scLEGA: an attention-based deep clustering method with a tendency for low expression of genes on single-cell RNA-seq data.

Single-cell RNA sequencing (scRNA-seq) enables the exploration of biological heterogeneity among different cell types within tissues at a resolution. Inferring cell types within tissues is foundational for downstream research. Most existing methods for cell type inference based on scRNA-seq data primarily utilize highly variable genes (HVGs) with higher expression levels as clustering features, overlooking the contribution of HVGs with lower expression levels. To address this, we have designed a novel cell type inference method for scRNA-seq data, termed scLEGA. scLEGA employs a novel zero-inflated negative binomial (ZINB) loss function that fully considers the contribution of genes with lower expression levels and combines two distinct scRNA-seq clustering strategies through a multi-head attention mechanism. It utilizes a low-expression optimized denoising autoencoder, based on the novel ZINB model, to extract low-dimensional features and handle dropout events, and a GCN-based graph autoencoder (GAE) that leverages neighbor information to guide dimensionality reduction. The iterative fusion of denoising and topological embedding in scLEGA facilitates the acquisition of cluster-friendly cell representations in the hidden embedding, where similar cells are brought closer together. Compared to 12 state-of-the-art cell type inference methods on 15 scRNA-seq datasets, scLEGA demonstrates superior performance in clustering accuracy, scalability, and stability. Our scLEGA model codes are freely available at https://github.com/Masonze/scLEGA-main.

CPPLS-MLP: a method for constructing cell-cell communication networks and identifying related highly variable genes based on single-cell sequencing and spatial transcriptomics data.

In the growth and development of multicellular organisms, the immune processes of the immune system and the maintenance of the organism's internal environment, cell communication plays a crucial role. It exerts a significant influence on regulating internal cellular states such as gene expression and cell functionality. Currently, the mainstream methods for studying intercellular communication are focused on exploring the ligand-receptor-transcription factor and ligand-receptor-subunit scales. However, there is relatively limited research on the association between intercellular communication and highly variable genes (HVGs). As some HVGs are closely related to cell communication, accurately identifying these HVGs can enhance the accuracy of constructing cell communication networks. The rapid development of single-cell sequencing (scRNA-seq) and spatial transcriptomics technologies provides a data foundation for exploring the relationship between intercellular communication and HVGs. Therefore, we propose CPPLS-MLP, which can identify HVGs closely related to intercellular communication and further analyze the impact of Multiple Input Multiple Output cellular communication on the differential expression of these HVGs. By comparing with the commonly used method CCPLS for constructing intercellular communication networks, we validated the superior performance of our method in identifying cell-type-specific HVGs and effectively analyzing the influence of neighboring cell types on HVG expression regulation. Source codes for the CPPLS_MLP R, python packages and the related scripts are available at 'CPPLS_MLP Github [https://github.com/wuzhenao/CPPLS-MLP]'.

CD147 Sparks Atherosclerosis by Driving M1 Phenotype and Impairing Efferocytosis.

BACKGROUND: Atherosclerosis is a globally prevalent chronic inflammatory disease with high morbidity and mortality. The development of atherosclerotic lesions is determined by macrophages. This study aimed to investigate the specific role of myeloid-derived CD147 (cluster of differentiation 147) in atherosclerosis and its translational significance. METHODS AND RESULTS: We generated mice with a myeloid-specific knockout of CD147 and mice with restricted CD147 overexpression, both in an apoE-deficient (ApoE-/-) background. Here, the myeloid-specific deletion of CD147 ameliorated atherosclerosis and inflammation. Consistent with our in vivo data, macrophages isolated from myeloid-specific CD147 knockout mice exhibited a phenotype shift from proinflammatory to anti-inflammatory macrophage polarization in response to lipopolysaccharide/IFN (interferon)-γ. These macrophages demonstrated a weakened proinflammatory macrophage phenotype, characterized by reduced production of NO and reactive nitrogen species derived from iNOS (inducible NO synthase). Mechanistically, the TRAF6 (tumor necrosis factor receptor-associated factor 6)-IKK (inhibitor of κB kinase)-IRF5 (IFN regulatory factor 5) signaling pathway was essential for the effect of CD147 on proinflammatory responses. Consistent with the reduced size of the necrotic core, myeloid-specific CD147 deficiency diminished the susceptibility of iNOS-mediated late apoptosis, accompanied by enhanced efferocytotic capacity mediated by increased secretion of GAS6 (growth arrest-specific 6) in proinflammatory macrophages. These findings were consistent in a mouse model with myeloid-restricted overexpression of CD147. Furthermore, we developed a new atherosclerosis model in ApoE-/- mice with humanized CD147 transgenic expression and demonstrated that the administration of an anti-human CD147 antibody effectively suppressed atherosclerosis by targeting inflammation and efferocytosis. CONCLUSIONS: Myeloid CD147 plays a crucial role in the growth of plaques by promoting inflammation in a TRAF6-IKK-IRF5-dependent manner and inhibiting efferocytosis by suppressing GAS6 during proinflammatory conditions. Consequently, the use of anti-human CD147 antibodies presents a complementary therapeutic approach to the existing lipid-lowering strategies for treating atherosclerotic diseases.

DeepICSH: a complex deep learning framework for identifying cell-specific silencers and their strength from the human genome.

Silencers are noncoding DNA sequence fragments located on the genome that suppress gene expression. The variation of silencers in specific cells is closely related to gene expression and cancer development. Computational approaches that exclusively rely on DNA sequence information for silencer identification fail to account for the cell specificity of silencers, resulting in diminished accuracy. Despite the discovery of several transcription factors and epigenetic modifications associated with silencers on the genome, there is still no definitive biological signal or combination thereof to fully characterize silencers, posing challenges in selecting suitable biological signals for their identification. Therefore, we propose a sophisticated deep learning framework called DeepICSH, which is based on multiple biological data sources. Specifically, DeepICSH leverages a deep convolutional neural network to automatically capture biologically relevant signal combinations strongly associated with silencers, originating from a diverse array of biological signals. Furthermore, the utilization of attention mechanisms facilitates the scoring and visualization of these signal combinations, whereas the employment of skip connections facilitates the fusion of multilevel sequence features and signal combinations, thereby empowering the accurate identification of silencers within specific cells. Extensive experiments on HepG2 and K562 cell line data sets demonstrate that DeepICSH outperforms state-of-the-art methods in silencer identification. Notably, we introduce for the first time a deep learning framework based on multi-omics data for classifying strong and weak silencers, achieving favorable performance. In conclusion, DeepICSH shows great promise for advancing the study and analysis of silencers in complex diseases. The source code is available at https://github.com/lyli1013/DeepICSH.

GTAD: a graph-based approach for cell spatial composition inference from integrated scRNA-seq and ST-seq data.

With the emergence of spatial transcriptome sequencing (ST-seq), research now heavily relies on the joint analysis of ST-seq and single-cell RNA sequencing (scRNA-seq) data to precisely identify cell spatial composition in tissues. However, common methods for combining these datasets often merge data from multiple cells to generate pseudo-ST data, overlooking topological relationships and failing to represent spatial arrangements accurately. We introduce GTAD, a method utilizing the Graph Attention Network for deconvolution of integrated scRNA-seq and ST-seq data. GTAD effectively captures cell spatial relationships and topological structures within tissues using a graph-based approach, enhancing cell-type identification and our understanding of complex tissue cellular landscapes. By integrating scRNA-seq and ST data into a unified graph structure, GTAD outperforms traditional 'pseudo-ST' methods, providing robust and information-rich results. GTAD performs exceptionally well with synthesized spatial data and accurately identifies cell spatial composition in tissues like the mouse cerebral cortex, cerebellum, developing human heart and pancreatic ductal carcinoma. GTAD holds the potential to enhance our understanding of tissue microenvironments and cellular diversity in complex bio-logical systems. The source code is available at https://github.com/zzhjs/GTAD.

C-C chemokine receptor type 7 (CCR7) regulates hepatic CD8 + T cell homeostasis and response to acute liver injury.

BACKGROUND AND AIMS: Acute liver failure (ALF) is a rare but life-threatening condition, and DILI, particularly acetaminophen toxicity, is the leading cause of ALF. Innate immune mechanisms further perpetuate liver injury, while the role of the adaptive immune system in DILI-related ALF is unclear. APPROACH AND RESULTS: We analyzed liver tissue from 2 independent patient cohorts with ALF and identified hepatic T cell infiltration as a prominent feature in human ALF. CD8 + T cells were characterized by zonation toward necrotic regions and an activated gene expression signature. In murine acetaminophen-induced liver injury, intravital microscopy revealed zonation of CD8 + but not CD4 + T cells at necrotic areas. Gene expression analysis exposed upregulated C-C chemokine receptor 7 (CCR7) and its ligand CCL21 in the liver as well as a broadly activated phenotype of hepatic CD8 + T cells. In 2 mouse models of ALF, Ccr7-/- mice had significantly aggravated early-phase liver damage. Functionally, CCR7 was not involved in the recruitment of CD8 + T cells, but regulated their activation profile potentially through egress to lymphatics. Ccr7-/- CD8 + T cells were characterized by elevated expression of activation, effector, and exhaustion profiles. Adoptive transfer revealed preferential homing of CCR7-deficient CD8 + T cells to the liver, and depletion of CD8 + T cells attenuated liver damage in mice. CONCLUSIONS: Our study demonstrates the involvement of the adaptive immune system in ALF in humans and mice. We identify the CCR7-CCL21 axis as an important regulatory pathway, providing downstream protection against T cell-mediated liver injury.

Novel C. elegans models of Lewy body disease reveal pathological protein interactions and widespread miRNA dysregulation.

Lewy body diseases (LBD) comprise a group of complex neurodegenerative conditions originating from accumulation of misfolded alpha-synuclein (α-syn) in the form of Lewy bodies. LBD pathologies are characterized by α-syn deposition in association with other proteins such as Amyloid ß (Aß), Tau, and TAR-DNA-binding protein. To investigate the complex interactions of these proteins, we constructed 2 novel transgenic overexpressing (OE) C. elegans strains (α-synA53T;Taupro-agg (OE) and α-synA53T;Aß1-42;Taupro-agg (OE)) and compared them with previously established Parkinson's, Alzheimer's, and Lewy Body Dementia disease models. The LBD models presented here demonstrate impairments including uncoordinated movement, egg-laying deficits, altered serotonergic and cholinergic signaling, memory and posture deficits, as well as dopaminergic neuron damage and loss. Expression levels of total and prone to aggregation α-syn protein were increased in α-synA53T;Aß1-42 but decreased in α-synA53T;Taupro-agg animals when compared to α-synA53T animals suggesting protein interactions. These alterations were also observed at the mRNA level suggesting a pre-transcriptional mechanism. miRNA-seq revealed that cel-miR-1018 was upregulated in LBD models α-synA53T, α-synA53T;Aß1-42, and α-synA53T;Taupro-agg compared with WT. cel-miR-58c was upregulated in α-synA53T;Taupro-agg but downregulated in α-synA53T and α-synA53T;Aß1-42 compared with WT. cel-miR-41-3p and cel-miR-355-5p were significantly downregulated in 3 LBD models. Our results obtained in a model organism provide evidence of interactions between different pathological proteins and alterations in specific miRNAs that may further exacerbate or ameliorate LBD pathology.

Complex genome assembly based on long-read sequencing.

High-quality genome chromosome-scale sequences provide an important basis for genomics downstream analysis, especially the construction of haplotype-resolved and complete genomes, which plays a key role in genome annotation, mutation detection, evolutionary analysis, gene function research, comparative genomics and other aspects. However, genome-wide short-read sequencing is difficult to produce a complete genome in the face of a complex genome with high duplication and multiple heterozygosity. The emergence of long-read sequencing technology has greatly improved the integrity of complex genome assembly. We review a variety of computational methods for complex genome assembly and describe in detail the theories, innovations and shortcomings of collapsed, semi-collapsed and uncollapsed assemblers based on long reads. Among the three methods, uncollapsed assembly is the most correct and complete way to represent genomes. In addition, genome assembly is closely related to haplotype reconstruction, that is uncollapsed assembly realizes haplotype reconstruction, and haplotype reconstruction promotes uncollapsed assembly. We hope that gapless, telomere-to-telomere and accurate assembly of complex genomes can be truly routinely achieved using only a simple process or a single tool in the future.

PIWI-interacting RNAs in human diseases: databases and computational models.

PIWI-interacting RNAs (piRNAs) are short 21-35 nucleotide molecules that comprise the largest class of non-coding RNAs and found in a large diversity of species including yeast, worms, flies, plants and mammals including humans. The most well-understood function of piRNAs is to monitor and protect the genome from transposons particularly in germline cells. Recent data suggest that piRNAs may have additional functions in somatic cells although they are expressed there in far lower abundance. Compared with microRNAs (miRNAs), piRNAs have more limited bioinformatics resources available. This review collates 39 piRNA specific and non-specific databases and bioinformatics resources, describes and compares their utility and attributes and provides an overview of their place in the field. In addition, we review 33 computational models based upon function: piRNA prediction, transposon element and mRNA-related piRNA prediction, cluster prediction, signature detection, target prediction and disease association. Based on the collection of databases and computational models, we identify trends and potential gaps in tool development. We further analyze the breadth and depth of piRNA data available in public sources, their contribution to specific human diseases, particularly in cancer and neurodegenerative conditions, and highlight a few specific piRNAs that appear to be associated with these diseases. This briefing presents the most recent and comprehensive mapping of piRNA bioinformatics resources including databases, models and tools for disease associations to date. Such a mapping should facilitate and stimulate further research on piRNAs.

CRISPRCasStack: a stacking strategy-based ensemble learning framework for accurate identification of Cas proteins.

CRISPR-Cas system is an adaptive immune system widely found in most bacteria and archaea to defend against exogenous gene invasion. One of the most critical steps in the study of exploring and classifying novel CRISPR-Cas systems and their functional diversity is the identification of Cas proteins in CRISPR-Cas systems. The discovery of novel Cas proteins has also laid the foundation for technologies such as CRISPR-Cas-based gene editing and gene therapy. Currently, accurate and efficient screening of Cas proteins from metagenomic sequences and proteomic sequences remains a challenge. For Cas proteins with low sequence conservation, existing tools for Cas protein identification based on homology cannot guarantee identification accuracy and efficiency. In this paper, we have developed a novel stacking-based ensemble learning framework for Cas protein identification, called CRISPRCasStack. In particular, we applied the SHAP (SHapley Additive exPlanations) method to analyze the features used in CRISPRCasStack. Sufficient experimental validation and independent testing have demonstrated that CRISPRCasStack can address the accuracy deficiencies and inefficiencies of the existing state-of-the-art tools. We also provide a toolkit to accurately identify and analyze potential Cas proteins, Cas operons, CRISPR arrays and CRISPR-Cas locus in prokaryotic sequences. The CRISPRCasStack toolkit is available at https://github.com/yrjia1015/CRISPRCasStack.

DeepITEH: a deep learning framework for identifying tissue-specific eRNAs from the human genome.

MOTIVATION: Enhancers are vital cis-regulatory elements that regulate gene expression. Enhancer RNAs (eRNAs), a type of long noncoding RNAs, are transcribed from enhancer regions in the genome. The tissue-specific expression of eRNAs is crucial in the regulation of gene expression and cancer development. The methods that identify eRNAs based solely on genomic sequence data have high error rates because they do not account for tissue specificity. Specific histone modifications associated with eRNAs offer valuable information for their identification. However, identification of eRNAs using histone modification data requires the use of both RNA-seq and histone modification data. Unfortunately, many public datasets contain only one of these components, which impedes the accurate identification of eRNAs. RESULTS: We introduce DeepITEH, a deep learning framework that leverages RNA-seq data and histone modification data from multiple samples of the same tissue to enhance the accuracy of identifying eRNAs. Specifically, deepITEH initially categorizes eRNAs into two classes, namely, regularly expressed eRNAs and accidental eRNAs, using histone modification data from multiple samples of the same tissue. Thereafter, it integrates both sequence and histone modification features to identify eRNAs in specific tissues. To evaluate the performance of DeepITEH, we compared it with four existing state-of-the-art enhancer prediction methods, SeqPose, iEnhancer-RD, LSTMAtt, and FRL, on four normal tissues and four cancer tissues. Remarkably, seven of these tissues demonstrated a substantially improved specific eRNA prediction performance with DeepITEH, when compared with other methods. Our findings suggest that DeepITEH can effectively predict potential eRNAs on the human genome, providing insights for studying the eRNA function in cancer. AVAILABILITY AND IMPLEMENTATION: The source code and dataset of DeepITEH have been uploaded to https://github.com/lyli1013/DeepITEH.

Phenotyping of single plant cells on a microfluidic cytometry platform with fluorescent, mechanical, and electrical modules.

Compared to animal cells, phenotypic characterization of single plant cells on microfluidic platforms is still rare. In this work, we collated population statistics on the morphological, biochemical, physical and electrical properties of Arabidopsis protoplasts under different external and internal conditions, using progressively improved microfluidic platforms. First, we analyzed the different effects of three phytohormones (auxin, cytokinin and gibberellin) on the primary cell wall (PCW) regeneration process using a microfluidic flow cytometry platform equipped with a single-channel fluorescence sensor. Second, we correlated the intracellular reactive oxygen species (ROS) level induced by heavy metal stress with the concurrent PCW regeneration process by using a dual-channel fluorescence sensor. Third, by integrating contraction channels, we were able to effectively discriminate variations in cell size while monitoring the intensity of intracellular ROS signaling. Fourth, by combining an electrical impedance electrode with the contraction channel, we analyzed the differences in electrical and mechanical properties of wild-type and mutant plant cells before and after primary cell wall regeneration. Overall, our work demonstrates the feasibility and sensitivity of microfluidic flow cytometry in high-throughput phenotyping of plant cells and provides a reference for assessing metabolic and physiological indicators of individual plant cells in multiple dimensions.

Commutability assessment of candidate reference materials for plasma renin activity measurement: current challenges.

OBJECTIVES: This study aims to evaluate the commutability of external quality assessment (EQA) materials and candidate reference materials (RMs) for plasma renin activity (PRA) assay. METHODS: Commutabilities of 16 candidate RMs were measured along with 40 clinical samples by the four different routine PRA assays, including three LC‒MS/MS assays and one chemiluminescence immunoassay. Sixteen candidate RMs included native/spiked human plasma pools (small-scale pools with <50 individuals) and current EQA materials (large-scale pools with >1,000 individuals). Difference in bias approach and linear regression with prediction interval approach were adopted to determine the commutability. Two-way variance analysis was used to estimate the effects of spiked and pool size on the commutability. Stability and homogeneity studies were performed. RESULTS: Precision and correlation performance of all assays was acceptable. In the difference in bias approach, the commutability results were not satisfactory (noncommutability: 14/16) and significant sample-specific effects were detected in assay pairs using different incubation buffers. For the prediction interval approach, no commutability was observed in the spiked small-scale pools; EQA materials (4/9) had more satisfactory commutability among all assays than the small-scale pools (2/7); RMs of large-scale pools tend to have better commutability no matter spiked or not. CONCLUSIONS: Commutable RMs were obtainable but challenging. Current EQA materials with relatively good commutability, stability, and homogeneity were appropriate RMs. Large-scale pools are tending to be commutable. Spiking in small-scale pools was not suggested to prepare RMs. MPs adopting a uniform incubation buffer would be preferable for further commutability research.

An LC-MS/MS method for serum cystatin C quantification and its comparison with two commercial immunoassays.

OBJECTIVES: The standardization of cystatin C (CysC) measurement has received increasing attention in recent years due to its importance in estimating glomerular filtration rate (GFR). Mass spectrometry-based assays have the potential to provide an accuracy base for CysC measurement. However, a precise, accurate and sustainable LC-MS/MS method for CysC is still lacking. METHODS: The developed LC-MS/MS method quantified CysC by detecting signature peptide (T3) obtained from tryptic digestion. Stable isotope labeled T3 peptide (SIL-T3) was spiked to control matrix effects and errors caused by liquid handling. The protein denaturation, reduction and alkylation procedures were combined into a single step with incubation time of 1 h, and the digestion lasted for 3.5 h. In the method validation, digestion time-course, imprecision, accuracy, matrix effect, interference, limit of quantification (LOQ), carryover, linearity, and the comparability to two routine immunoassays were evaluated. RESULTS: No significant matrix effect or interference was observed with the CysC measurement. The LOQ was 0.21 mg/L; the within-run and total imprecision were 1.33-2.05 % and 2.18-3.90 % for three serum pools (1.18-5.34 mg/L). The LC-MS/MS method was calibrated by ERM-DA471/IFCC and showed good correlation with two immunoassays traceable to ERM-DA471/IFCC. However, significant bias was observed for immunoassays against the LC-MS/MS method. CONCLUSIONS: The developed LC-MS/MS method is robust and simpler and holds the promise to provide an accuracy base for routine immunoassays, which will promote the standardization of CysC measurement.

Decomposition analysis on the equity of health examination utilization for the middle-aged and elderly people in China: based on longitudinal CHARLS data from 2011 to 2018.

BACKGROUND: This study aimed to investigate the utilization rate and equity of health examination service among the middle-aged and elderly population in China from 2011 to 2018. The contribution of various determinants to the inequity in health examination service utilization was also examined. METHODS: Data from the China Health and Retirement Longitudinal Survey (CHARLS) were analyzed to assess the health examination service utilization rate among the middle-aged and elderly population. A concentration curve and concentration index were employed to measure the equity of health examination service utilization and decomposed into its determining factors. Horizontal inequity index was applied to evaluate the trends in equity of health examination service. RESULTS: The health examination service utilization rates among the middle-aged and elderly population were 29.45%, 20.69%, 25.40%, and 32.05% in 2011, 2013, 2015, and 2018, respectively. The concentration indexes for health examination service utilization were 0.0080 (95% CI: - 0.0084, 0.0244), 0.0155 (95% CI: - 0.0054, 0.0363), 0.0095 (95% CI: - 0.0088, 0.0277), and - 0.0100 (95% CI: - 0.0254, 0.0054) from 2011 to 2018, respectively. The horizontal inequity index was positive from 2011 to 2018, evidencing a pro-rich inequity trend. Age, residence, education, region, and economic status were the major identified contributors influencing the equity of health examination service utilization. CONCLUSIONS: A pro-rich inequity existed in health examination service utilization among the middle-aged and elderly population in China. Reducing the wealth and regional gap, providing equal educational opportunities, and strengthening the capacity for chronic disease prevention and control are crucial for reducing the inequity in health examination service utilization.

Utilizing Deep Neural Networks to Fill Gaps in Small Genomes.

With the widespread adoption of next-generation sequencing technologies, the speed and convenience of genome sequencing have significantly improved, and many biological genomes have been sequenced. However, during the assembly of small genomes, we still face a series of challenges, including repetitive fragments, inverted repeats, low sequencing coverage, and the limitations of sequencing technologies. These challenges lead to unknown gaps in small genomes, hindering complete genome assembly. Although there are many existing assembly software options, they do not fully utilize the potential of artificial intelligence technologies, resulting in limited improvement in gap filling. Here, we propose a novel method, DLGapCloser, based on deep learning, aimed at assisting traditional tools in further filling gaps in small genomes. Firstly, we created four datasets based on the original genomes of Saccharomyces cerevisiae, Schizosaccharomyces pombe, Neurospora crassa, and Micromonas pusilla. To further extract effective information from the gene sequences, we also added homologous genomes to enrich the datasets. Secondly, we proposed the DGCNet model, which effectively extracts features and learns context from sequences flanking gaps. Addressing issues with early pruning and high memory usage in the Beam Search algorithm, we developed a new prediction algorithm, Wave-Beam Search. This algorithm alternates between expansion and contraction phases, enhancing efficiency and accuracy. Experimental results showed that the Wave-Beam Search algorithm improved the gap-filling performance of assembly tools by 7.35%, 28.57%, 42.85%, and 8.33% on the original results. Finally, we established new gap-filling standards and created and implemented a novel evaluation method. Validation on the genomes of Saccharomyces cerevisiae, Schizosaccharomyces pombe, Neurospora crassa, and Micromonas pusilla showed that DLGapCloser increased the number of filled gaps by 8.05%, 15.3%, 1.4%, and 7% compared to traditional assembly tools.

scZAG: Integrating ZINB-Based Autoencoder with Adaptive Data Augmentation Graph Contrastive Learning for scRNA-seq Clustering.

Single-cell RNA sequencing (scRNA-seq) is widely used to interpret cellular states, detect cell subpopulations, and study disease mechanisms. In scRNA-seq data analysis, cell clustering is a key step that can identify cell types. However, scRNA-seq data are characterized by high dimensionality and significant sparsity, presenting considerable challenges for clustering. In the high-dimensional gene expression space, cells may form complex topological structures. Many conventional scRNA-seq data analysis methods focus on identifying cell subgroups rather than exploring these potential high-dimensional structures in detail. Although some methods have begun to consider the topological structures within the data, many still overlook the continuity and complex topology present in single-cell data. We propose a deep learning framework that begins by employing a zero-inflated negative binomial (ZINB) model to denoise the highly sparse and over-dispersed scRNA-seq data. Next, scZAG uses an adaptive graph contrastive representation learning approach that combines approximate personalized propagation of neural predictions graph convolution (APPNPGCN) with graph contrastive learning methods. By using APPNPGCN as the encoder for graph contrastive learning, we ensure that each cell's representation reflects not only its own features but also its position in the graph and its relationships with other cells. Graph contrastive learning exploits the relationships between nodes to capture the similarity among cells, better representing the data's underlying continuity and complex topology. Finally, the learned low-dimensional latent representations are clustered using Kullback-Leibler divergence. We validated the superior clustering performance of scZAG on 10 common scRNA-seq datasets in comparison to existing state-of-the-art clustering methods.

Stack-VTP: prediction of vesicle transport proteins based on stacked ensemble classifier and evolutionary information.

Vesicle transport proteins not only play an important role in the transmembrane transport of molecules, but also have a place in the field of biomedicine, so the identification of vesicle transport proteins is particularly important. We propose a method based on ensemble learning and evolutionary information to identify vesicle transport proteins. Firstly, we preprocess the imbalanced dataset by random undersampling. Secondly, we extract position-specific scoring matrix (PSSM) from protein sequences, and then further extract AADP-PSSM and RPSSM features from PSSM, and use the Max-Relevance-Max-Distance (MRMD) algorithm to select the optimal feature subset. Finally, the optimal feature subset is fed into the stacked classifier for vesicle transport proteins identification. The experimental results show that the of accuracy (ACC), sensitivity (SN) and specificity (SP) of our method on the independent testing set are 82.53%, 0.774 and 0.836, respectively. The SN, SP and ACC of our proposed method are 0.013, 0.007 and 0.76% higher than the current state-of-the-art methods.

Arabidopsis seedlings respond differentially to nutrient efficacy of three rock meals by regulating root architecture and endogenous auxin homeostasis.

BACKGROUND: Plants show developmental plasticity with variations in environmental nutrients. Considering low-cost rock dust has been identified as a potential alternative to artificial fertilizers for more sustainable agriculture, the growth responses of Arabidopsis seedlings on three rock meals (basalt, granite, and marlstone) were examined for the different foraging behavior, biomass accumulation, and root architecture. RESULTS: Compared to ½ MS medium, basalt and granite meal increased primary root length by 13% and 38%, respectively, but marlstone caused a 66% decrease, and they all drastically reduced initiation and elongation of lateral roots but lengthened root hairs. Simultaneous supply of organic nutrients and trace elements increased fresh weight due to the increased length of primary roots and root hairs. When nitrogen (N), phosphorus (P), and potassium (K) were supplied individually, N proved most effective in improving fresh weight of seedlings growing on basalt and granite, whereas K, followed by P, was most effective for those growing on marlstone. Unexpectedly, the addition of N to marlstone negatively affected seedling growth, which was associated with repressed auxin biosynthesis in roots. CONCLUSIONS: Our data indicate that plants can recognize and adapt to complex mineral deficiency by adjusting hormonal homeostasis to achieve environmental sensitivity and developmental plasticity, which provide a basis for ecologically sound and sustainable strategies to maximize the use of natural resources and reduce the production of artificial fertilizers.

Carrier Modulation in 2D Transistors by Inserting Interfacial Dielectric Layer for Area-Efficient Computation.

2D materials with atomic thickness display strong gate controllability and emerge as promising materials to build area-efficient electronic circuits. However, achieving the effective and nondestructive modulation of carrier density/type in 2D materials is still challenging because the introduction of dopants will greatly degrade the carrier transport via Coulomb scattering. Here, a strategy to control the polarity of tungsten diselenide (WSe2 ) field-effect transistors (FETs) via introducing hexagonal boron nitride (h-BN) as the interfacial dielectric layer is devised. By modulating the h-BN thickness, the carrier type of WSe2 FETs has been switched from hole to electron. The ultrathin body of WSe2 , combined with the effective polarity control, together contribute to the versatile single-transistor logic gates, including NOR, AND, and XNOR gates, and the operation of only two transistors as a half adder in logic circuits. Compared with the use of 12 transistors based on static Si CMOS technology, the transistor number of the half adder is reduced by 83.3%. The unique carrier modulation approach has general applicability toward 2D logic gates and circuits for the improvement of area efficiency in logic computation.