FMCA-DTI: a fragment-oriented method based on a multihead cross attention mechanism to improve drug-target interaction prediction.

MOTIVATION: Identifying drug-target interactions (DTI) is crucial in drug discovery. Fragments are less complex and can accurately characterize local features, which is important in DTI prediction. Recently, deep learning (DL)-based methods predict DTI more efficiently. However, two challenges remain in existing DL-based methods: (i) some methods directly encode drugs and proteins into integers, ignoring the substructure representation; (ii) some methods learn the features of the drugs and proteins separately instead of considering their interactions. RESULTS: In this article, we propose a fragment-oriented method based on a multihead cross attention mechanism for predicting DTI, named FMCA-DTI. FMCA-DTI obtains multiple types of fragments of drugs and proteins by branch chain mining and category fragment mining. Importantly, FMCA-DTI utilizes the shared-weight-based multihead cross attention mechanism to learn the complex interaction features between different fragments. Experiments on three benchmark datasets show that FMCA-DTI achieves significantly improved performance by comparing it with four state-of-the-art baselines. AVAILABILITY AND IMPLEMENTATION: The code for this workflow is available at: https://github.com/jacky102022/FMCA-DTI.

Estimation of urban AQI based on interpretable machine learning.

Air pollution is an increasingly serious problem. Accurate and efficient prediction of air quality can effectively prevent air pollution and improve the quality of human life. The air quality index (AQI) is a dimensionless tool to describe air quality quantitatively. In this study, the machine learning (ML) method was used to estimate AQI for Shijiazhuang, China, as the research object, and pollutants and meteorological factors as data models. Specifically, eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Random Forest (RF) models were used. The experimental results show that XGBoost model captures the AQI variation trend well, and the R2 of XGBoost model is 0.929, which is 0.3% and 2.3% higher than the R2 of RF model and LightGBM model, respectively. In addition, through the SHAP-based model interpretation method, the study reveals the key factors of AQI variation, that is PM2.5 and PM10, play positive roles in the variation of AQI and AQI is less sensitive to meteorological factors. Finally, Beijing, Shanghai, Xi'an, and Guangzhou were selected to test the model's validity, and the model performance remained good. Our study shows that applying ML approach to air quality prediction is beneficial for efficiently assessing cities' future air quality.

Prediction of atmospheric pollutants in urban environment based on coupled deep learning model and sensitivity analysis.

Accurate and efficient predictions of pollutants in the atmosphere provide a reliable basis for the scientific management of atmospheric pollution. This study develops a model that combines an attention mechanism, convolutional neural network (CNN), and long short-term memory (LSTM) unit to predict the O3 and PM2.5 levels in the atmosphere, as well as an air quality index (AQI). The prediction results given by the proposed model are compared with those from CNN-LSTM and LSTM models as well as random forest and support vector regression models. The proposed model achieves a correlation coefficient between the predicted and observed values of more than 0.90, outperforming the other four models. The model errors are also consistently lower when using the proposed approach. Sobol-based sensitivity analysis is applied to identify the variables that make the greatest contribution to the model prediction results. Taking the COVID-19 outbreak as the time boundary, we find some homology in the interactions among the pollutants and meteorological factors in the atmosphere during different periods. Solar irradiance is the most important factor for O3, CO is the most important factor for PM2.5, and particulate matter has the most significant effect on AQI. The key influencing factors are the same over the whole phase and before the COVID-19 outbreak, indicating that the impact of COVID-19 restrictions on AQI gradually stabilized. Removing variables that contribute the least to the prediction results without affecting the model prediction performance improves the modeling efficiency and reduces the computational costs.

Improving the efficiency of machine learning in simulating sedimentary heavy metal contamination by coupling preposing feature selection methods.

Sediment cores were collected from Taihu Lake in China. The chronology was determined by radionuclide. Heavy metals and magnetic properties of each core slice were assessed, respectively. The concentrations of most heavy metals in sediments surged at 20 cm from the surface, accompanying the increase in the concentrations of single-domain magnetic particles. This may be resulted from the influence of anthropic activities on the lake's environment after the 1970s. Two feature selection methods, random forest (RF) and maximal information coefficient (MIC), were combined with support vector machine (SVM) model to simulate heavy metals, with the inclusion of selected magnetic and physicochemical parameters. Compared with the modeling results obtained with the full set of parameters, a reasonable simulation performance was obtained with RF and MIC. RF performed better than MIC by increasing the R2 of simulation models for Cd, Cr, Cu, Pb, and Sb. For heavy metals with high ecological risks (As, Cd, Cr, Hg, Pb, Sb), the correlation coefficients for observed and predicted data ranged from 0.73 to 0.97 with only 14-27% of the parameters selected by RF as input variables. The RF-RBF-SVM enabled heavy metal predictions based on the magnetic properties of the lake sediments.

An improved risk-explicit interval linear programming model for pollution load allocation for watershed management.

Although the risk-explicit interval linear programming (REILP) model has solved the problem of having interval solutions, it has an equity problem, which can lead to unbalanced allocation between different decision variables. Therefore, an improved REILP model is proposed. This model adds an equity objective function and three constraint conditions to overcome this equity problem. In this case, pollution reduction is in proportion to pollutant load, which supports balanced development between different regional economies. The model is used to solve the problem of pollution load allocation in a small transboundary watershed. Compared with the REILP original model result, our model achieves equity between the upstream and downstream pollutant loads; it also overcomes the problem of greatest pollution reduction, where sources are nearest to the control section. The model provides a better solution to the problem of pollution load allocation than previous versions.

Estimating and Predicting Metal Concentration Using Online Turbidity Values and Water Quality Models in Two Rivers of the Taihu Basin, Eastern China.

Turbidity (T) has been widely used to detect the occurrence of pollutants in surface water. Using data collected from January 2013 to June 2014 at eleven sites along two rivers feeding the Taihu Basin, China, the relationship between the concentration of five metals (aluminum (Al), titanium (Ti), nickel (Ni), vanadium (V), lead (Pb)) and turbidity was investigated. Metal concentration was determined using inductively coupled plasma mass spectrometry (ICP-MS). The linear regression of metal concentration and turbidity provided a good fit, with R(2) = 0.86-0.93 for 72 data sets collected in the industrial river and R(2) = 0.60-0.85 for 60 data sets collected in the cleaner river. All the regression presented good linear relationship, leading to the conclusion that the occurrence of the five metals are directly related to suspended solids, and these metal concentration could be approximated using these regression equations. Thus, the linear regression equations were applied to estimate the metal concentration using online turbidity data from January 1 to June 30 in 2014. In the prediction, the WASP 7.5.2 (Water Quality Analysis Simulation Program) model was introduced to interpret the transport and fates of total suspended solids; in addition, metal concentration downstream of the two rivers was predicted. All the relative errors between the estimated and measured metal concentration were within 30%, and those between the predicted and measured values were within 40%. The estimation and prediction process of metals' concentration indicated that exploring the relationship between metals and turbidity values might be one effective technique for efficient estimation and prediction of metal concentration to facilitate better long-term monitoring with high temporal and spatial density.

Seasonal and spatial variations of heavy metals in two typical Chinese rivers: concentrations, environmental risks, and possible sources.

Ten metals were analyzed in samples collected in three seasons (the dry season, the early rainy season, and the late rainy season) from two rivers in China. No observed toxic effect concentrations were used to estimate the risks. The possible sources of the metals in each season, and the dominant source(s) at each site, were assessed using principal components analysis. The metal concentrations in the area studied were found, using t-tests, to vary both seasonally and spatially (P = 0.05). The potential risks in different seasons decreased in the order: early rainy season > dry season > late rainy season, and Cd was the dominant contributor to the total risks associated with heavy metal pollution in the two rivers. The high population and industrial site densities in the Taihu basin have had negative influences on the two rivers. The river that is used as a source of drinking water (the Taipu River) had a low average level of risks caused by the metals. Metals accumulated in environmental media were the main possible sources in the dry season, and emissions from mechanical manufacturing enterprises were the main possible sources in the rainy season. The river in the industrial area (the Wusong River) had a moderate level of risk caused by the metals, and the main sources were industrial emissions. The seasonal and spatial distributions of the heavy metals mean that risk prevention and mitigation measures should be targeted taking these variations into account.

Simulation of water environmental capacity and pollution load reduction using QUAL2K for water environmental management.

In recent years, water quality degradation associated with rapid socio-economic development in the Taihu Lake Basin, China, has attracted increasing attention from both the public and the Chinese government. The primary sources of pollution in Taihu Lake are its inflow rivers and their tributaries. Effective water environmental management strategies need to be implemented in these rivers to improve the water quality of Taihu Lake, and to ensure sustainable development in the region. The aim of this study was to provide a basis for water environmental management decision-making. In this study, the QUAL2K model for river and stream water quality was applied to predict the water quality and environmental capacity of the Hongqi River, which is a polluted tributary in the Taihu Lake Basin. The model parameters were calibrated by trial and error until the simulated results agreed well with the observed data. The calibrated QUAL2K model was used to calculate the water environmental capacity of the Hongqi River, and the water environmental capacities of COD(Cr) NH(3)-N, TN, and TP were 17.51 t, 1.52 t, 2.74 t and 0.37 t, respectively. The results showed that the NH(3)-N, TN, and TP pollution loads of the studied river need to be reduced by 50.96%, 44.11%, and 22.92%, respectively to satisfy the water quality objectives. Thus, additional water pollution control measures are needed to control and reduce the pollution loads in the Hongqi River watershed. The method applied in this study should provide a basis for water environmental management decision-making.