Predicting Drug-drug Interaction with Graph Mutual Interaction Attention Mechanism.

Effective representation of molecules is a crucial step in AI-driven drug design and drug discovery, especially for drug-drug interaction (DDIs) prediction. Previous work usually models the drug information from the drug-related knowledge graph or the single drug molecules, but the interaction information between molecular substructures of drug pair is seldom considered, thus often ignoring the influence of bond information on atom node representation, leading to insufficient drug representation. Moreover, key molecular substructures have significant contribution to the DDIs prediction results. Therefore, in this work, we propose a novel Graph learning framework of Mutual Interaction Attention mechanism (called GMIA) to predict DDIs by effectively representing the drug molecules. Specifically, we build the node-edge message communication encoder to aggregate atom node and the incoming edge information for atom node representation and design the mutual interaction attention decoder to capture the mutual interaction context between molecular graphs of drug pairs. GMIA can bridge the gap between two encoders for the single drug molecules by attention mechanism. We also design a co-attention matrix to analyze the significance of different-size substructures obtained from the encoder-decoder layer and provide interpretability. In comparison with other recent state-of-the-art methods, our GMIA achieves the best results in terms of area under the precision-recall-curve (AUPR), area under the ROC curve (AUC), and F1 score on two different scale datasets. The case study indicates that our GMIA can detect the key substructure for potential DDIs, demonstrating the enhanced performance and interpretation ability of GMIA.

Non-invasive transdermal delivery of biomacromolecules with fluorocarbon-modified chitosan for melanoma immunotherapy and viral vaccines.

Transdermal drug delivery has been regarded as an alternative to oral delivery and subcutaneous injection. However, needleless transdermal delivery of biomacromolecules remains a challenge. Herein, a transdermal delivery platform based on biocompatible fluorocarbon modified chitosan (FCS) is developed to achieve highly efficient non-invasive delivery of biomacromolecules including antibodies and antigens. The formed nanocomplexes exhibits effective transdermal penetration ability via both intercellular and transappendageal routes. Non-invasive transdermal delivery of immune checkpoint blockade antibodies induces stronger immune responses for melanoma in female mice and reduces systemic toxicity compared to intravenous injection. Moreover, transdermal delivery of a SARS-CoV-2 vaccine in female mice results in comparable humoral immunity as well as improved cellular immunity and immune memory compared to that achieved with subcutaneous vaccine injection. Additionally, FCS-based protein delivery systems demonstrate transdermal ability for rabbit and porcine skins. Thus, FCS-based transdermal delivery systems may provide a compelling opportunity to overcome the skin barrier for efficient transdermal delivery of bio-therapeutics.

Transmucosal Delivery of Nasal Nanovaccines Enhancing Mucosal and Systemic Immunity.

Intranasal vaccines can induce protective immune responses at the mucosa surface entrance, preventing the invasion of respiratory pathogens. However, the nasal barrier remains a major challenge in the development of intranasal vaccines. Herein, a transmucosal nanovaccine based on cationic fluorocarbon modified chitosan (FCS) is developed to induce mucosal immunity. In our system, FCS can self-assemble with the model antigen ovalbumin and TLR9 agonist CpG, effectively promoting the maturation and cross-presentation of dendritic cells. More importantly, it can enhance the production of secretory immunoglobin A (sIgA) at mucosal surfaces for those intranasally vaccinated mice, which in the meantime showed effective production of immunoglobulin G (IgG) systemically. As a proof-of-concept study, such a mucosal vaccine inhibits ovalbumin-expressing B16-OVA melanoma, especially its lung metastases. Our work presents a unique intranasal delivery system to deliver antigen across mucosal epithelia and promote mucosal and systemic immunity.

Fe Single Atom Catalysts Promoting Polysulfide Redox Reduction in Quantum Dot Photovoltaics.

Developing cost-effective and highly efficient photocathodes toward polysulfide redox reduction is highly desirable for advanced quantum dot (QD) photovoltaics. Herein, we demonstrate nitrogen doped carbon (N-C) shell-supported iron single atom catalysts (Fe-SACs) capable of catalyzing polysulfide reduction in QD photovoltaics for the first time. Specifically, Fe-SACs with FeN4 active sites feature a power conversion efficiency of 13.7% for ZnCuInSe-QD photovoltaics (AM1.5G, 100 mW/cm2), which is the highest value for ZnCuInSe QD-based photovoltaics, outperforming those of Cu-SACs and N-C catalysts. Compared with N-C, Fe-SACs exhibit suitable energy level matching with polysulfide redox couples, revealed by the Kelvin probe force microscope, which accelerates the charge transferring at the interfaces of catalyst/polysulfide redox couple. Density functional theory calculations demonstrate that the outstanding catalytic activity of Fe-SACs originates from the preferable adsorption of S42- on the FeN4 active sites and the high activation degree of the S-S bonds in S42- initiated by the FeN4 active sites.

Highly Reversible Zn Anodes through a Hydrophobic Interface Formed by Electrolyte Additive.

Hydrogen evolution reaction and dendrite growth seriously break the Zn plating/stripping process at the electrolyte/electrode interface, causing the instability of the Zn anode of aqueous zinc ion batteries. To improve the Zn anode stability and reversibility, we report a new electrolyte additive of aqueous electrolyte with the hydrophobic group. This interfacial hydrophobicity maximises the exclusion of free water from the Zn anode surface, which blocks water erosion and reduces interfacial side reactions. Thus, in an optimal 2 M ZnSO4 electrolyte with 2 g·L-1 Tween-85, the hydrogen evolution reaction and other water-induced undesired reactions can be suppressed, which greatly improves the cycling stability and Coulombic efficiency (CE) of Zn plating/stripping process. The stable cycle time of the Zn//Zn symmetric battery reaches over 1300 h, especially at a high current density and a high areal capacity (more than 650 h at 5 mA·cm-2, 5 mAh·cm-2). The average Coulomb efficiency (CE) of Zn//Ti asymmetric cell achieves 98.11% after 300 cycles. The capacity retention rate of Zn//MnO2 full battery is up to 88.6% after 1000 cycles.

3D Cold-Trap Environment Printing for Long-Cycle Aqueous Zn-Ion Batteries.

Zn powder (Zn-P)-based anodes are always regarded as ideal anode candidates for zinc ion batteries owing to their low cost and ease of processing. However, the intrinsic negative properties of Zn-P-based anodes such as easy corrosion and uncontrolled dendrite growth have limited their further applications. Herein, a novel 3D cold-trap environment printing (3DCEP) technology is proposed to achieve the MXene and Zn-P (3DCEP-MXene/Zn-P) anode with highly ordered arrangement. Benefitting from the unique inhibition mechanism of high lattice matching and physical confinement effects within the 3DCEP-MXene/Zn-P anode, it can effectively homogenize the Zn2+ flux and alleviate the Zn deposition rate of the 3DCEP-MXene/Zn-P anode during Zn plating-stripping. Consequently, the 3DCEP-MXene/Zn-P anode exhibits a superior cycling lifespan of 1400 h with high coulombic efficiency of ≈9.2% in symmetric batteries. More encouragingly, paired with MXene and Co doped MnHCF cathode via 3D cold-trap environment printing (3 DCEP-MXene/Co-MnHCF), the 3DCEP-MXene/Zn-P//3DCEP-MXene/Co-MnHCF full battery delivers high cyclic durability with the capacity retention of 95.7% after 1600 cycles. This study brings an inspired universal pathway to rapidly fabricate a reversible Zn anode with highly ordered arrangement in a cold environment for micro-zinc storage systems.

Effectiveness of Low-Frequency Electrical Stimulation for Radical Hysterectomy Women: Systematic Review and Meta-Analysis.

INTRODUCTION: The aim of the study was to explore the effects of low-frequency electrical stimulation (LFES) in preventing urinary retention after radical hysterectomy (RH) in women with cervical cancer. METHODS: Seven electronic bibliographic databases were searched from inception to December 25, 2021. The mean difference (MD) or risk ratio (RR) with its corresponding 95% CI was selected as effect size. The meta-analysis of all data was conducted using RevMan 5.4 and the evidence was summarized according to GRADE (the grading of recommendation, assessment, development, and evaluation). RESULTS: Twelve randomized control trials consisting of 1,033 women with cervical cancer who had undergone RH were included. Compared with women in the control group, women receiving LFES had improved therapeutic effect (RR = 0.22, 95% CI: 0.16-0.29) and reduced residual urine volume (MD = -32.27, 95% CI: -34.10 to -30.43) and catheter retention time (MD = -4.46, 95% CI: -5.17 to -3.76) following treatment. Muscle strength scores of pelvic floor type I and type II muscle fibers in the LFES group were also higher than in the control group (MD = 1.07, 95% CI: 0.91-1.24). CONCLUSION: LFES may be an effective auxiliary treatment for women with cervical cancer after hysterectomy, which can help reduce the duration of indwelling urethral catheter and residual urine volume.

Creating enzyme-mimicking nanopockets in metal-organic frameworks for catalysis.

Numerous efforts are being made toward constructing artificial nanopockets inside heterogeneous catalysts to implement challenging reactions that are difficult to occur on traditional heterogeneous catalysts. Here, the enzyme-mimetic nanopockets are fabricated inside the typical UiO-66 by coordinating zirconium nodes with terephthalate (BDC) ligands and monocarboxylate modulators including formic acid (FC), acetic acid (AC), or trifluoroacetic acid (TFA). When used in transfer hydrogenation of alkyl levulinates with isopropanol toward γ-valerolactone (GVL), these modulators endow zirconium sites with enhanced activity and selectivity and good stability. The catalytic activity of UiO-66FC is ~30 times that of UiO-66, also outperforming the state-of-the-art heterogeneous catalysts. Distinct from general consensus on electron-withdrawing or electron-donating effect on the altered activity of metal centers, this improvement mainly originates from the conformational change of modulators in the nanopocket to assist forming the rate-determining six-membered ring intermediate at zirconium sites, which are stabilized by van der Waals force interactions.

Metonymy Processing in Chinese: A Linguistic Context-Sensitive Eye-Tracking Preliminary Study.

Current cognitively oriented research on metaphor proposes that understanding metaphorical expressions is a process of building embodied simulations, which are constrained by past and present bodily experiences. However, it has also been shown that metaphor processing is also constrained by the linguistic context but, to our knowledge, there is no comparable work in the domain of metonymy. As an initial attempt to fill this gap, the present study uses eye-tracking experimentation to explore this aspect of Chinese metonymy processing. It complements previous work on how the length of preceding linguistic context influences metonymic processing by focusing on: (1) the contextual information of both the preceding target words; (2) the immediate spillover after the target words; and (3) whether the logical relationship between the preceding contextual information and the target word is strong or weak (a 2 × 2 between-subject experiment with target words of literal/metonymy and logic of strong/weak). Results show that readers take longer to arrive at a literal interpretation than at a metonymic one when the preceding information is in a weak logic relationship with target words, although this disparity can disappear when the logic is strong. Another finding is that both the preceding and the spillover contextual information contribute to metonymy processing when the spillover information does more to the metonymy than it does to the literal meaning. This study further complements cognitive and pragmatic approaches to metonymy, which are centered on its conceptual nature and its role in interpretation, by drawing attention to how the components of sentences contribute to the metonymic processing of target words. Based on an experiment, a contextual model of Chinese metonymy processing is proposed.

Effect of acupuncture on gut microbiota in participants with subjective cognitive decline.

ABSTRACT: A close relationship has recently been described between subjective cognitive decline (SCD) and gut microbiota disorders. Herein, we aim to investigate the effect of electroacupuncture (EA) on gut microbiota in participants with SCD.We conducted a study of 60 participants with SCD. Sixty participants were allocated to either EA group (n = 30) or sham acupuncture group (n = 30). Both groups received 24 sessions of real acupuncture treatment or identical treatment sessions using the placebo needle. Global cognitive change based on a comprehensive neuropsychological test battery was evaluated to detect the clinical efficacy of acupuncture treatment at the baseline and the end of treatment. Faecal microbial analyses were carried out after collecting stools at T0 and T12 weeks. Microbiomes were analyzed by 16S ribosomal RNA gene sequencing. Correlation analyses were performed to investigate the relationships between the changes in gut microbiota and symptom improvement.Age is a particularly important factor leading to the severity of dementia. Compared with sham acupuncture group, the number of Escherichia-Shigella in EA group decreased after treatment. The number of Escherichia-Shigella in EA group decreased after treatment compared with EA group before treatment. Bifidobacterium is positively correlated with clinical efficacy Z-score and Montreal Cognitive Assessment Scale (both P < .005).Acupuncture could improve global cognitive change among SCD participants by regulating the intestinal flora. Dysbiosis was found in the gut microbiome in SCD and partially relieved by acupuncture. Our study suggests that gut microbiota could be a potential therapeutic target and diagnostic biomarker for SCD.

N-Phenyl-substituted poly(benzimidazole imide)s with high glass transition temperature and low coefficient of thermal expansion.

To obtain high thermostable materials for flexible display substrates, a series of copoly(benzimidazole imide)s was prepared using 5-amine-2-(4-aminobenzene)-1-phenyl-benzimidazole (N-PhPABZ) and 6(5)-amino-2-(4-aminobenzene)-benzimidazole (PABZ). Incorporating N-phenyl groups effectively healed the brittleness of the poly(benzimidazole imide)s (PBIIs) derived from pyromellitic dianhydride (PMDA), and the resultant homo- and copoly(benzimidazole imide)s displayed an outstandingly high glass transition temperature (T g > 450 °C) and a low coefficient of thermal expansion (CTE < 10 ppm K-1). Furthermore, the influence of removing intermolecular hydrogen bonds on the properties of these poly(benzimidazole imide)s was systematically analyzed. These data provide a feasible method to prepare superheat-resistant poly(benzimidazole imide)s without H-bonding.

Retroperitoneal Ectopic Pregnancy: A Case Report.

A retroperitoneal ectopic pregnancy is an extremely rare type of ectopic pregnancy and is difficult to diagnose and treat. Owing to its occult onset, it is life-threatening and often associated with high mortality. A 28-year-old woman was admitted to the emergency department of our hospital owing to soreness of the left lower quadrant of the abdomen and amenorrhea for 60 days. Dilatation and curettage were performed at a local hospital to induce abortion, but no gestational sac was found. Elevated plasma human chorionic gonadotropin levels suggested an ectopic pregnancy. An ultrasound showed an approximately 4.0 cm × 3.0 cm mass in front of the middle and upper poles of the left kidney. The plasma beta-human chorionic gonadotropin level was 99 286.00 mIU/mL. Under laparoscopy, an ovoid mass measuring approximately 4.0 cm × 5.0 cm below the left renal vessels and the abdominal aorta was successfully resected. Methotrexate (50 mg/m2) was locally injected, and the retroperitoneum was sutured. Villi were observed in histopathologic sections. This case report highlights the importance of considering the possibility of a retroperitoneal ectopic pregnancy for patients with abdominal pain. Laparoscopic surgery by an experienced surgeon is the preferred method of treatment for this condition.

The efficacy of niacin supplementation in type 2 diabetes patients: Study protocol of a randomized controlled trial.

BACKGROUND: Dyslipidemia is a main risk factor of cardiovascular disease in the diabetic patients. Niacin was found acutely to decrease the plasma concentration of free fatty acids by inhibiting their mobilization from adipose tissue. This present study is a double blinded, randomized, and prospective trial to determine the effect of niacin during dyslipidemia in type 2 diabetic patients. METHODS: This randomized controlled, double-blinded, single center trial is carried out according to the principles of Declaration of Helsinki. This present study was approved in institutional review committee of the Second Affiliated Hospital of Dalian Medical University. All the patients received the informed consent. Diabetic patients were randomized (1:1) to receive 3-month treatment with extended-release niacin or matching placebo. The major outcome of our present study was the change in the level of HbA1c from the baseline to week 12. Secondary outcome measures contained the levels of fasting blood glucose, the concentrations of serum transaminase, the other laboratory variables, and self-reported adverse events. The P < .05 was regarded as statistically significant. RESULTS: We assumed that adding the niacin to the medication in patients with type 2 diabetes would reduce dyslipidemia and achieve target lipid levels. TRIAL REGISTRATION: This study protocol was registered in Research Registry (researchregistry5925).

[Spatial-temporal trend of grassland net primary production and their driving factors in the Loess Plateau, China]. / é»„åœŸé«˜åŽŸè‰åœ°å‡€åˆçº§ç”Ÿäº§åŠ›æ—¶ç©ºè¶‹åŠ¿åŠå ¶é©±åŠ¨å› ç´ .

Net primary productivity (NPP) of grassland is a key link and important part of the ecosystem's carbon cycle. We estimated the changes of NPP in grasslands of the Loess Plateau with unchanged land use types during 2000-2015 and analyzed its responses to the variation of main climate factors (annual precipitation, annual heavy rainfall, annual effective rainfall days, annual average temperature, annual maximum temperature, annual minimum temperature) using piecewise linear regression and Pearson correlation analysis. The driving factors of grassland NPP were further analyzed by pixel-by-pixel with boosted regression tree analysis. The results showed that annual mean grassland NPP in the Loess Plateau showed an increasing trend during the study period, with 51.3% of the total grassland area showing a significant increasing trend. The average increase rate of annual mean NPP declined from 15.23 g C·m-2·a-1 in 2000-2004 to 3.58 g C·m-2·a-1 in 2004-2015. There was a significant positive correlation between grassland NPP and precipitation, but negative correlation with temperature factors. Annual precipitation was the dominant climatic factor affecting NPP of the whole study area with the highest relative importance. Annual maximum temperature was the dominant driving force of grassland NPP of central Loess Plateau, while annual minimum temperature mainly affected the growth of grassland in high-altitude area of the western Loess Plateau.

Prediction of the Drug-Drug Interaction Types with the Unified Embedding Features from Drug Similarity Networks.

Drug combination therapies are a promising strategy to overcome drug resistance and improve the efficacy of monotherapy in cancer, and it has been shown to lead to a decrease in dose-related toxicities. Except the synergistic reaction between drugs, some antagonistic drug-drug interactions (DDIs) exist, which is the main cause of adverse drug events. Precisely predicting the type of DDI is important for both drug development and more effective drug combination therapy applications. Recently, numerous text mining- and machine learning-based methods have been developed for predicting DDIs. All these methods implicitly utilize the feature of drugs from diverse drug-related properties. However, how to integrate these features more efficiently and improve the accuracy of classification is still a challenge. In this paper, we proposed a novel method (called NMDADNN) to predict the DDI types by integrating five drug-related heterogeneous information sources to extract the unified drug mapping features. NMDADNN first constructs the similarity networks by using the Jaccard coefficient and then implements random walk with restart algorithm and positive pointwise mutual information for extracting the topological similarities. After that, five network-based similarities are unified by using a multimodel deep autoencoder. Finally, NMDADNN implements the deep neural network (DNN) on the unified drug feature to infer the types of DDIs. In comparison with other recent state-of-the-art DNN-based methods, NMDADNN achieves the best results in terms of accuracy, area under the precision-recall curve, area under the ROC curve, F1 score, precision and recall. In addition, many of the promising types of drug-drug pairs predicted by NMDADNN are also confirmed by using the interactions checker tool. These results demonstrate the effectiveness of our NMDADNN method, indicating that NMDADNN has the great potential for predicting DDI types.

Sialyltransferase7A promotes angiotensin II-induced cardiomyocyte hypertrophy via HIF-1α-TAK1 signalling pathway.

AIMS: Sialylation is up-regulated during the development of cardiac hypertrophy. Sialyltransferase7A (Siat7A) mRNA is consistently over-expressed in the hypertrophic left ventricle of hypertensive rats independently of genetic background. The aims of this study were: (i) to detect the Siat7A protein levels and its roles in the pathological cardiomyocyte hypertrophy; (ii) to elucidate the effect of sialylation mediated by Siat7A on the transforming-growth-factor-ß-activated kinase (TAK1) expression and activity in cardiomyocyte hypertrophy; and (iii) to clarify hypoxia-inducible factor 1 (HIF-1) expression was regulated by Siat7A and transactivated TAK1 expression in cardiomyocyte hypertrophy. METHODS AND RESULTS: Siat7A protein level was increased in hypertrophic cardiomyocytes of human and rats subjected to chronic infusion of angiotensin II (ANG II). Delivery of adeno-associated viral (AAV9) bearing shRNA against rat Siat7A into the left ventricular wall inhibited ventricular hypertrophy. Cardiac-specific Siat7A overexpression via intravenous injection of an AAV9 vector encoding Siat7A under the cardiac troponin T (cTNT) promoter aggravated cardiac hypertrophy in ANG II-treated rats. In vitro, Siat7A knockdown inhibited the induction of Sialyl-Tn (sTn) antigen and cardiomyocyte hypertrophy stimulated by ANG II. Mechanistically, ANG II induced the activation of TAK1-nuclear factor kappa-light-chain-enhancer of activated B cells (NF-κB) signalling in parallel to up-regulation of Siat7A in hypertrophic cardiomyocytes. Siat7A knockdown inhibited activation of TAK1-NF-κB pathway. Interestingly, HIF-1α expression was increased in cardiomyocytes stimulated by ANG II but decreased after Siat7A knockdown. HIF-1α knockdown efficiently decreased TAK1 expression. ChIP and luciferase assays showed that HIF-1α transactivated the TAK1 promoter region (nt -1285 to -1274 bp) in the cardiomyocytes following ANG II stimulus. CONCLUSION: Siat7A was up-regulated in hypertrophic myocardium and promoted cardiomyocyte hypertrophy via activation of the HIF-1α-TAK1-NF-κB pathway.

MOF-based fibrous membranes adsorb PM efficiently and capture toxic gases selectively.

Air pollution is harmful to the functioning of the lungs, heart, and brain even at low concentrations of particle matter (PM) and toxic gases. Purification methods and materials have made tremendous progress to improve the purity of air to adhere to national quality standards. Metal-organic frameworks (MOFs) have an excellent gas adsorption capacity due to their high specific surface area and porous structure, but the intrinsic fragility of MOF crystals limits their application. In this study, we selected appropriate organic ligands to prepare MOF-surface-grown fibrous membranes using an electrospinning technique, which have an excellent ability to adsorb PM and capture toxic gases selectively. The efficiency of the MOF-surface-grown fibrous membranes to remove PM reached 99.99%, even for fine PM. More importantly, under low partial pressure and complex gas composition conditions, the fibrous membrane was able to selectively adsorb SO2. The concentration of SO2 dropped from 7300 ppb to 40 ppb. Interestingly, the MOF-surface-grown fibrous membrane had a higher purification capacity toward O3 than toward SO2. The concentration of O3 rapidly dropped from 3000 ppb to 7 ppb, which was far below national air quality standards (81 ppb). The MOF-surface-grown fibrous membrane was able to adsorb toxic atmospheric gases selectively, while not being influenced by the presence of other gases, such as CO2 and O2. MOF-based fibrous membranes prepared using a simple and inexpensive electrospinning technique have wide potential for practical use in the field of environmental protection and air purification.

Prediction of drug-target interaction by integrating diverse heterogeneous information source with multiple kernel learning and clustering methods.

BACKGROUND: Identification of potential drug-target interaction pairs is very important for pharmaceutical innovation and drug discovery. Numerous machine learning-based and network-based algorithms have been developed for predicting drug-target interactions. However, large-scale pharmacological, genomic and chemical datum emerged recently provide new opportunity for further heightening the accuracy of drug-target interactions prediction. RESULTS: In this work, based on the assumption that similar drugs tend to interact with similar proteins and vice versa, we developed a novel computational method (namely MKLC-BiRW) to predict new drug-target interactions. MKLC-BiRW integrates diverse drug-related and target-related heterogeneous information source by using the multiple kernel learning and clustering methods to generate the drug and target similarity matrices, in which the low similarity elements are set to zero to build the drug and target similarity correction networks. By incorporating these drug and target similarity correction networks with known drug-target interaction bipartite graph, MKLC-BiRW constructs the heterogeneous network on which Bi-random walk algorithm is adopted to infer the potential drug-target interactions. CONCLUSIONS: Compared with other existing state-of-the-art methods, MKLC-BiRW achieves the best performance in terms of AUC and AUPR. MKLC-BiRW can effectively predict the potential drug-target interactions.

Trend in the nutritional status of children aged 2-7 years in Luoding city, China: A panel study from 2004 to 2013.

To examine trends in the prevalence of wasting, stunting, overweight, and obesity among children in Luoding, a lower-middle-income city in southern China, we collected height, weight and other information on 65,908 pre-school children aged 2 to 7 years from 23 kindergartens, in which health examinations were conducted annually between 2004 and 2013. We used the growth standards of the World Health Organization (WHO) to calculate Z-scores for height and body mass index (BMI), and used the cut-offs recommended by WHO to define wasting, stunting, overweight, and obesity for each child. From 2004 to 2013, the prevalence of overweight increased from 3.70% to 7.27% and of obesity increased from 1.04% to 2.08%. Meanwhile, the prevalence of wasting decreased from 0.91% to 0.72% and of stunting decreased from 9.29% to 5.22%. These trends suggest there was still a double burden of nutritional status there. The nutritional interventions focusing on pre-school children should be comprehensively elaborated in lower-middle-income areas such as Luoding.

Identifying Drug-Target Interactions with Decision Templates.

BACKGROUND: During the development process of new drugs, identification of the drug-target interactions wins primary concerns. However, the chemical or biological experiments bear the limitation in coverage as well as the huge cost of both time and money. Based on drug similarity and target similarity, chemogenomic methods can be able to predict potential drug-target interactions (DTIs) on a large scale and have no luxurious need about target structures or ligand entries. OBJECTIVE: In order to reflect the cases that the drugs having variant structures interact with common targets and the targets having dissimilar sequences interact with same drugs. In addition, though several other similarity metrics have been developed to predict DTIs, the combination of multiple similarity metrics (especially heterogeneous similarities) is too naïve to sufficiently explore the multiple similarities. METHOD: In this paper, based on Gene Ontology and pathway annotation, we introduce two novel target similarity metrics to address above issues. More importantly, we propose a more effective strategy via decision template to integrate multiple classifiers designed with multiple similarity metrics. RESULTS: In the scenarios that predict existing targets for new drugs and predict approved drugs for new protein targets, the results on the DTI benchmark datasets show that our target similarity metrics are able to enhance the predictive accuracies in two scenarios. And the elaborate fusion strategy of multiple classifiers has better predictive power than the naïve combination of multiple similarity metrics. CONCLUSION: Compared with other two state-of-the-art approaches on the four popular benchmark datasets of binary drug-target interactions, our method achieves the best results in terms of AUC and AUPR for predicting available targets for new drugs (S2), and predicting approved drugs for new protein targets (S3).These results demonstrate that our method can effectively predict the drug-target interactions. The software package can freely available at https://github.com/NwpuSY/DT_all.git for academic users.