Development of a composite regional vulnerability index and its relationship with the impacts of the COVID-19 pandemic.

The interactions between vulnerability and human activities have largely been regarded in terms of the level of risk they pose, both internally and externally, for certain groups of disadvantaged individuals and regions/areas. However, to date, very few studies have attempted to develop a comprehensive composite regional vulnerability index, in relation to travel, housing, and social deprivation, which can be used to measure vulnerability at an aggregated level in the social sciences. Therefore, this research aims to develop a composite regional vulnerability index with which to examine the combined issues of travel, housing and socio-economic vulnerability (THASV index). It also explores the index's relationship with the impacts of the COVID-19 pandemic, reflecting both social and spatial inequality, using Greater London as a case study, with data analysed at the level of Middle Layer Super Output Areas (MSOAs). The findings show that most of the areas with high levels of composite vulnerability are distributed in Outer London, particularly in suburban areas. In addition, it is also found that there is a spatial correlation between the THASV index and the risk of COVID-19 deaths, which further exacerbates the potential implications of social deprivation and spatial inequality. Moreover, the results of the multiscale geographically weighted regression (MGWR) show that the travel and socio-economic indicators in a neighbouring district and the related vulnerability indices are strongly associated with the risk of dying from COVID-19. In terms of policy implications, the findings can be used to inform sustainable city planning and urban development strategies designed to resolve urban socio-spatial inequalities and the potential related impacts of COVID-19, as well as guiding future policy evaluation of urban structural patterns in relation to vulnerable areas.

Prediction of the Aqueous Solubility of Compounds Based on Light Gradient Boosting Machines with Molecular Fingerprints and the Cuckoo Search Algorithm.

Aqueous solubility is one of the most important physicochemical properties in drug discovery. At present, the prediction of aqueous solubility of compounds is still a challenging problem. Machine learning has shown great potential in solubility prediction. Most machine learning models largely rely on the setting of hyperparameters, and their performance can be improved by setting the hyperparameters in a better way. In this paper, we used MACCS fingerprints to represent the structural features and optimized the hyperparameters of the light gradient boosting machine (LightGBM) with the cuckoo search algorithm (CS). Based on the above representation and optimization, the CS-LightGBM model was established to predict the aqueous solubility of 2446 organic compounds and the obtained prediction results were compared with those obtained with the other six different machine learning models (RF, GBDT, XGBoost, LightGBM, SVR, and BO-LightGBM). The comparison results showed that the CS-LightGBM model had a better prediction performance than the other six different models. RMSE, MAE, and R 2 of the CS-LightGBM model were, respectively, 0.7785, 0.5117, and 0.8575. In addition, this model has good scalability and can be used to solve solubility prediction problems in other fields such as solvent selection and drug screening.

Revealing spatiotemporal interaction patterns behind complex cities.

Cities are typical dynamic complex systems that connect people and facilitate interactions. Revealing general collective patterns behind spatiotemporal interactions between residents is crucial for various urban studies, of which we are still lacking a comprehensive understanding. Massive cellphone data enable us to construct interaction networks based on spatiotemporal co-occurrence of individuals. The rank-size distributions of dynamic population of locations in all unit time windows are stable, although people are almost constantly moving in cities and hot-spots that attract people are changing over time in a day. A larger city is of a stronger heterogeneity as indicated by a larger scaling exponent. After aggregating spatiotemporal interaction networks over consecutive time windows, we reveal a switching behavior of cities between two states. During the "active" state, the whole city is concentrated in fewer larger communities, while in the "inactive" state, people are scattered in smaller communities. Above discoveries are universal over three cities across continents. In addition, a city stays in an active state for a longer time when its population grows larger. Spatiotemporal interaction segregation can be well approximated by residential patterns only in smaller cities. In addition, we propose a temporal-population-weighted-opportunity model by integrating a time-dependent departure probability to make dynamic predictions on human mobility, which can reasonably well explain the observed patterns of spatiotemporal interactions in cities.

Higher-order temporal network effects through triplet evolution.

We study the evolution of networks through 'triplets'-three-node graphlets. We develop a method to compute a transition matrix to describe the evolution of triplets in temporal networks. To identify the importance of higher-order interactions in the evolution of networks, we compare both artificial and real-world data to a model based on pairwise interactions only. The significant differences between the computed matrix and the calculated matrix from the fitted parameters demonstrate that non-pairwise interactions exist for various real-world systems in space and time, such as our data sets. Furthermore, this also reveals that different patterns of higher-order interaction are involved in different real-world situations. To test our approach, we then use these transition matrices as the basis of a link prediction algorithm. We investigate our algorithm's performance on four temporal networks, comparing our approach against ten other link prediction methods. Our results show that higher-order interactions in both space and time play a crucial role in the evolution of networks as we find our method, along with two other methods based on non-local interactions, give the best overall performance. The results also confirm the concept that the higher-order interaction patterns, i.e., triplet dynamics, can help us understand and predict the evolution of different real-world systems.

Gravity model in dockless bike-sharing systems within cities.

Due to previous technical challenges with the collection of data on riding behaviors, there have only been a few studies focusing on patterns and regularities of biking traffic, which are crucial to understand to help achieve a greener and more sustainable future urban development. Recently, with the booming of the sharing economy, and the development of the Internet of Things (IoT) and mobile payment technology, dockless bike-sharing systems that record information for every trip provide us with a unique opportunity to study the patterns of biking traffic within cities. We first reveal a spatial scaling relation between the cumulative volume of riding activities and the corresponding distance to the city center, and a power law distribution on the volume of biking flows between fine-grained locations in both Beijing and Shanghai. We validate the effectiveness of the general gravity model on predicting biking traffic at fine spatial resolutions, where population-related parameters are less than unity, indicating that smaller populations are relatively more important per capita in generating biking traffic. We then further study the impacts of spatial scale on the gravity model and reveal that the distance-related parameter grows in a similar way as population-related parameters when the spatial scale of the locations increases. In addition, the flow patterns of some special locations (sources and sinks) that cannot be fully explained by the gravity model are studied.

Prediction Model of Organic Molecular Absorption Energies based on Deep Learning trained by Chaos-enhanced Accelerated Evolutionary algorithm.

As an important physical property of molecules, absorption energy can characterize the electronic property and structural information of molecules. Moreover, the accurate calculation of molecular absorption energies is highly valuable. Present linear and nonlinear methods hold low calculation accuracies due to great errors, especially irregular complicated molecular systems for structures. Thus, developing a prediction model for molecular absorption energies with enhanced accuracy, efficiency, and stability is highly beneficial. By combining deep learning and intelligence algorithms, we propose a prediction model based on the chaos-enhanced accelerated particle swarm optimization algorithm and deep artificial neural network (CAPSO BP DNN) that possesses a seven-layer 8-4-4-4-4-4-1 structure. Eight parameters related to molecular absorption energies are selected as inputs, such as a theoretical calculating value Ec of absorption energy (B3LYP/STO-3G), molecular electron number Ne, oscillator strength Os, number of double bonds Ndb, total number of atoms Na, number of hydrogen atoms Nh, number of carbon atoms Nc, and number of nitrogen atoms NN; and one parameter representing the molecular absorption energy is regarded as the output. A prediction experiment on organic molecular absorption energies indicates that CAPSO BP DNN exhibits a favourable predictive effect, accuracy, and correlation. The tested absolute average relative error, predicted root-mean-square error, and square correlation coefficient are 0.033, 0.0153, and 0.9957, respectively. Relative to other prediction models, the CAPSO BP DNN model exhibits a good comprehensive prediction performance and can provide references for other materials, chemistry and physics fields, such as nonlinear prediction of chemical and physical properties, QSAR/QAPR and chemical information modelling, etc.

Prediction of pKa Values for Neutral and Basic Drugs based on Hybrid Artificial Intelligence Methods.

The pKa value of drugs is an important parameter in drug design and pharmacology. In this paper, an improved particle swarm optimization (PSO) algorithm was proposed based on the population entropy diversity. In the improved algorithm, when the population entropy was higher than the set maximum threshold, the convergence strategy was adopted; when the population entropy was lower than the set minimum threshold the divergence strategy was adopted; when the population entropy was between the maximum and minimum threshold, the self-adaptive adjustment strategy was maintained. The improved PSO algorithm was applied in the training of radial basis function artificial neural network (RBF ANN) model and the selection of molecular descriptors. A quantitative structure-activity relationship model based on RBF ANN trained by the improved PSO algorithm was proposed to predict the pKa values of 74 kinds of neutral and basic drugs and then validated by another database containing 20 molecules. The validation results showed that the model had a good prediction performance. The absolute average relative error, root mean square error, and squared correlation coefficient were 0.3105, 0.0411, and 0.9685, respectively. The model can be used as a reference for exploring other quantitative structure-activity relationships.

Effect of octylphenol on physiologic features during growth in Arabidopsis thaliana.

Alkylphenol ethoxylates are widely used as detergents, emulsifiers, solubilizers, wetting agents and dispersants. Octylphenol (OP) ethoxylates, one of alkylphenol ethoxylates, represent 15-20% of the market, and their metabolic residues may be discharged to surface waters, sediments and soils as a persistent and ubiquitous pollutant. We tested the response of Arabidopsis thaliana to different concentrations of OP. OP affected the germination percentage and mean germination period. 10d treatment with OP, especially high concentration (10 and 50 mg L(-1)), decreased shoot and root biomass and root length of 30 d-old A. thaliana. Content of chlorophyll was decreased but that of proline was increased in leaves with OP treatment. OP caused oxidative stress in leaves; malondialdehyde content was increased, and the activities of ascorbate peroxidase, catalase and superoxide dismutase were induced. OP affects the physiologic and morphologic features of A. thaliana during growth. Because plants might be exposed to OP for a long time in the surroundings, more attention needs to be paid to the effect of OP on plants.

Effect of endocrine disruptor nonylphenol on physiologic features and proteome during growth in Arabidopsis thaliana.

We studied the effects of nonylphenol (NP) on physiological features and proteome of Arabidopsis (Arabidopsis thaliana) during growth. Shoot biomass, root biomass and root length were decreased after 10d of NP treatment, especially in high NP concentration treatment (10 and 50 mg L(-1)). Levels of chlorophyll decreased but proline increased in leaves. NP caused oxidative stress; malondialdehyde content was increased with NP treatment, and the activities of ascorbate peroxidase, catalase, CuZnSOD and MnSOD were induced in leaves. The proteome of leaf tissue was analyzed by 2-D gel electrophoresis and mass spectrometry. NP might adversely affect the CO2 assimilation, signal transduction, the endomembrane system and photosynthetic oxygen evolution. NP affects the proteome and physiologic and morphological features of A. thaliana during growth at the concentration can be observed in the environment. Because plants might be exposed to NP for a long time in the surroundings, more attention needs to be paid to the effect of NP on plants.

Bioremediation of endocrine disruptor di-n-butyl phthalate ester by Deinococcus radiodurans and Pseudomonas stutzeri.

Di-n-butyl phthalate (DBP) is a group of phthalate esters (PAEs) that are widely used in cosmetics, perfumes, and plasticizers. Due to its high production and application figures, DBP is commonly found in wastewater, sewage sludge, and aquatic environments. It has been classified as suspected endocrine disruptors by most countries. In this study, we isolated two DBP degradable strains from activated sludge. The strains were identified with their 16S rRNA as Deinococcus radiodurans and Pseudomonas stutzeri. We constructed the optimal condition of DBP degradation by using different kinds of incubation factors such as temperature, initial pH, yeast extract and surfactants. The optimal conditions of DBP degradation for these two strains are: 30 degrees C, pH 7.5 and static culture. Besides, addition of 0.23 mM of Triton X-100 could enhance the DBP degradation for D. radiodurans. In the end, we amended these two strains into the origin activated sludge and analyzed the whole microbial community structure of mixed cultures by PCR-DGGE technique. The result showed that only D. radiodurans could survive in the activated sludge after 7d of incubation. Based on this work, we hope that these findings could provide some useful information for applying the bioremediation of DBP in our environment.