Single-cell multi-cohort dissection of the schizophrenia transcriptome.

The complexity and heterogeneity of schizophrenia have hindered mechanistic elucidation and the development of more effective therapies. Here, we performed single-cell dissection of schizophrenia-associated transcriptomic changes in the human prefrontal cortex across 140 individuals in two independent cohorts. Excitatory neurons were the most affected cell group, with transcriptional changes converging on neurodevelopment and synapse-related molecular pathways. Transcriptional alterations included known genetic risk factors, suggesting convergence of rare and common genomic variants on neuronal population-specific alterations in schizophrenia. Based on the magnitude of schizophrenia-associated transcriptional change, we identified two populations of individuals with schizophrenia marked by expression of specific excitatory and inhibitory neuronal cell states. This single-cell atlas links transcriptomic changes to etiological genetic risk factors, contextualizing established knowledge within the human cortical cytoarchitecture and facilitating mechanistic understanding of schizophrenia pathophysiology and heterogeneity.

Acute Effects of Growth Hormone on the Cellular Immunologic Landscape in Pediatric Patients.

INTRODUCTION: Growth hormone (GH) and the immune system have multiple bidirectional interactions. Data about the acute effects of GH on the immune system are lacking. The objective of our study was to evaluate the acute effects of GH on the immune system using time-of-flight mass cytometry. METHODS: This was a prospective study of pediatric patients who were being evaluated for short stature and underwent a GH stimulation test at a tertiary care center. Blood samples for immunologic markers, i.e., complete blood count (CBC) and time of flight mass cytometry (CyTOF), were collected at baseline (T0) and over the course of three hours (T3) of the test. Differences in immune profiling in patients by timepoint (T0, T3) and GH response (growth hormone sufficient (GHS) versus growth hormone deficient (GHD)) were calculated using a two-way ANOVA test.  Results: A total of 54 patients (39 boys and 15 girls) aged five to 18 years were recruited. Twenty-two participants tested GHD (peak GH <10 ng/ml). The CyTOF analysis showed a significant increase from T0 to T3 in granulocyte percentage, monocyte count, and dendritic cell (DC) count; in contrast, a significant decrease was seen in T lymphocytes (helper and cytotoxic) and IgD+ B lymphocytes. The CBC analysis supported these findings: an increase in total white blood cell count, absolute neutrophil count, and neutrophil percentage; a decrease in absolute lymphocyte count, lymphocyte percentage, absolute eosinophil count, and absolute monocyte count. No significant differences were found between CBC/CyTOF measurements and GH status at either time. CONCLUSIONS: This study provides the first high-resolution map of acute changes in the immune system with GH stimulation. This implies a key role for GH in immunomodulatory function.

Single-nucleus transcriptome analysis of human brain immune response in patients with severe COVID-19.

BACKGROUND: Coronavirus disease 2019 (COVID-19), caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection, has been associated with neurological and neuropsychiatric illness in many individuals. We sought to further our understanding of the relationship between brain tropism, neuro-inflammation, and host immune response in acute COVID-19 cases. METHODS: Three brain regions (dorsolateral prefrontal cortex, medulla oblongata, and choroid plexus) from 5 patients with severe COVID-19 and 4 controls were examined. The presence of the virus was assessed by western blot against viral spike protein, as well as viral transcriptome analysis covering > 99% of SARS-CoV-2 genome and all potential serotypes. Droplet-based single-nucleus RNA sequencing (snRNA-seq) was performed in the same samples to examine the impact of COVID-19 on transcription in individual cells of the brain. RESULTS: Quantification of viral spike S1 protein and viral transcripts did not detect SARS-CoV-2 in the postmortem brain tissue. However, analysis of 68,557 single-nucleus transcriptomes from three distinct regions of the brain identified an increased proportion of stromal cells, monocytes, and macrophages in the choroid plexus of COVID-19 patients. Furthermore, differential gene expression, pseudo-temporal trajectory, and gene regulatory network analyses revealed transcriptional changes in the cortical microglia associated with a range of biological processes, including cellular activation, mobility, and phagocytosis. CONCLUSIONS: Despite the absence of detectable SARS-CoV-2 in the brain at the time of death, the findings suggest significant and persistent neuroinflammation in patients with acute COVID-19.

Deep representation learning of electronic health records to unlock patient stratification at scale.

Deriving disease subtypes from electronic health records (EHRs) can guide next-generation personalized medicine. However, challenges in summarizing and representing patient data prevent widespread practice of scalable EHR-based stratification analysis. Here we present an unsupervised framework based on deep learning to process heterogeneous EHRs and derive patient representations that can efficiently and effectively enable patient stratification at scale. We considered EHRs of 1,608,741 patients from a diverse hospital cohort comprising a total of 57,464 clinical concepts. We introduce a representation learning model based on word embeddings, convolutional neural networks, and autoencoders (i.e., ConvAE) to transform patient trajectories into low-dimensional latent vectors. We evaluated these representations as broadly enabling patient stratification by applying hierarchical clustering to different multi-disease and disease-specific patient cohorts. ConvAE significantly outperformed several baselines in a clustering task to identify patients with different complex conditions, with 2.61 entropy and 0.31 purity average scores. When applied to stratify patients within a certain condition, ConvAE led to various clinically relevant subtypes for different disorders, including type 2 diabetes, Parkinson's disease, and Alzheimer's disease, largely related to comorbidities, disease progression, and symptom severity. With these results, we demonstrate that ConvAE can generate patient representations that lead to clinically meaningful insights. This scalable framework can help better understand varying etiologies in heterogeneous sub-populations and unlock patterns for EHR-based research in the realm of personalized medicine.

Artificial intelligence-enabled rapid diagnosis of COVID-19 patients.

For diagnosis of COVID-19, a SARS-CoV-2 virus-specific reverse transcriptase polymerase chain reaction (RT-PCR) test is routinely used. However, this test can take up to two days to complete, serial testing may be required to rule out the possibility of false negative results, and there is currently a shortage of RT-PCR test kits, underscoring the urgent need for alternative methods for rapid and accurate diagnosis of COVID-19 patients. Chest computed tomography (CT) is a valuable component in the evaluation of patients with suspected SARS-CoV-2 infection. Nevertheless, CT alone may have limited negative predictive value for ruling out SARS-CoV-2 infection, as some patients may have normal radiologic findings at early stages of the disease. In this study, we used artificial intelligence (AI) algorithms to integrate chest CT findings with clinical symptoms, exposure history, and laboratory testing to rapidly diagnose COVID-19 positive patients. Among a total of 905 patients tested by real-time RT-PCR assay and next-generation sequencing RT-PCR, 419 (46.3%) tested positive for SARS-CoV-2. In a test set of 279 patients, the AI system achieved an AUC of 0.92 and had equal sensitivity as compared to a senior thoracic radiologist. The AI system also improved the detection of RT-PCR positive COVID-19 patients who presented with normal CT scans, correctly identifying 17 of 25 (68%) patients, whereas radiologists classified all of these patients as COVID-19 negative. When CT scans and associated clinical history are available, the proposed AI system can help to rapidly diagnose COVID-19 patients.

Identification of therapeutic targets from genetic association studies using hierarchical component analysis.

BACKGROUND: Mapping disease-associated genetic variants to complex disease pathophysiology is a major challenge in translating findings from genome-wide association studies into novel therapeutic opportunities. The difficulty lies in our limited understanding of how phenotypic traits arise from non-coding genetic variants in highly organized biological systems with heterogeneous gene expression across cells and tissues. RESULTS: We present a novel strategy, called GWAS component analysis, for transferring disease associations from single-nucleotide polymorphisms to co-expression modules by stacking models trained using reference genome and tissue-specific gene expression data. Application of this method to genome-wide association studies of blood cell counts confirmed that it could detect gene sets enriched in expected cell types. In addition, coupling of our method with Bayesian networks enables GWAS components to be used to discover drug targets. CONCLUSIONS: We tested genome-wide associations of four disease phenotypes, including age-related macular degeneration, Crohn's disease, ulcerative colitis and rheumatoid arthritis, and demonstrated the proposed method could select more functional genes than S-PrediXcan, the previous single-step model for predicting gene-level associations from SNP-level associations.

Artificial intelligence-enabled rapid diagnosis of patients with COVID-19.

For diagnosis of coronavirus disease 2019 (COVID-19), a SARS-CoV-2 virus-specific reverse transcriptase polymerase chain reaction (RT-PCR) test is routinely used. However, this test can take up to 2 d to complete, serial testing may be required to rule out the possibility of false negative results and there is currently a shortage of RT-PCR test kits, underscoring the urgent need for alternative methods for rapid and accurate diagnosis of patients with COVID-19. Chest computed tomography (CT) is a valuable component in the evaluation of patients with suspected SARS-CoV-2 infection. Nevertheless, CT alone may have limited negative predictive value for ruling out SARS-CoV-2 infection, as some patients may have normal radiological findings at early stages of the disease. In this study, we used artificial intelligence (AI) algorithms to integrate chest CT findings with clinical symptoms, exposure history and laboratory testing to rapidly diagnose patients who are positive for COVID-19. Among a total of 905 patients tested by real-time RT-PCR assay and next-generation sequencing RT-PCR, 419 (46.3%) tested positive for SARS-CoV-2. In a test set of 279 patients, the AI system achieved an area under the curve of 0.92 and had equal sensitivity as compared to a senior thoracic radiologist. The AI system also improved the detection of patients who were positive for COVID-19 via RT-PCR who presented with normal CT scans, correctly identifying 17 of 25 (68%) patients, whereas radiologists classified all of these patients as COVID-19 negative. When CT scans and associated clinical history are available, the proposed AI system can help to rapidly diagnose COVID-19 patients.

Identifying Acute Low Back Pain Episodes in Primary Care Practice From Clinical Notes: Observational Study.

BACKGROUND: Acute and chronic low back pain (LBP) are different conditions with different treatments. However, they are coded in electronic health records with the same International Classification of Diseases, 10th revision (ICD-10) code (M54.5) and can be differentiated only by retrospective chart reviews. This prevents an efficient definition of data-driven guidelines for billing and therapy recommendations, such as return-to-work options. OBJECTIVE: The objective of this study was to evaluate the feasibility of automatically distinguishing acute LBP episodes by analyzing free-text clinical notes. METHODS: We used a dataset of 17,409 clinical notes from different primary care practices; of these, 891 documents were manually annotated as acute LBP and 2973 were generally associated with LBP via the recorded ICD-10 code. We compared different supervised and unsupervised strategies for automated identification: keyword search, topic modeling, logistic regression with bag of n-grams and manual features, and deep learning (a convolutional neural network-based architecture [ConvNet]). We trained the supervised models using either manual annotations or ICD-10 codes as positive labels. RESULTS: ConvNet trained using manual annotations obtained the best results with an area under the receiver operating characteristic curve of 0.98 and an F score of 0.70. ConvNet's results were also robust to reduction of the number of manually annotated documents. In the absence of manual annotations, topic models performed better than methods trained using ICD-10 codes, which were unsatisfactory for identifying LBP acuity. CONCLUSIONS: This study uses clinical notes to delineate a potential path toward systematic learning of therapeutic strategies, billing guidelines, and management options for acute LBP at the point of care.

Scaling structural learning with NO-BEARS to infer causal transcriptome networks.

Constructing gene regulatory networks is a critical step in revealing disease mechanisms from transcriptomic data. In this work, we present NO-BEARS, a novel algorithm for estimating gene regulatory networks. The NO-BEARS algorithm is built on the basis of the NO-TEARS algorithm with two improvements. First, we propose a new constraint and its fast approximation to reduce the computational cost of the NO-TEARS algorithm. Next, we introduce a polynomial regression loss to handle non-linearity in gene expressions. Our implementation utilizes modern GPU computation that can decrease the time of hours-long CPU computation to seconds. Using synthetic data, we demonstrate improved performance, both in processing time and accuracy, on inferring gene regulatory networks from gene expression data.

Genome-wide analysis indicates association between heterozygote advantage and healthy aging in humans.

BACKGROUND: Genetic diversity is known to confer survival advantage in many species across the tree of life. Here, we hypothesize that such pattern applies to humans as well and could be a result of higher fitness in individuals with higher genomic heterozygosity. RESULTS: We use healthy aging as a proxy for better health and fitness, and observe greater heterozygosity in healthy-aged individuals. Specifically, we find that only common genetic variants show significantly higher excess of heterozygosity in the healthy-aged cohort. Lack of difference in heterozygosity for low-frequency variants or disease-associated variants excludes the possibility of compensation for deleterious recessive alleles as a mechanism. In addition, coding SNPs with the highest excess of heterozygosity in the healthy-aged cohort are enriched in genes involved in extracellular matrix and glycoproteins, a group of genes known to be under long-term balancing selection. We also find that individual heterozygosity rate is a significant predictor of electronic health record (EHR)-based estimates of 10-year survival probability in men but not in women, accounting for several factors including age and ethnicity. CONCLUSIONS: Our results demonstrate that the genomic heterozygosity is associated with human healthspan, and that the relationship between higher heterozygosity and healthy aging could be explained by heterozygote advantage. Further characterization of this relationship will have important implications in aging-associated disease risk prediction.

MetaCyto: A Tool for Automated Meta-analysis of Mass and Flow Cytometry Data.

While meta-analysis has demonstrated increased statistical power and more robust estimations in studies, the application of this commonly accepted methodology to cytometry data has been challenging. Different cytometry studies often involve diverse sets of markers. Moreover, the detected values of the same marker are inconsistent between studies due to different experimental designs and cytometer configurations. As a result, the cell subsets identified by existing auto-gating methods cannot be directly compared across studies. We developed MetaCyto for automated meta-analysis of both flow and mass cytometry (CyTOF) data. By combining clustering methods with a silhouette scanning method, MetaCyto is able to identify commonly labeled cell subsets across studies, thus enabling meta-analysis. Applying MetaCyto across a set of ten heterogeneous cytometry studies totaling 2,926 samples enabled us to identify multiple cell populations exhibiting differences in abundance between demographic groups. Software is released to the public through Bioconductor (http://bioconductor.org/packages/release/bioc/html/MetaCyto.html).

Cell-specific prediction and application of drug-induced gene expression profiles.

Gene expression profiling of in vitro drug perturbations is useful for many biomedical discovery applications including drug repurposing and elucidation of drug mechanisms. However, limited data availability across cell types has hindered our capacity to leverage or explore the cell-specificity of these perturbations. While recent efforts have generated a large number of drug perturbation profiles across a variety of human cell types, many gaps remain in this combinatorial drug-cell space. Hence, we asked whether it is possible to fill these gaps by predicting cell-specific drug perturbation profiles using available expression data from related conditions--i.e. from other drugs and cell types. We developed a computational framework that first arranges existing profiles into a three-dimensional array (or tensor) indexed by drugs, genes, and cell types, and then uses either local (nearest-neighbors) or global (tensor completion) information to predict unmeasured profiles. We evaluate prediction accuracy using a variety of metrics, and find that the two methods have complementary performance, each superior in different regions in the drug-cell space. Predictions achieve correlations of 0.68 with true values, and maintain accurate differentially expressed genes (AUC 0.81). Finally, we demonstrate that the predicted profiles add value for making downstream associations with drug targets and therapeutic classes.

Automated cell type discovery and classification through knowledge transfer.

MOTIVATION: Recent advances in mass cytometry allow simultaneous measurements of up to 50 markers at single-cell resolution. However, the high dimensionality of mass cytometry data introduces computational challenges for automated data analysis and hinders translation of new biological understanding into clinical applications. Previous studies have applied machine learning to facilitate processing of mass cytometry data. However, manual inspection is still inevitable and becoming the barrier to reliable large-scale analysis. RESULTS: We present a new algorithm called utomated ell-type iscovery and lassification (ACDC) that fully automates the classification of canonical cell populations and highlights novel cell types in mass cytometry data. Evaluations on real-world data show ACDC provides accurate and reliable estimations compared to manual gating results. Additionally, ACDC automatically classifies previously ambiguous cell types to facilitate discovery. Our findings suggest that ACDC substantially improves both reliability and interpretability of results obtained from high-dimensional mass cytometry profiling data. AVAILABILITY AND IMPLEMENTATION: A Python package (Python 3) and analysis scripts for reproducing the results are availability on https://bitbucket.org/dudleylab/acdc . CONTACT: brian.kidd@mssm.edu or joel.dudley@mssm.edu. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Inner membrane fusion mediates spatial distribution of axonal mitochondria.

In eukaryotic cells, mitochondria form a dynamic interconnected network to respond to changing needs at different subcellular locations. A fundamental yet unanswered question regarding this network is whether, and if so how, local fusion and fission of individual mitochondria affect their global distribution. To address this question, we developed high-resolution computational image analysis techniques to examine the relations between mitochondrial fusion/fission and spatial distribution within the axon of Drosophila larval neurons. We found that stationary and moving mitochondria underwent fusion and fission regularly but followed different spatial distribution patterns and exhibited different morphology. Disruption of inner membrane fusion by knockdown of dOpa1, Drosophila Optic Atrophy 1, not only increased the spatial density of stationary and moving mitochondria but also changed their spatial distributions and morphology differentially. Knockdown of dOpa1 also impaired axonal transport of mitochondria. But the changed spatial distributions of mitochondria resulted primarily from disruption of inner membrane fusion because knockdown of Milton, a mitochondrial kinesin-1 adapter, caused similar transport velocity impairment but different spatial distributions. Together, our data reveals that stationary mitochondria within the axon interconnect with moving mitochondria through fusion and fission and that local inner membrane fusion between individual mitochondria mediates their global distribution.

Data-Driven Engineering of Social Dynamics: Pattern Matching and Profit Maximization.

In this paper, we define a new problem related to social media, namely, the data-driven engineering of social dynamics. More precisely, given a set of observations from the past, we aim at finding the best short-term intervention that can lead to predefined long-term outcomes. Toward this end, we propose a general formulation that covers two useful engineering tasks as special cases, namely, pattern matching and profit maximization. By incorporating a deep learning model, we derive a solution using convex relaxation and quadratic-programming transformation. Moreover, we propose a data-driven evaluation method in place of the expensive field experiments. Using a Twitter dataset, we demonstrate the effectiveness of our dynamics engineering approach for both pattern matching and profit maximization, and study the multifaceted interplay among several important factors of dynamics engineering, such as solution validity, pattern-matching accuracy, and intervention cost. Finally, the method we propose is general enough to work with multi-dimensional time series, so it can potentially be used in many other applications.

Shape component analysis: structure-preserving dimension reduction on biological shape spaces.

MOTIVATION: Quantitative shape analysis is required by a wide range of biological studies across diverse scales, ranging from molecules to cells and organisms. In particular, high-throughput and systems-level studies of biological structures and functions have started to produce large volumes of complex high-dimensional shape data. Analysis and understanding of high-dimensional biological shape data require dimension-reduction techniques. RESULTS: We have developed a technique for non-linear dimension reduction of 2D and 3D biological shape representations on their Riemannian spaces. A key feature of this technique is that it preserves distances between different shapes in an embedded low-dimensional shape space. We demonstrate an application of this technique by combining it with non-linear mean-shift clustering on the Riemannian spaces for unsupervised clustering of shapes of cellular organelles and proteins. AVAILABILITY AND IMPLEMENTATION: Source code and data for reproducing results of this article are freely available at https://github.com/ccdlcmu/shape_component_analysis_Matlab The implementation was made in MATLAB and supported on MS Windows, Linux and Mac OS. CONTACT: geyang@andrew.cmu.edu.

Toward automated denoising of single molecular Förster resonance energy transfer data.

A wide-field two-channel fluorescence microscope is a powerful tool as it allows for the study of conformation dynamics of hundreds to thousands of immobilized single molecules by Förster resonance energy transfer (FRET) signals. To date, the data reduction from a movie to a final set containing meaningful single-molecule FRET (smFRET) traces involves human inspection and intervention at several critical steps, greatly hampering the efficiency at the post-imaging stage. To facilitate the data reduction from smFRET movies to smFRET traces and to address the noise-limited issues, we developed a statistical denoising system toward fully automated processing. This data reduction system has embedded several novel approaches. First, as to background subtraction, high-order singular value decomposition (HOSVD) method is employed to extract spatial and temporal features. Second, to register and map the two color channels, the spots representing bleeding through the donor channel to the acceptor channel are used. Finally, correlation analysis and likelihood ratio statistic for the change point detection (CPD) are developed to study the two channels simultaneously, resolve FRET states, and report the dwelling time of each state. The performance of our method has been checked using both simulation and real data.