A contrastive learning approach to integrate spatial transcriptomics and histological images.

The rapid growth of spatially resolved transcriptomics technology provides new perspectives on spatial tissue architecture. Deep learning has been widely applied to derive useful representations for spatial transcriptome analysis. However, effectively integrating spatial multi-modal data remains challenging. Here, we present ConGcR, a contrastive learning-based model for integrating gene expression, spatial location, and tissue morphology for data representation and spatial tissue architecture identification. Graph convolution and ResNet were used as encoders for gene expression with spatial location and histological image inputs, respectively. We further enhanced ConGcR with a graph auto-encoder as ConGaR to better model spatially embedded representations. We validated our models using 16 human brains, four chicken hearts, eight breast tumors, and 30 human lung spatial transcriptomics samples. The results showed that our models generated more effective embeddings for obtaining tissue architectures closer to the ground truth than other methods. Overall, our models not only can improve tissue architecture identification's accuracy but also may provide valuable insights and effective data representation for other tasks in spatial transcriptome analyses.

Acupuncture and tuina knowledge graph with prompt learning.

Introduction: Acupuncture and tuina, acknowledged as ancient and highly efficacious therapeutic modalities within the domain of Traditional Chinese Medicine (TCM), have provided pragmatic treatment pathways for numerous patients. To address the problems of ambiguity in the concept of Traditional Chinese Medicine (TCM) acupuncture and tuina treatment protocols, the lack of accurate quantitative assessment of treatment protocols, and the diversity of TCM systems, we have established a map-filling technique for modern literature to achieve personalized medical recommendations. Methods: (1) Extensive acupuncture and tuina data were collected, analyzed, and processed to establish a concise TCM domain knowledge base. (2)A template-free Chinese text NER joint training method (TemplateFC) was proposed, which enhances the EntLM model with BiLSTM and CRF layers. Appropriate rules were set for ERE. (3) A comprehensive knowledge graph comprising 10,346 entities and 40,919 relationships was constructed based on modern literature. Results: A robust TCM KG with a wide range of entities and relationships was created. The template-free joint training approach significantly improved NER accuracy, especially in Chinese text, addressing issues related to entity identification and tokenization differences. The KG provided valuable insights into acupuncture and tuina, facilitating efficient information retrieval and personalized treatment recommendations. Discussion: The integration of KGs in TCM research is essential for advancing diagnostics and interventions. Challenges in NER and ERE were effectively tackled using hybrid approaches and innovative techniques. The comprehensive TCM KG our built contributes to bridging the gap in TCM knowledge and serves as a valuable resource for specialists and non-specialists alike.

Classifying breast cancer using multi-view graph neural network based on multi-omics data.

Introduction: As the evaluation indices, cancer grading and subtyping have diverse clinical, pathological, and molecular characteristics with prognostic and therapeutic implications. Although researchers have begun to study cancer differentiation and subtype prediction, most of relevant methods are based on traditional machine learning and rely on single omics data. It is necessary to explore a deep learning algorithm that integrates multi-omics data to achieve classification prediction of cancer differentiation and subtypes. Methods: This paper proposes a multi-omics data fusion algorithm based on a multi-view graph neural network (MVGNN) for predicting cancer differentiation and subtype classification. The model framework consists of a graph convolutional network (GCN) module for learning features from different omics data and an attention module for integrating multi-omics data. Three different types of omics data are used. For each type of omics data, feature selection is performed using methods such as the chi-square test and minimum redundancy maximum relevance (mRMR). Weighted patient similarity networks are constructed based on the selected omics features, and GCN is trained using omics features and corresponding similarity networks. Finally, an attention module integrates different types of omics features and performs the final cancer classification prediction. Results: To validate the cancer classification predictive performance of the MVGNN model, we conducted experimental comparisons with traditional machine learning models and currently popular methods based on integrating multi-omics data using 5-fold cross-validation. Additionally, we performed comparative experiments on cancer differentiation and its subtypes based on single omics data, two omics data, and three omics data. Discussion: This paper proposed the MVGNN model and it performed well in cancer classification prediction based on multiple omics data.

An individualized criterion for left bundle branch capture in patients with a narrow QRS complex.

BACKGROUND: Left bundle branch (LBB) pacing (LBBP) is a physiological pacing; however, the accuracy of current electrocardiographic criteria for LBBP remains inadequate. OBJECTIVE: The purpose of this study was to establish a novel individualized criterion to improve the accuracy of LBBP determination in patients with a narrow QRS complex. METHODS: Patients in whom both LBBP and left ventricular septal pacing (LVSP) were acquired during operation were enrolled. LBB conduction time (LBBCT) was measured from LBB potential (LBBpo) to intrinsic QRS onset. LBBpo-V6RWPT, Native-V6RWPT, and Paced-V6RWPT were respectively measured from LBBpo, intrinsic QRS onset, and stimulus to R-wave peak in V6. ΔV6RWPT was the difference value between Paced-V6RWPT and Native-V6RWPT. The accuracy of ΔV6RWPT criterion for determining LBBP was evaluated. RESULTS: In all 71 enrolled patients, ΔV6RWPT was <30 ms during LBBP (21.3 ± 4.6 ms; range 9.3-28.3 ms) but was >30 ms during LVSP (38.5 ± 4.6 ms; range 31.1-47.0 ms). The probability distribution of ΔV6RWPT was well separated between LBBP and LVSP. Sensitivity and specificity of the novel criterion of "ΔV6RWPT <30 ms" for determining LBBP both were 100%. However, the optimal cutoff value of Paced-V6RWPT for validation of LBBP was 64.2 ms, and sensitivity and specificity were 84.5% and 97.2%, respectively. Paced-V6RWPT during LBBP was equivalent to LBBpo-V6RWPT in all patients. There was a strong linear correlation between Native-V6RWPT and LBBpo-V6RWPT (r = 0.796; P <.001). CONCLUSION: ΔV6RWPT could be an accurate individualized criterion for determining LBB capture with high sensitivity and specificity and was superior over the fixed Paced-V6RWPT criterion.

Patient-derived organoids as personalized avatars and a potential immunotherapy model in cervical cancer.

Cervical cancer remains a significant health issue in developing countries. However, finding a preclinical model that accurately reproduces tumor characteristics is challenging. Therefore, we established a patient-derived organoids (PDOs) biobank containing 67 cases of heterogeneous cervical cancer that mimic the histopathological and genomic characteristics of parental tumors. The in vitro response of the organoids indicated their ability to capture the radiological heterogeneity of the patients. To model individual responses to adoptive T cell therapy (ACT), we expanded tumor-infiltrating lymphocytes (TILs) ex vivo and co-cultured them with paired organoids. The PDOs-TILs co-culture system demonstrates clear responses that correspond to established immunotherapy efficiency markers like the proportion of CTLs. This study supports the potential of the PDOs platform to guide treatment in prospective interventional trials in cervical cancer.

Comprehensive mapping of lunar surface chemistry by adding Chang'e-5 samples with deep learning.

Lunar surface chemistry is essential for revealing petrological characteristics to understand the evolution of the Moon. Existing chemistry mapping from Apollo and Luna returned samples could only calibrate chemical features before 3.0 Gyr, missing the critical late period of the Moon. Here we present major oxides chemistry maps by adding distinctive 2.0 Gyr Chang'e-5 lunar soil samples in combination with a deep learning-based inversion model. The inferred chemical contents are more precise than the Lunar Prospector Gamma-Ray Spectrometer (GRS) maps and are closest to returned samples abundances compared to existing literature. The verification of in situ measurement data acquired by Chang'e 3 and Chang'e 4 lunar rover demonstrated that Chang'e-5 samples are indispensable ground truth in mapping lunar surface chemistry. From these maps, young mare basalt units are determined which can be potential sites in future sample return mission to constrain the late lunar magmatic and thermal history.

HMGB1 induces macrophage pyroptosis in chronic endometritis.

BACKGROUND: Chronic endometritis (CE) reflects the local imbalance in the endometrial immune microenvironment after inflammation. High mobility group box 1 (HMGB1) is highly involved in both immunity and inflammation. In this study, we aimed to explore the roles of HMGB1 in the endometrium of patients with CE. METHODS: Endometrium and uterine fluid HMGB1 were tested in a cohort of infertile patients with or without CE. Expression levels of the pyroptosis marker, gasdermin D (GSDMD)-N-terminal (NT), in the human endometrium of patients with CE and controls were determined. Next, the role of HMGB1 as a driver of macrophage pyroptosis was investigated using human THP-1 cells in vitro and a CE mouse model in vivo. RESULTS: High expression levels of HMGB1 in biopsied endometrial tissue and uterine fluid were confirmed in a cohort of patients with CE. Positive correlation between the number of CD138+ cells and HMGB1 mRNA expression level were detected (rs = 0.592, P < 0.001). Meanwhile, we found that GSDMD-NT expression was significantly increased in the CE endometrium at both the transcriptional and translational levels. Moreover, co-localization of GSDMD-NT and macrophages was confirmed via the double immunostaining of GSDMD-NT and CD68. In vitro experiments revealed that macrophage pyroptosis was induced by HMGB1 in human THP-1-derived macrophages. Treatment with glycyrrhizic acid, an inhibitor of HMGB1, significantly suppressed endometrial pyroptosis and inflammation in the CE mouse model. CONCLUSIONS: HMGB1 effectively induced macrophage pyroptosis in the human endometrium, suggesting that its inhibition may serve as a novel treatment option for CE.

Water Quality Prediction Based on Machine Learning and Comprehensive Weighting Methods.

In the context of escalating global environmental concerns, the importance of preserving water resources and upholding ecological equilibrium has become increasingly apparent. As a result, the monitoring and prediction of water quality have emerged as vital tasks in achieving these objectives. However, ensuring the accuracy and dependability of water quality prediction has proven to be a challenging endeavor. To address this issue, this study proposes a comprehensive weight-based approach that combines entropy weighting with the Pearson correlation coefficient to select crucial features in water quality prediction. This approach effectively considers both feature correlation and information content, avoiding excessive reliance on a single criterion for feature selection. Through the utilization of this comprehensive approach, a comprehensive evaluation of the contribution and importance of the features was achieved, thereby minimizing subjective bias and uncertainty. By striking a balance among various factors, features with stronger correlation and greater information content can be selected, leading to improved accuracy and robustness in the feature-selection process. Furthermore, this study explored several machine learning models for water quality prediction, including Support Vector Machines (SVMs), Multilayer Perceptron (MLP), Random Forest (RF), XGBoost, and Long Short-Term Memory (LSTM). SVM exhibited commendable performance in predicting Dissolved Oxygen (DO), showcasing excellent generalization capabilities and high prediction accuracy. MLP demonstrated its strength in nonlinear modeling and performed well in predicting multiple water quality parameters. Conversely, the RF and XGBoost models exhibited relatively inferior performance in water quality prediction. In contrast, the LSTM model, a recurrent neural network specialized in processing time series data, demonstrated exceptional abilities in water quality prediction. It effectively captured the dynamic patterns present in time series data, offering stable and accurate predictions for various water quality parameters.

Multilayer Perceptron Network Optimization for Chaotic Time Series Modeling.

Chaotic time series are widely present in practice, but due to their characteristics-such as internal randomness, nonlinearity, and long-term unpredictability-it is difficult to achieve high-precision intermediate or long-term predictions. Multi-layer perceptron (MLP) networks are an effective tool for chaotic time series modeling. Focusing on chaotic time series modeling, this paper presents a generalized degree of freedom approximation method of MLP. We then obtain its Akachi information criterion, which is designed as the loss function for training, hence developing an overall framework for chaotic time series analysis, including phase space reconstruction, model training, and model selection. To verify the effectiveness of the proposed method, it is applied to two artificial chaotic time series and two real-world chaotic time series. The numerical results show that the proposed optimized method is effective to obtain the best model from a group of candidates. Moreover, the optimized models perform very well in multi-step prediction tasks.

Chinese Few-Shot Named Entity Recognition and Knowledge Graph Construction in Managed Pressure Drilling Domain.

Managed pressure drilling (MPD) is the most effective means to ensure drilling safety, and MPD is able to avoid further deterioration of complex working conditions through precise control of the wellhead back pressure. The key to the success of MPD is the well control strategy, which currently relies heavily on manual experience, hindering the automation and intelligence process of well control. In response to this issue, an MPD knowledge graph is constructed in this paper that extracts knowledge from published papers and drilling reports to guide well control. In order to improve the performance of entity extraction in the knowledge graph, a few-shot Chinese entity recognition model CEntLM-KL is extended from the EntLM model, in which the KL entropy is built to improve the accuracy of entity recognition. Through experiments on benchmark datasets, it has been shown that the proposed model has a significant improvement compared to the state-of-the-art methods. On the few-shot drilling datasets, the F-1 score of entity recognition reaches 33%. Finally, the knowledge graph is stored in Neo4J and applied for knowledge inference.

Efficacy and Safety of Moderate-Intensity Continuous Training on the Improvement of Cardiopulmonary Function in Patients After Transcatheter Aortic Valve Replacement (ENERGY): A Randomized Controlled Trial.

OBJECTIVES: To investigate the effect of moderate-intensity continuous training (MICT) on the improvement of cardiopulmonary function for patients undergoing transcatheter aortic valve replacement (TAVR). DESIGN: Randomized controlled study. SETTING AND PARTICIPANTS: Between August 20, 2021, and February 28, 2022, a total of 66 patients after TAVR were screened for inclusion and randomly divided into the MICT and control groups at a ratio of 1:1. MICT was scheduled 3 times per week for 3 months in the intervention group. Patients in the control group received one-time advice on physical activity according to the current guideline. METHODS: The primary endpoint was the 3-month change in peak oxygen consumption (peak VO2) assessed by cardiopulmonary exercise testing. The secondary endpoints included the 3-month change in 6-minute walk test (6MWT), the 12-Item Short Form Health Survey (SF-12), New York Heart Association (NYHA) class, echocardiographic parameters, and laboratory parameters. RESULTS: After 3 months, the change in peak VO2 was higher in the MICT group than that in the control group (1.63 mL/kg/min, 95% CI 0.58-2.67, P = .003). Change in 6MWT (21.55 m, 95% CI 0.38-42.71, P = .046) was higher in the MICT group compared with the control group. A significant change in favor of MICT was also observed for low-density lipoprotein cholesterol (-0.62 mmol/L, 95% CI -1.00 to -0.23, P = .002). However, there were no significant changes in other echocardiographic indices, laboratory parameters, and SF-12 between the 2 groups (all P > .05). CONCLUSIONS AND IMPLICATIONS: MICT had a positive effect on the cardiopulmonary function and physical capacity of patients after TAVR.

LFDNN: A Novel Hybrid Recommendation Model Based on DeepFM and LightGBM.

Hybrid recommendation algorithms perform well in improving the accuracy of recommendation systems. However, in specific applications, they still cannot reach the requirements of the recommendation target due to the gap between the design of the algorithms and data characteristics. In this paper, in order to learn higher-order feature interactions more efficiently and to distinguish the importance of different feature interactions better on the prediction results of recommendation algorithms, we propose a light and FM deep neural network (LFDNN), a hybrid recommendation model including four modules. The LightGBM module applies gradient boosting decision trees for feature processing, which improves LFDNN's ability to handle dense numerical features; the shallow model introduces the FM model for explicitly modeling the finite-order feature crosses, which strengthens the expressive ability of the model; the deep neural network module uses a fully connected feedforward neural network to allow the model to obtain more high-order feature crosses information and mine more data patterns in the features; finally, the Fusion module allows the shallow model and the deep model to obtain a better fusion effect. The results of comparison, parameter influence and ablation experiments on two real advertisement datasets shows that the LFDNN reaches better performance than the representative recommendation models.

Gut dysbiosis-derived ß-glucuronidase promotes the development of endometriosis.

OBJECTIVE: To explore the role of gut dysbiosis-derived ß-glucuronidase (GUSB) in the development of endometriosis (EMs). DESIGN: 16S rRNA sequencing of stool samples from women with (n = 35) or without (n = 30) endometriosis and from a mouse model was conducted to assess gut microbiome changes and identify molecular factors influencing the development of endometriosis. Experiments in vivo in an endometriosis C57BL6 mouse model and in vitro verified the level of GUSB and its role in the development of EMs. SETTING: Department of Obstetrics and Gynecology, The First Affiliated Hospital of Sun Yat-sen University; Guangdong Provincial Clinical Research Center for Obstetrical and Gynecological Diseases. PATIENT(S): Women of reproductive age with a histological diagnosis of endometriosis were enrolled in the endometriosis group (n = 35) and infertile or healthy age-matched women who had undergone a gynecological or radiological examination in the control group (n = 30). Fecal and blood samples were taken the day before surgery. Paraffin-embedded sections from 50 bowel endometriotic lesions, 50 uterosacral lesions, 50 samples without lesions, and 50 normal endometria were collected. INTERVENTION(S): None. MAIN OUTCOME MEASURE(S): Changes in the gut microbiome of patients with EMs and mice and the effect of ß-glucuronidase on the proliferation and invasion of endometrial stromal cells and the development of endometriotic lesions were assessed. RESULT(S): No difference in α and ß diversity was found between patients with EMs and controls. Immunohistochemistry analysis showed higher ß-glucuronidase expression in bowel lesions and uterosacral ligament lesions than in the normal endometrium (p<0.01). ß-Glucuronidase promoted the proliferation and migration of endometrial stromal cells during cell counting kit-8, Transwell, and wound-healing assays. Macrophage levels, especially M2, were higher in bowel lesions and uterosacral ligament lesions than in controls, and ß-glucuronidase promoted the M0 to M2 transition. Medium conditioned by ß-glucuronidase-treated macrophages promoted endometrial stromal cell proliferation and migration. ß-Glucuronidase increased the number and volume of endometriotic lesions and number of macrophages present in lesions in the mouse EMs model. CONCLUSION(S): This ß-Glucuronidase promoted EMs development directly or indirectly by causing macrophage dysfunction. The characterization of the pathogenic role of ß-glucuronidase in EMs has potential therapeutic implications.

Daily exercise improves the long-term prognosis of patients with acute coronary syndrome.

Objective: To demonstrate the effect of daily exercise on the incidence of major adverse cardiovascular events (MACE) for patients with acute coronary syndrome (ACS). Methods: A cohort of 9,636 patients with ACS were consecutively enrolled in our retrospective study between November 2015 and September 2017, which were used for model development. 6,745 patients were assigned as the derivation cohort and 2,891 patients were assigned as the validation cohort. The least absolute shrinkage and selection operator (LASSO) regression and COX regression were used to screen out significant variables for the construction of the nomogram. Multivariable COX regression analysis was employed for the development of a model represented by a nomogram. The nomogram was then evaluated for performance traits such as discrimination, calibration, and clinical efficacy. Results: Among 9,636 patients with ACS (mean [SD] age, 60.3 [10.4] years; 7,235 men [75.1%]), the 5-year incidence for MACE was 0.19 at a median follow-up of 1,747 (1,160-1,825) days. Derived from the LASSO regression and COX regression, the nomogram has included 15 factors in total including age, previous myocardial infarction (MI), previous percutaneous coronary intervention (PCI), systolic pressure, N-terminal Pro-B-type natriuretic peptide (NT-proBNP), high-density lipoprotein cholesterol (HDL), serum creatinine, left ventricular end-diastolic diameter (LVEDD), Killip class, the Synergy between Percutaneous Coronary Intervention with Taxus and Cardiac Surgery (SYNTAX) score, left anterior descending (LAD) stenosis (≥50%), circumflex (LCX) stenosis (≥50%), right coronary artery (RCA) stenosis (≥50%), exercise intensity, cumulative time. The 5-year area under the ROC curve (AUC) of derivation and validation cohorts were 0.659 (0.643-0.676) and 0.653 (0.629-0.677), respectively. The calibration plots showed the strong concordance performance of the nomogram model in both two cohorts. Moreover, decision curve analysis (DCA) also showed the usefulness of nomogram in clinical practice. Conclusion: The present work provided a prediction nomogram predicting MACE for patients with ACS after incorporating the already known factors and the daily exercise, which demonstrated the effectiveness of daily exercise on the improvement of prognosis for patients with ACS.

Ability to remotely monitor atrial high-rate episodes using a single-chamber implantable cardioverter-defibrillator with a floating atrial sensing dipole.

AIMS: To allow timely initiation of anticoagulation therapy for the prevention of stroke, the European guidelines on atrial fibrillation (AF) recommend remote monitoring (RM) of device-detected atrial high-rate episodes (AHREs) and progression of arrhythmia duration along pre-specified strata (6 min…<1 h, 1 h…<24 h, ≥ 24 h). We used the MATRIX registry data to assess the capability of a single-lead implantable cardioverter-defibrillator (ICD) with atrial sensing dipole (DX ICD system) to follow this recommendation in patients with standard indication for single-chamber ICD. METHODS AND RESULTS: In 1841 DX ICD patients with daily automatic RM transmissions, electrograms of first device-detected AHREs per patient in each duration stratum were adjudicated, and the corresponding positive predictive values (PPVs) for the detections to be true atrial arrhythmia were calculated. Moreover, the incidence and progression of new-onset AF was assessed in 1451 patients with no AF history. A total of 610 AHREs ≥6 min were adjudicated. The PPV was 95.1% (271 of 285) for episodes 6min…<1 h, 99.6% (253/254) for episodes 1 h…<24 h, 100% (71/71) for episodes ≥24 h, or 97.5% for all episodes (595/610). The incidence of new-onset AF was 8.2% (119/1451), and in 31.1% of them (37/119), new-onset AF progressed to a higher duration stratum. Nearly 80% of new-onset AF patients had high CHA2DS2-VASc stroke risk, and 70% were not on anticoagulation therapy. Age was the only significant predictor of new-onset AF. CONCLUSION: A 99.7% detection accuracy for AHRE ≥1 h in patients with DX ICD systems in combination with daily RM allows a reliable guideline-recommended screening for subclinical AF and monitoring of AF-duration progression.

scBGEDA: deep single-cell clustering analysis via a dual denoising autoencoder with bipartite graph ensemble clustering.

MOTIVATION: Single-cell RNA sequencing (scRNA-seq) is an increasingly popular technique for transcriptomic analysis of gene expression at the single-cell level. Cell-type clustering is the first crucial task in the analysis of scRNA-seq data that facilitates accurate identification of cell types and the study of the characteristics of their transcripts. Recently, several computational models based on a deep autoencoder and the ensemble clustering have been developed to analyze scRNA-seq data. However, current deep autoencoders are not sufficient to learn the latent representations of scRNA-seq data, and obtaining consensus partitions from these feature representations remains under-explored. RESULTS: To address this challenge, we propose a single-cell deep clustering model via a dual denoising autoencoder with bipartite graph ensemble clustering called scBGEDA, to identify specific cell populations in single-cell transcriptome profiles. First, a single-cell dual denoising autoencoder network is proposed to project the data into a compressed low-dimensional space and that can learn feature representation via explicit modeling of synergistic optimization of the zero-inflated negative binomial reconstruction loss and denoising reconstruction loss. Then, a bipartite graph ensemble clustering algorithm is designed to exploit the relationships between cells and the learned latent embedded space by means of a graph-based consensus function. Multiple comparison experiments were conducted on 20 scRNA-seq datasets from different sequencing platforms using a variety of clustering metrics. The experimental results indicated that scBGEDA outperforms other state-of-the-art methods on these datasets, and also demonstrated its scalability to large-scale scRNA-seq datasets. Moreover, scBGEDA was able to identify cell-type specific marker genes and provide functional genomic analysis by quantifying the influence of genes on cell clusters, bringing new insights into identifying cell types and characterizing the scRNA-seq data from different perspectives. AVAILABILITY AND IMPLEMENTATION: The source code of scBGEDA is available at https://github.com/wangyh082/scBGEDA. The software and the supporting data can be downloaded from https://figshare.com/articles/software/scBGEDA/19657911. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

CircVPRBP inhibits nodal metastasis of cervical cancer by impeding RACK1 O-GlcNAcylation and stability.

Lymph node (LN) metastasis is one of the most malignant clinical features in patients with cervical cancer (CCa). Understanding the mechanism of lymph node metastasis will provide treatment strategies for patients with CCa. Circular RNAs (circRNA) play a critical role in the development of human cancers. However, the role and mechanism of circRNAs in lymph node metastasis remain largely unknown. Here, it is reported that loss expression of circRNA circVPRBP was closely associated with LN metastasis and poor survival of CCa patients. In vitro and in vivo assays showed that circVPRBP overexpression notably inhibited lymphangiogenesis and LN metastasis, whereas RfxCas13d mediated silencing of circVPRBP promoted lymphangiogenesis and the ability of the cervical cancer cells to metastasize to the LNs. Mechanistically, circVPRBP could bind to RACK1 and shield the S122 O-GlcNAcylation site to promote RACK1 degradation, resulting in inhibition of Galectin-1 mediated lymphangiogenesis and LN metastasis in CCa. Taken together, the results demonstrate that circVPRBP is a potential prognostic biomarker and a novel therapeutic target for LN metastasis in CCa patients.

A comprehensive psychological tendency prediction model for pregnant women based on questionnaires.

More and more people are under high pressure in modern society, leading to growing mental disorders, such as antenatal depression for pregnant women. Antenatal depression can affect pregnant woman's physical and psychological health and child outcomes, and cause postpartum depression. Therefore, it is essential to detect the antenatal depression of pregnant women early. This study aims to predict pregnant women's antenatal depression and identify factors that may lead to antenatal depression. First, a questionnaire was designed, based on the daily life of pregnant women. The survey was conducted on pregnant women in a hospital, where 5666 pregnant women participated. As the collected data is unbalanced and has high dimensions, we developed a one-class classifier named Stacked Auto Encoder Support Vector Data Description (SAE-SVDD) to distinguish depressed pregnant women from normal ones. To validate the method, SAE-SVDD was firstly applied on three benchmark datasets. The results showed that SAE-SVDD was effective, with its F-scores better than other popular classifiers. For the antenatal depression problem, the F-score of SAE- SVDD was higher than 0.87, demonstrating that the questionnaire is informative and the classification method is successful. Then, by an improved Term Frequency-Inverse Document Frequency (TF-IDF) analysis, the critical factors of antenatal depression were identified as work stress, marital status, husband support, passive smoking, and alcohol consumption. With its generalizability, SAE-SVDD can be applied to analyze other questionnaires.

Bilateral septal pacing in combination with coronary venous pacing for cardiac resynchronization therapy.

BACKGROUND: Conventional right ventricular pacing combined with coronary venous pacing (CVP) is a mainstay for cardiac resynchronization therapy (CRT). However, QRS duration of conventional CRT may be frequently more than 130 ms. This study aimed to evaluate the effectiveness of QRS narrowing by bilateral septal pacing (BSP) in combination with CVP for CRT (BSP-CRT). METHODS: Fourteen patients with QRS > 130 ms of conventional CRT after failure of physiological conduction system pacing were enrolled. Electrophysiologic characteristics were compared among different modes of CRT during procedure. BSP which was defined as capture of both sides of interventricular septum manifested as shortened R wave peak time without a right bundle branch block QRS pattern. RESULTS: BSP-CRT were successfully achieved in 85.7% (12/14) patients. QRS duration at baseline was 185 ± 13 ms and significantly narrowed to 156 ± 9 ms during conventional CRT (n = 14, P < .001), to 143 ± 7 ms during left ventricular septal pacing (LVSP) in combination with CVP for CRT (LVSP-CRT) (n = 9, P < .001), and further to 122 ± 10 ms during BSP-CRT (n = 12, P < .001). Notably, among 7 patients in whom both LVSP and BSP were achieved, BSP-CRT outperformed LVSP-CRT at QRS narrowing by 16% (P < .001). At 3-month follow-up, left ventricular ejection fraction improved from 29 ± 6% to 41 ± 8% (P < .001). CONCLUSIONS: BSP-CRT resulted in superior acute electrical synchronization to conventional CRT and might be considered as an alternative to conventional CRT with QRS more than 130 ms.

scWMC: weighted matrix completion-based imputation of scRNA-seq data via prior subspace information.

MOTIVATION: Single-cell RNA sequencing (scRNA-seq) can provide insight into gene expression patterns at the resolution of individual cells, which offers new opportunities to study the behavior of different cell types. However, it is often plagued by dropout events, a phenomenon where the expression value of a gene tends to be measured as zero in the expression matrix due to various technical defects. RESULTS: In this article, we argue that borrowing gene and cell information across column and row subspaces directly results in suboptimal solutions due to the noise contamination in imputing dropout values. Thus, to impute more precisely the dropout events in scRNA-seq data, we develop a regularization for leveraging that imperfect prior information to estimate the true underlying prior subspace and then embed it in a typical low-rank matrix completion-based framework, named scWMC. To evaluate the performance of the proposed method, we conduct comprehensive experiments on simulated and real scRNA-seq data. Extensive data analysis, including simulated analysis, cell clustering, differential expression analysis, functional genomic analysis, cell trajectory inference and scalability analysis, demonstrate that our method produces improved imputation results compared to competing methods that benefits subsequent downstream analysis. AVAILABILITY AND IMPLEMENTATION: The source code is available at https://github.com/XuYuanchi/scWMC and test data is available at https://doi.org/10.5281/zenodo.6832477. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.