Memristor-based adaptive neuromorphic perception in unstructured environments.

Efficient operation of control systems in robotics or autonomous driving targeting real-world navigation scenarios requires perception methods that allow them to understand and adapt to unstructured environments with good accuracy, adaptation, and generality, similar to humans. To address this need, we present a memristor-based differential neuromorphic computing, perceptual signal processing, and online adaptation method providing neuromorphic style adaptation to external sensory stimuli. The adaptation ability and generality of this method are confirmed in two application scenarios: object grasping and autonomous driving. In the former, a robot hand realizes safe and stable grasping through fast ( ~ 1 ms) adaptation based on the tactile object features with a single memristor. In the latter, decision-making information of 10 unstructured environments in autonomous driving is extracted with an accuracy of 94% with a 40×25 memristor array. By mimicking human low-level perception mechanisms, the electronic neuromorphic circuit-based method achieves real-time adaptation and high-level reactions to unstructured environments.

Integrated Proteomics Analysis of Baseline Protein Expression in Pig Tissues.

The availability of an increasingly large amount of public proteomics data sets presents an opportunity for performing combined analyses to generate comprehensive organism-wide protein expression maps across different organisms and biological conditions. Sus scrofa, a domestic pig, is a model organism relevant for food production and for human biomedical research. Here, we reanalyzed 14 public proteomics data sets from the PRIDE database coming from pig tissues to assess baseline (without any biological perturbation) protein abundance in 14 organs, encompassing a total of 20 healthy tissues from 128 samples. The analysis involved the quantification of protein abundance in 599 mass spectrometry runs. We compared protein expression patterns among different pig organs and examined the distribution of proteins across these organs. Then, we studied how protein abundances were compared across different data sets and studied the tissue specificity of the detected proteins. Of particular interest, we conducted a comparative analysis of protein expression between pig and human tissues, revealing a high degree of correlation in protein expression among orthologs, particularly in brain, kidney, heart, and liver samples. We have integrated the protein expression results into the Expression Atlas resource for easy access and visualization of the protein expression data individually or alongside gene expression data.

De novo transcriptome assembly database for 100 tissues from each of seven species of domestic herbivore.

Domesticated herbivores are an important agricultural resource that play a critical role in global food security, particularly as they can adapt to varied environments, including marginal lands. An understanding of the molecular basis of their biology would contribute to better management and sustainable production. Thus, we conducted transcriptome sequencing of 100 to 105 tissues from two females of each of seven species of herbivore (cattle, sheep, goats, sika deer, horses, donkeys, and rabbits) including two breeds of sheep. The quality of raw and trimmed reads was assessed in terms of base quality, GC content, duplication sequence rate, overrepresented k-mers, and quality score distribution with FastQC. The high-quality filtered RNA-seq raw reads were deposited in a public database which provides approximately 54 billion high-quality paired-end sequencing reads in total, with an average mapping rate of ~93.92%. Transcriptome databases represent valuable resources that can be used to study patterns of gene expression, and pathways that are related to key biological processes, including important economic traits in herbivores.

Effectiveness of fecal DNA syndecan-2 methylation testing for detection of colorectal cancer in a high-risk Chinese population.

BACKGROUND: Colorectal cancer (CRC) is among the most prevalent and life-threatening malignancies worldwide. Syndecan-2 methylation (mSDC2) testing has emerged as a widely used biomarker for early detection of CRC in stool and serum samples. Cancer (CRC) is among the most prevalent and life-threatening malignancies worldwide. mSDC2 testing has emerged as a widely used biomarker for early detection of CRC in stool and serum samples. AIM: To validate the effectiveness of fecal DNA mSDC2 testing in the detection of CRC among a high-risk Chinese population to provide evidence-based data for the development of diagnostic and/or screening guidelines for CRC in China. METHODS: A high-risk Chinese cohort consisting of 1130 individuals aged 40-79 years was selected for evaluation via fecal mSDC2 testing. Sensitivity and specificity for CRC, advanced adenoma (AA) and advanced colorectal neoplasia (ACN) were determined. High-risk factors for the incidence of colorectal lesions were determined and a logistic regression model was constructed to reflect the efficacy of the test. RESULTS: A total of 1035 high-risk individuals were included in this study according to established criteria. Among them, 16 suffered from CRC (1.55%), 65 from AA (6.28%) and 189 from non-AAs (18.26%); 150 patients were diagnosed with polyps (14.49%). Diagnoses were established based upon colonoscopic and pathological examinations. Sensitivities of the mSDC2 test for CRC and AA were 87.50% and 40.00%, respectively; specificities were 95.61% for other groups. Positive predictive values of the mSDC2 test for CRC, AA and ACN were 16.09%, 29.89% and 45.98%, respectively; the negative predictive value for CRC was 99.79%. After adjusting for other high-risk covariates, mSDC2 test positivity was found to be a significant risk factor for the occurrence of ACN (P < 0.001). CONCLUSION: Our findings confirmed that offering fecal mSDC2 testing and colonoscopy in combination for CRC screening is effective for earlier detection of malignant colorectal lesions in a high-risk Chinese population.

CSANet: a lightweight channel and spatial attention neural network for grading diabetic retinopathy with optical coherence tomography angiography.

Background: Diabetic retinopathy (DR) is one of the most common eye diseases. Convolutional neural networks (CNNs) have proven to be a powerful tool for learning DR features; however, accurate DR grading remains challenging due to the small lesions in optical coherence tomography angiography (OCTA) images and the small number of samples. Methods: In this article, we developed a novel deep-learning framework to achieve the fine-grained classification of DR; that is, the lightweight channel and spatial attention network (CSANet). Our CSANet comprises two modules: the baseline model, and the hybrid attention module (HAM) based on spatial attention and channel attention. The spatial attention module is used to mine small lesions and obtain a set of spatial position weights to address the problem of small lesions being ignored during the convolution process. The channel attention module uses a set of channel weights to focus on useful features and suppress irrelevant features. Results: The extensive experimental results for the OCTA-DR and diabetic retinopathy analysis challenge (DRAC) 2022 data sets showed that the CSANet achieved state-of-the-art DR grading results, showing the effectiveness of the proposed model. The CSANet had an accuracy rate of 97.41% for the OCTA-DR data set and 85.71% for the DRAC 2022 data set. Conclusions: Extensive experiments using the OCTA-DR and DRAC 2022 data sets showed that the proposed model effectively mitigated the problems of mutual confusion between DRs of different severity and small lesions being neglected in the convolution process, and thus improved the accuracy of DR classification.

Image segmentation of mouse eye in vivo with optical coherence tomography based on Bayesian classification.

OBJECTIVES: Optical coherence tomography (OCT) is a new imaging technology that uses an optical analog of ultrasound imaging for biological tissues. Image segmentation plays an important role in dealing with quantitative analysis of medical images. METHODS: We have proposed a novel framework to deal with the low intensity problem, based on the labeled patches and Bayesian classification (LPBC) model. The proposed method includes training and testing phases. During the training phase, firstly, we manually select the sub-images of background and Region of Interest (ROI) from the training image, and then extract features by patches. Finally, we train the Bayesian model with the features. The segmentation threshold of each patch is computed by the learned Bayesian model. RESULTS: In addition, we have collected a new dataset of mouse eyes in vivo with OCT, named MEVOCT, which can be found at URL https://17861318579.github.io/LPBC. MEVOCT consists of 20 high-resolution images. The resolution of every image is 2048 × 2048 pixels. CONCLUSIONS: The experimental results demonstrate the effectiveness of the LPBC method on the new MEVOCT dataset. The ROI segmentation is of great importance for the distortion correction.

Deep-learning segmentation method for optical coherence tomography angiography in ophthalmology.

PURPOSE: The optic disc and the macular are two major anatomical structures in the human eye. Optic discs are associated with the optic nerve. Macular mainly involves degeneration and impaired function of the macular region. Reliable optic disc and macular segmentation are necessary for the automated screening of retinal diseases. METHODS: A swept-source OCTA system was designed to capture OCTA images of human eyes. To address these segmentation tasks, first, we constructed a new Optic Disc and Macula in fundus Image with optical coherence tomography angiography (OCTA) dataset (ODMI). Second, we proposed a Coarse and Fine Attention-Based Network (CFANet). RESULTS: The five metrics of our methods on ODMI are 98.91 % , 98.47 % , 89.77 % , 98.49 % , and 89.77 % , respectively. CONCLUSIONS: Experimental results show that our CFANet has achieved good performance on segmentation for the optic disc and macula in OCTA.

Expression Atlas update: insights from sequencing data at both bulk and single cell level.

Expression Atlas (www.ebi.ac.uk/gxa) and its newest counterpart the Single Cell Expression Atlas (www.ebi.ac.uk/gxa/sc) are EMBL-EBI's knowledgebases for gene and protein expression and localisation in bulk and at single cell level. These resources aim to allow users to investigate their expression in normal tissue (baseline) or in response to perturbations such as disease or changes to genotype (differential) across multiple species. Users are invited to search for genes or metadata terms across species or biological conditions in a standardised consistent interface. Alongside these data, new features in Single Cell Expression Atlas allow users to query metadata through our new cell type wheel search. At the experiment level data can be explored through two types of dimensionality reduction plots, t-distributed Stochastic Neighbor Embedding (tSNE) and Uniform Manifold Approximation and Projection (UMAP), overlaid with either clustering or metadata information to assist users' understanding. Data are also visualised as marker gene heatmaps identifying genes that help confer cluster identity. For some data, additional visualisations are available as interactive cell level anatomograms and cell type gene expression heatmaps.

SoyMD: a platform combining multi-omics data with various tools for soybean research and breeding.

Advanced multi-omics technologies offer much information that can uncover the regulatory mechanisms from genotype to phenotype. In soybean, numerous multi-omics databases have been published. Although they cover multiple omics, there are still limitations when it comes to the types and scales of omics datasets and analysis methods utilized. This study aims to address these limitations by collecting and integrating a comprehensive set of multi-omics datasets. This includes 38 genomes, transcriptomes from 435 tissue samples, 125 phenotypes from 6686 accessions, epigenome data involving histone modification, transcription factor binding, chromosomal accessibility and chromosomal interaction, as well as genetic variation data from 24 501 soybean accessions. Then, common analysis pipelines and statistical methods were applied to mine information from these multi-omics datasets, resulting in the successful establishment of a user-friendly multi-omics database called SoyMD (https://yanglab.hzau.edu.cn/SoyMD/#/). SoyMD provides researchers with efficient query options and analysis tools, allowing them to swiftly access relevant omics information and conduct comprehensive multi-omics data analyses. Another notable feature of SoyMD is its capability to facilitate the analysis of candidate genes, as demonstrated in the case study on seed oil content. This highlights the immense potential of SoyMD in soybean genetic breeding and functional genomics research.

A new retinal OCT-angiography diabetic retinopathy dataset for segmentation and DR grading.

PURPOSE: Diabetic retinopathy (DR) is one of the most common diseases caused by diabetes and can lead to vision loss or even blindness. The wide-field optical coherence tomography (OCT) angiography is non-invasive imaging technology and convenient to diagnose DR. METHODS: A newly constructed Retinal OCT-Angiography Diabetic retinopathy (ROAD) dataset is utilized for segmentation and grading tasks. It contains 1200 normal images, 1440 DR images, and 1440 ground truths for DR image segmentation. To handle the problem of grading DR, we propose a novel and effective framework, named projective map attention-based convolutional neural network (PACNet). RESULTS: The experimental results demonstrate the effectiveness of our PACNet. The accuracy of the proposed framework for grading DR is 87.5% on the ROAD dataset. CONCLUSIONS: The information on ROAD can be viewed at URL https://mip2019.github.io/ROAD. The ROAD dataset will be helpful for the development of the early detection of DR field and future research. TRANSLATIONAL RELEVANCE: The novel framework for grading DR is a valuable research and clinical diagnosis method.

Multiangle, self-powered sensor array for monitoring head impacts.

Mild concussions occur frequently and may come with long-term cognitive, affective, and physical sequelae. However, the diagnosis of mild concussions lacks objective assessment and portable monitoring techniques. Here, we propose a multiangle self-powered sensor array for real-time monitoring of head impact to further assist in clinical analysis and prevention of mild concussions. The array uses triboelectric nanogenerator technology, which converts impact force from multiple directions into electrical signals. With an average sensitivity of 0.214 volts per kilopascal, a response time of 30 milliseconds, and a minimum resolution of 1.415 kilopascals, the sensors exhibit excellent sensing capability over a range of 0 to 200 kilopascals. Furthermore, the array enables reconstructed head impact mapping and injury grade assessment via a prewarning system. By gathering standardized data, we expect to build a big data platform that will permit in-depth research of the direct and indirect effects between head impacts and mild concussions in the future.

Comparative transcriptome profiling reveals the multiple levels of crosstalk in phytohormone networks in Brassica napus.

Plant hormones are the intrinsic factors that control plant development. The integration of different phytohormone pathways in a complex network of synergistic, antagonistic and additive interactions has been elucidated in model plants. However, the systemic level of transcriptional responses to hormone crosstalk in Brassica napus is largely unknown. Here, we present an in-depth temporal-resolution study of the transcriptomes of the seven hormones in B. napus seedlings. Differentially expressed gene analysis revealed few common target genes that co-regulated (up- and down-regulated) by seven hormones; instead, different hormones appear to regulate distinct members of protein families. We then constructed the regulatory networks between the seven hormones side by side, which allowed us to identify key genes and transcription factors that regulate the hormone crosstalk in B. napus. Using this dataset, we uncovered a novel crosstalk between gibberellin and cytokinin in which cytokinin homeostasis was mediated by RGA-related CKXs expression. Moreover, the modulation of gibberellin metabolism by the identified key transcription factors was confirmed in B. napus. Furthermore, all data were available online from http://yanglab.hzau.edu.cn/BnTIR/hormone. Our study reveals an integrated hormone crosstalk network in Brassica napus, which also provides a versatile resource for future hormone studies in plant species.

AutoGMap: Learning to Map Large-Scale Sparse Graphs on Memristive Crossbars.

The sparse representation of graphs has shown great potential for accelerating the computation of graph applications (e.g., social networks and knowledge graphs) on traditional computing architectures (CPU, GPU, or TPU). But, the exploration of large-scale sparse graph computing on processing-in-memory (PIM) platforms (typically with memristive crossbars) is still in its infancy. To implement the computation or storage of large-scale or batch graphs on memristive crossbars, a natural assumption is that a large-scale crossbar is demanded, but with low utilization. Some recent works question this assumption; to avoid the waste of storage and computational resource, the fixed-size or progressively scheduled "block partition" schemes are proposed. However, these methods are coarse-grained or static and are not effectively sparsity-aware. This work proposes the dynamic sparsity-aware mapping scheme generating method that models the problem with a sequential decision-making model, and optimizes it by reinforcement learning (RL) algorithm (REINFORCE). Our generating model long short-term memory (LSTM), combined with the dynamic-fill scheme generates remarkable mapping performance on the small-scale graph/matrix data (complete mapping costs 43% area of the original matrix) and two large-scale matrix data (costing 22.5% area on qh882 and 17.1% area on qh1484). Our method may be extended to sparse graph computing on other PIM architectures, not limited to the memristive device-based platforms.

BnIR: A multi-omics database with various tools for Brassica napus research and breeding.

In the post-genome-wide association study era, multi-omics techniques have shown great power and potential for candidate gene mining and functional genomics research. However, due to the lack of effective data integration and multi-omics analysis platforms, such techniques have not still been applied widely in rapeseed, an important oil crop worldwide. Here, we report a rapeseed multi-omics database (BnIR; http://yanglab.hzau.edu.cn/BnIR), which provides datasets of six omics including genomics, transcriptomics, variomics, epigenetics, phenomics, and metabolomics, as well as numerous "variation-gene expression-phenotype" associations by using multiple statistical methods. In addition, a series of multi-omics search and analysis tools are integrated to facilitate the browsing and application of these datasets. BnIR is the most comprehensive multi-omics database for rapeseed so far, and two case studies demonstrated its power to mine candidate genes associated with specific traits and analyze their potential regulatory mechanisms.

Approximate Optimal Control for Nonlinear Systems With Periodic Event-Triggered Mechanism.

This article investigates the approximate optimal control problem for nonlinear affine systems under the periodic event triggered control (PETC) strategy. In terms of optimal control, a theoretical comparison of continuous control, traditional event-based control (ETC), and PETC from the perspective of stability convergence, concluding that PETC does not significantly affect the convergence rate than ETC. It is the first time to present PETC for optimal control target of nonlinear systems. A critic network is introduced to approximate the optimal value function based on the idea of reinforcement learning (RL). It is proven that the discrete updating time series from PETC can also be utilized to determine the updating time of the learning network. In this way, the gradient-based weight estimation for continuous systems is developed in discrete form. Then, the uniformly ultimately bounded (UUB) condition of controlled systems is analyzed to ensure the stability of the designed method. Finally, two illustrative examples are given to show the effectiveness of the method.

Suboptimal Leader-to-Coordination Control for Nonlinear Systems With Switching Topologies: A Learning-Based Method.

In the cooperative control for multiagent systems (MASs), the key issues of distributed interaction, nonlinear characteristics, and optimization should be considered simultaneously, which, however, remain intractable theoretically even to this day. Considering these factors, this article investigates leader-to-formation control and optimization for nonlinear MASs using a learning-based method. Under time-varying switching topology, a fully distributed state observer based on neural networks is designed to reconstruct the dynamics and the state trajectory of the leader signal with arbitrary precision under jointly connected topology assumption. Benefitted from the observers, formation for MASs under switching topologies is transformed into tracking control for each subsystem with continuous state generated by the observers. An augmented system with discounted infinite LQR performance index is considered to optimize the control effect. Due to the complexity of solving the Hamilton-Jacobi-Bellman equation, the optimal value function is approximated by a critic network via the integral reinforcement learning method without the knowledge of drift dynamics. Meanwhile, an actor network is also presented to assure stability. The tracking errors and estimation weighted matrices are proven to be uniformly ultimately bounded. Finally, two illustrative examples are given to show the effectiveness of this method.

Integrated View of Baseline Protein Expression in Human Tissues.

The availability of proteomics datasets in the public domain, and in the PRIDE database, in particular, has increased dramatically in recent years. This unprecedented large-scale availability of data provides an opportunity for combined analyses of datasets to get organism-wide protein abundance data in a consistent manner. We have reanalyzed 24 public proteomics datasets from healthy human individuals to assess baseline protein abundance in 31 organs. We defined tissue as a distinct functional or structural region within an organ. Overall, the aggregated dataset contains 67 healthy tissues, corresponding to 3,119 mass spectrometry runs covering 498 samples from 489 individuals. We compared protein abundances between different organs and studied the distribution of proteins across these organs. We also compared the results with data generated in analogous studies. Additionally, we performed gene ontology and pathway-enrichment analyses to identify organ-specific enriched biological processes and pathways. As a key point, we have integrated the protein abundance results into the resource Expression Atlas, where they can be accessed and visualized either individually or together with gene expression data coming from transcriptomics datasets. We believe this is a good mechanism to make proteomics data more accessible for life scientists.

CottonMD: a multi-omics database for cotton biological study.

Cotton is an important economic crop, and many loci for important traits have been identified, but it remains challenging and time-consuming to identify candidate or causal genes/variants and clarify their roles in phenotype formation and regulation. Here, we first collected and integrated the multi-omics datasets including 25 genomes, transcriptomes in 76 tissue samples, epigenome data of five species and metabolome data of 768 metabolites from four tissues, and genetic variation, trait and transcriptome datasets from 4180 cotton accessions. Then, a cotton multi-omics database (CottonMD, http://yanglab.hzau.edu.cn/CottonMD/) was constructed. In CottonMD, multiple statistical methods were applied to identify the associations between variations and phenotypes, and many easy-to-use analysis tools were provided to help researchers quickly acquire the related omics information and perform multi-omics data analysis. Two case studies demonstrated the power of CottonMD for identifying and analyzing the candidate genes, as well as the great potential of integrating multi-omics data for cotton genetic breeding and functional genomics research.