Epithelial-Mesenchymal Transformation Promotes the Progression of Hepatocellular Carcinoma through NF-κB/MMP9 Axis.

BACKGROUND: Primary liver cancer (PHC) stands as one of the most prevalent malignant diseases in clinical settings. Studies have indicated that transcatheter arterial chemoembolization (TACE) treatment exhibits superior clinical outcomes, potentially increasing the complete necrosis rate in patients with PHC. A correlation exists between the clinical outcomes of TACE surgery and the process of epithelial-mesenchymal transition (EMT), yet the underlying mechanism remains a mystery. Hence, it is crucial to investigate the impact and mechanism of EMT on hepatocellular carcinoma (HCC). METHODS: Retrospectively, patients with advanced liver cancer who underwent TACE were selected and categorized into two groups based on the assessment of clinical efficacy: the effective group and the ineffective group. The expression levels of nuclear factor-kappa B (NF-κB), matrix metalloproteinase 9 (MMP9), Ki-67, B-cell lymphoma-2 (Bcl-2), Bcl-2-associated X (Bax), Vimentin, E-cadherin, and N-cadherin in tumor tissues were evaluated using reverse transcription-polymerase chain reaction (RT-PCR). In vitro, Huh7 cells were cultured, and lentivirus infections were utilized to inhibit the overexpression of NF-κB and MMP9. The determination of EMT and cell viability was conducted through Cell Counting Kit-8 (CCK-8) assays, RT-PCR, and Western blot. RESULTS: Sixty patients diagnosed with advanced liver cancer were selected for the study. Based on their clinical outcomes, 30 patients with advanced hepatocellular carcinoma were categorized into the effective group, while the remaining 30 patients were categorized into the ineffective group. The results of the Western blot analysis indicated that, in comparison to the effective group, the expression levels of NF-κB, MMP9, Ki-67, Bcl-2, Vimentin, and N-cadherin were significantly higher in the tumor tissues of the ineffective group. Conversely, the expression of Bax and E-cadherin was notably lower in the effective group. Following the individual knockdown of NF-κB and MMP9, the cell experiments revealed a remarkable decrease in the expression levels of Ki-67, Bcl-2, Vimentin, and N-cadherin, whereas the expression of Bax and E-cadherin showed significant elevation (p < 0.05). Furthermore, there was a significant increase in cell viability and a decrease in cell apoptosis after the knockdown of NF-κB and MMP9. CONCLUSIONS: The NF-κB/MMP9 signaling axis serves as a pivotal regulator that fosters proliferation and impedes apoptosis in Huh7 cells by modulating the process of EMT.

An in-situ magnetising holder achieving 1.5 T in-plane field in 200 kV transmission electron microscope.

A strong in-plane magnetic field is required for Lorentz transmission electron microscopy (LTEM) to observe the evolution of the magnetic domain structure of materials with high coercivity, particularly for research on rare-earth permanent magnets. However, the maximum field of the present in-situ magnetising holder applied in 200-kV or 300-kV TEM does not exceed 0.1 T. In this study, the reason for the low field was analysed, and the field strength was significantly elevated by reducing the field application area of the field generator. From finite element method calculations and experimental measurements, a 1.5 T in-plane field was achieved by our new holder in a 200-kV TEM, and images with good quality could still be obtained. Using the newly developed holder, the magnetisation process of hot-pressed NdFeB magnets was observed. The in-situ magnetising holder can be used in research on a wide variety of magnetic materials.

Age-Related Changes in Urethral Structure and Responds to Injury: Single-Cell Atlas of a Rat Model of Vaginal Birth Injury induced Stress Urinary Incontinence.

Stress urinary incontinence (SUI) greatly affects the daily life of numerous women and is closely related to a history of vaginal delivery and aging. We used vaginal balloon dilation to simulate vaginal birth injury in young and middle-aged rats to produce a SUI animal model, and found that young rats restored urethral structure and function well, but not the middle-aged rats. To identify the characteristics of cellular and molecular changes in the urethral microenvironment during the repair process of SUI. We profiled 51,690 individual female rat urethra cells from 24 and 48 weeks old, with or without simulated vaginal birth injury. Cell interaction analysis showed that signal networks during repair process changed from resting to active, and aging altered the distribution but not the overall level of cell interaction in the repair process. Similarity analysis showed that muscle, fibroblasts, and immune cells underwent large transcriptional changes during aging and repair. In middle-aged rats, cell senescence occurs mainly in the superficial and middle urothelium due to cellular death and shedding, and the basal urothelium expressed many Senescence-Associated Secretory Phenotype (SASP) genes. In conclusion, we established the aging and vaginal balloon dilation (VBD) model of female urethral cell anatomy and the signal network landscape, which provides an insight into the normal or disordered urethra repair process and the scientific basis for developing novel SUI therapies.

Fine mapping of ClLOX, a QTL for powdery mildew resistance in watermelon (Citrullus lanatus L.).

KEY MESSAGE: ClLOX, is located on chromosome 2 and encodes a lipoxygenase gene, which induced watermelon powdery mildew resistance by inhibiting pathogen spread. Powdery mildew is one of the most severe fungal diseases reducing yield and quality of watermelon (Citrullus lanatus L.) and other cucurbit crops. Genes responsible for powdery mildew resistance in watermelon are highly valuable. In this study, we first identified the QTL pm-lox for powdery mildew resistance in watermelon, located within a 0.93 Mb interval of chromosome 2, via XP-GWAS method using two F2 populations. The F2:3 families from one of the F2 populations were then used for fine-mapping the pm-lox locus into a 9,883 bp physical region between 29,581,906 and 29,591,789, containing only two annotated genes. Of these, only ClG42_02g0161300 showed a significant differential expression between the resistant and susceptible lines after powdery mildew inoculation based on RNA sequencing (RNA-seq) and qRT-PCR analysis, and is designated ClLOX. Derived Cleaved Amplified Polymorphic Sequence (dCAPs) markers were developed and validated. In addition, our tests showed that the resistance was anti-spread rather than anti-infection of the pathogen. This study identified a new resistance gene (ClLOX), provided insights into the mechanism of powdery mildew resistance, and developed a molecular marker for watermelon breeding.

Machine Learning-Based Virtual Screening and Identification of the Fourth-Generation EGFR Inhibitors.

Epidermal growth factor receptor (EGFR) plays a pivotal regulatory role in treating patients with advanced nonsmall cell lung cancer (NSCLC). Following the emergence of the EGFR tertiary CIS C797S mutation, all types of inhibitors lose their inhibitory activity, necessitating the urgent development of new inhibitors. Computer systems employ machine learning methods to process substantial volumes of data and construct models that enable more accurate predictions of the outcomes of new inputs. The purpose of this article is to uncover innovative fourth-generation epidermal growth factor receptor tyrosine kinase inhibitors (EGFR-TKIs) with the aid of machine learning techniques. The paper's data set was high-dimensional and sparse, encompassing both structured and unstructured descriptors. To address this considerable challenge, we introduced a fusion framework to select critical molecule descriptors by integrating the full quadratic effect model and the Lasso model. Based on structural descriptors obtained from the full quadratic effect model, we conceived and synthesized a variety of small-molecule inhibitors. These inhibitors demonstrated potent inhibitory effects on the two mutated kinases L858R/T790M/C797S and Del19/T790M/C797S. Moreover, we applied our model to virtual screening, successfully identifying four hit compounds. We have evaluated these hit ADME characteristics and look forward to conducting activity evaluations on them in the future to discover a new generation of EGFR-TKI.

Thermal Stability of Skyrmion Tubes in Nanostructured Cuboids.

Magnetic skyrmions in bulk materials are typically regarded as two-dimensional structures. However, they also exhibit three-dimensional configurations, known as skyrmion tubes, that elongate and extend in-depth. Understanding the configurations and stabilization mechanism of skyrmion tubes is crucial for the development of advanced spintronic devices. However, the generation and annihilation of skyrmion tubes in confined geometries are still rarely reported. Here, we present direct imaging of skyrmion tubes in nanostructured cuboids of a chiral magnet FeGe using Lorentz transmission electron microscopy (TEM), while applying an in-plane magnetic field. It is observed that skyrmion tubes stabilize in a narrow field-temperature region near the Curie temperature (Tc). Through a field cooling process, metastable skyrmion tubes can exist in a larger region of the field-temperature diagram. Combining these experimental findings with micromagnetic simulations, we attribute these phenomena to energy differences and thermal fluctuations. Our results could promote topological spintronic devices based on skyrmion tubes.

CYP19A1 mediates severe SARS-CoV-2 disease outcome in males.

Male sex represents one of the major risk factors for severe COVID-19 outcome. However, underlying mechanisms that mediate sex-dependent disease outcome are as yet unknown. Here, we identify the CYP19A1 gene encoding for the testosterone-to-estradiol metabolizing enzyme CYP19A1 (also known as aromatase) as a host factor that contributes to worsened disease outcome in SARS-CoV-2-infected males. We analyzed exome sequencing data obtained from a human COVID-19 cohort (n = 2,866) using a machine-learning approach and identify a CYP19A1-activity-increasing mutation to be associated with the development of severe disease in men but not women. We further analyzed human autopsy-derived lungs (n = 86) and detect increased pulmonary CYP19A1 expression at the time point of death in men compared with women. In the golden hamster model, we show that SARS-CoV-2 infection causes increased CYP19A1 expression in the lung that is associated with dysregulated plasma sex hormone levels and reduced long-term pulmonary function in males but not females. Treatment of SARS-CoV-2-infected hamsters with a clinically approved CYP19A1 inhibitor (letrozole) improves impaired lung function and supports recovery of imbalanced sex hormones specifically in males. Our study identifies CYP19A1 as a contributor to sex-specific SARS-CoV-2 disease outcome in males. Furthermore, inhibition of CYP19A1 by the clinically approved drug letrozole may furnish a new therapeutic strategy for individualized patient management and treatment.

[Progress in application of adult endogenous neurogenesis in brain injury repair].

Persistent neurogenesis exists in the subventricular zone (SVZ) of the ventricles and the subgranular zone (SGZ) of the dentate gyrus of the hippocampus in the adult mammalian brain. Adult endogenous neurogenesis not only plays an important role in the normal brain function, but also has important significance in the repair and treatment of brain injury or brain diseases. This article reviews the process of adult endogenous neurogenesis and its application in the repair of traumatic brain injury (TBI) or ischemic stroke, and discusses the strategies of activating adult endogenous neurogenesis to repair brain injury and its practical significance in promoting functional recovery after brain injury.

Using Pointwise Mutual Information for Breast Cancer Health Disparities Research With SEER-Medicare Claims.

Identification of procedures using International Classification of Diseases or Healthcare Common Procedure Coding System codes is challenging when conducting medical claims research. We demonstrate how Pointwise Mutual Information can be used to find associated codes. We apply the method to an investigation of racial differences in breast cancer outcomes. We used Surveillance Epidemiology and End Results (SEER) data linked to Medicare claims. We identified treatment using two methods. First, we used previously published definitions. Second, we augmented definitions using codes empirically identified by the Pointwise Mutual Information statistic. Similar to previous findings, we found that presentation differences between Black and White women closed much of the estimated survival curve gap. However, we found that survival disparities were completely eliminated with the augmented treatment definitions. We were able to control for a wider range of treatment patterns that might affect survival differences between Black and White women with breast cancer.

Deep learning-assisted diagnosis of femoral trochlear dysplasia based on magnetic resonance imaging measurements.

BACKGROUND: Femoral trochlear dysplasia (FTD) is an important risk factor for patellar instability. Dejour classification is widely used at present and relies on standard lateral X-rays, which are not common in clinical work. Therefore, magnetic resonance imaging (MRI) has become the first choice for the diagnosis of FTD. However, manually measuring is tedious, time-consuming, and easily produces great variability. AIM: To use artificial intelligence (AI) to assist diagnosing FTD on MRI images and to evaluate its reliability. METHODS: We searched 464 knee MRI cases between January 2019 and December 2020, including FTD (n = 202) and normal trochlea (n = 252). This paper adopts the heatmap regression method to detect the key points network. For the final evaluation, several metrics (accuracy, sensitivity, specificity, etc.) were calculated. RESULTS: The accuracy, sensitivity, specificity, positive predictive value and negative predictive value of the AI model ranged from 0.74-0.96. All values were superior to junior doctors and intermediate doctors, similar to senior doctors. However, diagnostic time was much lower than that of junior doctors and intermediate doctors. CONCLUSION: The diagnosis of FTD on knee MRI can be aided by AI and can be achieved with a high level of accuracy.

Polypropylene fiber grafted calcium alginate with mesoporous silica for adsorption of Bisphenol A and Pb2.

Polypropylene grafted calcium alginate with mesoporous silica (PP-g-CaAlg@SiO2) for adsorbing Bisphenol A (BPA) and Pb2+ was prepared by calcium chloride (CaCl2) crosslinking and hydrochloric acid solution treatment. The PP-g-CaAlg@SiO2 was characterized by SEM, TEM, BET, XRD, FTIR and TG. PP-g-CaAlg@SiO2 exhibited excellent adsorption capacity for BPA and Pb2+, because the formation of reticulated nanorod structure increased its specific surface area. Subsequently, the adsorption behaviours of BPA and Pb2+, including adsorption isotherms and adsorption kinetics, were investigated. Afterward, isothermal titration calorimetry (ITC) and molecular dynamics (MD) simulation were performed to explore the adsorption mechanism. The results indicated that hydrogen bonding played the leading role in the adsorption of BPA, while the bonding of Pb2+ to carboxyl group binding sites was the focus of Pb2+ adsorption. In addition, the adsorption capacity of PP-g-CaAlg@SiO2 was stable over 10 cycles.

Mild and asymptomatic influenza B virus infection among unvaccinated pregnant persons: Implication for effectiveness of non-pharmaceutical intervention and vaccination to prevent influenza.

BACKGROUND: We estimated symptomatic and asymptomatic influenza infection frequency in community-dwelling unvaccinated pregnant persons to inform risk communication. METHODS: We collected residue sera from multiple antenatal-care blood draws during October 2016-April 2017. We determined influenza infection as seroconversion with ≥ 4-fold rise in antibody titers between any two serum samples by improved hemagglutinin-inhibition assay including ether-treated B antigens. The serology data were linked to the results of nuclei acid testing (rRT-PCR) based on acute respiratory illness (ARI) surveillance. RESULTS: Among all participants, 43 %(602/1384) demonstrated serology and/or rRT-PCR evidenced infection, and 44 %(265/602) of all infections were asymptomatic. ARI-associated rRT-PCR testing identified only 10 %(61/602) of total infections. Only 1 %(5/420) of the B Victoria cases reported ARI and had a rRT-PCR positive result, compared with 33 %(54/165) of the H3N2 cases. Among influenza ARI cases with multiple serum samples, 19 %(11/58) had seroconversion to a different subtype prior to the illness. CONCLUSIONS: The incidence of influenza B infection in unvaccinated pregnant persons is under-estimated substantially. Non-pharmaceutical intervention may have suboptimal effectiveness in preventing influenza B transmission due to the less clinical manifestation compared to influenza A. The findings support maternal influenza vaccination to protect pregnant persons and reduce consequent household transmission.

Biomimetic AgNPs@antimicrobial peptide/silk fibroin coating for infection-trigger antibacterial capability and enhanced osseointegration.

Endowing implant surfaces with combined antibacterial and osteogenic properties by drug-loaded coatings has made great strides, but how to achieve the combined excellence of infection-triggered bactericidal and in vivo-proven osteogenic activities without causing bacterial resistance still remains a formidable challenge. Herein, antimicrobial peptides (AMPs) with osteogenic fragments were designed and complexed on the surface of silver nanoparticle (AgNP) through hydrogen bonding, and the collagen structure-bionic silk fibroin (SF) was applied to carry AgNPs@ AMPs to achieve infection-triggered antibacterial and osteointegration. As verified by TEM, AMPs contributed to the dispersion and size-regulation of AgNPs, with a particle size of about 20 nm, and a clear protein corona structure was observed on the particle surface. The release curve of silver ion displayed that the SF-based coating owned sensitive pH-responsive properties. In the antibacterial test against S.aureus for up to 21 days, the antibacterial rate had always remained above 99%. Meanwhile, the underlying mechanism was revealed, originating from the destruction of the bacterial cell membranes and ROS generation. The SF-based coating was conducive to the adhesion, diffusion, and proliferation of bone marrow stem cells (BMSCs) on the surface, and promoted the expression of osteogenic genes and collagen secretion. The in vivo implantation results showed that compared with the untreated Ti implants, SF-based coating enhanced osseointegration at week 4 and 8. Overall, the AgNPs@AMPs-loaded SF-based coating presented the ability to synergistically inhibit bacteria and promote osseointegration, possessing tremendous potential application prospects in bone defects and related-infection treatments.

H7N9 avian influenza virus infection in men is associated with testosterone depletion.

Human infections with H7N9 avian influenza A virus that emerged in East China in 2013 and caused high morbidity rates were more frequently detected in men than in women over the last five epidemic waves. However, molecular markers associated with poor disease outcomes in men are still unknown. In this study, we systematically analysed sex hormone and cytokine levels in males and females with laboratory-confirmed H7N9 influenza in comparison to H7N9-negative control groups as well as laboratory-confirmed seasonal H1N1/H3N2 influenza cases (n = 369). Multivariable analyses reveal that H7N9-infected men present with considerably reduced testosterone levels associated with a poor outcome compared to non-infected controls. Regression analyses reveal that testosterone levels in H7N9-infected men are negatively associated with the levels of several pro-inflammatory cytokines, such as IL-6 and IL-15. To assess whether there is a causal relationship between low testosterone levels and avian H7N9 influenza infection, we used a mouse model. In male mice, we show that respiratory H7N9 infection leads to a high viral load and inflammatory cytokine response in the testes as well as a reduction in pre-infection plasma testosterone levels. Collectively, these findings suggest that monitoring sex hormone levels may support individualized management for patients with avian influenza infections.

Genome survey and development of 13 SSR markers in Eucalyptus cloeziana by NGS.

Eucalyptus cloeziana is a valuable timber tree species for its high durability and excellent sawmilling qualities. However, there is lack of complete genomic information for this plant, which severely constrains its genetic improvement. This study aim to survey the genome of E. cloeziana and determine the large-scale sequencing scheme of this species. Next-generation sequencing based on Illumina Hi- Seq X Ten platform was used to survey the E. cloeziana genome and its SSR markers development. We estimated the genome size to be 491.91 Mb and the heterozygosity rate to be 1.23%, with repetitive sequences accounting for 40.74%. The clean reads of E. cloeziana were assembled into 995,093 scaffolds (556,992,952 bp) with a N50 value of 2297 bp. In the GO database, the 10,172 genes annotated were matched to 50 functional gene groups in three categories of cell component, biological function and molecular function, respectively. Through KEGG pathways analysis, 10,802 genes were successfully annotated and 133 metabolic pathways were detected with the most abundant metabolism-related genes. Meanwhile, a total of 58,832 simple-sequence repeat (SSR) loci were identified in the E. cloeziana genome, and among them, dinucleotide repeats were the most abundant class. AG/CT, AT/AT, AAG/CTT were the three most frequent primitive types. Of the 50 genomic SSR primer pairs randomly selected for screening test, 13 showed polymorphism (PIC = 0.625). Three to nine alleles per locus (mean = 6.23) were observed, with the observed and expected heterozygosity at 0.317-1.000 and 0.276-0.838 across all the 44 E. cloeziana germplasms, respectively. Here, we report the genome information of E. cloeziana, and the novel 13 genomic SSR markers that were developed can be used as powerful tools for evaluating genetic diversity and population structure, and thus contribute to molecular breeding studies of E. cloeziana and other eucalypts.

Integration of CD34+CD117dim population signature improves the prognosis prediction of acute myeloid leukemia.

BACKGROUND: Acute Myeloid Leukemia (AML) is a hematological cancer characterized by heterogeneous hematopoietic cells. Through the use of multidimensional sequencing technologies, we previously identified a distinct myeloblast population, CD34+CD117dim, the proportion of which was strongly associated with the clinical outcome in t (8;21) AML. In this study, we explored the potential value of the CD34+CD117dim population signature (117DPS) in AML stratification. METHODS: Based on the CD34+CD117dim gene signature, the least absolute shrinkage and selection operator (LASSO) Cox regression analysis was performed to construct the 117DPS model using the gene expression data from Gene Expression Omnibus (GEO) database (GSE37642-GPL96 was used as training cohort; GSE37642-GPL570, GSE12417-GPL96, GSE12417-GPL570 and GSE106291 were used as validation cohorts). In addition, the RNA-seq data from The Cancer Genome Atlas (TCGA)-LAML and Beat AML projects of de-novo AML patients were also analyzed as validation cohorts. The differences of clinical features and tumor-infiltrating lymphocytes were further explored between the high-risk score group and low-risk score group. RESULTS: The high-risk group of the 117DPS model exhibited worse overall survival than the low-risk group in both training and validation cohorts. Immune signaling pathways were significantly activated in the high-risk group. Patients with high-risk score had a distinct pattern of infiltrating immune cells, which were closely related to clinical outcome. CONCLUSION: The 117DPS model established in our study may serve as a potentially valuable tool for predicting clinical outcome of patients with AML.

Semi-Supervised Cell Detection with Reliable Pseudo-Labels.

Pathological images play an important role in the diagnosis, treatment, and prognosis of cancer. Usually, pathological images contain complex environments and cells of different shapes. Pathologists consume a lot of time and labor costs when analyzing and discriminating the cells in the images. Therefore, fully annotated pathological image data sets are not easy to obtain. In view of the problem of insufficient labeled data, we input a large number of unlabeled images into the pretrained model to generate accurate pseudo-labels. In this article, we propose two methods to improve the quality of pseudo-labels, namely, the pseudo-labeling based on adaptive threshold and the pseudo-labeling based on cell count. These two pseudo-labeling methods take into account the distribution of cells in different pathological images when removing background noise, and ensure that accurate pseudo-labels are generated for each unlabeled image. Meanwhile, when pseudo-labels are used for model retraining, we perform data distillation on the feature maps of unlabeled images through an attention mechanism, which further improves the quality of training data. In addition, we also propose a multi-task learning model, which learns the cell detection task and the cell count task simultaneously, and improves the performance of cell detection through feature sharing. We verified the above methods on three different data sets, and the results show that the detection effect of the model with a large number of unlabeled images involved in retraining is improved by 9%-13% compared with the model that only uses a small number of labeled images for pretraining. Moreover, our methods have good applicability on the three data sets.

Quantitative Evaluation of Small Intestinal Hemorrhage Using Energy Spectrum CT Iodine-Water Map.

The objective of this research is to analyze the quantitative evaluation of human small intestinal bleeding by observing and analyzing animal experiments of small intestinal hemorrhage in rabbit models for the convenience of understanding the role of energy spectrum CT iodine-water diagram in animal experimental research of quantitative evaluation of small intestinal bleeding in rabbit models. Compared with the energy spectrum of iodine-water graph of a rabbit CT model, the present study studied the quantitative evaluation of small intestinal bleeding by using a rabbit model instead of human. According to the method mentioned above and the analysis of experimental data, the role of energy spectrum CT iodine-water map and the quantitative evaluation of human small intestinal bleeding have been understood. It was found that the energy spectrum CT iodine-water map replaces humans in the rabbit model for quantitative evaluation of small intestinal bleeding in animal experiments, which is important in the present study. Besides, based upon the combination of theoretical and experimental data, the ten flow rates set on the base material iodine (water) maps of the arterial phase and the portal phase can be analyzed to detect the leakage of contrast agent. The yield was 100%. The research results showed that the animal experiment of quantitative assessment of small intestinal bleeding by replacing the human body with the rabbit model in the energy spectrum CT iodine-water diagram is critical to humans in the study of small intestinal hemorrhagic diseases. In addition, it can be used to adjust the treatment plan timely according to the amount of bleeding to prevent shock or heavy bleeding that threatens patients' lives.

Context-aware learning for cancer cell nucleus recognition in pathology images.

MOTIVATION: Nucleus identification supports many quantitative analysis studies that rely on nuclei positions or categories. Contextual information in pathology images refers to information near the to-be-recognized cell, which can be very helpful for nucleus subtyping. Current CNN-based methods do not explicitly encode contextual information within the input images and point annotations. RESULTS: In this article, we propose a novel framework with context to locate and classify nuclei in microscopy image data. Specifically, first we use state-of-the-art network architectures to extract multi-scale feature representations from multi-field-of-view, multi-resolution input images and then conduct feature aggregation on-the-fly with stacked convolutional operations. Then, two auxiliary tasks are added to the model to effectively utilize the contextual information. One for predicting the frequencies of nuclei, and the other for extracting the regional distribution information of the same kind of nuclei. The entire framework is trained in an end-to-end, pixel-to-pixel fashion. We evaluate our method on two histopathological image datasets with different tissue and stain preparations, and experimental results demonstrate that our method outperforms other recent state-of-the-art models in nucleus identification. AVAILABILITY AND IMPLEMENTATION: The source code of our method is freely available at https://github.com/qjxjy123/DonRabbit. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.