Prediction of organic compound aqueous solubility using machine learning: a comparison study of descriptor-based and fingerprints-based models.

A reliable and practical determination of a chemical species' solubility in water continues to be examined using empirical observations and exhaustive experimental studies alone. Predictions of chemical solubility in water using data-driven algorithms can allow us to create a rationally designed, efficient, and cost-effective tool for next-generation materials and chemical formulations. We present results from two machine learning (ML) modeling studies to adequately predict various species' solubility using data for over 8400 compounds. Molecular-descriptors, the most used method in previous studies, and Morgan fingerprint, a circular-based hash of the molecules' structures, were applied to produce water solubility estimates. We trained all models on 80% of the total datasets using the Random Forest (RFs) technique as the regressor and tested the prediction performance using the remaining 20%, resulting in coefficient of determination (R2) test values of 0.88 and 0.81 and root-mean-square deviation (RMSE) test values 0.64 and 0.80 for the descriptors and circular fingerprint methods, respectively. We interpreted the produced ML models and reported the most effective features for aqueous solubility measures using the Shapley Additive exPlanations (SHAP) and thermodynamic analysis. Low error, ability to investigate the molecular-level interactions, and compatibility with thermodynamic quantities made the fingerprint method a distinct model compared to other available computational tools. However, it is worth emphasizing that physicochemical descriptor model outperformed the fingerprint model in achieving better predictive accuracy for the given test set.

Evaluating the Health Belief Model Constructs in Adopting the HPV Preventive Behavior.

Objective: Genital warts are a highly contagious sexually transmitted disease. It is caused by the human papillomavirus (HPV), which is transmitted through sexual contact. HPV is the most important cause of cervical cancer. This study aimed to evaluate the health belief model (HBM) constructs in adopting HPV preventive behavior in women referred to comprehensive health centers in Southwestern Iran. Materials and methods: This descriptive-analytical study was performed on 1000 women referring to health centers in Ahvaz during 2019-2020 who were selected via a two-stage stratified random sampling technique. Data were collected using a valid and reliable researcher-made questionnaire based on the HBM. The data were analyzed using descriptive statistics, t-test, ANOVA, Pearson correlation coefficient, and regression analysis in SPSS v.18, at a significance level lower than 0.05. Results: Total scale reliability of the tool was very good (α=0.828), as the Intra-cluster correlation coefficient (ICC) was to be 0.86. The mean of preventive behavior using an ANOVA test was significantly different at different levels of education (P <0.05). The mean and standard deviation of knowledge about HPV and preventive behavior was moderate (11.45±3.4). Pearson correlation coefficient showed a significant direct relationship between preventive behavior with awareness, perceived sensitivity, and self-efficacy and inversely related to perceived barriers. Perceived sensitivity (0.01) and self-efficacy (<0.001) were identified as the final predictors of behavior in regression analysis. Conclusion: As the results showed, designing programs to prevent HPV, considering the perceived role of perceived sensitivity and self-efficacy, increases the likelihood of effective interventions.

Men's knowledge of preconception health: A systematic review.

Preconception health is defined as the physical and psychological well-being of women and men throughout their reproductive life. It is a method that raises healthy fertility and focuses on activities that persons can take to minimize risks, raise healthy lifestyles, and increase preparation for pregnancy. The purpose of this systematic review study was to assess men's knowledge of preconception health. Electronic databases, including Web of Science, PubMed, Scopus, Sciencedirect, ProQuest, Cochrane, SAGE, Springer, Google Scholar, were searched for published studies from 2000 to March 2021 to identify the studies carried out on men's knowledge of preconception health. The quality assessment was done using the critical appraisal skills program tool for qualitative studies and the Newcastle-Ottawa scale for cross-sectional studies. Of the 1195 references identified in the initial search, 11 studies met the inclusion criteria. Because of the diversity in the study design and the data collection tools used in studies, meta-analysis was impossible. All the studies of the present systematic review found that men's preconception health knowledge is poor. This systematic review showed that men's preconception health knowledge is low. Due to the limited studies of men's knowledge about the importance of optimizing their health before pregnancy, further study of the issue is still required.

Exploring the reproductive health needs of men in the preconception period: A qualitative study.

BACKGROUND: Male reproductive health is a necessary pillar of childbearing. If a reproductive health assessment is conducted in the preconception period, the chance of a healthy pregnancy can increase. This qualitative study aimed to explore men's reproductive health needs before conception in Iran. MATERIALS AND METHODS: This research was a qualitative study conducted in Bushehr city, Iran to explore men's reproductive health needs from April 2021 to November 2021. 30 semistructured interviews were conducted with married men, women, healthcare providers, and specialists individually in the health centers. The sampling method used in this study was purpose-based with maximum variety. All interviews were digitally recorded and transcribed verbatim in Persian and analyzed using directional content analysis. MAXQDA software version 12 was used to facilitate data analysis. RESULTS: From the data analysis, 2 themes, 15 categories, and 38 subcategories emerged. The themes included evaluation and health promotion recommendations. It consisted of 10 categories: reproductive life plan evaluation, medical history evaluation, family and genetic history evaluation, social history evaluation, sexual health evaluation, medication evaluation, laboratory evaluation, physical examination, lifestyle evaluation, and mental health evaluation. Health promotion recommendations included five categories: nutritional recommendations, stress management, avoiding harmful behaviors, protective measures against harmful exposure, and need for education. CONCLUSIONS: Our results showed that men need a comprehensive evaluation of reproductive health and recommendations to improve their health in the preconception period. Our study findings can inform healthcare providers to increase men's participation in reproductive health.