Deep learning-assisted genome-wide characterization of massively parallel reporter assays.

Massively parallel reporter assay (MPRA) is a high-throughput method that enables the study of the regulatory activities of tens of thousands of DNA oligonucleotides in a single experiment. While MPRA experiments have grown in popularity, their small sample sizes compared to the scale of the human genome limits our understanding of the regulatory effects they detect. To address this, we develop a deep learning model, MpraNet, to distinguish potential MPRA targets from the background genome. This model achieves high discriminative performance (AUROC = 0.85) at differentiating MPRA positives from a set of control variants that mimic the background genome when applied to the lymphoblastoid cell line. We observe that existing functional scores represent very distinct functional effects, and most of them fail to characterize the regulatory effect that MPRA detects. Using MpraNet, we predict potential MPRA functional variants across the genome and identify the distributions of MPRA effect relative to other characteristics of genetic variation, including allele frequency, alternative functional annotations specified by FAVOR, and phenome-wide associations. We also observed that the predicted MPRA positives are not uniformly distributed across the genome; instead, they are clumped together in active regions comprising 9.95% of the genome and inactive regions comprising 89.07% of the genome. Furthermore, we propose our model as a screen to filter MPRA experiment candidates at genome-wide scale, enabling future experiments to be more cost-efficient by increasing precision relative to that observed from previous MPRAs.

Near real-time surveillance of the SARS-CoV-2 epidemic with incomplete data.

When responding to infectious disease outbreaks, rapid and accurate estimation of the epidemic trajectory is critical. However, two common data collection problems affect the reliability of the epidemiological data in real time: missing information on the time of first symptoms, and retrospective revision of historical information, including right censoring. Here, we propose an approach to construct epidemic curves in near real time that addresses these two challenges by 1) imputation of dates of symptom onset for reported cases using a dynamically-estimated "backward" reporting delay conditional distribution, and 2) adjustment for right censoring using the NobBS software package to nowcast cases by date of symptom onset. This process allows us to obtain an approximation of the time-varying reproduction number (Rt) in real time. We apply this approach to characterize the early SARS-CoV-2 outbreak in two Spanish regions between March and April 2020. We evaluate how these real-time estimates compare with more complete epidemiological data that became available later. We explore the impact of the different assumptions on the estimates, and compare our estimates with those obtained from commonly used surveillance approaches. Our framework can help improve accuracy, quantify uncertainty, and evaluate frequently unstated assumptions when recovering the epidemic curves from limited data obtained from public health systems in other locations.

Estimating the cumulative incidence of COVID-19 in the United States using influenza surveillance, virologic testing, and mortality data: Four complementary approaches.

Effectively designing and evaluating public health responses to the ongoing COVID-19 pandemic requires accurate estimation of the prevalence of COVID-19 across the United States (US). Equipment shortages and varying testing capabilities have however hindered the usefulness of the official reported positive COVID-19 case counts. We introduce four complementary approaches to estimate the cumulative incidence of symptomatic COVID-19 in each state in the US as well as Puerto Rico and the District of Columbia, using a combination of excess influenza-like illness reports, COVID-19 test statistics, COVID-19 mortality reports, and a spatially structured epidemic model. Instead of relying on the estimate from a single data source or method that may be biased, we provide multiple estimates, each relying on different assumptions and data sources. Across our four approaches emerges the consistent conclusion that on April 4, 2020, the estimated case count was 5 to 50 times higher than the official positive test counts across the different states. Nationally, our estimates of COVID-19 symptomatic cases as of April 4 have a likely range of 2.3 to 4.8 million, with possibly as many as 7.6 million cases, up to 25 times greater than the cumulative confirmed cases of about 311,000. Extending our methods to May 16, 2020, we estimate that cumulative symptomatic incidence ranges from 4.9 to 10.1 million, as opposed to 1.5 million positive test counts. The proposed combination of approaches may prove useful in assessing the burden of COVID-19 during resurgences in the US and other countries with comparable surveillance systems.

Sub-national levels and trends in contraceptive prevalence, unmet need, and demand for family planning in Nigeria with survey uncertainty.

BACKGROUND: Ambitious global goals have been established to provide universal access to affordable modern contraceptive methods. To measure progress toward such goals in populous countries like Nigeria, it's essential to characterize the current levels and trends of family planning (FP) indicators such as unmet need and modern contraceptive prevalence rates (mCPR). Moreover, the substantial heterogeneity across Nigeria and scale of programmatic implementation requires a sub-national resolution of these FP indicators. The aim of this study is to estimate the levels and trends of FP indicators at a subnational scale in Nigeria utilizing all available data and accounting for survey design and uncertainty. METHODS: We utilized all available cross-sectional survey data from Nigeria including the Demographic and Health Surveys, Multiple Indicator Cluster Surveys, National Nutrition and Health Surveys, and Performance, Monitoring, and Accountability 2020. We developed a hierarchical Bayesian model that incorporates all of the individual level data from each survey instrument, accounts for survey uncertainty, leverages spatio-temporal smoothing, and produces probabilistic estimates with uncertainty intervals. RESULTS: We estimate that overall rates and trends of mCPR and unmet need have remained low in Nigeria: the average annual rate of change for mCPR by state is 0.5% (0.4%,0.6%) from 2012-2017. Unmet need by age-parity demographic groups varied significantly across Nigeria; parous women express much higher rates of unmet need than nulliparous women. CONCLUSIONS: Understanding the estimates and trends of FP indicators at a subnational resolution in Nigeria is integral to inform programmatic decision-making. We identify age-parity-state subgroups with large rates of unmet need. We also find conflicting trends by survey instrument across a number of states. Our model-based estimates highlight these inconsistencies, attempt to reconcile the direct survey estimates, and provide uncertainty intervals to enable interpretation of model and survey estimates for decision-making.

Advances in using Internet searches to track dengue.

Dengue is a mosquito-borne disease that threatens over half of the world's population. Despite being endemic to more than 100 countries, government-led efforts and tools for timely identification and tracking of new infections are still lacking in many affected areas. Multiple methodologies that leverage the use of Internet-based data sources have been proposed as a way to complement dengue surveillance efforts. Among these, dengue-related Google search trends have been shown to correlate with dengue activity. We extend a methodological framework, initially proposed and validated for flu surveillance, to produce near real-time estimates of dengue cases in five countries/states: Mexico, Brazil, Thailand, Singapore and Taiwan. Our result shows that our modeling framework can be used to improve the tracking of dengue activity in multiple locations around the world.

Predicting dengue incidence leveraging internet-based data sources. A case study in 20 cities in Brazil.

The dengue virus affects millions of people every year worldwide, causing large epidemic outbreaks that disrupt people's lives and severely strain healthcare systems. In the absence of a reliable vaccine against dengue or an effective treatment to manage the illness in humans, most efforts to combat dengue infections have focused on preventing its vectors, mainly the Aedes aegypti mosquito, from flourishing across the world. These mosquito-control strategies need reliable disease activity surveillance systems to be deployed. Despite significant efforts to estimate dengue incidence using a variety of data sources and methods, little work has been done to understand the relative contribution of the different data sources to improved prediction. Additionally, scholarship on the topic had initially focused on prediction systems at the national- and state-levels, and much remains to be done at the finer spatial resolutions at which health policy interventions often occur. We develop a methodological framework to assess and compare dengue incidence estimates at the city level, and evaluate the performance of a collection of models on 20 different cities in Brazil. The data sources we use towards this end are weekly incidence counts from prior years (seasonal autoregressive terms), weekly-aggregated weather variables, and real-time internet search data. We find that both random forest-based models and LASSO regression-based models effectively leverage these multiple data sources to produce accurate predictions, and that while the performance between them is comparable on average, the former method produces fewer extreme outliers, and can thus be considered more robust. For real-time predictions that assume long delays (6-8 weeks) in the availability of epidemiological data, we find that real-time internet search data are the strongest predictors of dengue incidence, whereas for predictions that assume short delays (1-3 weeks), in which the error rate is halved (as measured by relative RMSE), short-term and seasonal autocorrelation are the dominant predictors. Despite the difficulties inherent to city-level prediction, our framework achieves meaningful and actionable estimates across cities with different demographic, geographic and epidemic characteristics.

Deep neural networks with controlled variable selection for the identification of putative causal genetic variants.

Deep neural networks (DNNs) have been successfully utilized in many scientific problems for their high prediction accuracy, but their application to genetic studies remains challenging due to their poor interpretability. Here we consider the problem of scalable, robust variable selection in DNNs for the identification of putative causal genetic variants in genome sequencing studies. We identified a pronounced randomness in feature selection in DNNs due to its stochastic nature, which may hinder interpretability and give rise to misleading results. We propose an interpretable neural network model, stabilized using ensembling, with controlled variable selection for genetic studies. The merit of the proposed method includes: flexible modelling of the nonlinear effect of genetic variants to improve statistical power; multiple knockoffs in the input layer to rigorously control the false discovery rate; hierarchical layers to substantially reduce the number of weight parameters and activations, and improve computational efficiency; and stabilized feature selection to reduce the randomness in identified signals. We evaluate the proposed method in extensive simulation studies and apply it to the analysis of Alzheimer's disease genetics. We show that the proposed method, when compared with conventional linear and nonlinear methods, can lead to substantially more discoveries.

Identification of putative causal loci in whole-genome sequencing data via knockoff statistics.

The analysis of whole-genome sequencing studies is challenging due to the large number of rare variants in noncoding regions and the lack of natural units for testing. We propose a statistical method to detect and localize rare and common risk variants in whole-genome sequencing studies based on a recently developed knockoff framework. It can (1) prioritize causal variants over associations due to linkage disequilibrium thereby improving interpretability; (2) help distinguish the signal due to rare variants from shadow effects of significant common variants nearby; (3) integrate multiple knockoffs for improved power, stability, and reproducibility; and (4) flexibly incorporate state-of-the-art and future association tests to achieve the benefits proposed here. In applications to whole-genome sequencing data from the Alzheimer's Disease Sequencing Project (ADSP) and COPDGene samples from NHLBI Trans-Omics for Precision Medicine (TOPMed) Program we show that our method compared with conventional association tests can lead to substantially more discoveries.

An early warning approach to monitor COVID-19 activity with multiple digital traces in near real time.

Given still-high levels of coronavirus disease 2019 (COVID-19) susceptibility and inconsistent transmission-containing strategies, outbreaks have continued to emerge across the United States. Until effective vaccines are widely deployed, curbing COVID-19 will require carefully timed nonpharmaceutical interventions (NPIs). A COVID-19 early warning system is vital for this. Here, we evaluate digital data streams as early indicators of state-level COVID-19 activity from 1 March to 30 September 2020. We observe that increases in digital data stream activity anticipate increases in confirmed cases and deaths by 2 to 3 weeks. Confirmed cases and deaths also decrease 2 to 4 weeks after NPI implementation, as measured by anonymized, phone-derived human mobility data. We propose a means of harmonizing these data streams to identify future COVID-19 outbreaks. Our results suggest that combining disparate health and behavioral data may help identify disease activity changes weeks before observation using traditional epidemiological monitoring.

Estimating the Cumulative Incidence of COVID-19 in the United States Using Four Complementary Approaches.

Effectively designing and evaluating public health responses to the ongoing COVID-19 pandemic requires accurate estimation of the prevalence of COVID-19 across the United States (US). Equipment shortages and varying testing capabilities have however hindered the useful-ness of the official reported positive COVID-19 case counts. We introduce four complementary approaches to estimate the cumulative incidence of symptomatic COVID-19 in each state in the US as well as Puerto Rico and the District of Columbia, using a combination of excess influenza-like illness reports, COVID-19 test statistics, COVID-19 mortality reports, and a spatially structured epidemic model. Instead of relying on the estimate from a single data source or method that may be biased, we provide multiple estimates, each relying on different assumptions and data sources. Across our four approaches emerges the consistent conclusion that on April 4, 2020, the estimated case count was 5 to 50 times higher than the official positive test counts across the different states. Nationally, our estimates of COVID-19 symptomatic cases as of April 4 have a likely range of 2.2 to 4.9 million, with possibly as many as 8.1 million cases, up to 26 times greater than the cumulative confirmed cases of about 311,000. Extending our method to May 16, 2020, we estimate that cumulative symptomatic incidence ranges from 6.0 to 10.3 million, as opposed to 1.5 million positive test counts. The proposed combination of approaches may prove useful in assessing the burden of COVID-19 during resurgences in the US and other countries with comparable surveillance systems.

An Early Warning Approach to Monitor COVID-19 Activity with Multiple Digital Traces in Near Real-Time.

Non-pharmaceutical interventions (NPIs) have been crucial in curbing COVID-19 in the United States (US). Consequently, relaxing NPIs through a phased re-opening of the US amid still-high levels of COVID-19 susceptibility could lead to new epidemic waves. This calls for a COVID-19 early warning system. Here we evaluate multiple digital data streams as early warning indicators of increasing or decreasing state-level US COVID-19 activity between January and June 2020. We estimate the timing of sharp changes in each data stream using a simple Bayesian model that calculates in near real-time the probability of exponential growth or decay. Analysis of COVID-19-related activity on social network microblogs, Internet searches, point-of-care medical software, and a metapopulation mechanistic model, as well as fever anomalies captured by smart thermometer networks, shows exponential growth roughly 2-3 weeks prior to comparable growth in confirmed COVID-19 cases and 3-4 weeks prior to comparable growth in COVID-19 deaths across the US over the last 6 months. We further observe exponential decay in confirmed cases and deaths 5-6 weeks after implementation of NPIs, as measured by anonymized and aggregated human mobility data from mobile phones. Finally, we propose a combined indicator for exponential growth in multiple data streams that may aid in developing an early warning system for future COVID-19 outbreaks. These efforts represent an initial exploratory framework, and both continued study of the predictive power of digital indicators as well as further development of the statistical approach are needed.

Improved Real-Time Influenza Surveillance: Using Internet Search Data in Eight Latin American Countries.

BACKGROUND: Novel influenza surveillance systems that leverage Internet-based real-time data sources including Internet search frequencies, social-network information, and crowd-sourced flu surveillance tools have shown improved accuracy over the past few years in data-rich countries like the United States. These systems not only track flu activity accurately, but they also report flu estimates a week or more ahead of the publication of reports produced by healthcare-based systems, such as those implemented and managed by the Centers for Disease Control and Prevention. Previous work has shown that the predictive capabilities of novel flu surveillance systems, like Google Flu Trends (GFT), in developing countries in Latin America have not yet delivered acceptable flu estimates. OBJECTIVE: The aim of this study was to show that recent methodological improvements on the use of Internet search engine information to track diseases can lead to improved retrospective flu estimates in multiple countries in Latin America. METHODS: A machine learning-based methodology that uses flu-related Internet search activity and historical information to monitor flu activity, named ARGO (AutoRegression with Google search), was extended to generate flu predictions for 8 Latin American countries (Argentina, Bolivia, Brazil, Chile, Mexico, Paraguay, Peru, and Uruguay) for the time period: January 2012 to December of 2016. These retrospective (out-of-sample) Influenza activity predictions were compared with historically observed flu suspected cases in each country, as reported by Flunet, an influenza surveillance database maintained by the World Health Organization. For a baseline comparison, retrospective (out-of-sample) flu estimates were produced for the same time period using autoregressive models that only leverage historical flu activity information. RESULTS: Our results show that ARGO-like models' predictive power outperform autoregressive models in 6 out of 8 countries in the 2012-2016 time period. Moreover, ARGO significantly improves on historical flu estimates produced by the now discontinued GFT for the time period of 2012-2015, where GFT information is publicly available. CONCLUSIONS: We demonstrate here that a self-correcting machine learning method, leveraging Internet-based disease-related search activity and historical flu trends, has the potential to produce reliable and timely flu estimates in multiple Latin American countries. This methodology may prove helpful to local public health officials who design and implement interventions aimed at mitigating the effects of influenza outbreaks. Our methodology generally outperforms both the now-discontinued tool GFT, and autoregressive methodologies that exploit only historical flu activity to produce future disease estimates.

Improved state-level influenza nowcasting in the United States leveraging Internet-based data and network approaches.

In the presence of health threats, precision public health approaches aim to provide targeted, timely, and population-specific interventions. Accurate surveillance methodologies that can estimate infectious disease activity ahead of official healthcare-based reports, at relevant spatial resolutions, are important for achieving this goal. Here we introduce a methodological framework which dynamically combines two distinct influenza tracking techniques, using an ensemble machine learning approach, to achieve improved state-level influenza activity estimates in the United States. The two predictive techniques behind the ensemble utilize (1) a self-correcting statistical method combining influenza-related Google search frequencies, information from electronic health records, and historical flu trends within each state, and (2) a network-based approach leveraging spatio-temporal synchronicities observed in historical influenza activity across states. The ensemble considerably outperforms each component method in addition to previously proposed state-specific methods for influenza tracking, with higher correlations and lower prediction errors.

Accurate Influenza Monitoring and Forecasting Using Novel Internet Data Streams: A Case Study in the Boston Metropolis.

BACKGROUND: Influenza outbreaks pose major challenges to public health around the world, leading to thousands of deaths a year in the United States alone. Accurate systems that track influenza activity at the city level are necessary to provide actionable information that can be used for clinical, hospital, and community outbreak preparation. OBJECTIVE: Although Internet-based real-time data sources such as Google searches and tweets have been successfully used to produce influenza activity estimates ahead of traditional health care-based systems at national and state levels, influenza tracking and forecasting at finer spatial resolutions, such as the city level, remain an open question. Our study aimed to present a precise, near real-time methodology capable of producing influenza estimates ahead of those collected and published by the Boston Public Health Commission (BPHC) for the Boston metropolitan area. This approach has great potential to be extended to other cities with access to similar data sources. METHODS: We first tested the ability of Google searches, Twitter posts, electronic health records, and a crowd-sourced influenza reporting system to detect influenza activity in the Boston metropolis separately. We then adapted a multivariate dynamic regression method named ARGO (autoregression with general online information), designed for tracking influenza at the national level, and showed that it effectively uses the above data sources to monitor and forecast influenza at the city level 1 week ahead of the current date. Finally, we presented an ensemble-based approach capable of combining information from models based on multiple data sources to more robustly nowcast as well as forecast influenza activity in the Boston metropolitan area. The performances of our models were evaluated in an out-of-sample fashion over 4 influenza seasons within 2012-2016, as well as a holdout validation period from 2016 to 2017. RESULTS: Our ensemble-based methods incorporating information from diverse models based on multiple data sources, including ARGO, produced the most robust and accurate results. The observed Pearson correlations between our out-of-sample flu activity estimates and those historically reported by the BPHC were 0.98 in nowcasting influenza and 0.94 in forecasting influenza 1 week ahead of the current date. CONCLUSIONS: We show that information from Internet-based data sources, when combined using an informed, robust methodology, can be effectively used as early indicators of influenza activity at fine geographic resolutions.

Time-dependent neurosphere-forming ability of adult rat spinal cord after irradiation.

To determine whether there was evidence for long-term time-dependent changes in neurosphere-forming ability of rat spinal cord after irradiation, a 15-mm length of spinal cord (C2-T2) of 10-week-old female rats was irradiated with a single dose of 2, 5, 10 or 19 Gy. Cells were isolated from the central 10-mm segment of the irradiated spinal cord immediately or at 0.5, 1, 2 or 5 months to form neurospheres. The number and sizes of neurospheres were determined at day 10, 12, 14 and 16 in vitro. The multipotential properties of neurosphere cells were assessed by immunocytochemistry using lineage-specific markers for neurons and glia. In nonirradiated controls, the number and size of the neurospheres decreased with increasing age of the animals. Regardless of the time after irradiation, there was a dose-dependent decrease in the number and size of neurospheres obtained from the irradiated cord compared to age-matched controls. Using three-way ANOVA, the number of neurospheres was dependent on radiation dose (P < 0.0001), time after irradiation (P < 0.0001), and day of counting in vitro (P < 0.0001). Compared to cells cultured immediately after irradiation, there was an increase in the relative plating efficiency of neurospheres cultured 1 month after irradiation. However, no further increase was apparent up to 5 months after irradiation. The multipotential properties of neurosphere cells in vitro remained unchanged with increasing time after irradiation. These results may suggest a time-dependent recovery of radiation damage using neurosphere-forming ability as the end point and agree with data that show time-dependent recovery of radiation damage in spinal cord using histological or functional end points.

Versican V1 isoform induces neuronal differentiation and promotes neurite outgrowth.

The chondroitin sulfate proteoglycan versican is one of the major extracellular components in the developing and adult brain. Here, we show that isoforms of versican play different roles in neuronal differentiation and neurite outgrowth. Expression of versican V1 isoform in PC12 cells induced complete differentiation, whereas expression of V2 induced an aborted differentiation accompanied by apoptosis. V1 promoted neurite outgrowth of hippocampal neurons, but V2 failed to do so. V1 transfection enhanced expression of epidermal growth factor receptor and integrins, and facilitated sustained extracellular signal-regulated kinase/MAPK phosphorylation. Blockade of the epidermal growth factor receptor, beta1 integrin, or Src significantly inhibited neuronal differentiation. Finally, we demonstrated that versican V1 isoform also promoted differentiation of neural stem cells into neurons. Our results have implications for understanding how versican regulates neuronal development, function, and repair.

A clonogenic survival assay of neural stem cells in rat spinal cord after exposure to ionizing radiation.

Neural stem cells play an important role in neurogenesis of the adult central nervous system (CNS). Inhibition of neurogenesis has been suggested to be an underlying mechanism of radiation-induced CNS damage. Here we developed an in vivo/ in vitro clonogenic assay to characterize the survival of neural stem cells after exposure to ionizing radiation. Cells were isolated from the rat cervical spinal cord and plated as single cell suspensions in defined medium containing epidermal growth factor and basic fibroblast growth factor. The survival of the proliferating cells was determined by their ability to form neurosphere colonies. The number and size of neurospheres were analyzed quantitatively at day 10, 12, 14 and 16 after plating. Plating cells from 5, 10 and 15 mm of the cervical spinal cord resulted in a linear increase in the number of neurospheres from day 10-16. Compared to the nonirradiated spinal cord, there was a significant decrease in the number and size of neurosphere colonies cultured from a 10-mm length of the rat spinal cord after a single dose of 5 Gy. When dissociated neurospheres derived from a spinal cord that had been irradiated with 5 Gy were allowed to differentiate, the percentages of neurons, oligodendrocytes and astrocytes as determined by immunocytohistochemistry were not altered compared to those from the nonirradiated spinal cord. Secondary neurospheres could be obtained from cells dissociated from primary neurospheres that had been cultured from the irradiated spinal cord. In conclusion, exposure to ionizing radiation reduces the clonogenic survival of neural stem cells cultured from the rat spinal cord. However, neural stem cells retain their pluripotent and self-renewing properties after irradiation. A neurosphere-based assay may provide a quantitative measure of the clonogenic survival of neural stem cells in the adult CNS after irradiation.

Radiation-induced alterations in mouse brain development characterized by magnetic resonance imaging.

PURPOSE: The purpose of this study was to identify regions of altered development in the mouse brain after cranial irradiation using longitudinal magnetic resonance imaging (MRI). METHODS AND MATERIALS: Female C57Bl/6 mice received a whole-brain radiation dose of 7 Gy at an infant-equivalent age of 2.5 weeks. MRI was performed before irradiation and at 3 time points following irradiation. Deformation-based morphometry was used to quantify volume and growth rate changes following irradiation. RESULTS: Widespread developmental deficits were observed in both white and gray matter regions following irradiation. Most of the affected brain regions suffered an initial volume deficit followed by growth at a normal rate, remaining smaller in irradiated brains compared with controls at all time points examined. The one exception was the olfactory bulb, which in addition to an early volume deficit, grew at a slower rate thereafter, resulting in a progressive volume deficit relative to controls. Immunohistochemical assessment revealed demyelination in white matter and loss of neural progenitor cells in the subgranular zone of the dentate gyrus and subventricular zone. CONCLUSIONS: MRI can detect regional differences in neuroanatomy and brain growth after whole-brain irradiation in the developing mouse. Developmental deficits in neuroanatomy persist, or even progress, and may serve as useful markers of late effects in mouse models. The high-throughput evaluation of brain development enabled by these methods may allow testing of strategies to mitigate late effects after pediatric cranial irradiation.