Fine mapping and analysis of a candidate gene controlling Phytophthora blight resistance in cucumber

Cucumber blight is a destructive disease. The best way to control this disease is resistance breeding. This study focuses on disease resistance gene mapping and molecular marker development. We used the resistant cucumber, JSH, and susceptible cucumber, B80, as parents to construct F2 populations. Bulked segregant analysis (BSA) combined with specific length amplified fragment sequencing (SLAF-seq) were used, from which we developed cleaved amplified polymorphic sequence (CAPs) markers to map the resistance gene. Resistance in F2 individuals showed a segregation ratio of resistance:susceptibility close to 3:1. The gene in JSH resistant cucumber was mapped to an interval of 9.25 kb, and sequencing results for the three genes in the mapped region revealed three mutations at base sites 225, 302, and 591 in the coding region of Csa5G139130 between JSH and B80, but no mutations in coding regions of Csa5G139140 and Csa5G139150. The mutations caused changes in amino acids 75 and 101 of the protein encoded by Csa5G139130, suggesting that Csa5G139130 is the most likely resistance candidate gene. We developed a molecular marker, CAPs-4, as a closely linked marker for the cucumber blight resistance gene. This is the first report on mapping of a cucumber blight resistance gene and will provideg a useful marker for molecular breeding of cucumber resistance to Phytophthora blight.

A Novel Skip-Connection Strategy by Fusing Spatial and Channel Wise Features for Multi-Region Medical Image Segmentation

Recent methods often introduce attention mechanisms into the skip connections of U-shaped networks to capture features. However, these methods usually overlook spatial information extraction in skip connections and exhibit inefficiency in capturing spatial and channel information. This issue prompts us to reevaluate the design of the skip-connection mechanism and propose a new deep-learning network called the Fusing Spatial and Channel Attention Network, abbreviated as FSCA-Net. FSCA-Net is a novel U-shaped network architecture that utilizes the Parallel Attention Transformer (PAT) to enhance the extraction of spatial and channel features in the skip-connection mechanism, further compensating for downsampling losses. We design the Cross-Attention Bridge Layer (CAB) to mitigate excessive feature and resolution loss when downsampling to the lowest level, ensuring meaningful information fusion during upsampling at the lowest level. Finally, we construct the Dual-Path Channel Attention (DPCA) module to guide channel and spatial information filtering for Transformer features, eliminating ambiguities with decoder features and better concatenating features with semantic inconsistencies between the Transformer and the U-Net decoder. FSCA-Net is designed explicitly for fine-grained segmentation tasks of multiple organs and regions. Our approach achieves over 48% reduction in FLOPs and over 32% reduction in parameters compared to the state-of-the-art method. Moreover, FSCA-Net outperforms existing segmentation methods on seven public datasets, demonstrating exceptional performance. The code has been made available on GitHub: https://github.com/Henry991115/FSCA-Net.

Prediction of drug-protein interaction based on dual channel neural networks with attention mechanism

The precise identification of drug-protein inter action (DPI) can significantly speed up the drug discovery process. Bioassay methods are time-consuming and expensive to screen for each pair of drug proteins. Machine-learning-based methods cannot accurately predict a large number of DPIs. Compared with traditional computing methods, deep learning methods need less domain knowledge and have strong data learning ability. In this study, we construct a DPI prediction model based on dual channel neural networks with an efficient path attention mechanism, called DCA-DPI. The drug molecular graph and protein sequence are used as the data input of the model, and the residual graph neural network and the residual convolution network are used to learn the feature representation of the drug and protein, respectively, to obtain the feature vector of the drug and the hidden vector of protein. To get a more accurate protein feature vector, the weighted sum of the hidden vector of protein is applied using the neural attention mechanism. In the end, drug and protein vectors are concatenated and input into the full connection layer for classification. In order to evaluate the performance of DCA-DPI, three widely used public data, Human, C.elegans and DUD-E, are used in the experiment. The evaluation metrics values in the experiment are superior to other relevant methods. Experiments show that our model is efficient for DPI prediction.

Large-Scale Data-Driven Optimization in Deep Modeling With an Intelligent Decision-Making Mechanism

This study focuses on building an intelligent decision-making attention mechanism in which the channel relationship and conduct feature maps among specific deep Dense ConvNet blocks are connected to each other. Thus, develop a novel freezing network with a pyramid spatial channel attention mechanism (FPSC-Net) in deep modeling. This model studies how specific design choices in the large-scale data-driven optimization and creation process affect the balance between the accuracy and effectiveness of the designed deep intelligent model. To this end, this study presents a novel architecture unit, which is termed as the "Activate-and-Freeze" block on popular and highly competitive datasets. In order to extract informative features by fusing spatial and channel-wise information together within local receptive fields and boost the representation power, this study constructs a Dense-attention module (pyramid spatial channel (PSC) attention) to perform feature recalibration, and through the PSC attention to model the interdependence among convolution feature channels. We join the PSC attention module in the activating and back-freezing strategy to search for one of the most important parts of the network for extraction and optimization. Experiments on various large-scale datasets demonstrate that the proposed method can achieve substantially better performance for improving the ConvNets representation power than the other state-of-the-art deep models.

Deep Adaptive Fuzzy Clustering for Evolutionary Unsupervised Representation Learning

Cluster assignment of large and complex datasets is a crucial but challenging task in pattern recognition and computer vision. In this study, we explore the possibility of employing fuzzy clustering in a deep neural network framework. Thus, we present a novel evolutionary unsupervised learning representation model with iterative optimization. It implements the deep adaptive fuzzy clustering (DAFC) strategy that learns a convolutional neural network classifier from given only unlabeled data samples. DAFC consists of a deep feature quality-verifying model and a fuzzy clustering model, where deep feature representation learning loss function and embedded fuzzy clustering with the weighted adaptive entropy is implemented. We joint fuzzy clustering to the deep reconstruction model, in which fuzzy membership is utilized to represent a clear structure of deep cluster assignments and jointly optimize for the deep representation learning and clustering. Also, the joint model evaluates current clustering performance by inspecting whether the resampled data from estimated bottleneck space have consistent clustering properties to improve the deep clustering model progressively. Experiments on various datasets show that the proposed method obtains a substantially better performance for both reconstruction and clustering quality compared to the other state-of-the-art deep clustering methods, as demonstrated with the in-depth analysis in the extensive experiments.

PMMNet: A Dual Branch Fusion Network of Point Cloud and Multi-View for Intracranial Aneurysm Classification and Segmentation

Intracranial aneurysm (IA) is a vascular disease of the brain arteries caused by pathological vascular dilation, which can result in subarachnoid hemorrhage if ruptured. Automatically classification and segmentation of intracranial aneurysms are essential for their diagnosis and treatment. However, the majority of current research is focused on two-dimensional images, ignoring the 3D spatial information that is also critical. In this work, we propose a novel dual-branch fusion network called the Point Cloud and Multi-View Medical Neural Network (PMMNet) for IA classification and segmentation. Specifically, one branch based on 3D point clouds serves the purpose of extracting spatial features, whereas the other branch based on multi-view images acquires 2D pixel features. Ultimately, the two types of features are fused for IA classification and segmentation. To extract both local and global features from 3D point clouds, Multilayer Perceptron (MLP) and the attention mechanism are used in parallel. In addition, a SPSA module is proposed for multi-view image feature learning, which extracts more exquisite channel and spatial multi-scale features from 2D images. Experiments conducted on the IntrA dataset outperform other state-of-the-art methods, demonstrating that the proposed PMMNet exhibits strong superiority on the medical 3D dataset. We also obtain competitive results on public datasets, including ModelNet40, ModelNet10, and ShapeNetPart, which further validate the robustness and generality of the PMMNet.

scAMAC: self-supervised clustering of scRNA-seq data based on adaptive multi-scale autoencoder

Cluster assignment is vital to analyzing single-cell RNA sequencing (scRNA-seq) data to understand high-level biological processes. Deep learning-based clustering methods have recently been widely used in scRNA-seq data analysis. However, existing deep models often overlook the interconnections and interactions among network layers, leading to the loss of structural information within the network layers. Herein, we develop a new self-supervised clustering method based on an adaptive multi-scale autoencoder, called scAMAC. The self-supervised clustering network utilizes the Multi-Scale Attention mechanism to fuse the feature information from the encoder, hidden and decoder layers of the multi-scale autoencoder, which enables the exploration of cellular correlations within the same scale and captures deep features across different scales. The self-supervised clustering network calculates the membership matrix using the fused latent features and optimizes the clustering network based on the membership matrix. scAMAC employs an adaptive feedback mechanism to supervise the parameter updates of the multi-scale autoencoder, obtaining a more effective representation of cell features. scAMAC not only enables cell clustering but also performs data reconstruction through the decoding layer. Through extensive experiments, we demonstrate that scAMAC is superior to several advanced clustering and imputation methods in both data clustering and reconstruction. In addition, scAMAC is beneficial for downstream analysis, such as cell trajectory inference. Our scAMAC model codes are freely available at https://github.com/yancy2024/scAMAC.

CFANet: Context Feature Fusion and Attention Mechanism Based Network for Small Target Segmentation in Medical Images

Medical image segmentation plays a crucial role in clinical diagnosis, treatment planning, and disease monitoring. The automatic segmentation method based on deep learning has developed rapidly, with segmentation results comparable to clinical experts for large objects, but the segmentation accuracy for small objects is still unsatisfactory. Current segmentation methods based on deep learning find it difficult to extract multiple scale features of medical images, leading to an insufficient detection capability for smaller objects. In this paper, we propose a context feature fusion and attention mechanism based network for small target segmentation in medical images called CFANet. CFANet is based on U-Net structure, including the encoder and the decoder, and incorporates two key modules, context feature fusion (CFF) and effective channel spatial attention (ECSA), in order to improve segmentation performance. The CFF module utilizes contextual information from different scales to enhance the representation of small targets. By fusing multi-scale features, the network captures local and global contextual cues, which are critical for accurate segmentation. The ECSA module further enhances the network's ability to capture long-range dependencies by incorporating attention mechanisms at the spatial and channel levels, which allows the network to focus on information-rich regions while suppressing irrelevant or noisy features. Extensive experiments are conducted on four challenging medical image datasets, namely ADAM, LUNA16, Thoracic OAR, and WORD. Experimental results show that CFANet outperforms state-of-the-art methods in terms of segmentation accuracy and robustness. The proposed method achieves excellent performance in segmenting small targets in medical images, demonstrating its potential in various clinical applications.

Prediction of toxicity outcomes following radiotherapy using deep learning-based models: A systematic review

PURPOSE

This study aims to perform a comprehensive systematic review of deep learning (DL) models in predicting RT-induced toxicity.

MATERIALS AND METHODS

A literature review was performed following the PRISMA guidelines. Systematic searches were performed in PubMed, Scopus, Cochrane and Embase databases from the earliest record up to September 2022. Related studies on deep learning models for radiotherapy toxicity prediction were selected based on predefined PICOS criteria.

RESULTS

Fourteen studies of radiotherapy-treated patients on different types of cancer [prostate (n=2), HNC (n=4), liver (n=2), lung (n=4), cervical (n=1), and oesophagus (n=1)] were eligible for inclusion in the systematic review. Information regarding patient characteristics and model development was summarized. Several approaches, such as ensemble learning, data augmentation, and transfer learning, that were utilized by selected studies were discussed.

CONCLUSION

Deep learning techniques are able to produce a consistent performance for toxicity prediction. Future research using large and diverse datasets and standardization of the study methodologies are required to improve the consistency of the research output.

Denoising adaptive deep clustering with self-attention mechanism on single-cell sequencing data

A large number of works have presented the single-cell RNA sequencing (scRNA-seq) to study the diversity and biological functions of cells at the single-cell level. Clustering identifies unknown cell types, which is essential for downstream analysis of scRNA-seq samples. However, the high dimensionality, high noise and pervasive dropout rate of scRNA-seq samples have a significant challenge to the cluster analysis of scRNA-seq samples. Herein, we propose a new adaptive fuzzy clustering model based on the denoising autoencoder and self-attention mechanism called the scDASFK. It implements the comparative learning to integrate cell similar information into the clustering method and uses a deep denoising network module to denoise the data. scDASFK consists of a self-attention mechanism for further denoising where an adaptive clustering optimization function for iterative clustering is implemented. In order to make the denoised latent features better reflect the cell structure, we introduce a new adaptive feedback mechanism to supervise the denoising process through the clustering results. Experiments on 16 real scRNA-seq datasets show that scDASFK performs well in terms of clustering accuracy, scalability and stability. Overall, scDASFK is an effective clustering model with great potential for scRNA-seq samples analysis. Our scDASFK model codes are freely available at https://github.com/LRX2022/scDASFK.

Global burden of metabolic diseases: data from Global Burden of Disease 2000-2019. A cosortium of metabolic disease

Funding Acknowledgements

Type of funding sources: None.

Background

The growing prevalence of metabolic diseases is a major concern. We sought to examine the global trends and mortality of metabolic diseases using estimates from the Global Burden of Diseases, Injuries and Risk Factors Study (GBD) 2019.

Methods

Global estimates of prevalence, deaths, and disability-adjusted life year (DALYs) from 2000-2019 were examined for metabolic diseases (type 2 diabetes mellitus [T2DM], hypertension, and nonalcoholic fatty liver disease [NAFLD]). For metabolic risk factors (hyperlipidemia and obesity), estimates were limited to mortality and DALYs. Death rates was compared across sex, World Health Organisation regions and Socio-demographic Index (SDI) quintiles. Age-standardised prevalence and death rates were presented per 100,000 population with 95% uncertainty intervals (UI).

Findings

From 2000 to 2019, prevalence rates increased for all metabolic diseases, with the most pronounced increase in high SDI countries. In 2019, the mean (95%UI) age-standardised prevalence per 100,000 population was estimated to be 15,023 (13,493-16,764) for NAFLD, 5,283 (4,864–5,720) for T2DM and 234 (171-313) for hypertension. The highest age-standardised death rates were observed in obesity (62·59 [39·92-89·13]; males, 66·55 [39·76-97·21]; females. 58·14 [38·53-81·39]), followed by hyperlipidemia (56·51 [41·83-73·62]; males, 67·33 [50·78-86·43]; females, 46·50 [32·70-62·38]), T2DM (18·49 [17·18-19·66], males, 67·33 [50·78-86·43]; females, 46·50 [32·70-62·38]), hypertension (15·16 [11·20-16·75]; males, 14·95 [10·32-16·75]; females, 15·05 [11·51-17·09]) and NAFLD (2·09 [1·61-2·60]; males, 2·38 [1·82-3·02]; females, 1·82 [1·41-2·27]). Mortality rates decreased over time in hyperlipidemia (-154%), hypertension (-52%) and NAFLD (-52%), but not in T2DM and obesity. The highest mortality for metabolic diseases was found in Eastern Mediterranean, and low to low-middle SDI countries.

Conclusion

The global prevalence of metabolic diseases has risen over the past two decades regardless of SDI. Attention is needed to address the unchanging mortality rates attributed to metabolic disease and the regional, socioeconomic, and sex disparities in mortality from metabolic disease.

Reconstructed meta-analysis of percutaneous coronary intervention versus coronary artery bypass grafting for left main disease

Background

Randomized controlled trials (RCTs) comparing percutaneous coronary intervention (PCI) with drug-eluting stents and coronary artery bypass grafting (CABG) for patients with left main coronary artery disease (LMCAD) have reported conflicting results.

Objectives

We performed a systematic review from inception to 23 May 2021 and one-stage reconstructed individual-patient data meta-analysis (IPDMA) that included 10-year mortality outcomes.

Methods

The primary outcome was 10-year all-cause mortality. Secondary outcomes included myocardial infarction (MI), stroke and unplanned revascularization at 5 years. We did IPDMA using published Kaplan-Meier curves to provide individual data points in coordinates and numbers at risk were used to increase the calibration accuracy of the reconstructed data. Shared frailty model or, when proportionality assumptions were not met, a restricted mean survival time model were fitted to compare outcomes between treatment groups.

Results

Of 583 articles retrieved, 5 RCTs were included. A total of 4595 patients from these 5 RCTs were randomly assigned to PCI (N=2297) or CABG (N=2298). The cumulative 10-year all-cause mortality after PCI and CABG was 12.0% versus 10.6% respectively (HR 1.093, 95% CI: 0.925–1.292; p=0.296). PCI conferred similar time-to-MI (RMST ratio 1.006, 95% CI: 0.992–1.021, p=0.391) and stroke (RMST ratio 1.005, 95% CI: 0.998–1.013, p=0.133) at 5 years. Unplanned revascularization was more frequent following PCI compared with CABG (HR 1.807, 95% CI: 1.524–2.144, p<0.001) at 5 years.

Conclusion

This meta-analysis using reconstructed participant-level time-to-event data showed no statistically significant difference in cumulative 10-year all-cause mortality between PCI versus CABG in the treatment of LMCAD.

Funding Acknowledgement

Type of funding sources: None.

THIRD bedside ultrasound protocol for rapid diagnosis of undifferentiated shock: a prospective observational study

INTRODUCTION

It is clinically challenging to differentiate the pathophysiological types of shock in emergency situations. Here, we evaluated the ability of a novel bedside ultrasound protocol (Tamponade/tension pneumothorax, Heart, Inferior vena cava, Respiratory system, Deep venous thrombosis/aorta dissection [THIRD]) to predict types of shock in the emergency department.

METHODS

An emergency physician performed the THIRD protocol on all patients with shock who were admitted to the emergency department. All patients were closely followed to determine their final clinical diagnoses. The kappa index, sensitivity, specificity, positive predictive value, and negative predictive value were calculated for the initial diagnostic impression provided by the THIRD protocol, compared with each patient's final diagnosis.

RESULTS

In total, 112 patients were enrolled in this study. The kappa index between initial impression and final diagnosis was 0.81 (95% confidence interval=0.73-0.89; P<0.001). For hypovolaemic, cardiogenic, distributive, and obstructive types of shock, the sensitivities of the THIRD protocol were 100%, 100%, 93%, and 100%, respectively; the sensitivity for a 'mixed' shock aetiology was 86%. The negative predictive value of the THIRD protocol for all five types of shock was ≥96%.

CONCLUSION

Initial diagnostic judgements determined using the THIRD protocol showed favourable agreement with the final diagnosis in patients who presented with undifferentiated shock. The THIRD protocol has great potential for use as a bedside approach that can guide the rapid management of undifferentiated shock in emergency settings, particularly for patients with obstructive, hypovolaemic, or cardiogenic shock.

Functional assessment of military aircrew applicants in a hypobaric chamber

Background

Aircrew are exposed to environmental pressure changes. In the Republic of Singapore Air Force (RSAF), applicants assessed to be at intermediate risk of otic barotrauma undergo a hypobaric chamber assessment [“trial of chamber” (TOC)] to functionally evaluate their suitability for military aircrew vocations.

Aims

To identify factors associated with TOC failure among applicants with otorhinolaryngological conditions.

Methods

All applicants to RSAF aircrew vocations who were assessed to be at intermediate risk of otic barotrauma over a 3-yr period were identified using the RSAF Aeromedical Centre’s electronic database. Their medical records, as well as the TOC assessment records of the subset of applicants who underwent TOC, were reviewed for demographic data, clinical findings, and TOC outcomes.

Results

Of the 483 identified applicants, 374 (77%) had abnormal otoscopic findings, 103 (21%) had rhinitis symptoms, and 6 (1%) had previous ENT surgery. 123 (25%) underwent TOC, of which 20 (16%) failed. Holding other predictor variables constant, the odds of TOC failure increased by 0.79 per unit decrease in BMI (95% CI 0.63–0.99), and the odds of TOC failure increased by 0.93 per kg decrease in body weight (95% CI 0.87–1.00). An abnormal tympanogram was not a statistically significant predictor of TOC failure (OR 1.96, 95% CI 0.59–6.42). Of the 47 applicants who passed TOC and were eventually recruited, none subsequently developed otic barotrauma (mean follow-up, 3.3 yr ± 1.5 yr).

Conclusions

Applicants with lower weight and BMI are more likely to develop otic barotrauma with environmental pressure change. Tympanometry cannot be reliably used to identify applicants who would more likely pass TOC.

scHFC: a hybrid fuzzy clustering method for single-cell RNA-seq data optimized by natural computation

Rapid development of single-cell RNA sequencing (scRNA-seq) technology has allowed researchers to explore biological phenomena at the cellular scale. Clustering is a crucial and helpful step for researchers to study the heterogeneity of cell. Although many clustering methods have been proposed, massive dropout events and the curse of dimensionality in scRNA-seq data make it still difficult to analysis because they reduce the accuracy of clustering methods, leading to misidentification of cell types. In this work, we propose the scHFC, which is a hybrid fuzzy clustering method optimized by natural computation based on Fuzzy C Mean (FCM) and Gath-Geva (GG) algorithms. Specifically, principal component analysis algorithm is utilized to reduce the dimensions of scRNA-seq data after it is preprocessed. Then, FCM algorithm optimized by simulated annealing algorithm and genetic algorithm is applied to cluster the data to output a membership matrix, which represents the initial clustering result and is taken as the input for GG algorithm to get the final clustering results. We also develop a cluster number estimation method called multi-index comprehensive estimation, which can estimate the cluster numbers well by combining four clustering effectiveness indexes. The performance of the scHFC method is evaluated on 17 scRNA-seq datasets, and compared with six state-of-the-art methods. Experimental results validate the better performance of our scHFC method in terms of clustering accuracy and stability of algorithm. In short, scHFC is an effective method to cluster cells for scRNA-seq data, and it presents great potential for downstream analysis of scRNA-seq data. The source code is available at https://github.com/WJ319/scHFC.