Multiple aortic root pseudoaneurysms with dissecting aneurysm of the interventricular septum diagnosed by multimodal imaging.

Aortic root pseudoaneurysm is a devastating complication post aortic valve replacement with a high mortality rate. And dissecting aneurysm into the interventricular septum is a rare variant of aortic root pseudoaneurysm, which is scarcely reported. Multimodal imaging is of great value in its diagnosis and differential diagnosis.

A case of minimally invasive small-incision off-pump ligation of a coronary artery fistula monitored by transesophageal echocardiography.

This case demonstrated intraoperative real-time transesophageal echocardiographic monitoring in minimally invasive small-incision Off-pump ligation of a coronary artery fistula,demonstrating the importance of esophageal echocardiography in surgical monitoring.

Melatonin targets MoIcl1 and works synergistically with fungicide isoprothiolane in rice blast control.

Melatonina natural harmless molecule-displays versatile roles in human health and crop disease control such as for rice blast. Rice blast, caused by the filamentous fungus Magnaporthe oryzae, is one devastating disease of rice. Application of fungicides is one of the major measures in the control of various crop diseases. However, fungicide resistance in the pathogen and relevant environmental pollution are becoming serious problems. By screening for possible synergistic combinations, here, we discovered an eco-friendly combination for rice blast control, melatonin, and the fungicide isoprothiolane. These compounds together exhibited significant synergistic inhibitory effects on vegetative growth, conidial germination, appressorium formation, penetration, and plant infection by M. oryzae. The combination of melatonin and isoprothiolane reduced the effective concentration of isoprothiolane by over 10-fold as well as residual levels of isoprothiolane. Transcriptomics and lipidomics revealed that melatonin and isoprothiolane synergistically interfered with lipid metabolism by regulating many common targets, including the predicted isocitrate lyase-encoding gene MoICL1. Furthermore, using different techniques, we show that melatonin and isoprothiolane interact with MoIcl1. This study demonstrates that melatonin and isoprothiolane function synergistically and can be used to reduce the dosage and residual level of isoprothiolane, potentially contributing to the environment-friendly and sustainable control of crop diseases.

Identification and validation of cellular senescence patterns to predict clinical outcomes and immunotherapeutic responses in lung adenocarcinoma.

BACKGROUND: Aging and senescence can alter immune cell fitness and influence the efficacy of lung cancer treatments, especially immunotherapy. However, the correlations between cellular senescence and tumor microenvironment are still not clearly clarified and the value of cellular senescence-related genes in evaluating the immune infiltration and clinical outcomes of lung adenocarcinoma (LUAD) need further investigated. METHODS: We identified three cellular senescence clusters by NMF algorithm and correlated the cellular senescence clusters with the immune landscape in LUAD patients. A prognostic scoring system was established using random survival forest algorithm and validated in 4 external cohorts. Multivariate Cox regression analysis was performed to evaluate the prognostic value of the scoring system. Expression of LYPD3 was evaluated by immunohistochemistry in LUAD samples. RESULTS: Based on the mRNA expression profiles of 278 cellular senescence-related genes, three cellular senescence clusters with distinct prognosis were identified. We characterized three cellular senescence clusters by differences in biological processes, EMT score, expression of immunomodulatory genes, extent of intratumor heterogeneity and response to immunotherapy. Meanwhile, a cellular senescence-related scoring system (CSS) was established and validated as an independent prognostic factor and immunotherapy predictor of LUAD. Patients with low CSS was characterized by prolonged survival time. In response to anti-cancer drugs, patients with low CSS exhibited higher sensitivities to molecular drugs, such as Roscovitine (CDKs inhibitor), Lenaidornide (TNF-α inhibitor), MK2206 (Akt 1/2/3 inhibitor), and especially increased response to anti-PD-1/L1 immunotherapy. CONCLUSIONS: This study demonstrated the correlations between cellular senescence patterns and tumor immune landscape in LUAD, which enhanced our understanding of the tumor immune microenvironment and provided new insights for improving the outcome of immunotherapy for LUAD patients.

The Discovery of New Drug-Target Interactions for Breast Cancer Treatment.

Drug-target interaction (DTIs) prediction plays a vital role in probing new targets for breast cancer research. Considering the multifaceted challenges associated with experimental methods identifying DTIs, the in silico prediction of such interactions merits exploration. In this study, we develop a feature-based method to infer unknown DTIs, called PsePDC-DTIs, which fuses information regarding protein sequences extracted by pseudo-position specific scoring matrix (PsePSSM), detrended cross-correlation analysis coefficient (DCCA coefficient), and an FP2 format molecular fingerprint descriptor of drug compounds. In addition, the synthetic minority oversampling technique (SMOTE) is employed for dealing with the imbalanced data after Lasso dimensionality reduction. Then, the processed feature vectors are put into a random forest classifier to perform DTIs predictions on four gold standard datasets, including nuclear receptors (NR), G-protein-coupled receptors (GPCR), ion channels (IC), and enzymes (E). Furthermore, we explore new targets for breast cancer treatment using its risk genes identified from large-scale genome-wide genetic studies using PsePDC-DTIs. Through five-fold cross-validation, the average values of accuracy in NR, GPCR, IC, and E datasets are 95.28%, 96.19%, 96.74%, and 98.22%, respectively. The PsePDC-DTIs model provides us with 10 potential DTIs for breast cancer treatment, among which erlotinib (DB00530) and FGFR2 (hsa2263), caffeine (DB00201) and KCNN4 (hsa3783), as well as afatinib (DB08916) and FGFR2 (hsa2263) are found with direct or inferred evidence. The PsePDC-DTIs model has achieved good prediction results, establishing the validity and superiority of the proposed method.

Identification immunophenotyping of lung adenocarcinomas based on the tumor microenvironment.

The tumor immune microenvironment is heterogeneous, and its impact on treatment responses is not well understood. It is still a challenge to analyze the interaction between malignant cells and the tumor microenvironment to apply suitable immunotherapy in lung adenocarcinoma. We performed the nonnegative matrix factorization method to 513 messenger RNA expression profiles of lung adenocarcinomas (LUADs) from The Cancer Genome Atlas (TCGA) to obtain an immune-related expression pattern. Subsequently, we characterized the immune-related gene signatures and clinical and survival characteristics. We used 576 patients from Gene Expression Omnibus to confirm our findings. Of the patients in the training cohort, 51% had a high immune enrichment score, high expression of immune cell signaling, cytolytic activity, and interferon (IFN)-related signatures (all P < .05). We denoted these as the Immune Class. We further subdivided the Immune Class into two subclasses based on the tumor microenvironment. These were denoted the Active Immune Class and Exhausted Immune Class. The former showed significant IFN, T-cells, M1 macrophage signatures, and better prognosis (all P < .05), while the latter presented an exhausted immune response with activated stromal enrichment, M2 macrophage signatures, and immunosuppressive factors such as WNT/transforming growth factor-ß (all P < .05). Furthermore, we predicted the response of our immunophenotypes to immunological checkpoint inhibitors (P < .05). Our findings provide a novel insight into the immune-related state of LUAD and can identify the patients who will be receptive to suitable immunotherapeutic treatments.

Exposure to Metalaxyl Disturbs the Skeletal Development of Zebrafish Embryos.

Metalaxyl is broadly applied in agriculture to control peronosporales-caused diseases in plant. To investigate the toxic effects, zebrafish embryos were exposed to metalaxyl at 5, 50 and 500 ng/L for 72 h, the development of larvae were assessed. A significant decreased survival rate, body length, hatching rate (48 h post-fertilization), and a significant increased spinal curvature rate were observed in the 500 ng/L treatment. The lengths of lower jaw, upper jaw and hyomandibular were significantly decreased in the 5, 50 and 500 ng/L groups; while the lower jaw width was significantly increased in the 500 ng/L group. The lengths of palatoquadrate, ceratohyal and ethmoid plate were reduced. Though cyp26a1 mRNA levels showed no significant change, the transcription of bmp2b (in the 500 ng/L group), ihh (in the 50 and 500 ng/L groups), shh (in the 5, 50 and 500 ng/L groups) were significantly up-regulated, which may be related to the abnormal development of the skeleton.

Platelet-derived growth factor-D expression mediates the effect of differentiated degree on prognosis in epithelial ovarian cancer.

Platelet-derived growth factor-D (PDGF-D) can enhance invasion and metastasis in several human malignancies. Although several studies have been performed to investigate the association between clinicopathological characteristics and prognosis in epithelial ovarian cancer (EOC), the mediation effect of PDGF-D on above-mentioned association have been seldom assessed. In this study, we detected the PDGF-D expression from the tissues of patients with EOC and further collected clinicopathological characteristics and prognostic information to identify whether PDGF-D mediated the effect of differentiated degree on prognosis in patients with EOC. A total of 190 paraffin-embedded tissue samples from patients with EOC between July 2005 and December 2010 were collected. We performed a Kaplan-Meier analysis for the association between differentiated degree and prognosis followed by a causal mediation analysis. The analysis results indicated that differentiated degree was associated with prognosis and PDGF-D mediated the effect of differentiated degree on prognosis in patients with EOC, which might be a potential target for ovarian cancer treatment.

The Aerosol Foam Formulation of the Fixed Combination Calcipotriene Plus Betamethasone Dipropionate Improves the Health-Related Quality of Life in Patients With Psoriasis Vulgaris: Results from the Randomized PSO-FAST Study.

INTRODUCTION: Psoriasis has a major impact on patient quality of life, similar to that seen in other chronic diseases, eg, diabetes. Health-related quality of life (HRQoL) measures are commonly included in clinical trial designs, capturing the disease burden and therapeutic success of a treatment. In the randomized, double-blind, phase III PSO-FAST (Psoriasis vulgaris, a Four-week, vehicle-controlled, efficacy And Safety Trial) study (nCT01866163), fixed combination calcipotriene (Cal) 0.005% plus betamethasone dipropionate (BD) 0.064% aerosol foam was compared with vehicle. By treatment end, 53% of patients using Cal/BD foam achieved treatment success.
OBJECTIVE: To compare the impact on HRQoL of Cal/BD foam vs vehicle in patients with mild-to-severe psoriasis.
METHOD: HRQoL was assessed by dermatology life-quality index (DLQI; baseline, weeks 1, 2, 4) and EQ-5D-5L (EQ-5D; baseline, week 4) questionnaires. A DLQI score of 0 (range, 0-30) indicates no effect on the patient's life; an EQ-5D utility score of 1 (range, 0-1) and an EQ-5D visual analog scale (VAS) score of 100 (range, 1-100) indicate perfect health.
RESULTS: 426 patients were randomized (Cal/BD foam, n=323; vehicle, n=103). Baseline mean DLQI scores were 9.9 (Cal/BD foam) and 10.3 (vehicle). The impact of psoriasis on HRQoL (EQ-5D utility score) at baseline was primarily driven by pain/discomfort (Cal/BD foam: 69.9%; vehicle: 65.0%) and anxiety/depression (Cal/BD foam: 45.3%; vehicle 44.7%). There was a greater improvement from baseline in DLQI score for Cal/BD foam vs vehicle at week 4 (-7.0 vs -4.4; P<.001); increased improvement was also seen in EQ-5D scores. At week 4, 48.1% of patients using Cal/BD foam reported no effect of psoriasis on their lives (DLQI = 0/1), and of patients using Cal/BD foam with baseline DLQI scores ≥5, 81.2% achieved a ≥5-point improvement.
CONCLUSION: Cal/BD aerosol foam improved HRQoL after 4 weeks, with most patients experiencing a clinically meaningful improvement and almost 50% reporting no impairment.

J Drugs Dermatol. 2016;15(8):981-987.

Ingenol mebutate gel for actinic keratosis.

BACKGROUND: Actinic keratosis is a common precursor to sun-related squamous-cell carcinoma. Treating actinic keratoses and the surrounding skin area (i.e., field therapy) can eradicate clinical and subclinical actinic keratoses. Topical field therapy currently requires weeks or months of treatment. We investigated the efficacy and safety of a new topical field therapy for actinic keratosis, ingenol mebutate gel (0.015% for face and scalp and 0.05% for trunk and extremities). METHODS: In four multicenter, randomized, double-blind studies, we randomly assigned patients with actinic keratoses on the face or scalp or on the trunk or extremities to receive ingenol mebutate or placebo (vehicle), self-applied to a 25-cm(2) contiguous field once daily for 3 consecutive days for lesions on the face or scalp or for 2 consecutive days for the trunk or extremities. Complete clearance (primary outcome) was assessed at 57 days, and local reactions were quantitatively measured. RESULTS: In a pooled analysis of the two trials involving the face and scalp, the rate of complete clearance was higher with ingenol mebutate than with placebo (42.2% vs. 3.7%, P<0.001). Local reactions peaked at day 4, with a mean maximum composite score of 9.1 on the local-skin-response scale (which ranges from 0 to 4 for six types of reaction, yielding a composite score of 0 to 24, with higher numbers indicating more severe reactions), rapidly decreased by day 8, and continued to decrease, approaching baseline scores by day 29. In a pooled analysis of the two trials involving the trunk and extremities, the rate of complete clearance was also higher with ingenol mebutate than with placebo (34.1% vs. 4.7%, P<0.001). Local skin reactions peaked between days 3 and 8 and declined rapidly, approaching baseline by day 29, with a mean maximum score of 6.8. Adverse events were generally mild to moderate in intensity and resolved without sequelae. CONCLUSIONS: Ingenol mebutate gel applied topically for 2 to 3 days is effective for field treatment of actinic keratoses. (Funded by LEO Pharma; ClinicalTrials.gov numbers, NCT00742391, NCT00916006, NCT00915551, and NCT00942604.).

Efficacy and Safety of Calcipotriene Plus Betamethasone Dipropionate Aerosol Foam in Patients With Psoriasis Vulgaris--a Randomized Phase III Study (PSO-FAST).

INTRODUCTION: An innovative aerosol foam formulation of calcipotriene 0.005% (Cal) plus betamethasone dipropionate 0.064% (BD) designed to improve treatment outcomes. OBJECTIVE: To compare the efficacy and safety of Cal/BD aerosol foam with aerosol foam vehicle in patients with psoriasis. DESIGN: Phase III, double-blind, randomized PSO-FAST (Cal/BD foam in PSOriasis vulgaris, a Four-week, vehicle-controlled, efficacy And Safety Trial) study recruited patients with ≥ mild severity psoriasis of the trunk and/or limbs from 27 US outpatient sites (NCT01866163). Patients were randomized (3:1) to Cal/BD foam or vehicle once-daily for 4 weeks. PRIMARY OUTCOME: proportion of patients at week 4 who achieved treatment success according to physician's global assessment. SECONDARY OUTCOMES: modified (excluding head) psoriasis area and severity index (mPASI) and patient's assessment of itch (visual analog scale). Safety was monitored by adverse events/calcium homeostasis. RESULTS: 426 patients enrolled between June and October 2013 (Cal/BD foam, n=323; vehicle, n=103). At week 4, significantly more patients using Cal/BD foam achieved treatment success versus vehicle (53.3 versus 4.8%; OR 30.3, 95% CI 9.7,94.3; P < .001) and mean mPASI score was significantly lower for patients using Cal/BD foam than vehicle (2.0 versus 5.5; adjusted difference -3.3, P <.001). Significantly greater itch relief was observed for patients using Cal/BD foam than vehicle (P = .010 at day 3, P < .001 from day 5). Adverse drug reactions were reported in 10 Cal/BD foam patients (3.1%) and two vehicle patients (1.9%); events occurred in one patient each except application site pain (Cal/BD foam, two patients; vehicle, one patient). There were no clinically significant changes in calcium homeostasis. CONCLUSIONS: Cal/BD foam was efficacious, achieved rapid itch relief and was well tolerated in patients with body psoriasis. This innovative aerosol foam formulation is expected to become a valuable treatment option.

A novel subtype based on driver methylation-transcription in lung adenocarcinoma.

AIMS: To identify driver methylation genes and a novel subtype of lung adenocarcinoma (LUAD) by multi-omics and elucidate its molecular features and clinical significance. METHODS: We collected LUAD patients from public databases, and identified driver methylation genes (DMGs) by MethSig and MethylMix algrothms. And novel driver methylation multi-omics subtypes were identified by similarity network fusion (SNF). Furthermore, the prognosis, tumor microenvironment (TME), molecular features and therapy efficiency among subtypes were comprehensively evaluated. RESULTS: 147 overlapped driver methylation were identified and validated. By integrating the mRNA expression and methylation of DMGs using SNF, four distinct patterns, termed as S1-S4, were characterized by differences in prognosis, biological features, and TME. The S2 subtype showed unfavorable prognosis. By comparing the characteristics of the DMGs subtypes with the traditional subtypes, S3 was concentrated in proximal-inflammatory (PI) subtype, and S4 was consisted of terminal respiratory unit (TRU) subtype and PI subtype. By analyzing TME and epithelial mesenchymal transition (EMT) features, increased immune infiltration and higher expression of immune checkpoint genes were found in S3 and S4. While S4 showed higher EMT score and expression of EMT associated genes, indicating S4 may not be as immunosensitive as the S3. Additionally, S3 had lower TIDE and higher IPS score, indicating its increased sensitivity to immunotherapy. CONCLUSION: The driver methylation-related subtypes of LUAD demonstrate prognostic predictive ability that could help inform treatment response and provide complementary information to the existing subtypes.

Exploring Factors Affecting Acceptance of Fecal Microbiota Transplantation for Patients with Recurrent Urinary Tract Infections: a Descriptive Qualitative Study.

Purpose: Patients with recurrent urinary tract infections face complex management challenges. Fecal microbiota transplantation is a superior treatment for chronic infectious diseases, but limited patient knowledge affects treatment decisions. This study aims to identify factors associated with hesitancy towards fecal microbiota transplantation among patients with recurrent urinary tract infections, to help physicians and nurses in providing accurate and useful information to patients. Patients and Methods: A descriptive qualitative approach was employed, utilizing semi-structured interviews conducted with patients experiencing recurrent urinary tract infections who expressed hesitancy towards fecal microbiota transplantation. The interviews took place between September 2021 and December 2022. Thematic analysis was conducted on the semi-structured interviews to identify perceived facilitators and barriers associated with fecal microbiota transplantation. Results: The analysis included interviews with thirty adult female patients with recurrent urinary tract infections. Four facilitators influencing patients' decision-making regarding fecal microbiota transplantation were identified: (1) the motivating role of hope and expectations for active patient participation; (2) the influence of healthcare providers, as well as family members and friends on patients' decisions to pursue fecal microbiota transplantation; (3) the patients' perception of fecal microbiota transplantation as a low-risk treatment option; and (4) the dedication to the advancement of medical treatments. In contrast, two primary barriers to accepting fecal microbiota transplantation were identified: (1) that conventional treatment controls disease activity, while fecal microbiota transplantation effects remain uncertain; and (2) that safety concerns surrounding fecal microbiota transplantation. Conclusion: Comprehensive information about fecal microbiota transplantation, including donor selection, sample processing, the procedure, and potential discomfort, is essential for patients and families to make informed treatment decisions. Registration: CHiCTR2100048970.

A bidirectional interpretable compound-protein interaction prediction framework based on cross attention.

The identification of compound-protein interactions (CPIs) plays a vital role in drug discovery. However, the huge cost and labor-intensive nature in vitro and vivo experiments make it urgent for researchers to develop novel CPI prediction methods. Despite emerging deep learning methods have achieved promising performance in CPI prediction, they also face ongoing challenges: (i) providing bidirectional interpretability from both the chemical and biological perspective for the prediction results; (ii) comprehensively evaluating model generalization performance; (iii) demonstrating the practical applicability of these models. To overcome the challenges posed by current deep learning methods, we propose a cross multi-head attention oriented bidirectional interpretable CPI prediction model (CmhAttCPI). First, CmhAttCPI takes molecular graphs and protein sequences as inputs, utilizing the GCW module to learn atom features and the CNN module to learn residue features, respectively. Second, the model applies cross multi-head attention module to compute attention weights for atoms and residues. Finally, CmhAttCPI employs a fully connected neural network to predict scores for CPIs. We evaluated the performance of CmhAttCPI on balanced datasets and imbalanced datasets. The results consistently show that CmhAttCPI outperforms multiple state-of-the-art methods. We constructed three scenarios based on compound and protein clustering and comprehensively evaluated the model generalization ability within these scenarios. The results demonstrate that the generalization ability of CmhAttCPI surpasses that of other models. Besides, the visualizations of attention weights reveal that CmhAttCPI provides chemical and biological interpretation for CPI prediction. Moreover, case studies confirm the practical applicability of CmhAttCPI in discovering anticancer candidates.

Isobavachalcone: A redox antifungal agent impairs the mitochondria protein of Cryptococcus neoformans.

Isobavachalcone (IBC) is a natural small molecule with various biological activities; however, its inhibitory effects on Cryptococcus neoformans remain unclear. In our study, IBC showed a good antifungal effect. Through in vitro experiments, its minimum inhibitory concentration was 0.5-1 µg/mL. It exhibited the same antifungal effect as Amphotericin B in brain and lung infections in in vivo experiments. IBC also showed a synergistic antifungal effect with emodin with lower toxicity, and C. neoformans did not develop drug resistance to IBC. In the mechanistic study, significantly damaged mitochondria of C. neoformans, a significant reduction in mitochondrial membrane potential and adenosine triphosphate production, and an increase in hydrogen peroxide (H2O2) caused by IBC were observed using transmission electron microscopy. Through drug affinity-responsive target stability combined with phenotype detection, riboflavin synthases of aconitase and succinate dehydrogenase were screened. Molecular docking, quantitative polymerase chain reaction experiments, target inhibitor and agonist intervention, molecular interaction measurements, and minimum inhibitory concentration detection of the constructed expression strains revealed that IBC targeted the activity of these two enzymes, interfered by the tricarboxylic acid cycle, inhibited the production of adenosine triphosphate, blocked electron transport, reduced mitochondrial membrane potential, and induced antioxidation imbalance and reactive oxygen species accumulation, thus producing an antifungal effect. Therefore, IBC is a promising lead drug and redox antifungal agent for C. neoformans.

Impact of coexisting type 2 diabetes mellitus on the urinary microbiota of kidney stone patients.

Objectives: Type 2 diabetes mellitus (T2DM) commonly complicates kidney stone disease (KSD). Our objective is to investigate the variations in the urinary microbiota between individuals with KSD alone and those with KSD plus T2DM. This exploration could have implications for disease diagnosis and treatment strategies. Methods: During lithotripsy, a ureterscope was employed, and 1 mL of urine was collected from the renal pelvis after bladder disinfection. Sequencing targeting the V3-V4 hypervariable region was performed using the 16S rRNA and Illumina Novaseq platform. Results: The Shannon index showed a significant decrease in the KSD plus T2DM group compared to the KSD-only group (false discovery rate = 0.041). Principal Coordinate Analysis (PCoA) demonstrated a distinct bacterial community in the KSD plus T2DM group compared to the KSD-only group (false discovery rate = 0.027). The abundance of Sphingomonas, Corynebacterium, and Lactobacillus was significantly higher in the KSD plus T2DM group than in the KSD-only group (false discovery rate < 0.05). Furthermore, Enhydrobacter, Chryseobacterium, and Allobaculum were positively correlated with fasting blood glucose and HbA1c values (P < 0.05). Conclusions: The urinary microbiota in the renal pelvis exhibits differences between patients with KSD plus T2DM and those with KSD alone. Further studies employing animal models are necessary to validate these distinctions, potentially paving the way for therapeutic developments based on the urinary microbiota.

Compound Event-Triggered Distributed MPC for Coupled Nonlinear Systems.

This article investigates the event-triggered distributed model predictive control (DMPC) for perturbed coupled nonlinear systems subject to state and control input constraints. A novel compound event-triggered DMPC strategy, including a compound triggering condition and a new constraint tightening approach, is developed. In this event-triggered strategy, two stability-related conditions are checked in a parallel manner, which relaxes the requirement of the decrease of the Lyapunov function. An open-loop prediction scheme to avoid periodic transmission is designed for the states in the terminal set. As a result, the number of triggering and transmission instants can be reduced significantly. Furthermore, the proposed constraint tightening approach solves the problem of the state constraint satisfaction, which is quite challenging due to the external disturbances and the mutual influences caused by dynamical coupling. Simulations are conducted at last to validate the effectiveness of the proposed algorithm.

Self-Supervised Spatiotemporal Clustering of Vehicle Emissions With Graph Convolutional Network.

Spatiotemporal clustering of vehicle emissions, which reveals the evolution pattern of air pollution from road traffic, is a challenging representation learning task due to the lack of supervision. Some recent work building upon graph convolutional network (GCN) models the intrinsic spatiotemporal correlations among the nodes in road networks as graph representations for clustering. However, these existing methods ignore the interactions between spatial and temporal variations in vehicle emissions, resulting in incomplete descriptions and inaccurate detection of the evolution pattern of air pollution. To address this issue, this article proposes a two-way self-supervised spatiotemporal representation learning scheme, in which the temporal and spatial features are progressively learned in a mutually reinforced manner. Our proposed method is based on the observation that though the variation in vehicle emissions in the road network is consistent in the spatial and temporal domains, its expression is more distinct in temporal sequences. To this end, the input emission data are first projected into an initial temporal representation space spanned by the captured features from a pretrained BiLSTM network. Then the generated distribution of temporal features is used to construct an objective constraint for high-purity clustering through a two-way self-supervised mechanism, which is leveraged as a constraint for the feature clustering of a GCN. Furthermore, to eliminate the initial errors, a joint optimization scheme is presented to generate the decoupled clustering results through the progressive refinement of representation and clustering. Our proposed method is evaluated on the traffic emission dataset of Xian city in 2020, and the experimental results have demonstrated the superiority against the state-of-the-art.

HiRAND: A novel GCN semi-supervised deep learning-based framework for classification and feature selection in drug research and development.

The prediction of response to drugs before initiating therapy based on transcriptome data is a major challenge. However, identifying effective drug response label data costs time and resources. Methods available often predict poorly and fail to identify robust biomarkers due to the curse of dimensionality: high dimensionality and low sample size. Therefore, this necessitates the development of predictive models to effectively predict the response to drugs using limited labeled data while being interpretable. In this study, we report a novel Hierarchical Graph Random Neural Networks (HiRAND) framework to predict the drug response using transcriptome data of few labeled data and additional unlabeled data. HiRAND completes the information integration of the gene graph and sample graph by graph convolutional network (GCN). The innovation of our model is leveraging data augmentation strategy to solve the dilemma of limited labeled data and using consistency regularization to optimize the prediction consistency of unlabeled data across different data augmentations. The results showed that HiRAND achieved better performance than competitive methods in various prediction scenarios, including both simulation data and multiple drug response data. We found that the prediction ability of HiRAND in the drug vorinostat showed the best results across all 62 drugs. In addition, HiRAND was interpreted to identify the key genes most important to vorinostat response, highlighting critical roles for ribosomal protein-related genes in the response to histone deacetylase inhibition. Our HiRAND could be utilized as an efficient framework for improving the drug response prediction performance using few labeled data.

Outcomes and prognosis of non-small cell lung cancer patients who underwent curable surgery: a protocol for a real-world, retrospective, population-based and nationwide Chinese National Lung Cancer Cohort (CNLCC) study.

INTRODUCTION: Surgery is one of the main approaches for the comprehensive treatment of early and locally advanced non-small cell lung cancer (NSCLC). This study conducts a nationwide multicentre study to explore factors that could influence the outcomes of patients with I-IIIA NSCLC who underwent curable surgery in real-world scenarios. METHODS AND ANALYSIS: All patients diagnosed with NSCLC between January 2013 and December 2020 will be identified from 30 large public medical services centres in mainland China. The algorithm of natural language processing and artificial intelligence techniques were used to extract data from electronic health records of enrolled patients who fulfil the inclusion criteria. Six categories of parameters are collected and stored from the electronic records, then the parameters will be structured as a high-quality structured case report form. The code book will be compiled and each parameter will be classified and designated a code. In addition, the study retrieves the survival status and causes of death of patients from the Chinese Centre for Disease Control and Prevention. The primary endpoints are overall survival and the secondary endpoint is disease-free survival. Finally, an online platform is formed for data queries and the original records will be stored as secure electronic documents. ETHICS AND DISSEMINATION: The study has been approved by the Ethical Committee of the Chinese Academy of Medical Sciences. Study findings will be disseminated via presentations at conferences and publications in open-access journals. This study has been registered in the Chinese Trial Register (ChiCTR2100052773) on 11 May 2021, http://www.chictr.org.cn/showproj.aspx?proj=136659. TRIAL REGISTRATION NUMBER: ChiCTR2100052773.