Abstract Single-cell RNA-sequencing (scRNA-Seq) is widely used to reveal the heterogeneity and dynamics of tissues, organisms, and complex diseases, but its analyses still suffer from multiple grand challenges, including the sequencing sparsity and complex differential patterns in gene expression. We introduce the scGNN (single-cell graph neural network) to provide a hypothesis-free deep learning framework for scRNA-Seq analyses. This framework formulates and aggregates cell–cell relationships with graph neural networks and models heterogeneous gene expression patterns using a left-truncated mixture Gaussian model. scGNN integrates three iterative multi-modal autoencoders and outperforms existing tools for gene imputation and cell clustering on four benchmark scRNA-Seq datasets. In an Alzheimer’s disease study with 13,214 single nuclei from postmortem brain tissues, scGNN successfully illustrated disease-related neural development and the differential mechanism. scGNN provides an effective representation of gene expression and cell–cell relationships. It is also a powerful framework that can be applied to general scRNA-Seq analyses.
Background and aims The incidence of colorectal cancer (CRC) is increasing in adults younger than 50, and early screening remains challenging due to cost and under-utilization. To identify individuals aged 35–50 years who may benefit from early screening, we developed a prediction model using machine learning and electronic health record (EHR)-derived factors. Methods We enrolled 3,116 adults aged 35–50 at average-risk for CRC and underwent colonoscopy between 2017–2020 at a single center. Prediction outcomes were (1) CRC and (2) CRC or high-risk polyps. We derived our predictors from EHRs (e.g., demographics, obesity, laboratory values, medications, and zip code-derived factors). We constructed four machine learning-based models using a training set (random sample of 70% of participants): regularized discriminant analysis, random forest, neural network, and gradient boosting decision tree. In the testing set (remaining 30% of participants), we measured predictive performance by comparing C-statistics to a reference model (logistic regression). Results The study sample was 55.1% female, 32.8% non-white, and included 16 (0.05%) CRC cases and 478 (15.3%) cases of CRC or high-risk polyps. All machine learning models predicted CRC with higher discriminative ability compared to the reference model [e.g., C-statistics (95%CI); neural network: 0.75 (0.48–1.00) vs. reference: 0.43 (0.18–0.67); P = 0.07] Furthermore, all machine learning approaches, except for gradient boosting, predicted CRC or high-risk polyps significantly better than the reference model [e.g., C-statistics (95%CI); regularized discriminant analysis: 0.64 (0.59–0.69) vs. reference: 0.55 (0.50–0.59); P<0.0015]. The most important predictive variables in the regularized discriminant analysis model for CRC or high-risk polyps were income per zip code, the colonoscopy indication, and body mass index quartiles. Discussion Machine learning can predict CRC risk in adults aged 35–50 using EHR with improved discrimination. Further development of our model is needed, followed by validation in a primary-care setting, before clinical application.
Precise segmentation of wheat spikes from a complex background is necessary for obtaining image-based phenotypic information of wheat traits such as yield estimation and spike morphology. A new instance segmentation method based on a Hybrid Task Cascade model was proposed to solve the wheat spike detection problem with improved detection results. In this study, wheat images were collected from fields where the environment varied both spatially and temporally. Res2Net50 was adopted as a backbone network, combined with multi-scale training, deformable convolutional networks, and Generic ROI Extractor for rich feature learning. The proposed methods were trained and validated, and the average precision (AP) obtained for the bounding box and mask was 0.904 and 0.907, respectively, and the accuracy for wheat spike counting was 99.29%. Comprehensive empirical analyses revealed that our method (Wheat-Net) performed well on challenging field-based datasets with mixed qualities, particularly those with various backgrounds and wheat spike adjacence/occlusion. These results provide evidence for dense wheat spike detection capabilities with masking, which is useful for not only wheat yield estimation but also spike morphology assessments.
Abstract Robust associations are strong indicators for causalities but challenging for identification from high-dimensional datasets. In examples of metagenomic research where microbiota is highly complex and variable, low concordance between studies in identifying disease-causative microbes has become the main obstacle in the field. Here, we develop a simple method—Virtual Twins (VTwins)—for inferring robust associations, imitating the twins in genetic research. From the original groups, paired samples of distinct phenotypes but matched taxonomical profiles are selected to reconstruct a “Twin” cohort, where statistical significance is often achieved. In direct comparison to current methods by revisiting the largest meta-analysis metagenomic dataset, VTwins can 10-fold reduce the sample-size for recalling disease-associated microbes robustly across-datasets and constructing machine-learning models of the same accuracy level as pooled samples in predicting disease status. In practice, VTwins is straightforward, powerful, and versatile in handling highly variable and high-dimensional datasets, suggesting potentials in mining causalities in the Big-data Era.
Objective To record and analyze the changes in the ocular surface and cornea in diabetic patients using a battery of ophthalmic tests and high resolution laser scanning confocal microscopy. Methods Prospective case control study. One hundred and eight patients with type 2 diabetes and 33 normal people (controls) were enrolled in this study. Based on the classification stages of diabetic retinopathy, patients were divided into 2 groups, those 42 patients (59 eyes) with non-diabetic retinopathy (NDR) and 66 patients (86 eyes) with proliferative diabetic retinopathy (PDR). All patients were examined using corneal sensitivity measurements, Schirmer's I test,non-invasive tear film break-up time (BUT), and corneal fluorescein staining. The testing regime also included DR-1 tear film interferometer camera and corneal confocal microscopy examinations.Parameters among groups were analyzed with a one-way ANOVA, a chi-square test and Spearman's rank correlation analysis. Results There was a significant difference between the NDR group (32％ were equal to or greater than grade Ⅲ) and the control group (14％) in the tear film test (P＜0.01). Corneal sensitivity was significantly lower in the PDR group [(33.0±12.4)mm] than in the control group [(47.2±9.7)mm] (P＜0.01). Tear secretion was (11.8±4.2)mm in the PDR group, and (15.2 ±4.3)mm in the control group. The difference between the two groups was statistically significant (P＜0.01). Tear film BUT was significantly shorter in the diabetic group [(7.3±2.5)s] than in the control group [(13.7±4.0)s] (P＜0.01). There was a sgnificant difference between the PDR group (50％ were equal to or gerater than grade Ⅲ) and the control group (14％) in the tear tim test (P＜0.01). Seventy-four percent patients were positive in PDR group in corneal fluorescein staining, much higher than control group (8％) (P＜0.01). Densities of corneal epithelium and corneal nerve fiber were all significantly lower in the PDR group [(4407±480)/mm2, (898±153)μm/field] than in the control group [(4736±313)/mm2, (1231±176)μm/field], respectively (P＜0.05 in both comparisons). The longer the duration of diabetes, the more serious the decrease in corneal sensitivity (r=-0.657, P=0.020) and the more corneal fluorescein staining (r=0.460, P=0.012) and the less corneal nerve fiber (r=-0.473, P=0.020). Conclusion Ocular surface disorders and retinopathies are common among diabetic patients. The results presented demonstrate significant degrees of corneal damage, especially in the PDR group. The ocular surfaces of PDR patients should be examined regularly to aid in early diagnosis and treatment.
Key words:
Diabetes mellitus,type 2; Diabetic retinopathy,proliferative; Cornea; Ocular surface
Both Kaposi’s sarcoma-associated herpesvirus (KSHV) and Epstein-Barr virus (EBV) establish the persistent, life-long infection primarily at the latent status, and associate with certain types of tumors, such as B cell lymphomas, especially in immuno-compromised individuals including people living with HIV (PLWH). Lytic reactivation of these viruses can be employed to kill tumor cells harboring latently infected viral episomes through the viral cytopathic effects and the subsequent antiviral immune responses. In this study, we identified that polo-like kinase 1 (PLK1) is induced by KSHV de novo infection as well as lytic switch from KSHV latency. We further demonstrated that PLK1 depletion or inhibition facilitates KSHV reactivation and promotes cell death of KSHV-infected lymphoma cells. Mechanistically, PLK1 regulates Myc that is critical to both maintenance of KSHV latency and support of cell survival, and preferentially affects the level of H3K27me3 inactive mark both globally and at certain loci of KSHV viral episomes. Furthremore, we recognized that PLK1 inhibition synergizes with STAT3 inhibition to efficiently induce KSHV reactivation. We also confirmed that PLK1 depletion or inhibition yields the similar effect on EBV lytic reactivation and cell death of EBV-infected lymphoma cells. Lastly, we noticed that PLK1 in B cells is elevated in the context of HIV infection and caused by HIV Nef protein to favor KSHV/EBV latency.
With the arrival of the climax of the development and utilization of underground space, new con- struction techniques were continuously developed to construct tunnels under more severe condi- tions. However, present design techniques sometimes cannot appropriately reflect the construc- tion techniques. Traditional design methods were still used, such as uniform rigidity ring model, beam spring model, multi-hinge ring model, etc. On account of the well-balanced progress be- tween construction and design in the shield tunneling method, an innovation of the design tech- nique is required. This paper shows an outline of the design technique of shield tunnel at present and improvements required for design technique.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
'%3e%3cpath fill='%23012169' d='M0 0v30h60V0z'/%3e%3cpath stroke='%23fff' stroke-width='6' d='m0 0 60 30m0-30L0 30'/%3e%3cpath stroke='%23C8102E' stroke-width='4' d='m0 0 60 30m0-30L0 30' clip-path='url(%23b)'/%3e%3cpath stroke='%23fff' stroke-width='10' d='M30 0v30M0 15h60'/%3e%3cpath stroke='%23C8102E' stroke-width='6' d='M30 0v30M0 15h60'/%3e%3c/g%3e%3c/svg%3e)
