Macrophage membrane-biomimetic adhesive polycaprolactone nanocamptothecin for improving cancer-targeting efficiency and impairing metastasis

The recent remarkable success and safety of mRNA lipid nanoparticle technology for producing severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) vaccines has stimulated intensive efforts to expand nanoparticle strategies to treat various diseases. Numerous synthetic nanoparticles have been developed for pharmaceutical delivery and cancer treatment. However, only a limited number of nanotherapies have enter clinical trials or are clinically approved. Systemically administered nanotherapies are likely to be sequestered by host mononuclear phagocyte system (MPS), resulting in suboptimal pharmacokinetics and insufficient drug concentrations in tumors. Bioinspired drug-delivery formulations have emerged as an alternative approach to evade the MPS and show potential to improve drug therapeutic efficacy. Here we developed a biodegradable polymer-conjugated camptothecin prodrug encapsulated in the plasma membrane of lipopolysaccharide-stimulated macrophages. Polymer conjugation revived the parent camptothecin agent (e.g., 7-ethyl-10-hydroxy-camptothecin), enabling lipid nanoparticle encapsulation. Furthermore, macrophage membrane cloaking transformed the nonadhesive lipid nanoparticles into bioadhesive nanocamptothecin, increasing the cellular uptake and tumor-tropic effects of this biomimetic therapy. When tested in a preclinical murine model of breast cancer, macrophage-camouflaged nanocamptothecin exhibited a higher level of tumor accumulation than uncoated nanoparticles. Furthermore, intravenous administration of the therapy effectively suppressed tumor growth and the metastatic burden without causing systematic toxicity. Our study describes a combinatorial strategy that uses polymeric prodrug design and cell membrane cloaking to achieve therapeutics with high efficacy and low toxicity. This approach might also be generally applicable to formulate other therapeutic candidates that are not compatible or miscible with biomimetic delivery carriers. © 2022 The Authors

Free energy perturbation–based large-scale virtual screening for effective drug discovery against COVID-19

As a theoretically rigorous and accurate method, FEP-ABFE (Free Energy Perturbation-Absolute Binding Free Energy) calculations showed great potential in drug discovery, but its practical application was difficult due to high computational cost. To rapidly discover antiviral drugs targeting SARS-CoV-2 Mpro and TMPRSS2, we performed FEP-ABFE–based virtual screening for ∼12,000 protein-ligand binding systems on a new generation of Tianhe supercomputer. A task management tool was specifically developed for automating the whole process involving more than 500,000 MD tasks. In further experimental validation, 50 out of 98 tested compounds showed significant inhibitory activity towards Mpro, and one representative inhibitor, dipyridamole, showed remarkable outcomes in subsequent clinical trials. This work not only demonstrates the potential of FEP-ABFE in drug discovery but also provides an excellent starting point for further development of anti-SARS-CoV-2 drugs. Besides, ∼500 TB of data generated in this work will also accelerate the further development of FEP-related methods. © The Author(s) 2022.

COVID-19 Forecasting Based on Local Mean Decomposition and Temporal Convolutional Network

Since the outbreak of coronavirus disease 2019 (COVID-19) has resulted in a dramatic loss of human life and economic disruption worldwide from early 2020, numerous studies focusing on COVID-19 forecasting were presented to yield accurate predicting results. However, most existing methods could not provide satisfying forecasting performance due to tons of assumptions, poor capability to learn appropriate parameters, etc. Therefore, in this paper, we combine a traditional time series decomposition: local mean decomposition (LMD) with temporal convolutional network (TCN) as a general framework to overcome these shortcomings. Based on the particular architecture, it can solve weekly new confirmed cases forecasting problem perfectly. Extensive experiments show that the proposed model significantly outperforms lots of state-of-the-art forecasting methods, and achieves desirable performance in terms of root mean squared log error (RMSLE), mean absolute percentage error (MAPE), Pearson correlation (PCORR), and coefficient of determination (R-2). To be specific, it could reach 0.9739, 0.8908, and 0.7461 on R-2 when horizon is 1, 2, and 3 respectively, which proves the effectiveness and robustness of our LMD-TCN model.

Assessing the Causal Impact of Online Instruction due to COVID-19 on Students' Grades and its aftermath on Grade Prediction Models

The COVID-19 pandemic forced many educational institutions to transition to online learning activities. This significantly impacted various aspects of students' lives. Many of the studies aimed at assessing the impact of the online instruction on students' wellbeing and performance have mainly focused on issues such as mental health. However, the impact on student grades-a key measure of student success-has been given little attention. The handful existing studies are either focused on primary schools-where the dynamics are different from higher education-or based on statistical correlations, which are usually not causally rigorous, therefore, prone to biased estimates due to various confounding variables. There are many variables associated with students' grades, thus, to assess the causal impact of the online instruction on students' grades, there is a need for a causally-grounded approach that can control for confounding variables. To that end, we use a causal tree to investigate the impact of online instruction on the grades of the general population as well as different demographic subgroups. Our analysis is based on the demographic and engagement data for the 2019 (offline/control) and 2020 (online/treatment) cohorts of 3 mandatory courses in an Australian university. For all 3 courses, our results show that for any given student in the population, the average grade they would have gotten, had they studied offline, reduced by 3.6%, 4.7%, and 14% respectively. Further analyses show that among students with similar level of (low) engagement with the virtual learning environment, the average grade international students would have gotten, had they studied face-to-face, reduced by 19.9%, 36.6%, and 46.9% more than their domestic counterparts despite having similar engagement for the 3 courses respectively. These subgroup disparities have the potential to exacerbate existing inequalities. Given the current concerns about algorithmic bias in learning analytics (LA), we trained grade prediction models with the data and investigated for algorithmic bias. Interestingly, we find that by simply changing citizenship status, a student gets a new predicted grade, entirely different from what was initially predicted given their actual citizenship status. This implies that researchers must be careful when building LA models on COVID-19 era data. © 2022 ACM.

Free energy perturbation-based large-scale virtual screening for effective drug discovery against COVID-19

As a theoretically rigorous and accurate method, FEP-ABFE (Free Energy Perturbation-Absolute Binding Free Energy) calculations showed great potential in drug discovery, but its practical application was difficult due to high computational cost. To rapidly discover antiviral drugs targeting SARS-CoV-2 M- pro and TMPRSS2, we performed FEP-ABFE-based virtual screening for similar to 12,000 protein-ligand binding systems on a new generation of Tianhe supercomputer. A task management tool was specifically developed for automating the whole process involving more than 500,000 MD tasks. In further experimental validation, 50 out of 98 tested compounds showed significant inhibitory activity towards M- pro , and one representative inhibitor, dipyridamole, showed remarkable outcomes in subsequent clinical trials. This work not only demonstrates the potential of FEP-ABFE in drug discovery but also provides an excellent starting point for further development of anti-SARS-CoV-2 drugs. Besides, similar to 500 TB of data generated in this work will also accelerate the further development of FEP-related methods.

The Impact of COVID-19 on Online Games: Machine Learning and Difference-in-Difference

By intervening in people’s behavior, governments in several nations have established a variety of strategies to slow down the spread of COVID-19 pandemic. At the same time, it has a different impact on everyone. Data from the Steam platform online games between January 2018 and February 2021 was used for this project’s analysis. Through the difference-in-difference model in Synthetic Control Methods to quantify and analyze, crucial positive effect on Steam’s online players during COVID-19 and the increase of the number of online players and the released games of the platform in 2020 had been found. The machine learning prediction model was created using the daily totals of the online gaming players of the most popular games on the site. The Ridge regression, whose R squared reached 0.805, had been demonstrated by the experimental results that it got the best performance. Simultaneously, this work found the features of the COVID-19 pandemic and the features of the human mobility, which helps to build a great majority of the predictive models. © 2022, Springer Nature Singapore Pte Ltd.

COVID-19's Impact on the Box office: Machine Learning and Difference-in-Difference

As COVID-19 continues to spread around the world, and non-pharmacological interventions (NPIs) continue to be strengthened, the impact of COVID-19 on the film industry has not yet been clearly quantified. In this study, the Difference-in-Difference model is used to quantify the impact of the COVID-19 pandemic on the box office. Results indicate that the COVID-19 pandemic has a significant negative effect on the daily global box office. Additionally, based on a research dataset containing information on movies and COVID-19, ten machine learning methods were used to build a prediction model of the cumulative global box office. The experimental results showed that Extremely Randomized Trees had the best predictive performance, and it was found that COVID-19 features helped improve the predictive performance of several models. © 2021 IEEE.

Detection Capability Prediction Based on Broad Learning System during the COVID-19 Pandemic

The greatest threat to global health is the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-Cov-2) currently. COVID-19 was declared as a global pandemic on March 11, 2020. For this highly contagious disease, the way of human-to-human transmission has forced us to implement large-scale COVID-19 testing worldwide. On February 21, 2021, 120 million people have already undergone COVID-19 testing. The large scale of COVID-19 testing has driven innovation in strategies, technologies, and concepts for managing public health testing. It is an unprecedented global testing program. In this study, we describe the role of COVID-19 testing while establishing a comprehensive and validated research dataset that includes data from 189 countries and 893 regions between August 8, 2019, and March 3, 2021. Through our analysis, we observed that the more COVID-19 testings provided, the more confirmed cases were detected. The availability of large-scale COVID-19 testing is indispensable to fully control the outbreak, as it is the main way to cut off the source of COVID-19 transmission. Then we used this dataset to predict the COVID-19 detection capabilities of each country by Machine Learning, Ensemble Learning, and Broad Learning System. Experimental results show that Broad Learning System significantly outperformed the Machine Learning. The R2 of predicted the ability of the COVID-19 testing can reach 0.999921. © 2021 IEEE.

Optimizing broad learning system hyper-parameters through particle swarm optimization for predicting COVID-19 in 184 Countries

The Coronavirus Disease 2019 (COVID-19) began to outbreak since December 2019 and widely spread over the world. How to accurately predict the spread of COVID-19 is one of the essential issues for controlling the pandemic. This study establishes a general model that can predict the trend of COVID-19 in a country based on historical COVID-19 data in 184 countries. First, Savitzky-Golay (S-G) filter is utilized to detect multiple waves of COVID-19 in a country. Then, a PSO-SIR (particle swarm optimization susceptible-infected-recovery) model is provided for data augmentation. Finally, a novel PSO-BLS (particle swarm optimization broad learning system) is proposed for predicting the trend of COVID-19. Experimental results show that compared with the deep learning models (ANN, CNN, LSTM, and GRU), the PSO-BLS algorithm has higher accuracy and stability in predicting the number of active infected cases and removed cases. © 2021 IEEE.

Impact of COVID-19 lockdown on human activity and air quality in China

During the Coronavirus disease 2019 outbreak, the Chinese government rapidly takes action to lockdown cities to prevent the spread of the virus. Therefore, migrations and inner-city activities are reducing dramatically in the lockdown period. In this study, we explore the correlation between human activity and air pollution by studying the changes of air pollutants between 2019 and 2020. Besides, we investigate the relationships between migration strength and air pollutants by establishing a migration-air-pollutant network. Experimental results demonstrate that the changes in PM2.5, PM10, and NO2 concentration in 2020 are smaller than in 2019. However, the correlation between city activities and most air pollutants is not apparent. Expect the concentration of PM2.5 in Wuhan and the concentration of SO2 in Beijing, while the migration strength is not relative to air pollutants. © 2020 IEEE.