Influence of Interface Modification on the Moisture Absorption and Thermal Resistance of Ramie Fiber/Degradable Epoxy Composites.

Natural fiber/degradable epoxy composites have received much attention for their advantages of low carbon emissions, low environmental pollution, and utilization of renewable resources. However, the poor interfacial bonding strength and inferior moisture resistance of natural fiber/degradable epoxy composites restrict their application areas. In order to improve the moisture and heat resistance of natural fiber/degradable epoxy resin-based composites, this study modified the surfaces of ramie fibers with hydroxylated carbon nanotubes, silane coupling agents, and sodium hydroxide, respectively. Three types of modified ramie fiber/degradable epoxy composites, namely F-CN-DEP, F-Si-DEP, and F-OH-DEP, were prepared using a winding forming process. The water absorption rate and short-beam shear strength of the materials were tested under different environments, and the fiber morphology and thermal-mechanical properties of the materials were investigated by scanning electron microscopy (SEM) and dynamic mechanical analysis (DMA). The results show that F-CN-DEP exhibited the lowest moisture absorption rate; the highest shear strength, of 43.8 MPa; and a glass transition temperature (Tg) of 121.7 °C. The results demonstrate that carbon nanotubes on the fiber surface can improve the interfacial stability of ramie fiber/degradable epoxy composites in humid and hot environments. These results give guidelines for the development of natural fiber/degradable epoxy composites.

Lightweight ZnO/Carbonated Cotton Fiber Nanocomposites for Electromagnetic Interference Applications: Preparation and Properties.

Electromagnetic wave pollution has become a significant harm posed to human health and precision instruments. To shelter such instruments from electromagnetic radiation, high-frequency electromagnetic interference (EMI) shielding materials are extremely desirable. The focus of this research is lightweight, high-absorption EMI shielding composites. Simple aqueous dispersion and drying procedures were used to prepare cotton fiber (CF)-based sheets combined with various zinc oxide (ZnO) contents. These composites were carbonated in a high-temperature furnace at 800 °C for two hours. The obtained CF/ZnO samples have densities of 1.02-1.08 g/cm3. The EMI shielding effectiveness of CF-30% ZnO, CF-50% ZnO, and CF-70% ZnO reached 32.06, 38.08, and 34.69 dB, respectively, to which more than 80% of absorption is attributed. The synergetic effects of carbon networks and surface structures are responsible for the high EMI shielding performance; various reflections inside the interconnected networks may also help in improving their EMI shielding performance.

Effects of rice-prawn (Macrobrachium nipponense) co-culture on the microbial community of soil.

In the Lixiahe region of China, co-culture has been rapidly promoted in flooded paddy fields owing to its ecological and economic benefits. Rice-prawn co-culture can reduce the damage of crab and shrimp to rice growth and paddy field and substantially change the soil microbial community and soil fertility. In this study, we compared changes in the soil microbial community and soil fertility in waterlogged paddies under conventional rice culture (CR), rice-prawn (Macrobrachium nipponense) co-culture (RP), and pond culture (PC). The microbial abundance in RP was significantly higher than that in CR. RP soil microbial diversity was significantly higher than PC soil microbial diversity. The dominant bacteria in RP soil were Proteobacteria, Chloroflexi, and Bacteroidetes. Compared with those in CR, total organic matter (TOM) and total nitrogen in RP were relatively stable, available potassium and available phosphorus (AP) decreased, and other indicators increased significantly. Soil fertility significantly benefited from co-culture, with total organic carbon (TOC) increasing. Interactive relationship analysis showed that TOM, TOC, AP, and NH4+-N were the main factors affecting the microbial community. Co-occurrence network analyses showed that network modularity increased with co-culture, indicating that a unique soil microbial community formed under co-culture, improving the adaptability and tolerance to co-culture. Thus, RP is a suitable culture method for this commercially important species. The results of this study can inform the practical operation of fertilizer use and sustainable development of rice-prawn aquaculture systems. KEY POINTS: • Microbial abundance and diversity increased under rice-prawn co-culture. • Co-culture significantly improved soil fertility, with an increase in TOC. • Rice-prawn co-culture is an ecologically suitable culture method for prawns.

TRPM2-AS promotes the malignancy of osteosarcoma cells by targeting miR-15b-5p/PPM1D axis.

Osteosarcoma (OS) is a malignant tumor with a low survival rate and a high incidence rate worldwide. Although research has reported the involvement of long non-coding RNAs (lncRNAs) in the pathogenesis of OS cells, the role of TRPM2-AS, miR-15b-5p, and PPM1D in OS progression remains unclear. This study aimed to examine the interaction of the TRPM2-AS/miR-15b-5p/PPM1D axis in OS cells to gain new insights into the molecular mechanism and pathogenesis of OS. After performing in vitro functional assays, we discovered that TRPM2-AS was overexpressed in OS cells. TRPM2-AS silencing impaired OS cell viability, proliferation, and migration, while it induced apoptosis in OS cells in vitro. Our experimental analysis also revealed that PPM1D is a direct target of miR-15b-5p. TRPM2-AS silencing was found to reverse the tumorigenic effect of the miR-15b-5p inhibitor, while the miR-15b-5p inhibitor restored the inhibition of OS caused by silencing PPM1D. Moreover, our findings revealed that miR-15b-5p exerted its tumor-suppressive role by directly targeting PPM1D. In conclusion, this study suggests that TRPM2-AS could promote OS cell malignancy by sponging miR-15b-5p/PPM1D axis.

Research progress on metformin in the prevention and treatment for oral diseases / 口腔疾病防治

@#Metformin is currently the first-line drug for the treatment of diabetes. In addition to its hypoglycemic effect, it has also been found to have other potential effects, such as anti-inflammatory, odontogenic differentiation-promoting, osteogenic differentiation-promoting, and antitumor effects. Previous studies have shown that metformin can promote the healing of periapical lesions, and its mechanism may be related to the promotion of osteogenic differentiation and the induction of dental pulp cell differentiation by activation of adenylate-activated protein kinase by dimethyldiphosphate. Clinical indexes, such as the probing depth, attachment loss level and probing bleeding index, were significantly improved in patients with periodontitis treated with metformin, which may play a role in the prevention and treatment of periodontal disease by promoting the proliferation, migration and osteogenic differentiation of periodontal ligament stem cells. Metformin has been proven to inhibit the growth and proliferation of tumor cells and plays an important role in the prevention and treatment of oral tumors such as oral squamous cell carcinoma. At present, research remains in the in vitro and animal experimental stage, and the related mechanism needs to be further explored. Clinical trials remain in the evaluation of clinical indicators, so large-scale, long-term, multicenter, randomized controlled clinical trials need to be further developed

Oral mosapride can provide additional anti-emetic efficacy following total joint arthroplasty under general anesthesia: a randomized, double-blinded clinical trial.

BACKGROUND: We sought to determine (1) whether the addition of prophylactic oral mosapride to a protocol including dexamethasone and ondansetron further reduces postoperative nausea and vomiting (PONV) compared with ondansetron alone or the combination of both; (2) whether preemptive application of oral mosapride provides additional clinical benefits for bowel function and appetite, thus improving functional recovery. METHODS: We randomized 240 patients undergoing total hip and knee arthroplasty to receive placebo (Control, n = 80), dexamethasone (10 mg) before anesthesia induction (Dexa, n = 82), or dexamethasone (10 mg) before anesthesia induction as well as oral mosapride (5 mg) before and after surgery (Mosa+Dexa, n = 78). Patients were assessed at 0-6, 6-12, 12-24, and 24-48 h postoperatively. Primary outcomes were incidence and severity of PONV as well as complete response. Secondary outcomes were appetite, time until first defecation and ambulation, patient satisfaction score, and length of hospital stay. RESULTS: Mosa+Dexa patients showed significantly lower incidence of nausea at 6-12 h (3.8%) and over the entire evaluation period (6.4%), as well as a higher rate of complete response (89.7%) than other patients. Mosa+Dexa patients required less time to achieve first defecation and ambulation, they were hospitalized for shorter time, and they were more satisfied with clinical care. CONCLUSION: Addition of oral mosapride further reduced incidence of PONV, especially postoperative nausea, during 6-12 h postoperatively. Moreover, preemptive application of oral mosapride can further improve appetite, bowel function, ambulation and length of hospital stay. TRIAL REGISTRATION: The study protocol was registered at the Chinese Clinical Trial Registry ( ChiCTR1800015896 ), prospectively registered on 27/04/2018.

In Silico Prediction of Metabolic Epoxidation for Drug-like Molecules via Machine Learning Methods.

Epoxidation is one of the reactions in drug metabolism. Since epoxide metabolites would bind with proteins or DNA covalently, drugs should avoid epoxidation metabolism in the body. Due to the instability of epoxide, it is difficult to determine epoxidation experimentally. In silico models based on big data and machine learning methods are hence valuable approaches to predict whether a compound would undergo epoxidation. In this study, we collected 884 epoxidation data manually from various sources, and finally got 829 unique sites of epoxidation. Three types of molecular fingerprints with different lengths (1024, 2048 or 4096 bits) were used to describe the reaction sites. Six machine learning methods were used to build the classification models. The training set and test set were randomly divided into 8 : 2, and 54 models were constructed and evaluated. Four best models were selected for feature selection. The features were then chosen and verified by external validation set. The resulted optimal model had the accuracy and AUC (area under the curve) values at 0.873 and 0.944 for the test set, 0.838 and 0.987 for the external validation set, respectively. The models built in this study could accurately predict whether a compound will undergo epoxidation and which part is most susceptible to epoxidation, which is of great significance for drug design.

Effect of Ginsenoside Rg1 on the intervertebral disc degeneration rats and the degenerative pulposus cells and its mechanism.

OBJECTIVE: To explore the effect of ginsenoside Rg1 on intervertebral disc degeneration (IVDD) in vivo and in vitro and its mechanism. METHODS: 60 rats were underwent surgery to construct rat models of IVDD and divided in the sham group, model group and gradient G-Rg1 groups (10 mg/kg/d, 20 mg/kg/d and 40 mg/kg/d).The change of histology was observed by HE staining, the water content and the expression of ß-catenin in IVD were detected. Rat nucleus pulposus cells(NPCs) were isolated from IVDD rats and divided in D-NPCs group, and gradient G-Rg1 groups(20 µg/ml, 50 µg/ml and 100 µg/ml).The cell proliferation activity, cell apoptosis rate,the expression of proteins related to ECM and Wnt/ß-catenin were detected respectively, Finally the agonist of Wnt/ß-catenin pathway LiCl was used for reversed experiments. RESULTS: In vivo, G-Rg1 treatment could improve the structural disorganization, low water content, NPCs number and aggrecan and collagenⅡ expression in IVD and down-regulate the expression of ß-catenin. In vitro NPCs, G-Rg1 treatment could improve the low cell proliferation, high apoptosis rate and low expression of aggrecan and collagenⅡ in degenerative NPCs in a dose-dependent manner.G-Rg1 treatment could down-regulate the expression of proteins related to ß-catenin signal and LiCl could reverse the increase of cell proliferation and ECM synthesis, decrease of apoptosis of degenerative NPCs induced by G-Rg1. CONCLUSION: G-Rg1 could promote ECM synthesis of degenerative NPCs and inhibiting its apoptosis, improve the IVDD via inhibiting the Wnt/ß-catenin pathway.

Insights into the interaction mechanisms of estrogen-related receptor alpha (ERRα) with ligands via molecular dynamics simulations.

Estrogen-related receptor alpha (ERRα), a member of nuclear receptors (NRs), participates in energy metabolism. Recent experiments identified that several agonists to increase the activity of ERRα, which have a therapeutic effect in improving insulin sensitivity and lowering blood glucose levels. However, the detailed molecular mechanism about how the ligands affect the structure of ERRα remains elusive. To better understand the conformational change of ERRα complexed with agonists and inverse agonists, unbiased molecular dynamics (MD) simulations were performed on the ligand binding domain of ERRα (ERRα-LBD) bound with different ligands. According to the results, the ERRα-agonist interactions were more stable in the presence of the peroxisome proliferator-activated receptor γ coactivator 1α (PGC-1α). More importantly, we observed that the binding of inverse agonists would decrease the stability of helix 12 (H12) of ERRα. Moreover, we suggested that Phe232 and Phe414 should be key residues in the interaction pathway from ligands to H12, which provided a possible explanation about how ligands impact the structure of ERRα. These results would provide insights into the design of novel and efficient agonists of ERRα to treat metabolic diabetes.Communicated by Ramaswamy H. Sarma.

Design, synthesis and biological evaluation of chalcones as reversers of P-glycoprotein-mediated multidrug resistance.

Overexpression of P-glycoprotein (P-gp) is one of the major causes for multidrug resistance (MDR), which has become a major obstacle in cancer therapy. One hopeful approach to reverse the MDR is to develop inhibitors of P-gp in expression and/or function. Here, we designed and synthesized a series of chalcone derivatives as P-gp inhibitors and evaluated their potential reversal activities against MDR. Among them, the most active compound MY3 had little intrinsic cytotoxicity and showed the highest activity (RF = 50.19) in reversing DOX resistance in MCF-7/DOX cells. Further studies demonstrated that MY3 could increase intracellular accumulation of DOX and inhibit expression of P-gp at mRNA and protein levels. More importantly, MY3 significantly enhanced the efficacy of DOX against the tumor xenografts bearing MCF-7/DOX cells with the precondition of unchanged body weight. Therefore, MY3 might represent a promising lead to develop MDR reversal agents for cancer chemotherapy.

In silico prediction of chemical aquatic toxicity for marine crustaceans via machine learning.

Aquatic toxicity is a crucial endpoint for evaluating chemically adverse effects on ecosystems. Therefore, we developed in silico methods for the prediction of chemical aquatic toxicity in marine environment. At first, a diverse data set including different crustacean species was constructed. We then built local binary models using Mysidae data and global binary models using Mysidae, Palaemonidae, and Penaeidae data. Molecular fingerprints and descriptors were employed to represent chemical structures separately. All the models were built by six machine learning methods. The AUC (area under the receiver operating characteristic curve) values of the better local and global models were around 0.8 and 0.9 for the test sets, respectively. We also identified several chemicals with selective toxicity on different species. The analysis of selective toxicity would promote to design greener chemicals in a specific environment. Finally, to understand and interpret the models, we explored the relationships between chemical aquatic toxicity and the molecular descriptors. Our study would be helpful in gaining further insights into marine organisms, prediction of chemical aquatic toxicity and prioritization of environmental hazard assessment.

Insights into mechanisms and severity of drug-induced liver injury via computational systems toxicology approach.

Liver is the central place for drug metabolism. Drug-induced liver injury (DILI) is hence inevitable, and has become one of the leading causes for drug failure in development and drug withdrawal from the market. Due to lack of reliable preclinical and in vivo toxicology test conditions, it is time-consuming, laborious and costly to interpret the mechanisms of DILI through bioassays. In this paper, we developed a computational systems toxicology approach to investigate the molecular mechanisms of DILI. Totally 1478 DILI compounds were collected, together with 1067 known targets for 896 DILI compounds. Then, 173 new potential targets of these compounds were predicted by our bSDTNBI (balanced substructure-drug-target network-based inference) method. After network analysis, 145 primary genes were found to relate with hepatotoxicity and have higher expression in liver, among which 26 genes were predicted by our method, such as CYP2E1, GSTA1, EPHX1, ADH1B, ADH1C, ALDH2, F7, and IL2. A scoring function, DILI-Score, was further proposed to assess the hepatotoxic severity of a given compound. Finally, as case studies, we analyzed the mechanisms of DILI from the perspective of off-targets, and found out the pivotal genes for liver injuries induced by tyrosine kinase inhibitors and TAK-875. This work would be helpful for better understanding mechanisms of DILI and provide clues for reducing risk of DILI.

Prediction of the skin sensitising potential and potency of compounds via mechanism-based binary and ternary classification models.

Skin sensitisation, one of the most frequent forms of human immune toxicity, is authenticated to be a significant endpoint in the field of drug discovery and cosmetics. Due to the drawbacks of traditional animal testing methods, in silico methods have advanced to study skin sensitisation. In this study, mechanism-based binary and ternary classification models were constructed with a comprehensive data set. 1007 compounds were collected to develop five series of local and global models based on mechanisms. In each series, compounds were classified into five groups according to EC3 values, and applied as training sets, test sets and external validation sets. For each of the five series, 81 binary classification models and 81 ternary classification models were acquired via 9 molecular fingerprints and 9 machine learning methods using a novel KNIME workflow. Meanwhile, the applicability domains for the best 10 models were figured out to certify the rationality of prediction effect. In addition, 8 toxic substructures probably causing skin sensitisation were identified to speculate whether a compound is a skin sensitiser. The mechanism-based prediction models and the toxic substructures can be applied to predict the skin sensitising potential and potency of compounds.

A Causal Relationship in Spinal Cord Injury Rat Model Between Microglia Activation and EGFR/MAPK Detected by Overexpression of MicroRNA-325-3p.

Microglial activation and inflammatory response played an important role in the secondary injury of spinal cord injury (SCI). Several microRNAs were associated with this procedure, but the underlying molecular mechanism was poorly understood. Sprague-Dawley (SD) rats were divided into four groups: SCI group (n = 7), agomiR-325-3p group (n = 7), and their control groups. Expression of miR-325-3p and proteins in epidermal growth factor receptor (EGFR)/mitogen-activated protein kinase (MAPK) signaling pathway was evaluated in microglia from SCI rats and primary microglia/BV2 cells activated by lipopolysaccharide (LPS). Concentrations of interleukin-1ß (IL-1ß) and tumor necrosis factor α (TNF-α) in supernatants were measured by ELISA. Low expression of miR-325-3p and activation of EGFR/MAPK was observed in microglia of SCI and LPS-induced primary microglia. Overexpression of miR-325-3p in LPS-induced BV2 cells inhibited microglial activation and release of TNF-α and IL-1ß. Luciferase reporter assay confirmed that miR-325-3p negatively regulated EGFR by targeting its 3'-untranslated regions. Additionally, agomiR-325-3p inhibited the activation of microglia and EGFR/MAPK, alleviating the inflammatory response. These results indicated that miR-325-3p attenuated secondary injury after SCI through inhibition of EGFR/MAPK signaling pathway, the microglial activation, and the release of inflammatory cytokines, suggesting that miR-325-3p may be employed as a therapeutic target for SCI.

ADMET-score - a comprehensive scoring function for evaluation of chemical drug-likeness.

Chemical absorption, distribution, metabolism, excretion, and toxicity (ADMET), play key roles in drug discovery and development. A high-quality drug candidate should not only have sufficient efficacy against the therapeutic target, but also show appropriate ADMET properties at a therapeutic dose. A lot of in silico models are hence developed for prediction of chemical ADMET properties. However, it is still not easy to evaluate the drug-likeness of compounds in terms of so many ADMET properties. In this study, we proposed a scoring function named the ADMET-score to evaluate drug-likeness of a compound. The scoring function was defined on the basis of 18 ADMET properties predicted via our web server admetSAR. The weight of each property in the ADMET-score was determined by three parameters: the accuracy rate of the model, the importance of the endpoint in the process of pharmacokinetics, and the usefulness index. The FDA-approved drugs from DrugBank, the small molecules from ChEMBL and the old drugs withdrawn from the market due to safety concerns were used to evaluate the performance of the ADMET-score. The indices of the arithmetic mean and p-value showed that the ADMET-score among the three data sets differed significantly. Furthermore, we learned that there was no obvious linear correlation between the ADMET-score and QED (quantitative estimate of drug-likeness). These results suggested that the ADMET-score would be a comprehensive index to evaluate chemical drug-likeness, and might be helpful for users to select appropriate drug candidates for further development.

In Silico Prediction of Endocrine Disrupting Chemicals Using Single-Label and Multilabel Models.

Endocrine disruption (ED) has become a serious public health issue and also poses a significant threat to the ecosystem. Due to complex mechanisms of ED, traditional in silico models focusing on only one mechanism are insufficient for detection of endocrine disrupting chemicals (EDCs), let alone offering an overview of possible action mechanisms for a known EDC. To remove these limitations, in this study both single-label and multilabel models were constructed across six ED targets, namely, AR (androgen receptor), ER (estrogen receptor alpha), TR (thyroid receptor), GR (glucocorticoid receptor), PPARg (peroxisome proliferator-activated receptor gamma), and aromatase. Two machine learning methods were used to build the single-label models, with multiple random under-sampling combining voting classification to overcome the challenge of data imbalance. Four methods were explored to construct the multilabel models that can predict the interaction of one EDC against multiple targets simultaneously. The single-label models of all the six targets have achieved reasonable performance with balanced accuracy (BA) values from 0.742 to 0.816. Each top single-label model was then joined to predict the multilabel test set with BA values from 0.586 to 0.711. The multilabel models could offer a significant boost over the single-label baselines with BA values for the multilabel test set from 0.659 to 0.832. Therefore, we concluded that single-label models could be employed for identification of potential EDCs, while multilabel ones are preferable for prediction of possible mechanisms of known EDCs.

Computational insights into the interaction mechanisms of estrogen-related receptor alpha with endogenous ligand cholesterol.

Estrogen-related receptor alpha (ERRα) has attracted increasing concerns. ERRα, orphan nuclear receptor, plays important roles in energy metabolism. Therefore, small molecule agonists of ERRα could be a potential therapeutic strategy in the treatment of metabolic diseases such as diabetes. Recently, Wei et al. identified cholesterol as the endogenous agonist of ERRα. However, the detailed molecular mechanism of cholesterol bound with ERRα remains ambiguous. Thus, in this study molecular docking and molecular dynamics (MD) simulations were performed to characterize how cholesterol affects the behavior of ERRα. Based on the results, we found that a proven residue Phe232 and others including Leu228, Glu235, Arg276, and Phe399 were key residues to ligand binding. A hydrogen-bonding interaction between cholesterol and Glu235 ensured the orientation of the ligand in the binding pocket, while hydrophobic interactions between cholesterol and the above-mentioned residues promoted the stability of ERRα-cholesterol complex. In the presence of the proliferator-activated receptor γ coactivator 1α (PGC-1α), the cholesterol-ERRα interaction became more stable. Interestingly, we observed that cholesterol facilitated the binding of ERRα with its coactivator PGC-1α via stabilizing the conformation of helix 12 and the interaction surface of ERRα/PGC-1α. Overall, these findings would be valuable for the future rational design of novel ERRα agonists.

admetSAR 2.0: web-service for prediction and optimization of chemical ADMET properties.

SUMMARY: admetSAR was developed as a comprehensive source and free tool for the prediction of chemical ADMET properties. Since its first release in 2012 containing 27 predictive models, admetSAR has been widely used in chemical and pharmaceutical fields. This update, admetSAR 2.0, focuses on extension and optimization of existing models with significant quantity and quality improvement on training data. Now 47 models are available for either drug discovery or environmental risk assessment. In addition, we added a new module named ADMETopt for lead optimization based on predicted ADMET properties. AVAILABILITY AND IMPLEMENTATION: Free available on the web at http://lmmd.ecust.edu.cn/admetsar2/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

LINC00969 promotes the degeneration of intervertebral disk by sponging miR-335-3p and regulating NLRP3 inflammasome activation.

Long noncoding RNAs (LncRNAs) may serve as miRNA sponges to regulate the expressions of miRNA target genes. LncRNA LINC00969 has been indicated to be upregulated in intervertebral disk degeneration. However, the regulatory mechanism of LINC00969 in intervertebral disk degeneration progression remains unclear. Differently expressed LINC00969, miR-335-3p, and thioredoxin-interacting protein (TXNIP) were determined in nucleus pulposus (NP) tissues and cells isolated from patients with intervertebral disk degeneration. The interaction between LINC00969, miR-335-3p, and TXNIP was also assessed. In this study, we demonstrated that LINC00969 was highly expressed, whereas miR-335-3p was aberrantly downregulated in NP tissues and cells of intervertebral disk degeneration patients. In addition, our results suggested that LINC00969 enhanced NP cell apoptosis. More importantly, LINC00969 was identified to function as a competitive endogenous RNA (ceRNA) for miR-335-3p to positively regulate TXNIP expression in vitro. Our study provided evidence for the cross-talk between LINC00969, miR-335-3p, and TXNIP, shedding light on the therapy for intervertebral disk degeneration. © 2018 IUBMB Life, 71(5):611-618, 2019.

Computational Prediction of Site of Metabolism for UGT-Catalyzed Reactions.

The investigation of metabolically liable sites of xenobiotics mediated by UDP-glucuronosyltransferases (UGTs) is important for lead optimization in early drug discovery. However, it is time-consuming and costly to identify potentially susceptible sites experimentally. Hence, in silico approaches have been developed to predict the site of metabolism (SOM) of UGT-catalyzed substrates. In the present work, four major types of reactions catalyzed by UGTs were collected from the Handbook of Metabolic Pathways of Xenobiotics along with their corresponding glucuronidation products. These observed and nonobserved SOMs were identified and encoded by atom environment fingerprints. Four resampling methods were performed to treat data imbalance, while four feature selection methods were utilized to choose appropriate features. Three tree-form machine learning algorithms were conducted to build discriminating models, and optimal models were then obtained for the different types of reaction. The results indicated that all of the chosen best models showed area under the curve values ranging from 0.713 to 0.869 for two independent external validation sets. Our study could supply valuable information for optimization of pharmacokinetic profiles and contribute to metabolism prediction.