Accurate prediction of drug-induced adverse drug reactions (ADRs) is crucial for drug safety evaluation, as it directly impacts public health and safety. While various models have shown promising results in predicting ADRs, their accuracy still needs improvement. Additionally, many existing models often lack interpretability when linking molecular structures to specific ADRs and frequently rely on manually selected molecular fingerprints, which can introduce bias. To address these challenges, we propose ToxBERT, an efficient transformer encoder model that leverages attention and masking mechanisms for simplified molecular input line entry system (SMILES) representations. Our results demonstrate that ToxBERT achieved area under the receiver operating characteristic curve (AUROC) scores of 0.839, 0.759, and 0.664 for predicting drug-induced QT prolongation (DIQT), rhabdomyolysis, and liver injury, respectively, outperforming previous studies. Furthermore, ToxBERT can identify drug substructures that are closely associated with specific ADRs. These findings indicate that ToxBERT is not only a valuable tool for understanding the mechanisms underlying specific drug-induced ADRs but also for mitigating potential ADRs in the drug discovery pipeline.

Efficient drug response prediction is crucial for reducing drug development costs and time, but current computational models struggle with limited experimental data and out-of-distribution issues between in vitro and in vivo settings. To address this, we introduced drug response prediction meta-learner (metaDRP), a novel few-shot learning model designed to enhance predictive accuracy with limited sample sizes across diverse drug-tissue tasks. metaDRP achieves performance comparable to state-of-the-art models in both genomics of drug sensitivity in cancer (GDSC) drug screening and in vivo datasets, while effectively mitigating out-of-distribution problems, making it reliable for translating findings from controlled environments to clinical applications. Additionally, metaDRP's inherent interpretability offers reliable insights into drug mechanisms of action, such as elucidating the pathways and molecular targets of drugs like epothilone B and pemetrexed. This work provides a promising approach to overcoming data scarcity and out-of-distribution challenges in drug response prediction, while promoting the integration of few-shot learning in this field.

Objective:To explore the effect of parental rearing patterns and their consistency on the emotional and behavioral problems of preschool children.Methods:From October to November 2017, 27 987 children aged 3 to 6 years old from 109 kindergartens in 11 cities of Hubei, Anhui and Jiangsu Provinces were selected by using the cluster sampling method. A total of 27 200 valid questionnaires which were completed by subjects' parents were collected. The emotional and behavioral problems of preschool children were collected by "strengths and difficulties questionnaire" and the parental rearing patterns were evaluated by the "Parental Behavior Scale". The differences in emotional and behavioral abnormality rates of preschool children with different characteristics were analyzed; with emotional and behavioral problems as dependent variables and parental support/participation and compulsion/hostility as independent variables, the multivariate logistic regression model was used to analyze the effect of parental rearing patterns and their consistency on the emotional and behavioral problems of preschool children.Results:The age of children was (4.35±0.96) years old, and 51.4% of children were 13 975 males. There were 24 634 (90.6%) urban children and 17 916 (65.9%) only children. Both parents with strong support/participation accounted for 14.9%, and those with poor support/participation accounted for 11.9%; both parents with strong compulsion/hostility accounted for 15.2%, and those with low compulsion/hostility accounted for 11.3%. The rates of emotional symptoms, conduct behavior, hyperactive behavior, peer interaction, total difficulty score, and abnormal prosocial behavior of preschool children were 9.5%, 9.5%, 18.2%, 24.5%, 11.2%, and 10.2%, respectively. The multivariate logistic regression model analysis showed that after adjusting for gender, only child, living area, family economic status, mother′s age and education level, father′s education level, and other factors, compared with fathers/mothers with strong support/participation and low compulsion/hostility and parents with strong support/participation and low compulsion/hostility, preschool children who had fathers/mothers with poor support/participation and strong compulsion/hostility or parents with poor support/participation and strong compulsion/hostility were more likely to have emotional symptoms, conduct behavior, hyperactive behavior, peer interaction, total difficulty score, and abnormal prosocial behavior ( P<0.05). Conclusions:Parental rearing patterns and their consistency are related to the emotional and behavioral problems of preschool children.

Objective:To explore the effect of parental rearing patterns and their consistency on the emotional and behavioral problems of preschool children.Methods:From October to November 2017, 27 987 children aged 3 to 6 years old from 109 kindergartens in 11 cities of Hubei, Anhui and Jiangsu Provinces were selected by using the cluster sampling method. A total of 27 200 valid questionnaires which were completed by subjects' parents were collected. The emotional and behavioral problems of preschool children were collected by "strengths and difficulties questionnaire" and the parental rearing patterns were evaluated by the "Parental Behavior Scale". The differences in emotional and behavioral abnormality rates of preschool children with different characteristics were analyzed; with emotional and behavioral problems as dependent variables and parental support/participation and compulsion/hostility as independent variables, the multivariate logistic regression model was used to analyze the effect of parental rearing patterns and their consistency on the emotional and behavioral problems of preschool children.Results:The age of children was (4.35±0.96) years old, and 51.4% of children were 13 975 males. There were 24 634 (90.6%) urban children and 17 916 (65.9%) only children. Both parents with strong support/participation accounted for 14.9%, and those with poor support/participation accounted for 11.9%; both parents with strong compulsion/hostility accounted for 15.2%, and those with low compulsion/hostility accounted for 11.3%. The rates of emotional symptoms, conduct behavior, hyperactive behavior, peer interaction, total difficulty score, and abnormal prosocial behavior of preschool children were 9.5%, 9.5%, 18.2%, 24.5%, 11.2%, and 10.2%, respectively. The multivariate logistic regression model analysis showed that after adjusting for gender, only child, living area, family economic status, mother′s age and education level, father′s education level, and other factors, compared with fathers/mothers with strong support/participation and low compulsion/hostility and parents with strong support/participation and low compulsion/hostility, preschool children who had fathers/mothers with poor support/participation and strong compulsion/hostility or parents with poor support/participation and strong compulsion/hostility were more likely to have emotional symptoms, conduct behavior, hyperactive behavior, peer interaction, total difficulty score, and abnormal prosocial behavior ( P<0.05). Conclusions:Parental rearing patterns and their consistency are related to the emotional and behavioral problems of preschool children.

Objective: To analyze the detection rate of sleep problems such as sleep delay and deficiency in preschool children in the middle and lower reaches of the Yangtze River in China,and to provide the reference for the standard of sleeping mode among preschool students. Methods: From October to November 2017, a questionnaire survey was conducted among 27 200 preschool children in 11 cities in Hubei, Anhui and Jiangsu provinces in the middle and lower reaches of the Yangtze River in China. Epidemiology of sleep delays, deficiencies and sleep patterns in preschool children was described. Results: The detection rate of sleep problems in preschool children in the middle and lower reaches of the Yangtze River was 15.3%. Taking the length of sleep and bedtime as the main analysis points, it was found that the average sleeping time point of each age group was 21:31, and the detection rate of bedtime delay was 86.5%. The average length of sleep was (10.60±1.12) hours. The detection rate of sleep deprivation in preschool children was 15.7%. Sleep delay was positively correlated with girls, age increase and parents’ higher educational level (P<0.05), and negatively correlated with living in the city, non-only child and bedroom without TV (P<0.01) .The detection rate of sleep deprivation was positively correlated with children of high age group (4yearold group：OR=1.32，95%CI=1.19-1.46；5-year-old group：OR=2.10，95%CI=1.91-2.32；6-year-old group：OR=2.47，95%CI=2.20-2.77)(P<0.01), and negatively correlated with no TV in bedroom (OR=0.91，95%CI=0.84-0.98) and no light in sleep (OR=0.87，95%CI=0.78-0.97)(P<0.05). Conclusion Preschool children sleep delay and sleep deprivation and other sleep problems are more prominent, affected by family environment and other factors.

Objective: To explore the blood lead level and its relationship with behavior in school-age children from rural areas of Chongqing. Methods: A total of 697 students from grades 3 to 6 in the fall semester of 2014 from 14 rural townships in one district of Chongqing was selected by using the random cluster sampling method. Blood were sampled to analyze the lead level. Neurobehavioral tests were performed to determine their personal cognitive and memory ability. Questionnaires and physical examinations were administered to obtain the information of confounding factors. All students were divided into Q₁-Q₄ groups according to the quartile of their blood lead level. The relationship between the blood lead level and behavior was analyzed by multivariate logistic regression model and restricted spline regression model. Results: The mean age of 697 students was (10.07±1.36) years old, and the median (interquartile range) of their blood lead level was 44.31 (35.42) μg/L. Multivariate logistic regression model showed that after adjusting for age, gender, body mass index and maternal culture level, compared with Q₁ group, the OR (95%CI) values of high digit symbol substitution test (DSST) scores and high overall memory quotient (MQ) scores in Q₃ group were 1.65 (1.01-2.70) and 2.10 (1.21-3.62), and the OR (95%CI) value of high long term memory (LTM) scores in Q₄ group was 0.53 (0.31-0.92). The results of the restricted spline regression model showed that the dose-response curves between the blood lead level and MQ/LTM test scores were both parabolic (P<0.05). Conclusion The blood lead level of school-age children from rural areas of Chongqing is the same as that from other areas of China, but slightly higher than that from other areas of Chongqing. Children with higher blood lead level have poor long-term memory ability.

Objective To explore the blood lead level and its relationship with behavior in school?age children from rural areas of Chongqing. Methods A total of 697 students from grades 3 to 6 in the fall semester of 2014 from 14 rural townships in one district of Chongqing was selected by using the random cluster sampling method. Blood were sampled to analyze the lead level. Neurobehavioral tests were performed to determine their personal cognitive and memory ability. Questionnaires and physical examinations were administered to obtain the information of confounding factors. All students were divided into Q1-Q4 groups according to the quartile of their blood lead level. The relationship between the blood lead level and behavior was analyzed by multivariate logistic regression model and restricted spline regression model. Results The mean age of 697 students was (10.07±1.36) years old, and the median (interquartile range) of their blood lead level was 44.31 (35.42) μg/L. Multivariate logistic regression model showed that after adjusting for age, gender, body mass index and maternal culture level, compared with Q1 group, the OR (95%CI ) values of high digit symbol substitution test (DSST) scores and high overall memory quotient (MQ) scores in Q 3 group were 1.65 (1.01-2.70) and 2.10 (1.21-3.62), and the OR (95%CI ) value of high long term memory (LTM) scores in Q4 group was 0.53 (0.31-0.92). The results of the restricted spline regression model showed that the dose?response curves between the blood lead level and MQ/LTM test scores were both parabolic (P<0.05). Conclusion The blood lead level of school?age children from rural areas of Chongqing is the same as that from other areas of China, but slightly higher than that from other areas of Chongqing. Children with higher blood lead level have poor long?term memory ability.

Objective To explore the blood lead level and its relationship with behavior in school?age children from rural areas of Chongqing. Methods A total of 697 students from grades 3 to 6 in the fall semester of 2014 from 14 rural townships in one district of Chongqing was selected by using the random cluster sampling method. Blood were sampled to analyze the lead level. Neurobehavioral tests were performed to determine their personal cognitive and memory ability. Questionnaires and physical examinations were administered to obtain the information of confounding factors. All students were divided into Q1-Q4 groups according to the quartile of their blood lead level. The relationship between the blood lead level and behavior was analyzed by multivariate logistic regression model and restricted spline regression model. Results The mean age of 697 students was (10.07±1.36) years old, and the median (interquartile range) of their blood lead level was 44.31 (35.42) μg/L. Multivariate logistic regression model showed that after adjusting for age, gender, body mass index and maternal culture level, compared with Q1 group, the OR (95%CI ) values of high digit symbol substitution test (DSST) scores and high overall memory quotient (MQ) scores in Q 3 group were 1.65 (1.01-2.70) and 2.10 (1.21-3.62), and the OR (95%CI ) value of high long term memory (LTM) scores in Q4 group was 0.53 (0.31-0.92). The results of the restricted spline regression model showed that the dose?response curves between the blood lead level and MQ/LTM test scores were both parabolic (P<0.05). Conclusion The blood lead level of school?age children from rural areas of Chongqing is the same as that from other areas of China, but slightly higher than that from other areas of Chongqing. Children with higher blood lead level have poor long?term memory ability.

Objective To understand the implementation of New Rural Cooperative Medicine(NRCM)in Hunan Province carried out in Miluo City.Methods Qualitative study was combined with secondary data collection.Results Government in Miluo took initatives to organize NRCM and financed it with the NRCM Funds;each peasant could enjoy NRCM by paying only 10 yuan,and the NRCM participation rate reached 73.6%;currently reimbursement mainly focused on hospitalization,lowest-payment for seeking care,and reimbursement proportion varied in health facilities at different levels;the health facilities and peasants benefited a lot from NRCM.Conclusions The NRCM participation is increasing,funds allocated properly,peasants welcoming it.Further measures for NRCM improvement may include allocating more funds,perfecting reimbursement procedures.Besides,the NRCM for some population like persons without children or suffering severe disease awaits solution.