Biophysical modeling with variational autoencoders for bimodal, single-cell RNA sequencing data.

Here we present biVI, which combines the variational autoencoder framework of scVI with biophysical models describing the transcription and splicing kinetics of RNA molecules. We demonstrate on simulated and experimental single-cell RNA sequencing data that biVI retains the variational autoencoder's ability to capture cell type structure in a low-dimensional space while further enabling genome-wide exploration of the biophysical mechanisms, such as system burst sizes and degradation rates, that underlie observations.

Corrigendum: Detection of COVID-19 epidemic outbreak using machine learning.

[This corrects the article DOI: 10.3389/fpubh.2023.1252357.].

Deciphering the History of ERK Activity from Fixed-Cell Immunofluorescence Measurements.

The Ras/ERK pathway drives cell proliferation and other oncogenic behaviors, and quantifying its activity in situ is of high interest in cancer diagnosis and therapy. Pathway activation is often assayed by measuring phosphorylated ERK. However, this form of measurement overlooks dynamic aspects of signaling that can only be observed over time. In this study, we combine a live, single-cell ERK biosensor approach with multiplexed immunofluorescence staining of downstream target proteins to ask how well immunostaining captures the dynamic history of ERK activity. Combining linear regression, machine learning, and differential equation models, we develop an interpretive framework for immunostains, in which Fra-1 and pRb levels imply long term activation of ERK signaling, while Egr-1 and c-Myc indicate recent activation. We show that this framework can distinguish different classes of ERK dynamics within a heterogeneous population, providing a tool for annotating ERK dynamics within fixed tissues.

siVAE: interpretable deep generative models for single-cell transcriptomes.

Neural networks such as variational autoencoders (VAE) perform dimensionality reduction for the visualization and analysis of genomic data, but are limited in their interpretability: it is unknown which data features are represented by each embedding dimension. We present siVAE, a VAE that is interpretable by design, thereby enhancing downstream analysis tasks. Through interpretation, siVAE also identifies gene modules and hubs without explicit gene network inference. We use siVAE to identify gene modules whose connectivity is associated with diverse phenotypes such as iPSC neuronal differentiation efficiency and dementia, showcasing the wide applicability of interpretable generative models for genomic data analysis.

Biophysical modeling with variational autoencoders for bimodal, single-cell RNA sequencing data.

We motivate and present biVI, which combines the variational autoencoder framework of scVI with biophysically motivated, bivariate models for nascent and mature RNA distributions. While previous approaches to integrate bimodal data via the variational autoencoder framework ignore the causal relationship between measurements, biVI models the biophysical processes that give rise to observations. We demonstrate through simulated benchmarking that biVI captures cell type structure in a low-dimensional space and accurately recapitulates parameter values and copy number distributions. On biological data, biVI provides a scalable route for identifying the biophysical mechanisms underlying gene expression. This analytical approach outlines a generalizable strategy for treating multimodal datasets generated by high-throughput, single-cell genomic assays.

Detection of COVID-19 epidemic outbreak using machine learning.

Background: The coronavirus disease (COVID-19) pandemic has spread rapidly across the world, creating an urgent need for predictive models that can help healthcare providers prepare and respond to outbreaks more quickly and effectively, and ultimately improve patient care. Early detection and warning systems are crucial for preventing and controlling epidemic spread. Objective: In this study, we aimed to propose a machine learning-based method to predict the transmission trend of COVID-19 and a new approach to detect the start time of new outbreaks by analyzing epidemiological data. Methods: We developed a risk index to measure the change in the transmission trend. We applied machine learning (ML) techniques to predict COVID-19 transmission trends, categorized into three labels: decrease (L0), maintain (L1), and increase (L2). We used Support Vector Machine (SVM), Random Forest (RF), and XGBoost (XGB) as ML models. We employed grid search methods to determine the optimal hyperparameters for these three models. We proposed a new method to detect the start time of new outbreaks based on label 2, which was sustained for at least 14 days (i.e., the duration of maintenance). We compared the performance of different ML models to identify the most accurate approach for outbreak detection. We conducted sensitivity analysis for the duration of maintenance between 7 days and 28 days. Results: ML methods demonstrated high accuracy (over 94%) in estimating the classification of the transmission trends. Our proposed method successfully predicted the start time of new outbreaks, enabling us to detect a total of seven estimated outbreaks, while there were five reported outbreaks between March 2020 and October 2022 in Korea. It means that our method could detect minor outbreaks. Among the ML models, the RF and XGB classifiers exhibited the highest accuracy in outbreak detection. Conclusion: The study highlights the strength of our method in accurately predicting the timing of an outbreak using an interpretable and explainable approach. It could provide a standard for predicting the start time of new outbreaks and detecting future transmission trends. This method can contribute to the development of targeted prevention and control measures and enhance resource management during the pandemic.

The economic impact of COVID-19 interventions: A mathematical modeling approach.

Prior to vaccination or drug treatment, non-pharmaceutical interventions were almost the only way to control the coronavirus disease 2019 (COVID-19) epidemic. After vaccines were developed, effective vaccination strategies became important. The prolonged COVID-19 pandemic has caused enormous economic losses worldwide. As such, it is necessary to estimate the economic effects of control policies, including non-pharmaceutical interventions and vaccination strategies. We estimated the costs associated with COVID-19 according to different vaccination rollout speeds and social distancing levels and investigated effective control strategies for cost minimization. Age-structured mathematical models were developed and used to study disease transmission epidemiology. Using these models, we estimated the actual costs due to COVID-19, considering costs associated with medical care, lost wages, death, vaccination, and gross domestic product (GDP) losses due to social distancing. The lower the social distancing (SD) level, the more important the vaccination rollout speed. SD level 1 was cost-effective under fast rollout speeds, but SD level 2 was more effective for slow rollout speeds. If the vaccine rollout rate is fast enough, even implementing SD level 1 will be cost effective and can control the number of critically ill patients and deaths. If social distancing is maintained at level 2 at the beginning and then relaxed when sufficient vaccinations have been administered, economic costs can be reduced while maintaining the number of patients with severe symptoms below the intensive care unit (ICU) capacity. Korea has wellequipped medical facilities and infrastructure for rapid vaccination, and the public's desire for vaccination is high. In this case, the speed of vaccine supply is an important factor in controlling the COVID-19 epidemic. If the speed of vaccination is fast, it is possible to maintain a low level of social distancing without a significant increase in the number of deaths and hospitalized patients with severe symptoms, and the corresponding costs can be reduced.

Vaccination Prioritization Strategies for COVID-19 in Korea: A Mathematical Modeling Approach.

Coronavirus disease 2019 (COVID-19) vaccination has recently started worldwide. As the vaccine supply will be limited for a considerable period of time in many countries, it is important to devise the effective vaccination strategies that reduce the number of deaths and incidence of infection. One of the characteristics of COVID-19 is that the symptom, severity, and mortality of the disease differ by age. Thus, when the vaccination supply is limited, age-dependent vaccination priority strategy should be implemented to minimize the incidences and mortalities. In this study, we developed an age-structured model for describing the transmission dynamics of COVID-19, including vaccination. Using the model and actual epidemiological data in Korea, we estimated the infection probability for each age group under different levels of social distancing implemented in Korea and investigated the effective age-dependent vaccination strategies to reduce the confirmed cases and fatalities of COVID-19. We found that, in a lower level of social distancing, vaccination priority for the age groups with the highest transmission rates will reduce the incidence mostly, but, in higher levels of social distancing, prioritizing vaccination for the elderly age group reduces the infection incidences more effectively. To reduce mortalities, vaccination priority for the elderly age group is the best strategy in all scenarios of levels of social distancing. Furthermore, we investigated the effect of vaccine supply and efficacy on the reduction in incidence and mortality.

Assessment of Social Distancing for Controlling COVID-19 in Korea: An Age-Structured Modeling Approach.

The outbreak of the novel coronavirus disease 2019 (COVID-19) occurred all over the world between 2019 and 2020. The first case of COVID-19 was reported in December 2019 in Wuhan, China. Since then, there have been more than 21 million incidences and 761 thousand casualties worldwide as of 16 August 2020. One of the epidemiological characteristics of COVID-19 is that its symptoms and fatality rates vary with the ages of the infected individuals. This study aims at assessing the impact of social distancing on the reduction of COVID-19 infected cases by constructing a mathematical model and using epidemiological data of incidences in Korea. We developed an age-structured mathematical model for describing the age-dependent dynamics of the spread of COVID-19 in Korea. We estimated the model parameters and computed the reproduction number using the actual epidemiological data reported from 1 February to 15 June 2020. We then divided the data into seven distinct periods depending on the intensity of social distancing implemented by the Korean government. By using a contact matrix to describe the contact patterns between ages, we investigated the potential effect of social distancing under various scenarios. We discovered that when the intensity of social distancing is reduced, the number of COVID-19 cases increases; the number of incidences among the age groups of people 60 and above increases significantly more than that of the age groups below the age of 60. This significant increase among the elderly groups poses a severe threat to public health because the incidence of severe cases and fatality rates of the elderly group are much higher than those of the younger groups. Therefore, it is necessary to maintain strict social distancing rules to reduce infected cases.

Systems-Level Properties of EGFR-RAS-ERK Signaling Amplify Local Signals to Generate Dynamic Gene Expression Heterogeneity.

Intratumoral heterogeneity is associated with aggressive tumor behavior, therapy resistance, and poor patient outcomes. Such heterogeneity is thought to be dynamic, shifting over periods of minutes to hours in response to signaling inputs from the tumor microenvironment. However, models of this process have been inferred from indirect or post-hoc measurements of cell state, leaving the temporal details of signaling-driven heterogeneity undefined. Here, we developed a live-cell model system in which microenvironment-driven signaling dynamics can be directly observed and linked to variation in gene expression. Our analysis reveals that paracrine signaling between two cell types is sufficient to drive continual diversification of gene expression programs. This diversification emerges from systems-level properties of the EGFR-RAS-ERK signaling cascade, including intracellular amplification of amphiregulin-mediated paracrine signals and differential kinetic filtering by target genes including Fra-1, c-Myc, and Egr1. Our data enable more precise modeling of paracrine-driven transcriptional variation as a generator of gene expression heterogeneity. A record of this paper's transparent peer review process is included in the Supplemental Information.

Mild weight loss reduces inflammatory cytokines, leukocyte count, and oxidative stress in overweight and moderately obese participants treated for 3 years with dietary modification.

Obesity-induced oxidative stress and inflammation are involved in the pathogenesis of cardiovascular disease. We investigated whether diet-induced, long-term, mild weight loss improved proinflammatory cytokine levels, leukocyte count, and oxidative stress. Overweight/obese participants (25 ≤ body mass index < 34 kg/m(2), N = 122, 30-59 years) joined a 3-year-long clinical intervention involving daily 100-kcal calorie deficits. Successful weight loss was defined as a reduction in initial body weight equal to 2 kg after the clinical intervention period. Body weight in the successful mild weight loss group (SWL, n = 50) changed 5.4% (-4.16 ± 0.31 kg) compared to 0.05 ± 0.14 kg in the unsuccessful weight loss group (n = 49). After 3 years, SWL participants exhibited significantly reduced insulin, triglycerides, total and low-density lipoprotein cholesterol, free fatty acids, and leukocyte count (P = .030). Furthermore, in the SWL group, serum interleukin (IL)-1ß, IL-6, and urinary 8-epi-prostaglandin (PG)F2α were significantly reduced (45%, 30%, and 14%, respectively). In contrast, the unsuccessful weight loss group exhibited significant increases in percentage of body fat, waist circumference, oxidized low-density lipoprotein, and tumor necrosis factor-α, as well as a significant decrease in high-density lipoprotein cholesterol. After adjusting for baseline values, the 2 groups demonstrated significantly different percentage of body fat, waist circumference, leukocyte count (P = .018), insulin, IL-6 (P = .031), IL-1ß (P < .001), and tumor necrosis factor-α (P < .001), as well as urinary 8-epi-PGF2α (P = .036). A positive correlation existed between IL-1ß and urinary 8-epi-PGF2α (r = 0.435, P < .001) and between changes in IL-6 and urinary 8-epi-PGF2α (r = 0.393, P < .001). Long-term mild weight loss reduces inflammatory cytokine levels, leukocyte counts, and oxidative stress and may reverse the elevated oxidative stress induced by inflammatory mediators in the overweight and obese.