Search

Executive compensation is an important part of the internal governance of commercial banks, and the rationality of the compensation mechanism directly affects the bank’s risk-taking. Based on the panel data of 34 listed small- and medium-sized banks in China from 2012 to 2020, this paper empirically examines the impact and mechanism between executive compensation and the risk-taking level of small- and medium-sized banks. We find that executives’ short-term executive compensation significantly and positively affects the risk-taking level of small- and medium-sized banks, while executives’ long-term executive compensation significantly and negatively affects the risk-taking. Furthermore, considering the specificity of the capital structure of small- and medium-sized banks, we analyse the moderating effect of the capital structure on the above roles and find that there is a partial moderating effect of the capital structure on the relationship between executive short-term compensation and risk-taking in small- and medium-sized banks. This study provides theoretical foundations and countermeasures for improving the executive compensation mechanism and optimising the equity structure to reduce the risk-taking of small- and medium-sized banks and maintain the stability of the financial system. [ABSTRACT FROM AUTHOR]

How to enhance competitive advantage and turn green commitment into practice is a problem that corporates must face under sustainable development. This research examines the impact of environmental, social, and governance (ESG) performance on corporate green innovation and the role digital transformation plays in it. We use a panel fixed effects model for empirical analysis based on sample data of 1070 Chinese-listed corporates from 2011 to 2020. The empirical results show that better ESG performance leads to more acquisition of green innovation by corporates. This effect is more significant under the promotion of digital transformation. The role of ESG performance and digital transformation is markedly heterogeneous across different types of corporates. Among private corporates, technology-based corporates, and ecological corporates, the improvement of green innovation by ESG performance is more apparent, and the promotion effect of digital transformation is more significant. Our findings suggest that creating conditions for corporate ESG performance improvement and digital transformation at the macro level and enhancing corporates' subjective willingness for sustainable development and digitalization at the micro level will enable them to develop their green innovation capabilities by leaps and bounds. [ABSTRACT FROM AUTHOR]

Maintaining the stability of the carbon market is of great significance for China to meet its goal of "Double Carbon," but at the beginning of 2020 the COVID-19 pandemic emerged and the economy was greatly affected. A natural question is whether it impacted domestic carbon markets. This paper thus presents the event research method on eight carbon emission trading markets in China, because it can timely exhibit the benefits investors gained during the COVID-19 pandemic and also can overcome the difficulty of separating those benefits from the overall performance of the carbon market via high-frequency data. The results herein confirm that China's carbon market has reacted negatively to the COVID-19 pandemic, which mainly relates to the mandatory blockade and isolation policy adopted by the central government. The production and operation activities of enterprises decreased along with the demand for carbon quotas. Because of the panic, investors also had a negative attitude towards the carbon market, influencing the supply and demand curve of carbon quotas and causing a decline in carbon prices. Under the effectiveness of government epidemic prevention and control policies, we further find that the negative impact was gradually eliminated. Overall, our findings offer some important information for the decision-making of governments, carbon market investors, and policymakers. [ABSTRACT FROM AUTHOR]

This research conducts an empirical study on arbitrage opportunities in the crude oil futures market of Shanghai International Energy Exchange in the period of China's economic change, 2020–2022. We use the daily closing price data of crude oil futures sc2303 and sc2212 to test whether there is a statistical arbitrage opportunity in China's crude oil futures market. Taking the most commonly used 12 + 6 rolling window mode in statistical arbitrage, we select several one-year periods that pass the cointegration test during the formation period and apply the optimal opening, closing, and stop loss thresholds based on the highest yield during the formation period to the trading period. Finally, we draw the following conclusions: (i) the pair trading strategy based on the cointegration model is profitable in China's crude oil futures market; (ii) the 12 + 6 window model can be applied to the pair trading strategy based on China's crude oil futures. Our research proves the effectiveness of pair trading strategy in China's crude oil futures market for institutional and individual investors. [ABSTRACT FROM AUTHOR]

In this study, we use the spatial econometric model with panel data to investigate the mechanism and effect of economic growth on public health in Western China. The research results show that the spatial agglomeration effects are significant on the public health performance in Western China. Economic growth significantly promotes local public health status during the range of our sample data, leading to reduced human mortality. Environmental pollution significantly increases human mortality not only in local province but also in neighboring provinces. As GRP per capita of a province continues to increase, the impact of environmental pollution on increasing human mortality has diminished gradually. Moreover, improving the level of technological progress and healthcare services significantly improve public health. Interestingly, as GRP per capita of a province continues to increase, the impact of technological progress and healthcare services on decreasing human mortality has gradually weakened. [ABSTRACT FROM AUTHOR]

Our research investigates the relationship between policy stability and clean energy investment via panel data covering 44 countries spanning the time period 2000–2020. Specifically considering the heterogeneity among countries with different levels of clean energy investment, we employ a panel quantile regression model on the sample data and further test the heterogeneity with a sub-sample of developing countries. Findings show that countries with higher levels of clean energy investment (CEI) exhibit a negative relationship between policy stability and CEI, while countries with lower levels of clean energy investment (CEI) have a positive relationship. We spot other factors that affect CEI and further conduct a robustness test on the model. These results offer critical policy implications on how to promote clean energy investment. [ABSTRACT FROM AUTHOR]

Rapidly increasing cryptocurrency prices have encouraged cryptocurrency miners to participate in cryptocurrency production, increasing network hashrates and electricity consumption. Growth in network hashrates has further crowded out small cryptocurrency investors owing to the heightened costs of mining hardware and electricity. These changes prompt cryptocurrency miners to become new investors, leading to cryptocurrency price increases. The potential bidirectional relationship between cryptocurrency price and electricity consumption remains unidentified. Hence, this research thus utilizes July 31 2015–July 12 2019 data from 13 cryptocurrencies to investigate the short- and long-run causal effects between cryptocurrency transaction and electricity consumption. Particularly, we consider structural breaks induced by external shocks through stationary analysis and comovement relationships. Over the examined time period, we found that the series of cryptocurrency transaction and electricity consumption gradually returns to mean convergence after undergoing daily shocks, with prices trending together with hashrates. Transaction fluctuations exert both a temporary effect and permanent influence on electricity consumption. Therefore, owing to the computational power deployed to wherever high profit is found, transactions are vital determinants of electricity consumption. [ABSTRACT FROM AUTHOR]

Water resources are an important part of the ecosystem. The nexus of extreme weather events and water quality is of great significance in the climate change economics theory and related literature. This research thus investigates the impact of extreme weather events on water quality by using unbalanced panel data covering 62 countries from 1991 to 2018 and finds that extreme weather may strongly hurt water quality, which not only is impactful in the current year but also lasts over the next 10 years. We further show that floods have a greater negative impact on water quality than droughts. In addition, the significant impact on water quality is manifested in non-high-income countries and in countries with low technology innovation related to water resources, but not in high-income countries nor in countries with high water innovation. Overall, the findings merit particular attention from policy makers. [ABSTRACT FROM AUTHOR]

This research estimates the effect of climate change on bank performance by considering the mediating role of natural disasters via unbalanced panel data from 2005 to 2018 in 127 countries. Moreover, this paper uses forest land, carbon dioxide emissions, and temperature change to measure climate change, takes economic loss and the number of deaths as costs of natural disasters, and utilizes the non-performing loan ratio and the ratio of bank capital to assets as bank performance. The following conclusions are reached according to our empirical evidence. First, forest land has a strong negative effect on the non-performing loan ratio. Second, forest land decreases the economic losses and deaths due to natural disasters, and natural disasters also decrease banks' non-performing loan ratio. We also find that forest land increases the ratio of bank capital to assets through decreasing natural disasters. Third, there is a significant mediating effect of climate change on bank performance via natural disasters in high-income countries, but not in low-income countries. Finally, the decline of forest land and the rise of carbon dioxide emissions both have significantly positive effects on man-made disasters, which increase banks' non-performing loan ratio and decrease the ratio of bank capital to assets. One policy implication is that improving climate change, preventing natural disasters, and promoting financial institutions can help decrease the economic losses of natural disasters and banks. [ABSTRACT FROM AUTHOR]

This research examines the effects of executive political connections on corporate performance by comparing firms with mergers and acquisitions (M&As) and firms without M&A activities in the energy sector using China Securities Regulatory Commission industry data from 2008 to 2018. We integrate two theoretical approaches, resource dependence and the agency view into one framework, and find that executives' political connections have a positive effect on corporate performance when there are no M&A activities, which is consistent with the resource dependence theory; however, well-connected executives harm firm performance through M&A activities. Our main results still hold after considering endogeneity issues, substituting relevant variables, comparing the effect of the global financial crisis, and controlling for market structure. Our study provides significant insight into the energy sector, which can help practitioners and policymakers who want to make advancements in firms' competitiveness through better implementation of policies related to M&A. [ABSTRACT FROM AUTHOR]

Owing to economics are usually linked with energy production, economic policy may have an instantaneous adjustment according to the current monetary, financial, cultural circumstances. This research thus investigates the dynamic co-movement as well as cointegration relationships between economic policy uncertainty (EPU) and disparate energy productions, i.e., Chinese coal, natural gas, crude oil, electricity as well as renewable energy, during the period from January 1995 to October 2019 in China. We compare the two EPU indices and make empirical and robust analysis to get more evidence for the time-varying co-movement between energy production and EPU. The empirical results show that there are stationary properties and cointegration relationships between energy production and EPU. By utilizing wavelet co-movement analysis in the time-frequency domain, our results show a significant positive co-movement among disparate energy productions and EPU at high frequencies, i.e., in the short term, but weaker co-movement at low frequencies, i.e., in the long term. Hence, the phase-difference series are mostly around the zero line, implying the variables behave to the dynamics of the co-movement with positive causality. Policy recommendations are offered in accordance with our finding. [ABSTRACT FROM AUTHOR]

Taking China provincial-level data during 2003–2017 as the basic space-time unit, this research applies the Moran index and spatial econometric model to analyze the spatial pattern change trend and spillover effects of regional innovation output. The results show that, first, provincial innovation outputs mainly concentrate in the coastal economic belt and Yangtze economic zone. Second, there is a correlation in space for provincial innovation output, and the growth rate of provincial innovation output has a positive spillover effect. The rate of conditional β-convergence is 3.926%, and the half-life cycle of convergence is 17.665 years. Third, environmental regulations have pushed the development of regional innovation to some extent. Fourth and finally, regional innovation input and its spillover effects impact the level of regional innovation output. Innovation output, environment regulation, and R&D internal expenditure are the main paths for innovation's spillover effect. [ABSTRACT FROM AUTHOR]

This research investigates the time-varying correlation as well as long-run cointegration relationship between the carbon prices of the European market and the China market during the period 2013–2020. We adopt the Lagrange Multiplier (LM) unit root and cointegration test based on the univariate unit root test with one structural break and wavelet coherency analysis in the time–frequency domain. Overall, we validate a long-run cointegration among carbon prices of different markets when considering structural breaks. Additionally, there is a significant correlation among the carbon prices in the long term, but a weaker correlation in the short term, as presented by wavelet coherency. Hence, there is a solid foundation for the integration of China's carbon market with the global carbon market. Article Highlights: We investigate the carbon prices of the Europe market and the China market during the period 2013–2020. We find long-run cointegration among carbon prices of different markets when considering structural breaks. There a significant correlation among the carbon prices in the long term. China government should continue to integrate national carbon market. [ABSTRACT FROM AUTHOR]

Our paper firstly investigates political stability as an underlying mechanism for the phenomenon of environmental spillovers across countries. If political stability exerts a significant impact on environmental quality and it is contagious across country borders, political stability of neighboring countries would be an impetus for environmental spillovers. Taking into account structural breaks in empirical analysis, we test these hypotheses based on an annual country-level panel data set during 2002 to 2018. Utilizing the dynamic ordinary least square (DOLS) method and the panel-based Vector Error Correction (VEC) model, we demonstrate that an improvement in political stability in one country not only enhances the environmental quality of its own, but also meliorates that of its neighbors through the spillovers of political stability. Our results also withstand sensitivity checks for cross-sectional dependence in the panel. Several policy implications are provided in accordance with our findings. [ABSTRACT FROM AUTHOR]

We examine the short-term and long-term causal effects between epidemics and electricity CO2 emissions by using panel data from 30 countries over the period of 1990 to 2017. The results show that there is bidirectional relationship between epidemics and electricity CO2 emissions, especially in OECD and Asian countries. [ABSTRACT FROM AUTHOR]

The spillover effects of European Union Allowances (EUA) spot and futures markets are important for investors in order to understand the relevance and risk management of product prices. This paper uses non-linear methods of Granger causality to test the mean spillover relationship between the two markets and then analyzes volatility spillovers between the two by the non-linear TVP-VAR spillover index. The results show that (1) the non-linear Granger causality test better reflects the mean spillover relationship between EUA spot and futures; (2) there is a bidirectional non-linear mean spillover effect between EUA spot and futures prices for the European Union Emissions Trading Scheme (EU ETS) phases II and III; and (3) volatility spillovers, appearing in EUA spot and future markets in both phases, work increasingly strong over time and are vulnerable to financial crises and extreme events. [ABSTRACT FROM AUTHOR]

Using panel data consisting of 116 countries, this research investigates the effects of natural hazards on financial systems, including banking system, insurance system, and stock markets. Considering the moderating effects of financial risk, we introduce the interaction between natural hazards and financial risk and also analyze the heterogeneity of income level. Our main conclusions are as follows. (1) Though natural hazards do not significantly influence the banking system directly, they do impact the banking system through financial risk. The moderating effects of natural hazards on the banking system through financial risk are significantly negative. (2) The impacts of natural hazards on the insurance system are dynamic and last over a long period, while the moderating effects of natural hazards through financial risk are significantly negative. (3) The effects of natural hazards on the stock markets and the moderating effects through financial risk are significantly negative. (4) The negative effects of natural hazards on the financial system through financial risk are higher in low-income countries than those in high-income countries. From these results, we offer policy implications such as establishing a complete economic system and lowering the financial risk. [ABSTRACT FROM AUTHOR]

To investigate the effects of regulation on environmental pollution under Chinese-style fiscal decentralization, this research analyzes annual data over the period 2003 to 2017 covering 30 provinces in China with the spatial economic model. The empirical results show significant spatial agglomeration effects on the emissions of wastewater, sulfur dioxide, and solid waste. Environmental regulation helps reduce discharge of wastewater and solid waste, but does not help reduce the emission of sulfur dioxide; because there is significantly positive externality in treating pollutants with high fluidity, cost is larger than revenue for local governments. The relationship between fiscal decentralization and pollutants shapes an inverted U-shaped curve. We finally offer some implications in accordance with our empirical finding, such as the intensity of environmental regulation should be suitable for economic development, different measures should be taken based on the fluidity of pollutants, and a new evaluation system should be established. [ABSTRACT FROM AUTHOR]

Background: Loss of the neuromonitoring signal (LOS) during thyroidectomy signifies recurrent laryngeal nerve (RLN) injury, which is one of the common complications, especially by traction injury. Transient intraoperative LOS means spontaneous recovery of nerve function during surgery or within 6-month post-surgery. Few articles discuss intraoperative recovery time and transient LOS, and there is no consensus on the risk factors for RLN traction injury and its recovery course; thus, we wanted to determine the maximum intraoperative recovery time. Materials and methods: This retrospective study included patients who had undergone thyroidectomies at Tainan National Cheng Kung University Hospital between January 2015 and August 2018. A total of 775 patients (with 1000 nerves at risk) who underwent intermittent intraoperative neuromonitoring during thyroidectomy were included in this study. The LOS nerves were divided into 4 groups based on the LOS subtype and the intraoperative status of the recovery. The postoperative vocal cord function was determined by thyroid ultrasound and/or laryngoscope. All the patients would be followed up postoperatively in 2–3 days, 1 week, 2 weeks, and 4–6 weeks. Results: LOS occurred in 67 of 775 (8.6%) patients and in 70 of 1000 nerves at risk (7.0%). There were 2 in 70 nerves (2.9%) with LOS type 1 (segmental nerve traction injury) with intraoperative recovery (Group 1), 5 (7.1%) with LOS type 1 without intraoperative recovery (Group 2), 47 (67.1%) with LOS type 2 (global injury) with intraoperative recovery (Group 3), and 16 (22.8%) with LOS type 2 without intraoperative recovery (Group 4). All LOS type 1 (segmental nerve injury) nerves had pathologic lesions near the RLN or vagus nerve, but none had invaded the nerves (p < 0.05). The resolving time intraoperatively in the 2 patients in Group 1 was 5 min and 10 min, respectively. The resolving time intraoperatively in Group 3 was 1–20 min, and the average time was 4.8 min. In Group 2, 3 injured nerves recovered within 6 weeks postoperatively, and 2 nerves in 12 weeks. In Group 4, all the 16 injured nerves recovered within 6 weeks postoperatively. Conclusion: Applying intermittent intraoperative neuromonitoring during thyroidectomy, traction recurrent laryngeal nerve injury still happened in 7.0%. 70% of the injured nerves recovered the function intraoperatively after releasing the traction, and the longest duration of recovery is 20 min. [ABSTRACT FROM AUTHOR]

To investigate the effects of government environmental regulation and industrial structure changes on carbon dioxide emissions, this research analyzes annual data over the period 2003–2015 covering 30 provinces in China (except for Tibet) with the panel smooth transition regression (PSTR) model. The empirical results show obvious non-linear effects of environmental regulation and industrial structure on carbon dioxide emission. Taking the effects of both linearity and non-linearity into consideration, environmental regulation will reduce carbon emissions with the change of industrial structure rationalization (SR). When the level of industrial structure optimization (SH) is low, environmental regulation promotes carbon dioxide emissions. When the level of industrial structure optimization (SH) is high, environmental regulation plays a significant inhibitive role on carbon dioxide emissions. The Kuznets relationship between GDP per capita (PGDP) and carbon dioxide emissions is influenced by local industrial structure rationalization and industrial structure optimization. Therefore, environmental regulation policies suitable for local conditions should be made based on the transition of the local industrial structure. [ABSTRACT FROM AUTHOR]

Political incentive is one of the most efficient methods to promote local officials to push for both economic growth and environmental progress in the context of China. Since previous scholars have never investigated the relationships between political turnover and environmental governance at the municipal level, in this work, we proxy pollution by SO2, COD, SOOT, and NHx and examine whether environmental performance affects the political turnover of the municipal party secretary by exploiting a panel conditional logit with a fixed-effect model for the period 2002-2013. The results indicate that environmental performance does not significantly impact the turnover of municipal party secretaries, offering evidence that an increase of SO2 is associated with the likelihood of promotion under the panel multinomial logit approach. However, a higher GDP growth rate plays the determinant factor affecting the promotion of China’s municipal party secretaries. Specific policy recommendations are proposed in accordance with our empirical findings. [ABSTRACT FROM AUTHOR]

Employing data of one belt one road (OBOR) countries from 2002 to 2013, this study compares the contagious corruption difference between geographic border and distance through the dynamic spatial econometric model. The empirical results not only confirm that corruption in OBOR countries exists under various contagious channels, but also indicate that border effects, serving as contagious channels for corruption, are better than distance effects. The empirical implication is that OBOR countries with a common border tend to possess contagious corruption due to the hosts’ demonstration effect and the convenience of transferring illegal assets. We advise that those OBOR countries should enhance the supervision of cash flow, look for any opportunity of kicking back a portion of the stolen money, and establish a specific task force on corruption. [ABSTRACT FROM AUTHOR]

As is well known, Chinese central government has full authority to determine the provincial and local officials’ turnover. However, China has not in detail interpreted the standards of officials’ promotions so far. In this paper, the latest database of city-level leaders for the period between 2002 and 2013 is utilized to investigate the influences of economic performance on party secretaries’ odds of being promoted. The estimation results by a panel multinomial logit method indicate that municipal annual GDP per capita is significantly positively associated with leaders’ chances of promotion. Specifically, the average GDP growth rates during leaders’ tenures have much higher effects. Moreover, some important factors of leaders’ personal characteristics also affect the political turnover. For instance, party secretaries’ connection with China’s Communist Youth League, political experience, educational level and professional expertise all have positive impacts on their chances of obtaining a promotion. In contrast, leaders’ ages and tenures are found to be negatively related to their promotion possibilities. [ABSTRACT FROM AUTHOR]

In this paper we investigate whether the ratio of female population is related with lower corruption, utilizing a multinational panel data with 80 countries for the period 2000-2012 and employing the Generalized Method of Moments as well as the ordered probit regression methods. This is the first study on the impacts of different female groups on corruption. Overall speaking, the estimation results are pluralistic. Higher female ratios in the legislative branch and in the labor force are significantly associated with a lower level of corruption, while the female ratio in secondary enrollment is positively related with corruption; however, the female ratio of the whole population has insignificant impacts on corruption. The policy implications are that a simple enhanced female ratio and educational level are not the effective way to inhibit corruption in our sample countries, whereas improvements of the female ratio in the legislative branch and the labor force contribute to controlling corruption. These results are basically robust for the two estimation methods and for the two subsamples of developed and developing countries. As a result, the estimation results on the relationship between corruption and gender might vary remarkably when different indicators for the female groups are utilized, which should some light on future studies. [ABSTRACT FROM AUTHOR]

This study investigates the long-run co-movement between venture capital and technological innovation for 28 provinces (including autonomous regions) in China, using the panel cointegration and panel-based error correction model over the 2001-2012 period. Our results confirm that venture capital and innovation have long-run cointegrated relationships as well as bidirectional causality for the whole country. Analysis of sub-samples again discovers similar results in both the eastern and central regions, but not in the western region. The policy implication shows that China's development of innovations should be based on more venture capital input and that the government should establish a long-run innovation policy to accelerate the development of venture capital. We also offer several constructive suggestions for governments in the western provinces. [ABSTRACT FROM AUTHOR]

Theoretical studies suggest that there is a close association between fiscal decentralization and economic growth. However, whether this linkage holds in China or not is a matter of ongoing debate in recent empirical studies. In this paper, we investigate the impact of the 1994 tax sharing system on economic growth in China. Using a panel dataset for 29 provinces in China over the 1995-2014 period in a simultaneous equations system that controls for the simultaneity of fiscal decentralization, physical capital accumulation and economic growth, the influence of decentralization on economic growth is estimated. The estimation results indicate that there is an inverted-U shaped relationship between fiscal decentralization and economic growth. Because the optimal level of fiscal decentralization that maximizes economic growth is higher than the data for most provinces, further decentralization is in general helpful to China's economic growth. [ABSTRACT FROM AUTHOR]

Waldmann (Q J Econ 107:1283-1302, 1992) established long ago that being improvements in health, medical personnel are the valued input factor of the health production function. Previous research, however, has generally ignored the importance of medical personnel in the health production function and has almost exclusively focused on health expenditure. Thus, the motivation behind this study is to identify the relationship between two health indicators, namely medical personnel, i.e., registered nurses and physicians, and average life expectancy in Taiwan. From the empirical results, we find that there is a long-term equilibrium relationship between the two variables and that medical personnel play a crucial role in the medical care system. Finally, the forecast error variance in life expectancy is mainly explained by itself. Moreover, medical personnel have a positive initial impact on life expectancy, and similar innovations are discovered vice versa in the impulse response functions. Some policy implications can be obtained via our empirical results. [ABSTRACT FROM AUTHOR]

These topics could be divided into four streams, including environmental policy and innovation, environmental governance at the micro-level, macroeconomics outcomes of environmental policy, and water quality management. Chen, Wang, Sun, Chen, Zhang, and Ye employ trophic level index (TLI), water quality index (WQI), modified Nemerow pollution index (NPI), and the random forest (RF) model to evaluate water quality. This special issue is on environmental governance and innovation. [Extracted from the article]

This paper investigates the impact of government ideology on energy efficiency using data for a panel of 23 OECD countries over the 1980-2013 period. With dynamic panel data method applied, our evidence suggests that government ideology is a significant determinant of energy efficiency. Specifically, we show that left-wing parties are associated with energy efficiency improvements. Overall, our results are robust to the two measures of energy efficiency variables, alternative measures of government ideology variables, using annual and 3-year averages of the data, the inclusion of economic and political variables, and to model specifications. [ABSTRACT FROM AUTHOR]

This article examines whether natural disaster losses vary under the tenure of a government with a different ideology. Using panel data for 123 countries over the period of 1975-2013, we find that right-wing governments experience fewer natural disaster losses (measured by people's deaths, those affected, and economic damages) in the case of the full sample. We hence account for possible heterogeneity in our sample and re-estimate the empirical model between 30 OECD countries and 93 non-OECD countries. In summary, we again discover that right-wing governments suffer less natural disaster damages in non-OECD countries, but this effect is statistically insignificant at conventional levels in OECD countries. We believe that the results herein have important implications for the policies of disaster prevention. In addition, voters will be able to choose a responsible government via the voting booth in accordance with our findings. Overall, our results suggest that a more partisan ideology could more precisely capture policy attitudes, especially in developing countries. [ABSTRACT FROM AUTHOR]

Machine learning is a well-known approach for virtual screening. Recently, deep learning, a machine learning algorithm in artificial neural networks, has been applied to the advancement of precision medicine and drug discovery. In this study, we performed comparative studies between deep neural networks (DNN) and other ligand-based virtual screening (LBVS) methods to demonstrate that DNN and random forest (RF) were superior in hit prediction efficiency. By using DNN, several triple-negative breast cancer (TNBC) inhibitors were identified as potent hits from a screening of an in-house database of 165,000 compounds. In broadening the application of this method, we harnessed the predictive properties of trained model in the discovery of G protein-coupled receptor (GPCR) agonist, by which computational structure-based design of molecules could be greatly hindered by lack of structural information. Notably, a potent (~ 500 nM) mu-opioid receptor (MOR) agonist was identified as a hit from a small-size training set of 63 compounds. Our results show that DNN could be an efficient module in hit prediction and provide experimental evidence that machine learning could identify potent hits in silico from a limited training set. [ABSTRACT FROM AUTHOR]