DLpTCR: an ensemble deep learning framework for predicting immunogenic peptide recognized by T cell receptor.

Accurate prediction of immunogenic peptide recognized by T cell receptor (TCR) can greatly benefit vaccine development and cancer immunotherapy. However, identifying immunogenic peptides accurately is still a huge challenge. Most of the antigen peptides predicted in silico fail to elicit immune responses in vivo without considering TCR as a key factor. This inevitably causes costly and time-consuming experimental validation test for predicted antigens. Therefore, it is necessary to develop novel computational methods for precisely and effectively predicting immunogenic peptide recognized by TCR. Here, we described DLpTCR, a multimodal ensemble deep learning framework for predicting the likelihood of interaction between single/paired chain(s) of TCR and peptide presented by major histocompatibility complex molecules. To investigate the generality and robustness of the proposed model, COVID-19 data and IEDB data were constructed for independent evaluation. The DLpTCR model exhibited high predictive power with area under the curve up to 0.91 on COVID-19 data while predicting the interaction between peptide and single TCR chain. Additionally, the DLpTCR model achieved the overall accuracy of 81.03% on IEDB data while predicting the interaction between peptide and paired TCR chains. The results demonstrate that DLpTCR has the ability to learn general interaction rules and generalize to antigen peptide recognition by TCR. A user-friendly webserver is available at http://jianglab.org.cn/DLpTCR/. Additionally, a stand-alone software package that can be downloaded from https://github.com/jiangBiolab/DLpTCR.

Sources of PM2.5 and its responses to emission reduction strategies in the Central Plains Economic Region in China: Implications for the impacts of COVID-19.

The Central Plains Economic Region (CPER) located along the transport path to the Beijing-Tianjin-Hebei area has experienced severe PM2.5 pollution in recent years. However, few modeling studies have been performed on the sources of PM2.5, especially the impacts of emission reduction strategies. In this study, the Nested Air Quality Prediction Model System (NAQPMS) with an online tracer-tagging module was adopted to investigate source sectors of PM2.5 and a series of sensitivity tests were conducted to investigate the impacts of different sector-based mitigation strategies on PM2.5 pollution. The response surfaces of pollutants to sector-based emission changes were built. The results showed that resident-related sector (resident and agriculture), fugitive dust, traffic and industry emissions were the main sources of PM2.5 in Zhengzhou, contributing 49%, 19%, 15% and 13%, respectively. Response surfaces of pollutants to sector-based emission changes in Henan revealed that the combined reduction of resident-related sector and industry emissions efficiently decreased PM2.5 in Zhengzhou. However, reduced emissions in only the Henan region barely satisfied the national air quality standard of 75 µg/m3, whereas a 50%-60% reduction in resident-related sector and industry emissions over the whole region could reach this goal. On severely polluted days, even a 60% reduction in these two sectors over the whole region was insufficient to satisfy the standard of 75 µg/m3. Moreover, a reduction in traffic emissions resulted in an increase in the O3 concentration. The results of the response surface method showed that PM2.5 in Zhengzhou decreased by 19% in response to the COVID-19 lockdown, which approached the observed reduction of 21%, indicating that the response surface method could be employed to study the impacts of the COVID-19 lockdown on air pollution. This study provides a scientific reference for the formulation of pollution mitigation strategies in the CPER.

COVID-19, Urbanization Pattern and Economic Recovery: An Analysis of Hubei, China.

In the context of the rapid development of urbanization and increasing population mobility in China, the outbreak of COVID-19 has had a significant impact on China's economy and society. This article uses China UnionPay transaction data and takes Hubei, the worst-hit region by COVID-19 in China, as an example, to conduct empirical analysis using the generalized method of moments (GMM) of the impact of current urbanization patterns on the spread of the epidemic and economic recovery from the perspectives of time, industry, and regional differences. The study found that during the different stages of COVID-19, including discovery, outbreak, and subsidence, the overall impact of urbanization on the economy in Hubei Province was first positive, then became negative, and finally gradually increased. This process had significant industrial and urban heterogeneity, which was mainly manifested in losses in tourism and catering industries that were significantly greater than those in the audio-visual entertainment and digital office industries. Similarly, the recovery speed of large cities was lower than that of small and medium-sized cities. The main reason for these differences is that the one-sided problem of urbanization is more obvious in areas with higher urbanization rates. COVID-19 has drawn attention to the development of urbanization in the future, that is, the development path of one-sided economic resource agglomeration and scale expansion should be abandoned, with greater attention paid to the improvement of service functions and the development of amenities. This transformation is necessary to enhance urban economic resilience and reduce public health risks.

COVID-19, Urbanization Pattern and Economic Recovery: An Analysis of Hubei, China

In the context of the rapid development of urbanization and increasing population mobility in China, the outbreak of COVID-19 has had a significant impact on China’s economy and society. This article uses China UnionPay transaction data and takes Hubei, the worst-hit region by COVID-19 in China, as an example, to conduct empirical analysis using the generalized method of moments (GMM) of the impact of current urbanization patterns on the spread of the epidemic and economic recovery from the perspectives of time, industry, and regional differences. The study found that during the different stages of COVID-19, including discovery, outbreak, and subsidence, the overall impact of urbanization on the economy in Hubei Province was first positive, then became negative, and finally gradually increased. This process had significant industrial and urban heterogeneity, which was mainly manifested in losses in tourism and catering industries that were significantly greater than those in the audio-visual entertainment and digital office industries. Similarly, the recovery speed of large cities was lower than that of small and medium-sized cities. The main reason for these differences is that the one-sided problem of urbanization is more obvious in areas with higher urbanization rates. COVID-19 has drawn attention to the development of urbanization in the future, that is, the development path of one-sided economic resource agglomeration and scale expansion should be abandoned, with greater attention paid to the improvement of service functions and the development of amenities. This transformation is necessary to enhance urban economic resilience and reduce public health risks.

Impacts of COVID-19 lockdown, Spring Festival and meteorology on the NO2 variations in early 2020 over China based on in-situ observations, satellite retrievals and model simulations.

The lockdown measures due to COVID-19 affected the industry, transportation and other human activities within China in early 2020, and subsequently the emissions of air pollutants. The decrease of atmospheric NO2 due to the COVID-19 lockdown and other factors were quantitively analyzed based on the surface concentrations by in-situ observations, the tropospheric vertical column densities (VCDs) by different satellite retrievals including OMI and TROPOMI, and the model simulations by GEOS-Chem. The results indicated that due to the COVID-19 lockdown, the surface NO2 concentrations decreased by 42% ± 8% and 26% ± 9% over China in February and March 2020, respectively. The tropospheric NO2 VCDs based on both OMI and high quality (quality assurance value (QA) ≥ 0.75) TROPOMI showed similar results as the surface NO2 concentrations. The daily variations of atmospheric NO2 during the first quarter (Q1) of 2020 were not only affected by the COVID-19 lockdown, but also by the Spring Festival (SF) holiday (January 24-30, 2020) as well as the meteorology changes due to seasonal transition. The SF holiday effect resulted in a NO2 reduction from 8 days before SF to 21 days after it (i.e. January 17 - February 15), with a maximum of 37%. From the 6 days after SF (January 31) to the end of March, the COVID-19 lockdown played an important role in the NO2 reduction, with a maximum of 51%. The meteorology changes due to seasonal transition resulted in a nearly linear decreasing trend of 25% and 40% reduction over the 90 days for the NO2 concentrations and VCDs, respectively. Comparisons between different datasets indicated that medium quality (QA ≥ 0.5) TROPOMI retrievals might suffer large biases in some periods, and thus attention must be paid when they are used for analyses, data assimilations and emission inversions.