Dynamic polarization fusion network (DPFN) for imaging in different scattering systems.

Deep learning has broad applications in imaging through scattering media. Polarization, as a distinctive characteristic of light, exhibits superior stability compared to light intensity within scattering media. Consequently, the de-scattering network trained using polarization is expected to achieve enhanced performance and generalization. For getting optimal outcomes in diverse scattering conditions, it makes sense to train expert networks tailored for each corresponding condition. Nonetheless, it is often unfeasible to acquire the corresponding data for every possible condition. And, due to the uniqueness of polarization, different polarization information representation methods have different sensitivity to different environments. As another of the most direct approaches, a generalist network can be trained with a range of polarization data from various scattering situations, however, it requires a larger network to capture the diversity of the data and a larger training set to prevent overfitting. Here, in order to achieve flexible adaptation to diverse environmental conditions and facilitate the selection of optimal polarization characteristics, we introduce a dynamic learning framework. This framework dynamically adjusts the weights assigned to different polarization components, thus effectively accommodating a wide range of scattering conditions. The proposed architecture incorporates a Gating Network (GTN) that efficiently integrates multiple polarization features and dynamically determines the suitable polarization information for various scenarios. Experimental result demonstrates that the network exhibits robust generalization capabilities across continuous scattering conditions.

Hyperuricemia promotes the progression of atherosclerosis by activating endothelial cell pyroptosis via the ROS/NLRP3 pathway.

Hyperuricemia closely correlates with the development of atherosclerosis, but little is known of the mechanism by which atherosclerosis progression occurs in hyperuricemia. Atherosclerosis appears to involve pyroptosis, an emerging mechanism of proinflammatory regulated cell death. This study tested the hypothesis that pyroptosis underlies the relationship between hyperuricemia and atherosclerosis, using ApoE-/- mice (a model of atherosclerosis), human umbilical vein endothelial cells (HUVECs), and human atherosclerotic arterial samples. We found that hyperuricemia can aggravate the aortic atherosclerotic plaque-load in ApoE-/- mice and promote endothelial cell pyroptosis. Additionally, hyperuricemia can increase the levels of serum inflammatory factors (including IL-1ß and IL-18). Exposure to lipopolysaccharide plus a high concentration of soluble uric acid (≥12 mg/dL) induced cell pyroptosis in HUVECs, as evidenced by increased expression of pyroptosis-related proteins and elevated release of lactate dehydrogenase (a marker of tissue damage). Further, MCC950, a selective nucleotide-binding oligomerization domain (NOD)-like receptor 3 (NLRP3) inflammasome inhibitor, and N-acetyl- l-cysteine, an antioxidant, attenuated HUVEC pyroptosis by inhibiting activation of the NLRP3 inflammasome and production of intracellular reactive oxygen species (ROS). Finally, we detected significantly higher expression of pyroptosis-associated proteins in carotid specimens from patients with hyperuricemia. Collectively, our findings suggest that hyperuricemia can aggravate endothelial cell pyroptosis in aortic atherosclerotic plaques, promoting the development of atherosclerosis. Additionally, a high concentration of soluble uric acid can trigger the activation stage of the NLRP3 inflammasome, mediating endothelial cell pyroptosis, and this process is regulated by the cellular ROS level.

Self-attention module in a multi-scale improved U-net (SAM-MIU-net) motivating high-performance polarization scattering imaging.

Polarization imaging has outstanding advantages in the field of scattering imaging, which still encounters great challenges in heavy scattering media systems even though there are helps from deep learning technology. In this paper, we propose a self-attention module (SAM) in multi-scale improved U-net (SAM-MIU-net) for the polarization scattering imaging, which can extract a new combination of multidimensional information from targets effectively. The proposed SAM-MIU-net can focus on the stable feature carried by polarization characteristics of the target, so as to enhance the expression of the available features, and make it easier to extract polarization features which help to recover the detail of targets for the polarization scattering imaging. Meanwhile, the SAM's effectiveness has been verified in a series of experiments. Based on proposed SAM-MIU-net, we have investigated the generalization abilities for the targets' structures and materials, and the imaging distances between the targets and the ground glass. Experimental results demonstrate that our proposed SAM-MIU-net can achieve high-precision reconstruction of target information under incoherent light conditions for the polarization scattering imaging.

TSMPN-PSI: high-performance polarization scattering imaging based on three-stage multi-pipeline networks.

Polarization imaging, which provides multidimensional information beyond traditional intensity imaging, has prominent advantages for complex imaging tasks, particularly in scattering environments. By introducing deep learning (DL) into computational imaging and sensing, polarization scattering imaging (PSI) has obtained impressive progresses, however, it remains a challenging but long-standing puzzle due to the fact that scattering medium can result in significant degradation of the object information. Herein, we explore the relationship between multiple polarization feature learning strategy and the PSI performances, and propose a new multi-polarization driven multi-pipeline (MPDMP) framework to extract rich hierarchical representations from multiple independent polarization feature maps. Based on the MPDMP framework, we introduce a well-designed three-stage multi-pipeline networks (TSMPN) architecture to achieve the PSI, named TSMPN-PSI. The proposed TSMPN-PSI comprises three stages: pre-processing polarization image for de-speckling, multiple polarization feature learning, and target information reconstruction. Furthermore, we establish a real-world polarization scattering imaging system under active light illumination to acquire a dataset of real-life scenarios for training the model. Both qualitative and quantitative experimental results show that the proposed TSMPN-PSI achieves higher generalization performance than other methods on three testing data sets refer to imaging distances, target structures, and target materials and their background materials. We believe that our work presents a new framework for the PSI and paves the way to its pragmatic applications.

I-DNAN6mA: Accurate Identification of DNA N6-Methyladenine Sites Using the Base-Pairing Map and Deep Learning.

The recent discovery of numerous DNA N6-methyladenine (6mA) sites has transformed our perception about the roles of 6mA in living organisms. However, our ability to understand them is hampered by our inability to identify 6mA sites rapidly and cost-efficiently by existing experimental methods. Developing a novel method to quickly and accurately identify 6mA sites is critical for speeding up the progress of its function detection and understanding. In this study, we propose a novel computational method, called I-DNAN6mA, to identify 6mA sites and complement experimental methods well, by leveraging the base-pairing rules and a well-designed three-stage deep learning model with pairwise inputs. The performance of our proposed method is benchmarked and evaluated on four species, i.e., Arabidopsis thaliana, Drosophila melanogaster, Rice, and Rosaceae. The experimental results demonstrate that I-DNAN6mA achieves area under the receiver operating characteristic curve values of 0.967, 0.963, 0.947, 0.976, and 0.990, accuracies of 91.5, 92.7, 88.2, 0.938, and 96.2%, and Mathew's correlation coefficient values of 0.855, 0.831, 0.763, 0.877, and 0.924 on five benchmark data sets, respectively, and outperforms several existing state-of-the-art methods. To our knowledge, I-DNAN6mA is the first approach to identify 6mA sites using a novel image-like representation of DNA sequences and a deep learning model with pairwise inputs. I-DNAN6mA is expected to be useful for locating functional regions of DNA.

Inhibition of mitochondrial fission alters neo-intimal hyperplasia via PI3K/Akt signaling in arteriovenous fistulas.

BACKGROUND/OBJECTIVE: Arteriovenous fistulas (AVFs) are the preferred vascular access for hemodialysis of patients with end-stage renal disease. However, there is a high incidence of AVF failures caused by insufficient outward remodeling or venous neo-intimal hyperplasia formation. Abnormal proliferation and migration of vascular smooth muscle cells (VSMCs) play an important role in many cardiovascular diseases. Abnormal VSMC proliferation and migration could be abolished by inhibition of mitochondrial division. METHOD: We found that abnormal proliferation and migration of VSMCs and increased mitochondrial fission were associated with AVF stenosis in patients. We also investigated the mechanisms, particularly the role of mitochondrial dynamics, underlying these VSMC behaviors. In vitro, we observed that inhibition of mitochondrial fission and Akt phosphorylation can diminish proliferation and migration of VSMCs induced by platelet-derived growth factor-BB (PDGF-BB). In vivo, daily intraperitoneal injections of mitochondrial division inhibitor 1 (Mdivi-1) decreased VSMC proliferation and reduced AVF wall thickness in a rat AVF model. CONCLUSION AND RESULT: Our results suggest that inhibition of mitochondrial fission improves AVF patency by reducing wall thickening through the PI3K/Akt signaling pathway. Therefore, inhibition of mitochondrial fission has the clinical potential to improve AVF patency.

Predicting RNA solvent accessibility from multi-scale context feature via multi-shot neural network.

Knowledge of RNA solvent accessibility has recently become attractive due to the increasing awareness of its importance for key biological process. Accurately predicting the solvent accessibility of RNA is crucial for understanding its 3D structure and biological function. In this study, we develop a novel computational method, termed M2pred, for accurately predicting the solvent accessibility of RNA from sequence-based multi-scale context feature. In M2pred, three single-view features, i.e., base-pairing probabilities, position-specific frequency matrix, and a binary one-hot encoding, are first generated as three feature sources, and immediately concatenated to engender a super feature. Secondly, for the super feature, the matrix-format features of each nucleotide are extracted using an initialized sliding window technique, and regularly stacked into a cube-format feature. Then, using multi-scale context feature extraction strategy, a pyramid feature constructed of contextual feature of four scales related to target nucleotides is extracted from the cube-format feature. Finally, a customized multi-shot neural network framework, which is equipped with four different scales of receptive fields mainly integrating several residual attention blocks, is designed to dig discrimination information from the contextual pyramid feature. Experimental results demonstrate that the proposed M2pred achieve a high prediction performance and outperforms existing state-of-the-art prediction methods of RNA solvent accessibility.

Association Between Nadir Hematocrit and Severe Acute Kidney Injury After Off-Pump Coronary Artery Bypass Graft Surgery: A Retrospective Cohort Study Based on the MIMIC-IV Database.

BACKGROUND We aimed to evaluate the association between postoperative nadir hematocrit (Hct) and severe acute kidney injury (AKI) in patients undergoing off-pump coronary artery bypass graft (OPCABG) surgery. MATERIAL AND METHODS Data of patients who received OPCABG were extracted from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. A generalized additive model was applied to explore the relationship between nadir Hct and severe AKI. Patients were divided into 4 groups by quartiles of postoperative nadir Hct, with the lowest group (Hct <25%) as reference. We conducted multivariate logistic regression models to calculate adjusted odds ratios (OR) and 95% CI and evaluate trend among the 4 groups. RESULTS In total, 1783 OPCABG patients were included. A nonlinear association between nadir Hct and severe AKI was identified. After adjusting for potential confounders, nadir Hct was negatively associated with risk of severe AKI when Hct was less than 31%; there was no statistical significance between highest Hct group (Hct ≥31%) and control group (Hct <25%; P>0.05). Tests for trend were significant (P<0.05). Subgroup analyses showed each 1% increase in postoperative nadir Hct was associated with a 23% decrease in risk of severe AKI (OR, 0.77; P=0.002) in lower BMI group (<30 kg/m²). CONCLUSIONS The association between postoperative nadir Hct and severe AKI in patients after OPCABG was nonlinear. Lower nadir Hct may be associated with increased risk of severe AKI when Hct values are less than 31%. However, no statistical significance was found between the highest Hct group and control group.

Histopathological analysis of incompetent great saphenous veins after mechanochemical ablation treatment - An ex-vivo experiment.

BACKGROUND: The endovascular technique of mechanochemical ablation (MOCA) has become popular in treating patients with saphenous reflux. We reported the histopathological findings in human ex-vivo incompetent great saphenous veins following treatment with saline, polidocanol, mechanical ablation and MOCA using ClariVein device. METHODS: Twenty-four vein GSV specimens were obtained via traditional surgery and treated with four methods: Group A: 0.9% normal saline (NS); Group B: 3% polidocanol; Group C: mechanical ablation + 0.9% NS; Group D: mechanical ablation + 3% polidocanol (MOCA). Hematoxylin and eosin (HE), Masson's trichrome and immunohistochemical staining were performed on each specimen and integrated optical densities were measured with vWF and a-SMA stains and statistically evaluated. vWF staining was used to assess endothelial damage and a a-SMA staining was used to assess media injury. RESULTS: HE and Masson's trichrome staining of Groups C and D revealed severe damage to the endothelium and media compared to Groups A and B. The statistical result of vWF staining showed the damage of endothelium was significantly increased by Group D compared to Groups A, B and C. The statistical result of a-SMA staining showed the damage of media was significantly increased by Groups C and D compared to Groups A and B. CONCLUSIONS: The mechanism of MOCA was caused by both endothelium damage and media tearing. The damage of endothelium was significantly increased by MOCA when compared with mechanical ablation alone.

Role of pyroptosis in atherosclerosis and its therapeutic implications.

Atherosclerosis is a significant cardiovascular burden and a leading cause of death worldwide, recognized as a chronic sterile inflammatory disease. Pyroptosis is a novel proinflammatory regulated cell death, characterized by cell swelling, plasma membrane bubbling, and robust release of proinflammatory cytokines (such as interleukin IL-1ß and IL-18). Mounting studies have addressed the crucial contribution of pyroptosis to atherosclerosis and clarified the candidate therapeutic agents targeting pyroptosis for atherosclerosis. Herein, we review the initial characterization of pyroptosis, the detailed mechanisms of pyroptosis, current evidence about pyroptosis and atherosclerosis, and potential therapeutic strategies that target pyroptosis in the development of atherosclerosis.

Improved protein relative solvent accessibility prediction using deep multi-view feature learning framework.

The accurate prediction of the relative solvent accessibility of a protein is critical to understanding its 3D structure and biological function. In this study, a novel deep multi-view feature learning (DMVFL) framework that integrates three different neural network units, i.e., bidirectional long short-term memory recurrent neural network, squeeze-and-excitation, and fully-connected hidden layer, with four sequence-based single-view features, i.e., position-specific scoring matrix, position-specific frequency matrix, predicted secondary structure, and roughly predicted three-state relative solvent accessibility probability, is developed to accurately predict relative solvent accessibility information of protein. On the basis of this newly developed framework, one new protein relative solvent accessibility predictor was proposed and called DMVFL-RSA, which employs a customized multiple feedback mechanism that helps to extract discriminative information embedded in the four single-view features. In benchmark tests on TEST524 and CASP14-derived (CASP14set) datasets, DMVFL-RSA outperforms other existing state-of-the-art protein relative solvent accessibility predictors when predicting two-state (exposure threshold of 25%), three-state (exposure thresholds of 9% and 36%), and four-state (exposure thresholds of 4%, 25%, and 50%) discrete values. For real-valued prediction on TEST524 and CASP14set, DMVFL-RSA has also gained high Pearson correlation coefficient values, indicating a positive correlation between the predicted and native relative solvent accessibility. Detailed analyses show that the major advantages of DMVFL-RSA lie in the high efficiency of the DMVFL framework, the applied multiple feedback mechanism, and the strong sensitivity of the sequence-based features. The web server of DMVFL-RSA is freely available at https://jun-csbio.github.io/DMVFL-RSA/for academic use. The standalone package of DMVFL-RSA is downloadable at https://github.com/XueQiangFan/DMVFL-RSA.

Therapeutic Effects of Medication Use on Intermittent Claudication: A Network Meta-analysis.

OBJECTIVE: To systematically evaluate the therapeutic effects of commonly used drugs for the treatment of intermittent claudication in patients with peripheral arterial diseases. METHODS: We systematically searched bibliographic databases for randomized clinical trials published between 2000 and 2020, through the China National Knowledge Infrastructure, WanFang Data, PubMed, MEDLINE, Embase, and Cochrane library. Included studies focused on therapeutic effects of beraprost, clopidogrel, aspirin, sarpogrelate and cilostazol on treating intermittent claudication. The outcome measures were maximum walking distance, pain-free walking distance, ankle-brachial index, and severe adverse events. The quality of included trials was evaluated by using the bias risk assessment tool recommended by the Cochrane, after extracting data from the literatures. Stata was used to conduct the network meta-analysis. RESULTS: There were 27 randomized control trials included in the study, covering in total 9491 patients. The network meta-analysis results showed that for maximum walking distance, better therapeutic effect was noted in using beraprost, sarpogrelate, and cilostazol. Beraprost, beraprost combined with aspirin, and sarpogrelate were better in improving pain-free walking distance than other drugs. For the ankle-brachial index, cilostazol combined with clopidogrel, sarpogrelate, and beraprost had better therapeutic effects than others. The use of sarpogrelate, beraprost, and aspirin was associated with a lower ratio of severe adverse events than the use of cilostazol and placebo. CONCLUSIONS: Among the commonly used drugs for the treatment of intermittent claudication, beraprost and sarpogrelate may have better efficacy in improving the walking distance and ankle-brachial index, with a beneficial effect on cardiovascular and cerebrovascular comorbidities.

Drug-Coated Balloon versus Bare Nitinol Stent in Femoropopliteal Artery: 12 Months Outcome from a Single Center in China.

OBJECT: The study sought to compare the safety and effectiveness of drug-coated balloon (DCB) with bare nitinol stent in patients with complex femoropopliteal(FP) lesions in real-world practice. METHODS: Patients with symptomatic (Rutherford stage 2 to 5) femoropopliteal lesions who underwent DCB or bare nitinol stent implantation at the Department of Cardiovascular Surgery of China-Japan Friendship Hospital from June 2016 to September 2017 were included. Demographics, angiographic and procedural variables were included. Freedom from target lesion revascularization (TLR), primary patency and major adverse events were obtained from follow-up results at 3,6 and12 months. Descriptive analysis was performed on all variables. RESULTS: A total of 90 eligible patients were enrolled, which included 51 DCB subjects (mean age, 63.1 ± 13.2 years; 76.5% male) with 55 lesions and 39 nitinol stent subjects (mean age, 66.5 ± 10.5 years; 61.5% male) with 42 lesions. Significant higher primary patency was observed in the DCB group compared with the stent group (74.5% vs. 52.4%; log-rank test P = 0.018; HR 0.335, 95%CI 0.124-0.903, P = 0.031). The rates of freedom from TLR (f-TLR) were 78.2% and 59.5% (log-rank test P = 0.032) for the DCB group and the stent group, respectively, at 12 months. CD-TLR rates were 18.2% vs. 38.1% with a P-value of 0.023. Female sex (HR 6.122, 95%CI 1.880-19.934, P = 0.003), lesion length over 20 cm (HR 5.514, 95%CI 2.312-13.148, P < 0.001) and renal insufficiency (HR 2.609, 95%CI 1.087-6.260, P = 0.032) were suggested as independent risk factors of reducing primary patency. There were no significant differences in major adverse events between the 2 groups. CONCLUSION: The result above demonstrates that DCB treatment has higher primary patency and lower TLR at 12 months than nitinol stent. These data confirm the safety and effectiveness of the DCB for patients with complex femoropopliteal lesions.

Identification of ligand-binding residues using protein sequence profile alignment and query-specific support vector machine model.

Information embedded in ligand-binding residues (LBRs) of proteins is important for understanding protein functions. How to accurately identify the potential ligand-binding residues is still a challenging problem, especially only protein sequence is given. In this paper, we establish a new query-specific computational method, named I-LBR, for the identification of LBRs without directly using the information of protein 3D structure. I-LBR includes two modes, named as I-LBRGP and I-LBRLS, for the general-purpose and ligand-specific LBR identification. For both modes, I-LBR first construct the specific training subset based on the query sequence information; then use support vector machine (SVM) algorithm to learn the LBR identification model; finally, predict the probability of each residue in query protein belongs to the class of LBR. Experimental results on four testing dataset demonstrate that I-LBRLS is the better choice against I-LBRGP, when the ligand type/types of the query protein binds is/are known. Comparing to other state-of-the-art LBR identification methods, I-LBR can achieve a better or comparable performance. The web-server of I-LBR and dataset used in this study are freely available for academic use at https://jun-csbio.github.io/I-LBR.

Hybrid and Endovascular Treatment of Pulmonary Sequestration: Two Case Reports and Literature Review.

Pulmonary sequestration is an uncommon congenital pulmonary anomaly associated with aberrant systemic arteries which usually originate from the thoracic aorta or abdominal aorta. Traditionally, surgical resection and ligation of the feeding vessels are the gold standard treatments of the disease. Endovascular intervention and hybrid operation are promising treatment options. However, the case reports with endovascular and hybrid treatment are sparse to our knowledge. We presented 2 symptomatic adult patients with pulmonary sequestration successfully treated by hybrid operation and transcatheter embolization, respectively. Besides, we reviewed 37 previously reported cases of pulmonary sequestration treated by endovascular or hybrid treatment.

A Systematic Review of Early Results Following Synchronous or Staged Carotid Artery Stenting and Coronary Artery Bypass Grafting.

Background The optimal management of patients with concomitant coronary artery disease (CAD) and severe carotid artery stenosis remains a controversy. We performed a systematic review of studies comparing early outcomes of synchronous or staged carotid artery stenting (CAS) and coronary artery bypass grafting (CABG) in the treatment of patients with concomitant CAD and severe carotid artery stenosis. Methods Multiple databases were systematically searched to identify studies of synchronous or staged CAS and CABG in the treatment of concomitant severe carotid and coronary artery disease published from 2005 to 2015. The quality of studies was assessed using the MINORS scale. The demographic data, risk factors, 30-day outcomes, and antiplatelet strategy were extracted. Results 23 studies were identified with a total of 873 and 459 patients in the staged and synchronous group, respectively. The observed overall death/stroke/MI rate was 8.5% (95% CI: 7.6-9.4%) in staged group and 4.8% (95% CI: 3.8-5.8%) in synchronous group. It seems that the synchronous group has better 30-day outcomes, but these data could not be compared statistically. Conclusion Our systematic review suggests either synchronous or staged CAS and CABG can be chosen for the treatment of concomitant carotid and coronary artery disease. It seems that the synchronous approach is relatively convenient and the antiplatelet strategy is relatively definite. For these patients, hybrid revascularization by synchronous CAS and CABG might be a feasible and promising therapeutic strategy. Our conclusions and the quality of the existing data suggest that a randomized controlled trial is needed to define the best treatment for patients with concomitant carotid and coronary artery disease.

Feasibility and Safety of Simultaneous Carotid Endarterectomy and Carotid Stenting for Bilateral Carotid Stenosis: A Single-Center Experience using a Hybrid Procedure.

BACKGROUND: The treatment for bilateral carotid stenosis (BCS) is challenging, and the optimal treatment strategy is not clear. We report our experience of treating 8 patients with BCS by simultaneous carotid endarterectomy (CEA) and carotid stenting (CAS), thereby providing an alternative for vascular surgeons. METHODS: Between October 2010 and August 2014, 8 patients (5 males and 3 females; range, 53-82 years; mean, 69 ± 8.8 years) underwent simultaneous CEA and CAS in our hospital. CEA before CAS was done in 5 patients, and CAS before CEA was done in 3 patients. One patient also underwent simultaneous coronary artery bypass grafting due to unstable angina. Intraoperative transcranial Doppler ultrasonography, carotid shunts, patches, and embolic protection devices were used in all patients. Instances of hyperperfusion syndrome (HPS), hemodynamic depression, stroke, myocardial infarction (MI), and death were recorded. RESULTS: All patients completed the procedure. One patient developed postprocedural HPS. After systemic treatment, he recovered completely. There were no deaths, major and/or minor strokes, or MI, nor did any patient exhibit lower palsy in cranial nerves in the perioperative period (<30 days) or on clinical follow-up (3 and 6 months). We observed no restenosis and no recurrent symptoms during follow-up. CONCLUSIONS: After careful preoperative assessment and preparation, simultaneous CEA and CAS for high-grade BCS may be considered as an alternative management strategy in carefully selected patients.

[Clinical outcomes of synchronous revascularization on patients concomitant carotid and coronary artery severe stenosis].

OBJECTIVE: To analyze the outcomes of synchronous revascularization for patients concomitant carotid and coronary artery severe stenosis. METHODS: From May 2012 to April 2014, 12 cases who received one-stage operation was retrospective analyzed, including the characteristics, methods of treatment, perioperative complications and health survey 30 days post procedure. Two subgroups were divided according to the different treatment methods on carotid artery, WIC and SF-36 scale were applied to compare the basic condition and recovery situation between 2 groups, the hospital stay time, costs, ventilation time, drainage and blood transfusion volume were also be compared. RESULTS: Totally 30 coronary vessels 8 carotid endarterectomy (CEA) and 5 carotid artery stenting (CAS) were performed on 12 patients. One patient also received coronary artery bypass grafting and bilateral carotid artery revascularization (CEA on right and CAS on left). Two (16.67%) minor stroke, 1 (8.33%) TIA, 1 wound infection occurred within 30 days post procedure, and 11 (91.67%) received blood component transfusion. No myocardial infarction and death occured. The average hospital stay time were (36.5 ± 25.3) days, ventilator application (37.5 ± 31.2) hours, postoperative drainage volume from pericardial and mediastinal was (347.92 ± 105.69) ml, infusion of concentrated red cell was 4.3 U. WIC was (5.57 ± 1.51) in CEA and (4.25 ± 1.50) in CAS subgroup, there was no significantly statistical difference (t = 1.40, P > 0.05). the results of SF-36 was (3.63 ± 1.76) and (5.44 ± 1.05) in CEA and CAS subgroup, there was no significantly statistical difference (t = -1.85, P > 0.05). In hospital stay time, ventilator application time, transfusion and drainage volume, hospitalization costs were also no significant statistical difference between two groups. CONCLUSIONS: The early outcome of synchronous revascularization on concomitant carotid and coronary severe stenosis disease is satisfactory. The clinical results are similar in the CEA and CAS subgroup.

Ense-i6mA: Identification of DNA N6-methyl-adenine Sites Using XGB-RFE Feature Se-lection and Ensemble Machine Learning.

DNA N6-methyladenine (6mA) is an important epigenetic modification that plays a vital role in various cellular processes. Accurate identification of the 6mA sites is fundamental to elucidate the biological functions and mechanisms of modification. However, experimental methods for detecting 6mA sites are high-priced and time-consuming. In this study, we propose a novel computational method, called Ense-i6mA, to predict 6mA sites. Firstly, five encoding schemes, i.e., one-hot encoding, gcContent, Z-Curve, K-mer nucleotide frequency, and K-mer nucleotide frequency with gap, are employed to extract DNA sequence features. Secondly, to our knowledge, it is the first time that eXtreme gradient boosting coupled with recursive feature elimination is applied to 6mA sites prediction domain to remove noisy features for avoiding over-fitting, reducing computing time and complexity. Then, the best subset of features is fed into base-classifiers composed of Extra Trees, eXtreme Gradient Boosting, Light Gradient Boosting Machine, and Support Vector Machine. Finally, to minimize generalization errors, the prediction probabilities of the base-classifiers are aggregated by averaging for inferring the final 6mA sites results. We conduct experiments on two species, i.e., Arabidopsis thaliana and Drosophila melanogaster, to compare the performance of Ense-i6mA against the recent 6mA sites prediction methods. The experimental results demonstrate that the proposed Ense-i6mA achieves area under the receiver operating characteristic curve values of 0.967 and 0.968, accuracies of 91.4% and 92.0%, and Mathew's correlation coefficient values of 0.829 and 0.842 on two benchmark datasets, respectively, and outperforms several existing state-of-the-art methods.