTRODUCTION: Readmission and death in cirrhosis are common, expensive, and difficult to predict. Our aim was to evaluate the abilities of multiple artificial intelligence (AI) techniques to predict clinical outcomes based on variables collected at admission, during hospitalization, and at discharge. METHODS: We used the multicenter North American Consortium for the Study of End-Stage Liver Disease (NACSELD) cohort of cirrhotic inpatients who are followed up through 90-days postdischarge for readmission and death. We used statistical methods to select variables that are significant for readmission and death and trained 3 AI models, including logistic regression (LR), kernel support vector machine (SVM), and random forest classifiers (RFC), to predict readmission and death. We used the area under the receiver operating characteristic curve (AUC) from 10-fold crossvalidation for evaluation to compare sexes. Data were compared with model for end-stage liver disease (MELD) at discharge. RESULTS: We included 2,170 patients (57 ± 11 years, MELD 18 ± 7, 61% men, 79% White, and 8% Hispanic). The 30-day and 90-day readmission rates were 28% and 47%, respectively, and 13% died at 90 days. Prediction for 30-day readmission resulted in 0.60 AUC for all patients with RFC, 0.57 AUC with LR for women-only subpopulation, and 0.61 AUC with LR for men-only subpopulation. For 90-day readmission, the highest AUC was achieved with kernel SVM and RFC (AUC = 0.62). We observed higher predictive value when training models with only women (AUC = 0.68 LR) vs men (AUC = 0.62 kernel SVM). Prediction for death resulted in 0.67 AUC for all patients, 0.72 for women-only subpopulation, and 0.69 for men-only subpopulation, all with LR. MELD-Na model AUC was similar to those from the AI models. DISCUSSION: Despite using multiple AI techniques, it is difficult to predict 30- and 90-day readmissions and death in cirrhosis. AI model accuracies were equivalent to models generated using only MELD-Na scores. Additional biomarkers are needed to improve our predictive capability (See also the visual abstract at http://links.lww.com/AJG/B710).

Leveraging electrophysiologic correlates of word encoding to map seizure onset zone in focal epilepsy: Task-dependent changes in epileptiform activity, spectral features, and functional connectivity.

OBJECTIVE: Verbal memory dysfunction is common in focal, drug-resistant epilepsy (DRE). Unfortunately, surgical removal of seizure-generating brain tissue can be associated with further memory decline. Therefore, localization of both the circuits generating seizures and those underlying cognitive functions is critical in presurgical evaluations for patients who may be candidates for resective surgery. We used intracranial electroencephalographic (iEEG) recordings during a verbal memory task to investigate word encoding in focal epilepsy. We hypothesized that engagement in a memory task would exaggerate local iEEG feature differences between the seizure onset zone (SOZ) and neighboring tissue as compared to wakeful rest ("nontask"). METHODS: Ten participants undergoing presurgical iEEG evaluation for DRE performed a free recall verbal memory task. We evaluated three iEEG features in SOZ and non-SOZ electrodes during successful word encoding and compared them with nontask recordings: interictal epileptiform spike (IES) rates, power in band (PIB), and relative entropy (REN; a functional connectivity measure). RESULTS: We found a complex pattern of PIB and REN changes in SOZ and non-SOZ electrodes during successful word encoding compared to nontask. Successful word encoding was associated with a reduction in local electrographic functional connectivity (increased REN), which was most exaggerated in temporal lobe SOZ. The IES rates were reduced during task, but only in the non-SOZ electrodes. Compared with nontask, REN features during task yielded marginal improvements in SOZ classification. SIGNIFICANCE: Previous studies have supported REN as a biomarker for epileptic brain. We show that REN differences between SOZ and non-SOZ are enhanced during a verbal memory task. We also show that IESs are reduced during task in non-SOZ, but not in SOZ. These findings support the hypothesis that SOZ and non-SOZ respond differently to task and warrant further exploration into the use of cognitive tasks to identify functioning memory circuits and localize SOZ.

Recommendations for performance optimizations when using GATK3.8 and GATK4.

BACKGROUND: Use of the Genome Analysis Toolkit (GATK) continues to be the standard practice in genomic variant calling in both research and the clinic. Recently the toolkit has been rapidly evolving. Significant computational performance improvements have been introduced in GATK3.8 through collaboration with Intel in 2017. The first release of GATK4 in early 2018 revealed rewrites in the code base, as the stepping stone toward a Spark implementation. As the software continues to be a moving target for optimal deployment in highly productive environments, we present a detailed analysis of these improvements, to help the community stay abreast with changes in performance. RESULTS: We re-evaluated multiple options, such as threading, parallel garbage collection, I/O options and data-level parallelization. Additionally, we considered the trade-offs of using GATK3.8 and GATK4. We found optimized parameter values that reduce the time of executing the best practices variant calling procedure by 29.3% for GATK3.8 and 16.9% for GATK4. Further speedups can be accomplished by splitting data for parallel analysis, resulting in run time of only a few hours on whole human genome sequenced to the depth of 20X, for both versions of GATK. Nonetheless, GATK4 is already much more cost-effective than GATK3.8. Thanks to significant rewrites of the algorithms, the same analysis can be run largely in a single-threaded fashion, allowing users to process multiple samples on the same CPU. CONCLUSIONS: In time-sensitive situations, when a patient has a critical or rapidly developing condition, it is useful to minimize the time to process a single sample. In such cases we recommend using GATK3.8 by splitting the sample into chunks and computing across multiple nodes. The resultant walltime will be nnn.4 hours at the cost of $41.60 on 4 c5.18xlarge instances of Amazon Cloud. For cost-effectiveness of routine analyses or for large population studies, it is useful to maximize the number of samples processed per unit time. Thus we recommend GATK4, running multiple samples on one node. The total walltime will be ∼34.1 hours on 40 samples, with 1.18 samples processed per hour at the cost of $2.60 per sample on c5.18xlarge instance of Amazon Cloud.

Correction to: Recommendations for performance optimizations when using GATK3.8 and GATK4.

Following publication of the original article [1], the author explained that Table 2 is displayed incorrectly. The correct Table 2 is given below. The original article has been corrected.

Detection and visualization of complex structural variants from long reads.

BACKGROUND: With applications in cancer, drug metabolism, and disease etiology, understanding structural variation in the human genome is critical in advancing the thrusts of individualized medicine. However, structural variants (SVs) remain challenging to detect with high sensitivity using short read sequencing technologies. This problem is exacerbated when considering complex SVs comprised of multiple overlapping or nested rearrangements. Longer reads, such as those from Pacific Biosciences platforms, often span multiple breakpoints of such events, and thus provide a way to unravel small-scale complexities in SVs with higher confidence. RESULTS: We present CORGi (COmplex Rearrangement detection with Graph-search), a method for the detection and visualization of complex local genomic rearrangements. This method leverages the ability of long reads to span multiple breakpoints to untangle SVs that appear very complicated with respect to a reference genome. We validated our approach against both simulated long reads, and real data from two long read sequencing technologies. We demonstrate the ability of our method to identify breakpoints inserted in synthetic data with high accuracy, and the ability to detect and plot SVs from NA12878 germline, achieving 88.4% concordance between the two sets of sequence data. The patterns of complexity we find in many NA12878 SVs match known mechanisms associated with DNA replication and structural variant formation, and highlight the ability of our method to automatically label complex SVs with an intuitive combination of adjacent or overlapping reference transformations. CONCLUSIONS: CORGi is a method for interrogating genomic regions suspected to contain local rearrangements using long reads. Using pairwise alignments and graph search CORGi produces labels and visualizations for local SVs of arbitrary complexity.

Synovial cysts at the cervicothoracic junction: Illustrative series of three cases.

Background: Spinal synovial cysts are an uncommon pathology, estimated to affect 0.65-2.6% of the population. Cervical spinal synovial cysts are even rarer, accounting for only 2.6% of spinal synovial cysts. They are more commonly found in the lumbar spine. When they occur, they can compress the spinal cord or surrounding nerve roots resulting in neurological symptoms, particularly when they increase in size. Decompression and cyst resection are the most common treatment and typically result in resolution of symptoms. Methods: The authors present three cases of spinal synovial cysts occurring at the C7-T1 junction. They occurred in patients aged 47, 56, and 74, respectively, and presented with symptoms of pain and radiculopathy. Diagnosis was made with computed tomography (CT) scan and magnetic resonance imaging (MRI). The cysts were managed with laminectomy, resection, and fusion. Results: All patients reported full resolution of symptoms. There were no intra or postoperative complications. Conclusion: Cervical spinal synovial cysts are an uncommon cause of radiculopathy and pain in the upper extremities. They can be diagnosed through CT scans and MRI, and treatment with laminectomy, resection, and fusion results in excellent outcomes.

Individualized Seizure Cluster Prediction Using Machine Learning and Chronic Ambulatory Intracranial EEG.

Epilepsy patients often experience acute repetitive seizures, known as seizure clusters, which can progress to prolonged seizures or status epilepticus if left untreated. Predicting the onset of seizure clusters is crucial to enable patients to receive preventative treatments. Additionally, studying the patterns of seizure clusters can help predict the seizure type (isolated or cluster) after observing a just occurred seizure. This paper presents machine learning models that use bivariate intracranial EEG (iEEG) features to predict seizure clustering. Specifically, we utilized relative entropy (REN) as a bivariate feature to capture potential differences in brain region interactions underlying isolated and cluster seizures. We analyzed a large ambulatory iEEG dataset collected from 15 patients and spanned up to 2 years of recordings for each patient, consisting of 3341 cluster seizures (from 427 clusters) and 369 isolated seizures. The dataset's substantial number of seizures per patient enabled individualized analyses and predictions. We observed that REN was significantly different between isolated and cluster seizures in majority of the patients. Machine learning models based on REN: 1) predicted whether a seizure will occur soon after a given seizure with up to 69.5% Area under the ROC Curve (AUC), 2) predicted if a seizure is the first one in a cluster with up to 55.3% AUC, outperforming baseline techniques. Overall, our findings could be beneficial in addressing the clinical burden associated with seizure clusters, enabling patients to receive timely treatments and improving their quality of life.

Genomic and Synthetic Biology Digital Biosecurity.

Trends toward automation of synthetic biology and the individualization of biology and medicine raise varied and critical security issues. Digital biosecurity brings together researchers working in secure algorithms, vulnerability assessments, and emerging threat models. The fundamental goal of this digital biosecurity workshop is to identify and present distinct areas of research around making the next generation of biology safer and more secure. The workshop will include a panel overview of the field, including representatives from academia, industry, and non-profits. It will also include novel presentations from the research community. We expect that attendees will leave this workshop with a new appreciation of the research and implementation challenges in maintaining the digital aspects of biosecurity.

Noniatrogenic spinal cord ischemia: A patient level meta-analysis of 125 case reports and series.

Background: Guidelines are needed to manage spinal cord infarctions. Here, we evaluated the incidence of noniatrogenic spinal ischemia, focusing on the spinal levels involved, and the relative efficacy of different management strategies. Methods: We performed a meta-analysis of 147 patients who sustained noniatrogenic spinal cord ischemia within the past 10 years. The most common causes of injury were idiopathic (i.e., 47% medical/surgery-related) followed by systemic/chronic conditions (23.6%) and aortic vascular pathology (20%). Postdiagnostic treatment options included rehabilitation in 53.7% of patients, while steroids (35.37%), antiplatelets aggregates (30.61%), and anticoagulation (18.37%) were also used. Results: Traumatic causes of spinal cord ischemia were associated with worse outcomes, while those without a clear diagnosis despite extensive work-up had better results. At discharge, patients managed with cerebrospinal fluid (CSF) drainage had significant improvement (P = 0.04), while other therapies were not effective. Notably, ischemia mostly occurring between the T4 and T7 levels and was associated with the worst outcomes. In this thoracic "watershed" region, thoracic cord ischemia was most likely attributed to an increased susceptibility toto cord under-perfusion in this region (P < 0.05). Conclusion: This meta-analysis revealed a variety of etiologies for noniatrogenic typically T4-T7 spinal cord ischemia. Several different treatment strategies may be utilized in this patient population, including CSF drainage, blood pressure elevation, corticosteroids, antiplatelets/anticoagulants/thrombolytics, mannitol, naloxone, surgical revascularization, hyperbaric oxygen, and systemic hypothermia.

PB-Motif-A Method for Identifying Gene/Pseudogene Rearrangements With Long Reads: An Application to CYP21A2 Genotyping.

Long read sequencing technologies have the potential to accurately detect and phase variation in genomic regions that are difficult to fully characterize with conventional short read methods. These difficult to sequence regions include several clinically relevant genes with highly homologous pseudogenes, many of which are prone to gene conversions or other types of complex structural rearrangements. We present PB-Motif, a new method for identifying rearrangements between two highly homologous genomic regions using PacBio long reads. PB-Motif leverages clustering and filtering techniques to efficiently report rearrangements in the presence of sequencing errors and other systematic artifacts. Supporting reads for each high-confidence rearrangement can then be used for copy number estimation and phased variant calling. First, we demonstrate PB-Motif's accuracy with simulated sequence rearrangements of PMS2 and its pseudogene PMS2CL using simulated reads sweeping over a range of sequencing error rates. We then apply PB-Motif to 26 clinical samples, characterizing CYP21A2 and its pseudogene CYP21A1P as part of a diagnostic assay for congenital adrenal hyperplasia. We successfully identify damaging variation and patient carrier status concordant with clinical diagnosis obtained from multiplex ligation-dependent amplification (MLPA) and Sanger sequencing. The source code is available at: github.com/zstephens/pb-motif.

Exogene: A performant workflow for detecting viral integrations from paired-end next-generation sequencing data.

The integration of viruses into the human genome is known to be associated with tumorigenesis in many cancers, but the accurate detection of integration breakpoints from short read sequencing data is made difficult by human-viral homologies, viral genome heterogeneity, coverage limitations, and other factors. To address this, we present Exogene, a sensitive and efficient workflow for detecting viral integrations from paired-end next generation sequencing data. Exogene's read filtering and breakpoint detection strategies yield integration coordinates that are highly concordant with long read validation. We demonstrate this concordance across 6 TCGA Hepatocellular carcinoma (HCC) tumor samples, identifying integrations of hepatitis B virus that are also supported by long reads. Additionally, we applied Exogene to targeted capture data from 426 previously studied HCC samples, achieving 98.9% concordance with existing methods and identifying 238 high-confidence integrations that were not previously reported. Exogene is applicable to multiple types of paired-end sequence data, including genome, exome, RNA-Seq and targeted capture.

Lumbar Spine Surgery and What We Lost in the Era of the Coronavirus Pandemic: A Survey of the Lumbar Spine Research Society.

STUDY DESIGN: This was a survey of the surgeon members of the Lumbar Spine Research Society (LSRS). OBJECTIVE: The purpose of this study was to assess trends in surgical practice and patient management involving elective and emergency surgery in the early months of the coronavirus pandemic. SUMMARY OF BACKGROUND DATA: The novel coronavirus has radically disrupted medical care in the first half of 2020. Little data exists regarding the exact nature of its effect on spine care. METHODS: A 53-question survey was sent to the surgeon members of the LSRS. Respondents were contacted via email 3 times over a 2-week period in late April. Questions concentrated on surgical and clinical practice patterns before and after the pandemic. Other data included elective surgical schedules and volumes, as well as which emergency cases were being performed. Surgeons were asked about the status of coronavirus disease 2019 (COVID-19) virus testing. Circumstances for performing surgical intervention on patients with and without testing as well as patients testing positive were explored. RESULTS: A total of 43 completed surveys were returned of 174 sent to active surgeons in the LSRS (25%). Elective lumbar spine procedures decreased by 90% in the first 2 months of the pandemic, but emergency procedures did not change. Patients with "stable" lumbar disease had surgeries deferred indefinitely, even beyond 8 weeks if necessary. In-person outpatient visits became increasingly rare events, as telemedicine consultations accounted for 67% of all outpatient spine appointments. In total, 91% surgeons were under some type of confinement. Only 11% of surgeons tested for the coronavirus on all surgical patients. CONCLUSIONS: Elective lumbar surgery was significantly decreased in the first few months of the coronavirus pandemic, and much of outpatient spine surgery was practiced via telemedicine. Despite these constraints, spine surgeons performed emergency surgery when indicated, even when the COVID-19 status of patients was unknown. LEVEL OF EVIDENCE: Level IV.

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.

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.

Unsupervised machine-learning classification of electrophysiologically active electrodes during human cognitive task performance.

Identification of active electrodes that record task-relevant neurophysiological activity is needed for clinical and industrial applications as well as for investigating brain functions. We developed an unsupervised, fully automated approach to classify active electrodes showing event-related intracranial EEG (iEEG) responses from 115 patients performing a free recall verbal memory task. Our approach employed new interpretable metrics that quantify spectral characteristics of the normalized iEEG signal based on power-in-band and synchrony measures. Unsupervised clustering of the metrics identified distinct sets of active electrodes across different subjects. In the total population of 11,869 electrodes, our method achieved 97% sensitivity and 92.9% specificity with the most efficient metric. We validated our results with anatomical localization revealing significantly greater distribution of active electrodes in brain regions that support verbal memory processing. We propose our machine-learning framework for objective and efficient classification and interpretation of electrophysiological signals of brain activities supporting memory and cognition.