Predicting Natural Rubber Crystallinity by a Novel Machine Learning Algorithm Based on Molecular Dynamics Simulation Data.

Natural rubber (NR) with excellent mechanical properties, mainly attributed to its strain-induced crystallization (SIC), has garnered significant scientific and technological interest. With the aid of molecular dynamics (MD) simulations, we can investigate the impacts of crucial structural elements on SIC on the molecular scale. Nonetheless, the computational complexity and time-consuming nature of this high-precision method constrain its widespread application. The integration of machine learning with MD represents a promising avenue for enhancing the speed of simulations while maintaining accuracy. Herein, we developed a crystallinity algorithm tailored to the SIC properties of natural rubber materials. With the data enhancement algorithm, the high evaluation value of the prediction model ensures the accuracy of the computational simulation results. In contrast to the direct utilization of small sample prediction algorithms, we propose a novel concept grounded in feature engineering. The proposed machine learning (ML) methodology consists of (1) An eXtreme Gradient Boosting (XGB) model to predict the crystallinity of NR; (2) a generative adversarial network (GAN) data augmentation algorithm to optimize the utilization of the limited training data, which is utilized to construct the XGB prediction model; (3) an elaboration of the effects induced by phospholipid and protein percentage (ω), hydrogen bond strength (εH), and non-hydrogen bond strength (εNH) of natural rubber materials with crystallinity prediction under dynamic conditions are analyzed by employing weight integration with feature importance analysis. Eventually, we succeeded in concluding that εH has the most significant effect on the strain-induced crystallinity, followed by ω and finally εNH.

A Machine Learning Framework to Predict the Tensile Stress of Natural Rubber: Based on Molecular Dynamics Simulation Data.

Natural rubber (NR), with its excellent mechanical properties, has been attracting considerable scientific and technological attention. Through molecular dynamics (MD) simulations, the effects of key structural factors on tensile stress at the molecular level can be examined. However, this high-precision method is computationally inefficient and time-consuming, which limits its application. The combination of machine learning and MD is one of the most promising directions to speed up simulations and ensure the accuracy of results. In this work, a surrogate machine learning method trained with MD data is developed to predict not only the tensile stress of NR but also other mechanical behaviors. We propose a novel idea based on feature processing by combining our previous experience in performing predictions of small samples. The proposed ML method consists of (i) an extreme gradient boosting (XGB) model to predict the tensile stress of NR, and (ii) a data augmentation algorithm based on nearest-neighbor interpolation (NNI) and the synthetic minority oversampling technique (SMOTE) to maximize the use of limited training data. Among the data enhancement algorithms that we design, the NNI algorithm finally achieves the effect of approaching the original data sample distribution by interpolating at the neighborhood of the original sample, and the SMOTE algorithm is used to solve the problem of sample imbalance by interpolating at the clustering boundaries of minority samples. The augmented samples are used to establish the XGB prediction model. Finally, the robustness of the proposed models and their predictive ability are guaranteed by high performance values, which indicate that the obtained regression models have good internal and external predictive capacities.

Artificial Intelligence Combined With Big Data to Predict Lymph Node Involvement in Prostate Cancer: A Population-Based Study.

BACKGROUND: A more accurate preoperative prediction of lymph node involvement (LNI) in prostate cancer (PCa) would improve clinical treatment and follow-up strategies of this disease. We developed a predictive model based on machine learning (ML) combined with big data to achieve this. METHODS: Clinicopathological characteristics of 2,884 PCa patients who underwent extended pelvic lymph node dissection (ePLND) were collected from the U.S. National Cancer Institute's Surveillance, Epidemiology, and End Results (SEER) database from 2010 to 2015. Eight variables were included to establish an ML model. Model performance was evaluated by the receiver operating characteristic (ROC) curves and calibration plots for predictive accuracy. Decision curve analysis (DCA) and cutoff values were obtained to estimate its clinical utility. RESULTS: Three hundred and forty-four (11.9%) patients were identified with LNI. The five most important factors were the Gleason score, T stage of disease, percentage of positive cores, tumor size, and prostate-specific antigen levels with 158, 137, 128, 113, and 88 points, respectively. The XGBoost (XGB) model showed the best predictive performance and had the highest net benefit when compared with the other algorithms, achieving an area under the curve of 0.883. With a 5%~20% cutoff value, the XGB model performed best in reducing omissions and avoiding overtreatment of patients when dealing with LNI. This model also had a lower false-negative rate and a higher percentage of ePLND was avoided. In addition, DCA showed it has the highest net benefit across the whole range of threshold probabilities. CONCLUSIONS: We established an ML model based on big data for predicting LNI in PCa, and it could lead to a reduction of approximately 50% of ePLND cases. In addition, only ≤3% of patients were misdiagnosed with a cutoff value ranging from 5% to 20%. This promising study warrants further validation by using a larger prospective dataset.

A Novel Machine Learning Algorithm Combined With Multivariate Analysis for the Prognosis of Renal Collecting Duct Carcinoma.

OBJECTIVES: To investigate the clinical and non-clinical characteristics that may affect the prognosis of patients with renal collecting duct carcinoma (CDC) and to develop an accurate prognostic model for this disease. METHODS: The characteristics of 215 CDC patients were obtained from the U.S. National Cancer Institute's surveillance, epidemiology and end results database from 2004 to 2016. Univariate Cox proportional hazard model and Kaplan-Meier analysis were used to compare the impact of different factors on overall survival (OS). 10 variables were included to establish a machine learning (ML) model. Model performance was evaluated by the receiver operating characteristic curves (ROC) and calibration plots for predictive accuracy and decision curve analysis (DCA) were obtained to estimate its clinical benefits. RESULTS: The median follow-up and survival time was 16 months during which 164 (76.3%) patients died. 4.2, 32.1, 50.7 and 13.0% of patients were histological grade I, II, III, and IV, respectively. At diagnosis up to 61.9% of patients presented with a pT3 stage or higher tumor, and 36.7% of CDC patients had metastatic disease. 10 most clinical and non-clinical factors including M stage, tumor size, T stage, histological grade, N stage, radiotherapy, chemotherapy, age at diagnosis, surgery and the geographical region where the care delivered was either purchased or referred and these were allocated 95, 82, 78, 72, 49, 38, 36, 35, 28 and 21 points, respectively. The points were calculated by the XGBoost according to their importance. The XGBoost models showed the best predictive performance compared with other algorithms. DCA showed our models could be used to support clinical decisions in 1-3-year OS models. CONCLUSIONS: Our ML models had the highest predictive accuracy and net benefits, which may potentially help clinicians to make clinical decisions and follow-up strategies for patients with CDC. Larger studies are needed to better understand this aggressive tumor.

Effects of oral α-lipoic acid administration on body weight in overweight or obese subjects: a crossover randomized, double-blind, placebo-controlled trial.

OBJECTIVE: Alpha-lipoic acid (ALA) has shown beneficial properties on diabetes and obesity. The aim of this study was to examine the effects of oral ALA on body weight in subjects with overweight or obese. DESIGN: Single-centre, randomized, double-blind, crossover controlled study. PARTICIPANTS: A total of 166 subjects of Chinese Han ethnicity with a BMI ≥25 kg/m2 were screened and 103 subjects fulfilled the study requirements, in terms of informed consent and participation to the study. MEASUREMENTS: The subjects were randomized (1:1) to receive either ALA (1200 mg/day) or placebo treatment in a crossover design for 8 weeks. The primary end-point was the change in body weight. The secondary end-points were the changes in waist circumference, BMI, lipid profile, plasma leptin levels and the adverse events that occurred following ALA treatment. RESULTS: The changes in the body weight and waist circumference noted in the ALA group were significantly different compared to the placebo group as demonstrated by mixed model statistical analysis (both P < 0·05). No real weight reduction was seen in the ALA group, and no significant differences were noted as regards cholesterol levels, triglyceride levels, high-density lipoprotein cholesterol levels and adverse events between the two groups. The administration of ALA was well tolerated, and no serious adverse events were noted. CONCLUSIONS: Oral administration of ALA (1200 mg/day) for 8 weeks induced mild weight loss accompanied by a reduction in waist circumference.

Parental factors affecting the circumcision of non-Muslim Chinese boys include education and family history.

AIM: This study investigated the prevalence of circumcision among non-Muslim schoolboys in Urumqi, China, and how acceptable their parents found the practice. METHODS: A convenient cluster sample of non-Muslim schoolboys (n = 3614) aged six to 15 years of age and 873 mothers and 927 fathers completed self-administered questionnaires. We compared the consistency of the circumcision status reported by students and their parents and analysed the factors that influenced the parents to have their child circumcised. RESULTS: The mean age at circumcision was 8.3 years and the adjusted prevalence was 46.2%. Up to 45.4% of fathers and 66% of mothers with uncircumcised sons were willing to circumcise their sons after receiving further information on circumcision. Mothers were more likely to support circumcision if they had higher education levels and higher family income, were employed as government officials and had family members who had been circumcised, including their husband. Fathers were more likely to support circumcision if they were highly educated and had been circumcised themselves. CONCLUSION: The prevalence and acceptability of circumcision were higher than expected in this traditional schoolboy population in Urumqi, China. Factors that increased parental support for circumcision included high education and the father being circumcised.

Tagging SNPs in REN, AGTR1 and AGTR2 genes and response of renin activity, angiotensin II and aldosterone concentrations to antihypertensive treatment in Kazakans.

HYPOTHESIS: Polymorphisms of REN, AGTR1 and AGTR2 may be associated with responses of renin-angiotensin-aldosterone system (RAAS) activity phenotypes to angiotensin-converting enzyme inhibitor (ACEI) antihypertensive treatment. MATERIALS AND METHODS: A total of 400 first diagnosed Kazak hypertensives were randomly allocated to two groups and received a 3-week course of either captopril and atenolol as monotherapy under double blinding. Genotype-phenotype association analyses were performed by covariance analyses between baseline level and responses of blood pressure, renin, angiotensin II and aldosterone concentrations with tagging single nucleotide polymorphisms (SNPs) in REN, AGTR1 and AGTR2 genes. A false discovery rate method was used to adjust multiple testing. RESULTS: After adjustment for multiple testing, we found that the G allele of rs6676670 (T/G) in intron 1 of REN was significantly associated with higher baseline aldosterone concentrations (p < 0.0001, explained variance (EV) = 2.3%). Significant associations after adjustments were also found between the A allele of rs2887284, with higher baseline renin activity (p = 0.022, EV = 1.0%), higher responses of renin (p = 0.018 EV = 5.4%), and higher responses of angiotensin II (p = 0.0255, EV = 3.13%) to the treatment of ACEI. The carriers of the A allele of rs2887284 appeared to be more sensitive to the ACEI treatment. CONCLUSION: rs2887284 in intron 9 of REN is associated with the response of renin and angiotensin II levels to ACEI treatment.

[The effect of oral alpha-lipoic acid in overweight/obese individuals on brachial-ankle pulse wave velocity and supine blood pressure: a randomized, crossover, double-blind, placebo-controlled trial].

OBJECTIVE: To investigate the effect of oral alpha-lipoic acid (ALA) supplement on brachial-ankle pulse wave velocity (baPWV), supine systolic blood pressure (SBP) and diastolic blood pressure (DBP) in overweight/obese individuals. An 8-week double-blind, randomized, placebo-controlled and cross-over trial with a 4-week washout between cross-over periods. METHODS: Sixty-three males and 40 females aged 22 - 57 years old who met the inclusion criteria as (1) Han ethnicity; (2) 20 - 60 years old; (3) BMI ≥ 25 kg/m(2) and having at least one of the following risk factors: borderline hypertension (130 mm Hg ≤ SBP < 140 mm Hg and/or 85 mm Hg ≤ supine DBP< 90 mm Hg), dyslipidemia (fasting total cholesterol ≥ 5.2 mmol/L or HDL-C < 1.04 mmol/L), or impaired fasting glucose (6.1 mmol/L ≤ fasting glucose < 7.0 mmol/L); (4) Not on any antioxidant vitamin supplement. They were randomly assigned to Group 1 or Group 2 in a 1:1 ratio balanced for gender. Group 1 received 8 weeks ALA (1200 mg/day) followed by 4-week washout period and followed by another 8 weeks placebo; while Group 2 received 8 weeks placebo (1200 mg/day) followed by 4-week washout period, and followed by ALA treatment for 8 weeks. BaPWV and supine blood pressure were measured at the beginning of 1(st) phase and 2(nd) phase and at the endpoint of the whole trial. Mixed effect linear regression model was performed to compare the change of baPWV and supine blood pressure between ALA group and placebo group. RESULTS: BaPWV decreased -33.03 cm/s ± 130.70 cm/s for ALA group and increased 5.66 cm/s ± 139.89 cm/s for placebo group, supine systolic blood pressure decreased -4.09 mm Hg ± 9.18 mm Hg for ALA group and -2.32 mm Hg ± 8.16 mm Hg for placebo group. Supine diastolic blood pressure decreased -1.29 mm Hg ± 6.55 mm Hg for ALA group and -0.48 mm Hg ± 6.63 mm Hg for placebo group. These three mix-effect models did not show significant effect of ALA treatment after adjustment on baseline values, sex, age, treatment sequence or period. CONCLUSION: The current trial did not provide evidence that oral intake of ALA for 8 weeks had significant effects on lowering baPWV, supine systolic blood pressure or supine diastolic blood pressure.