Analysis of Mechanical Properties of Fiber-Reinforced Soil Cement Based on Kaolin.

Adding fibers into cement to form fiber-reinforced soil cement material can effectively enhance its physical and mechanical properties. In order to investigate the effect of fiber type and dosage on the strength of fiber-reinforced soil cement, polypropylene fibers (PPFs), polyvinyl alcohol fibers (PVAFs), and glass fibers (GFs) were blended according to the mass fraction of the mixture of cement and dry soil (0.5%, 1%, 1.5%, and 2%). Unconfined compressive strength tests, split tensile strength tests, scanning electron microscopy (SEM) tests, and mercury intrusion porosimetry (MIP) pore structure analysis tests were conducted. The results indicated that the unconfined compressive strength of the three types of fiber-reinforced soil cement peaked at a fiber dosage of 0.5%, registering 26.72 MPa, 27.49 MPa, and 27.67 MPa, respectively. The split tensile strength of all three fiber-reinforced soil cement variants reached their maximum at a 1.5% fiber dosage, recording 2.29 MPa, 2.34 MPa, and 2.27 MPa, respectively. The predominant pore sizes in all three fiber-reinforced soil cement specimens ranged from 10 nm to 100 nm. Furthermore, analysis from the perspective of energy evolution revealed that a moderate fiber dosage can minimize energy loss. This paper demonstrates that the unconfined compressive strength test, split tensile strength test, scanning electron microscopy (SEM), and mercury intrusion porosimetry (MIP) pore structure analysis offer theoretical underpinnings for the utilization of fiber-reinforced soil cement in helical pile core stiffening and broader engineering applications.

Portable fluorescent lateral flow assay for ultrasensitive point-of-care analysis of acute myocardial infarction related microRNA.

Point-of-care quantitative analysis of tracing microRNA disease-biomarkers remains a great challenge in the clinical diagnosis. In this paper, we developed a portable fluorescent lateral flow assay for ultrasensitive quantified detection of acute myocardial infarction related microRNAs in bio-samples. SiO2@DQD (bilayer quantum dots assembly with SiO2 core) based fluorescent lateral flow strip was fabricated as the analysis tool. In order to quantify the tracing microRNA in biosamples, a catalytic hairpin assembly and CRISPR/Cas12a cascade amplification method was performed and combined with the fabricated SiO2@DQD lateral flow strip. Thus, our platform gathered double advantages of portability and ultrasensitive quantification. Based on our strips, target myocardial biomarker microRNA-133a can be detected with a detection limit of 0.32 fM, which was almost 1000-fold sensitive compared with previous reported microRNAs-lateral flow strips. Significantly, this portable fluorescent strip can directly detect microRNAs in serum without any pretreatment and PCR amplification steps. When spiked in serum samples, a recovery of 99.65 %-102.38 % can be obtained. Therefore, our method offers a potential tool for ultrasensitive quantification of diseases related microRNA in the point-of-care diseases diagnosis field.

Integrated network pharmacology and molecular docking analyses of the mechanisms underlying the antihypertensive effects of lotusine.

Hypertension is a modifiable cardiovascular risk factor and cause of death worldwide. Lotusine, an alkaloid extracted from a plant used in traditional Chinese Medicine, has shown anti-hypertensive effects. However, its therapeutic efficacy requires further investigation. We adopted integrated network pharmacology and molecular docking approaches with the aim of investigating lotusine's antihypertensive effects and mechanisms of action in rat models. After identifying the optimal intravenous dosage, we observed the effects of lotusine administration on two-kidney, one-clip (2K1C) rats and spontaneously hypertensive rats (SHRs). Based on network pharmacology and molecular docking analyses, we measured renal sympathetic nerve activity (RSNA) to evaluate lotusine's effect. Finally, an abdominal aortic coarctation (AAC) model was established to evaluate lotusine's long-term effects. The network pharmacology analysis identified 21 intersection targets; of these, 17 were also implicated by the neuroactive live receiver interaction. Further integrated analysis showed high lotusine affinity for the cholinergic receptor nicotinic alpha 2 subunit, adrenoceptor beta 2, and adrenoceptor alpha 1B. Blood pressure of the 2K1C rats and SHRs decreased after treatment with 2.0 and 4.0 mg/kg of lotusine (P < 0.001 versus saline control). We also observed RSNA decreases consistent with the network pharmacology and molecular docking analysis results. Results from the AAC rat model indicated that myocardial hypertrophy was decreased with lotusine administration, demonstrated by echocardiography and hematoxylin and eosin and Masson staining. This study provides insights into the antihypertensive effects and underlying mechanisms of lotusine; lotusine may exert long-term protective effects against myocardial hypertrophy caused by elevated blood pressure.

Magnetic SERS Strip Based on 4-mercaptophenylboronic Acid-Modified Fe3O4@Au for Active Capture and Simultaneous Detection of Respiratory Bacteria.

The rapid diagnosis and detection of respiratory bacteria at the early stage can effectively control the epidemic spread and bacterial infection. Here, we designed a rapid, ultrasensitive, and quantitative lateral flow immunoassay (LFA) strip for simultaneous detection of respiratory bacteria S. aureus and S. pneumoniae. In this assay, the surface enhanced Raman scattering (SERS) tags were designed through combining magnetite Raman enhancement nanoparticle Fe3O4@Au/DTNB and recognition element 4-mercaptophenylboronic acid (4-MPBA). Further, 4-MPBA could capture multiple bacteria in a complex environmental solution. Based on the strategies, Fe3O4@Au/DTNB-mediated magnetic enrichment and 4-MPBA-mediated universal capture capabilities improved the detection sensitivity, the limits of detection for S. aureus and S. pneumoniae were as low as 8 and 13 CFU mL-1, respectively, which were more sensitive than those of colloidal gold method. The Fe3O4@Au/DTNB/Au/4-MPBA-LFA also exhibited good reproducibility, excellent specificity, and high recovery rates in sputum samples, indicating its potential application in the detection of respiratory bacteria samples.

Effects of Tai Chi on health status in adults with chronic heart failure: A systematic review and meta-analysis.

Background: Chronic heart failure (CHF) is among the top causes of cardiovascular morbidity, and most patients with CHF have poor health status. Tai Chi, a mind-body exercise that originated in China, is beneficial for health status. This study was conducted to evaluate the effects of Tai Chi on health status in adults with CHF. Methods: The Cochrane Library, PubMed, Embase, Web of Science, China National Knowledge Infrastructure, Wanfang Database, Chinese Biomedical Database, and Chinese Scientific Journal Database were searched from the inception to 22 October 2021. This meta-analysis was performed using the fixed- or random-effects model. Continuous outcomes were carried out using mean difference (MD) or standardized mean difference (SMD) with 95% confidence interval (CI). Dichotomous outcomes were determined using risk ratio (RR) with 95%CI. The Grading of Recommendations, Assessment, Development and Evaluations (GRADE)pro Guideline Development Tool (GDT) online software was used to present outcome-specific information regarding overall certainty of evidence from studies. Results: In total, 15 studies including 1,236 participants were finally included. Compared with usual care alone, Tai Chi combined with usual care achieved efficacy in improving Minnesota Living with Heart Failure Questionnaire (MD = -8.51; 95% CI: -10.32 to -6.70; p < 0.00001), 6-min walk test (MD = 43.47; 95% CI: 33.38 to 54.10; p < 0.00001), left ventricular ejection fraction (MD = 6.07; 95% CI: 3.44 to 8.70; p < 0.00001), B-type natriuretic peptide/N-terminal fragment of pro-BNP (SMD = -1.12; 95% CI: -1.70 to -0.54; p = 0.0002), Hamilton Depression Rating Scale (MD = -2.89; 95% CI: -4.87 to -0.91; p = 0.004), Pittsburgh Sleep Quality Index (MD = -2.25; 95% CI: -3.88 to -0.61; p = 0.007), timed up and go test (MD = -1.34; 95% CI: -2.50 to -0.19; p = 0.02), and reduced the risk of heart failure hospitalization (RR = 0.47; 95% CI: 0.25 to 0.88; p = 0.02). However, there was no difference in the outcome of peak oxygen uptake (MD = 1.38; 95% CI: -1.51 to 4.28; p = 0.35). All-cause mortality or cardiovascular death could not be evaluated due to insufficient data. The certainty of evidence ranged from very low to moderate due to the risk of bias, inconsistency, imprecision, and publication bias. Conclusion: Tai Chi might be safe and showed beneficial effects on health status in patients with CHF. However, more high-quality and long-term studies are still needed to further evaluate the effects of Tai Chi.

A Randomized Controlled Trial on the Efficacy of Xinnaoning Capsule in the Treatment of CSAP Complicated With Qi Stagnation and Blood Stasis Syndrome.

Objective: This study was designed to explore the efficacy and safety of Xinnaoning Capsule (XNNC) in the treatment of patients with chronic stable angina pectoris (CSAP) complicated with Qi stagnation and blood stasis syndrome. Methods: A total of 240 patients with CSAP complicated with Qi stagnation and blood stasis syndrome who met the inclusion criteria were enrolled from 8 medical centers across China. The trial treatment lasted 14 weeks, including a 2-week lead-in period and a 12-week double-blind treatment period. Patients in the experimental group were treated with XNNC, while patients in the control group were treated with placebos. Thereafter, examinations were conducted on the efficacy of angina pectoris before and after treatment and the relief of symptoms, followed by the recording of grading changes in angina severity, changes in the number of angina pectoris, and the amount of taken nitroglycerin. Finally, adverse events were assessed. Results: Compared with the control group, the total score and the effective rate of angina pectoris were significantly increased in the experimental group, accompanied by the statistically significant improvement in the severity of angina pectoris (all p < 0.05). Furthermore, there was no statistically significant difference in the adverse events and serious adverse events between the experimental group and the control group (p = 1.0000) before and after treatment. Conclusion: XNNC is a safe and effective medicine for patients with CSAP complicated with Qi stagnation and blood stasis syndrome.

Acarbose for Postprandial Hypotension With Glucose Metabolism Disorders: A Systematic Review and Meta-Analysis.

Background: Postprandial hypotension (PPH) is an independent predictive factor of all-cause mortality in older people. Drug management has not achieved a satisfactory effect yet. In recent years, many studies have found that acarbose may be effective in the treatment of PPH with glucose metabolism disorders. Objective: To assess the efficacy and safety of acarbose on PPH with glucose metabolism disorders. Methods: PubMed (MEDLINE), Cochrane, EMBASE, Web of Science, Clinical Trials, and relevant Chinese databases were searched from inception to October 1, 2020. Randomized controlled studies of acarbose in the treatment of PPH with glucose metabolism disorders were included. Review Manager 5.3 software was used for quality evaluation and meta-analysis. GRADEpro GDT software was used to GRADE the evidence for the research objectives. Results: A total of 4 randomized controlled studies including 202 participants were identified after screening. The meta-analysis showed that acarbose significantly attenuated the decrease in postprandial systolic blood pressure [weighted mean difference (MD): -9.84, 95% CI: -13.34 to -6.33], diastolic blood pressure (MD: -6.86, 95% CI: -12.89 to -0.83), and mean arterial pressure (MD: -8.10, 95% CI: -12.40 to -3.49) compared with the control group. One study reported a case of adverse reactions that included mild abdominal distension in the acarbose group (4.8%, 1/21). No adverse reactions were reported in the other three studies. Conclusion: Acarbose may attenuate the decrease in postprandial blood pressure and avoid the occurrence of PPH in patients with PPH and abnormal glucose metabolism disorders. More clinical trials are needed to make a clear conclusion. Registration: PROSPERO CRD42020171335.

Acupoint injection treatment for non-dialysis dependent chronic kidney disease: A meta-analysis of randomized controlled trials.

AIM: To analyze the effects of acupoint injection in the treatment of non-dialysis dependent chronic kidney disease through a systematic review with meta-analysis. METHODS: This systematic review with meta-analysis was conducted following the recommendations of the declaration of PRISMA. Full-text literature of randomized controlled trial of acupoint injection therapy for non-dialysis chronic kidney disease was searched in PubMed, Embase, Cochrane Library, China National Knowledge Internet, the Chinese Scientific Journal Database, the Wanfang Database, China Biology Medicine database. The efficacy and safety of acupoint injection for non-dialysis chronic kidney disease were evaluated. RESULTS: Seventeen studies containing 1414 patients met the criteria. The results shows that acupoint injection combined with basic treatment can significantly improve the levels of Ccr (WMD = 4.81; 95% CI:2.54 to 7.08) and Hb (WMD = 4.56; 95% CI:1.72 to 7.39), reduce the levels of BUN (WMD = -0.90; 95% CI: -1.26 to -0.54)and Scr (WMD = -7.66; 95% CI: -12.39 to -2.93), and improve the effective rate (OR = 3.12; 95% CI: 2.29 to 4.26). CONCLUSION: Our current analysis showed that combined acupoint injection therapy can reduce the levels of BUN and Scr, and increase Ccr and Hb in non-dialysis CKD patients. However, the existing evidence is still insufficient due to the high risk of included trial bias, and future research needs to improve methodological quality.Registration number: CRD42020168143.

Exploratory study on the safety and effectiveness of Yizhi Qingxin Decoction (capsules) in the treatment of hypertension in the elderly with mild cognitive impairment (deficiency of kidney essence syndrome).

BACKGROUND: Hypertension in the elderly with cognitive impairment has been one of the global health issues. Mild cognitive impairment (MCI) is the state of transition between the normal aging process and cognitive changes of unformed dementia. Diagnosis and treatment of MCI are the keys to prevent dementia, and hypertension is one of the important influencing factors of MCI. Our preclinical experiment found that Yizhi Qingxin Decoction (YQD) could effectively reduce the blood pressure of spontaneously hypertensive rats (SHR), improve their spatial learning and memory abilities in Morris water maze, and play a neuroprotective role. The objective is to estimate the safety and efficacy of YQD (capsules) in the treatment of hypertension in the elderly with MCI (deficiency of kidney essence syndrome) through this study. METHODS: According to the random number generated by the block random method, 100 participants will be randomly and equally divided into the treatment group (YQD) or the control group (Ginkgo biloba extract tablets). The conversion rate of dementia will be used as the main evaluating indicator by the CDR scale. The MoCA scale, MMSE scale, ADCS-MCI-ADL-24 scale, CGIC-KDS scale, and 24-h ambulatory blood pressure will be used as the secondary evaluating indicator. Safety will be evaluated based on specific manifestations of adverse reactions and the incidence of adverse events. OBJECTIVE: The objective is to estimate the curative effect of YQD (capsules) on hypertension in the elderly with MCI (deficiency of kidney essence syndrome), and to evaluate the safety of its clinical application. TRIAL REGISTRATION: Chinese Clinical Trial Registry (ICTRP member): ChiCTR2000030292.

The protective effects of angelica organic acid against ox-LDL-induced autophagy dysfunction of HUVECs.

BACKGROUND: Angelica root is the dry root of the Umbelliferae plant Angelica sinensis (oliv) Diels. Angelica organic acid (OA) is the main active ingredient in Angelica sinensis, and it exerts potential anti-atherosclerotic effects by preventing Oxidized low-density lipoprotein (Ox-LDL) induced endothelial injury. To study the protective effects of OA on ox-LDL-induced HUVECs autophagic flux dysfunction and inflammatory injury. METHODS: OA were isolated by water extraction and alcohol precipitation, and then the content of ferulic acid (FA) in the OA was determined by high performance liquid chromatography. The ox-LDL-induced endothelial injury model was established. The effect of ferulic acid on the survival of Human umbilical vein endothelial cells (HVUECs) was detected by CCK-8 assay. HUVECs were pretreated with different concentrations of OA (20 µmol/L, 40 µmol/L, and 80 µmol/L), and Western Blot was used to detect the expressions of LC3II, p62, MCP-1, VCAM-1 and LOX-1. The autophagosomes in HUVECs were observed by transmission electron microscopy (TEM). RESULTS: 20 µmol/L OA could increase the expression of LC3II and decrease the expression of p62, MCP-1, VCAM-1 and LOX-1. The results of TEM showed that angelica organic acids promoted cell organelle degradation in autolysosomes. CONCLUSION: OA could reduce inflammation, protect endothelial cells and play an anti-atherosclerotic role by enhancing the autophagy flux of damaged endothelial cells, in which FA the major active ingredient of OA played a major role.

Anti-aging role of Chinese herbel medicine: an overview of scientific evidence from 2008 to 2018.

The aging of the population has become a global health problem. It is an important risk factor for major diseases such as cardiovascular disease, Alzheimer's disease, Parkinson's disease, and cancer. Presently, there is no definite and effective anti-aging treatment. Chinese herbal medicine has a long history of application and is often used for aging-related diseases in China. A large number of clinical and preclinical studies on the anti-aging effect of Chinese herbal medicine has been performed. Through literature research, we reviewed the anti-aging clinical research of Chinese herbal medicine and preclinical research of Chinese herbal medicine monomers, components, extracts, and compounds, and their mechanisms. Results from preclinical studies have shown that Chinese herbal medicines have beneficial anti-aging effects. The mechanism mainly includes anti-oxidative stress, anti-inflammatory, neuroprotection, apoptosis and mitochondrial function regulation, etc. However, more detailed high-quality clinical trials are required for future investigation of the anti-aging effects of Chinese herbal medicines.

Triterpenes from Poria cocos are revealed as potential retinoid X receptor selective agonists based on cell and in silico evidence.

Poria cocos is an edible and medicinal fungus that is widely used in Traditional Chinese Medicines as well as in modern applications. Retinoid X receptor (RXR) occupies a central place in nuclear receptor signaling, and a pharmacological RXR-dependent pathway is involved in myeloid cell function. Here, structural information for 82 triterpenes from P. cocos and 17 known RXR agonists was collected in a compound library and retrieved for a molecular docking study. Three triterpenes, 16α-hydroxytrametenolic acid (HTA), pachymic acid (PA), and polyporenic acid C (PPAC), were identified as novel RXR-specific agonists based on luciferase reporter assays and in silico evidence. Treatment with HTA, PA, and PPAC significantly induced differentiation of the human promyelocytic leukemia cell line HL-60 with EC50 values of 21.0 ± 0.52, 6.7 ± 0.37, and 9.4 ± 0.65 µM, respectively. These effects were partly blocked by the RXR antagonist UVI3003, suggesting that an RXR-dependent pathway may play an important role in their anti-acute promyelocytic leukemia (APL) effects. Taken together, triterpenes from P. cocos are revealed as naturally occurring RXR selective agonists with the potential for anti-cancer activity. These results suggest a novel approach to the treatment or prevention of APL.

Oxymatrine exerts organ- and tissue-protective effects by regulating inflammation, oxidative stress, apoptosis, and fibrosis: From bench to bedside.

Oxymatrine is a quinazine alkaloid extracted from Sophora flavescens with various therapeutic effects such as organ- and tissue-protective, anti-inflammatory, anti-cancer, and anti-viral effects. In this review, we summarize the protective effects of oxymatrine on damaged organs and tissues by analyzing both in vivo and in vitro studies. The mechanisms of protective effects of oxymatrine are mainly related to its anti-inflammatory, anti-oxidative stress, anti- or pro-apoptotic, anti-fibrotic, metabolism-regulation, and anti-nociceptive functions. In addition, a variety of signal pathways, cells, and molecules are influenced by oxymatrine, and by these comprehensive actions, maximum therapeutic effects can be achieved. Furthermore, we summarize the protective effects in clinical studies and adverse effects of oxymatrine. It is believed that through more in-depth animal experiments and standardized clinical research, oxymatrine holds a bright future in the process of organ and tissue protection and has a significant therapeutic promise to translate from bench to bedside.

Investigation of Crystal Structures in Structure-Based Virtual Screening for Protein Kinase Inhibitors.

Protein kinases are important drug targets in several therapeutic areas ,and structure-based virtual screening (SBVS) is an important strategy in discovering lead compounds for kinase targets. However, there are multiple crystal structures available for each target, and determining which one is the most favorable is a key step in molecular docking for SBVS due to the ligand induce-fit effect. This work aimed to find the most desirable crystal structures for molecular docking by a comprehensive analysis of the protein kinase database which covers 190 different kinases from all eight main kinase families. Through an integrated self-docking and cross-docking evaluation, 86 targets were eventually evaluated on a total of 2608 crystal structures. Results showed that molecular docking has great capability in reproducing conformation of crystallized ligands and for each target, the most favorable crystal structure was selected, and the AGC family outperformed the other family targets based on RMSD comparison. In addition, RMSD values, GlideScore, and corresponding bioactivity data were compared and demonstrated certain relationships. This work provides great convenience for researchers to directly select the optimal crystal structure in SBVS-based kinase drug design and further validates the effectiveness of molecular docking in drug discovery.

Investigation of Machine Intelligence in Compound Cell Activity Classification.

Machine intelligence has been greatly developed in the past decades and has been widely used in many fields. In the recent years, many reports have shown its satisfactory effect in drug discovery. In this study, machine intelligence methods were explored to assist the cell activity prediction. Multiple machine intelligence methods including support vector machine, decision tree, random forest, extra trees, gradient boosting machine, convolutional neural network, long short-term memory network, and gated recurrent unit network were employed to separate compounds based on their cell activity. Different from some reported classification models, compounds were expressed as a string by the simplified molecular input line entry system and directly used as input rather than any chemical descriptors, which mimicked natural language processing. Both the single cell strain and whole data set under the balanced and imbalanced data distributions were discussed, respectively. Different activity cutoffs were set for the single (Z-score = 3) and the whole (Z-score = 5 and 6) data set. Nine metrics were used to evaluate the models including accuracy, precision, recall, f1-score, area under the receiver operating characteristic curve score, Cohen's κ, Brier score, Matthews correlation coefficient, and balanced accuracy. The results show that the gradient boosting machine is competent at balanced data distribution, and convolutional neural network is qualified for the imbalanced one. The results demonstrate that both classic machine learning methods and deep learning methods have potential in classification of compound cell activity.

Efficacy and safety of Xinnaoning capsule in treating chronic stable angina (qi stagnation and blood stasis syndrome): Study protocol for a multicenter, randomized, double-blind, placebo-controlled trial.

BACKGROUND: Chronic stable angina (CSA) is a cardiovascular disease with high prevalence. At present, drug treatment is still the main measure of stable angina pectoris. Traditional Chinese medicine has a long history in the treatment of CSA. Qi stagnation and Blood stasis syndrome is a common syndrome of CSA. Xinnaoning (XNN) capsule is considered as an effective adjuvant treatment for CSA with the efficacy of promoting qi and blood circulation but lack of high-quality clinical evidence. The purpose of this study is to evaluate the efficacy and safety of XNN capsule compared with placebo by clinical trial. METHODS: This multicenter, randomized, double-blind, placebo-controlled trial will be conducted with a total of 240 participants diagnosed with chronic stable angina (qi stagnation and blood stasis syndrome). The participants will be randomized (1:1) into groups receiving either XNN or placebo for 12 weeks. After a 2-week run-in period, they will receive either XNN or placebo (3 pills, 3 times daily) for 12 weeks on the basis of conventional therapy. The primary outcomes include changes in the integral scores of angina symptoms. The secondary outcome measures include changes in the total score of traditional Chinese medicine syndrome, severity grading of angina pectoris, the number of angina pectoris per week, nitroglycerin dosage, score of seattle angina scale, serum homocysteine, incidence of cardiovascular events. Safety outcomes will also be assessed. Adverse events will be monitored throughout the trial. RESULTS: This study will investigate whether XNN capsule can alleviate clinical symptoms, and improve quality of life of patients with chronic stable angina (qi stagnation and blood stasis syndrome). The results of this study will provide clinical evidence for the application of XNN capsule in the treatment of chronic stable angina. TRIAL REGISTRATION: ClinicalTrials.gov: NCT03914131.

In Silico Prediction of Human Intravenous Pharmacokinetic Parameters with Improved Accuracy.

Human pharmacokinetics is of great significance in the selection of drug candidates, and in silico estimation of pharmacokinetic parameters in the early stage of drug development has become the trend of drug research owing to its time- and cost-saving advantages. Herein, quantitative structure-property relationship studies were carried out to predict four human pharmacokinetic parameters including volume of distribution at steady state (VDss), clearance (CL), terminal half-life (t1/2), and fraction unbound in plasma (fu), using a data set consisting of 1352 drugs. A series of regression models were built using the most suitable features selected by Boruta algorithm and four machine learning methods including support vector machine (SVM), random forest (RF), gradient boosting machine (GBM), and XGBoost (XGB). For VDss, SVM showed the best performance with R2test = 0.870 and RMSEtest = 0.208. For the other three pharmacokinetic parameters, the RF models produced the superior prediction accuracy (for CL, R2test = 0.875 and RMSEtest = 0.103; for t1/2, R2test = 0.832 and RMSEtest = 0.154; for fu, R2test = 0.818 and RMSEtest = 0.291). Assessed by 10-fold cross validation, leave-one-out cross validation, Y-randomization test and applicability domain evaluation, these models demonstrated excellent stability and predictive ability. Compared with other published models for human pharmacokinetic parameters estimation, it was further confirmed that our models obtained better predictive ability and could be used in the selection of preclinical candidates.

Prediction of hERG K+ channel blockage using deep neural networks.

Human ether-a-go-go-related gene (hERG) K+ channel blockage may cause severe cardiac side-effects and has become a serious issue in safety evaluation of drug candidates. Therefore, improving the ability to avoid undesirable hERG activity in the early stage of drug discovery is of significant importance. The purpose of this study was to build predictive models of hERG activity by deep neural networks. For each combination of sampling methods and descriptors, deep neural networks with different architectures were implemented to build classification models. The optimal model M15 with three hidden layers, undersampling method, and 2D descriptors yielded the prediction accuracy of 0.78 and F1 score of 0.75 on the test set as well as accuracy of 0.77 and F1 score of 0.34 on the external validation set, outperforming the other 35 models including 9 random forest models. Particularly, the optimal model M15 achieved the highest F1 score and the second highest accuracy when compared with other five methods from four groups using different machine learning algorithms with the same external validation set. It can be believed that this model has powerful capability on prediction of hERG toxicity, which is of great benefit for developing novel drug candidates.

A combined drug discovery strategy based on machine learning and molecular docking.

Data mining methods based on machine learning play an increasingly important role in drug design and discovery. In the current work, eight machine learning methods including decision trees, k-Nearest neighbor, support vector machines, random forests, extremely randomized trees, AdaBoost, gradient boosting trees, and XGBoost were evaluated comprehensively through a case study of ACC inhibitor data sets. Internal and external data sets were employed for cross-validation of the eight machine learning methods. Results showed that the extremely randomized trees model performed best and was adopted as the first step of virtual screening. Together with structure-based virtual screening in the second step, this combined strategy obtained desirable results. This work indicates that the combination of machine learning methods with traditional structure-based virtual screening can effectively strengthen the ability in finding potential hits from large compound database for a given target.

Virtual Screening Strategy Combined Bayesian Classification Model, Molecular Docking for Acetyl-CoA Carboxylases Inhibitors.

INTRODUCTION: Acetyl-CoA Carboxylases (ACC) have been an important target for the therapy of metabolic syndrome, such as obesity, hepatic steatosis, insulin resistance, dyslipidemia, non-alcoholic fatty liver disease (NAFLD), non-alcoholic steatohepatitis (NASH), type 2 diabetes (T2DM), and some other diseases. METHODS: In this study, virtual screening strategy combined with Bayesian categorization modeling, molecular docking and binding site analysis with protein ligand interaction fingerprint (PLIF) was adopted to validate some potent ACC inhibitors. First, the best Bayesian model with an excellent value of Area Under Curve (AUC) value (training set AUC: 0.972, test set AUC: 0.955) was used to screen compounds of validation library. Then the compounds screened by best Bayesian model were further screened by molecule docking again. RESULTS: Finally, the hit compounds evaluated with four percentages (1%, 2%, 5%, 10%) were verified to reveal enrichment rates for the compounds. The combination of the ligandbased Bayesian model and structure-based virtual screening resulted in the identification of top four compounds which exhibited excellent IC 50 values against ACC in top 1% of the validation library. CONCLUSION: In summary, the whole strategy is of high efficiency, and would be helpful for the discovery of ACC inhibitors and some other target inhibitors.