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

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

AMPFLDAP: Adaptive Message Passing and Feature Fusion on Heterogeneous Network for LncRNA-Disease Associations Prediction

Exploration of the intricate connections between long noncoding RNA (lncRNA) and diseases, referred to as lncRNA-disease associations (LDAs), plays a pivotal and indispensable role in unraveling the underlying molecular mechanisms of diseases and devising practical treatment approaches. It is imperative to employ computational methods for predicting lncRNA-disease associations to circumvent the need for superfluous experimental endeavors. Graph-based learning models have gained substantial popularity in predicting these associations, primarily because of their capacity to leverage node attributes and relationships within the network. Nevertheless, there remains much room for enhancing the performance of these techniques by incorporating and harmonizing the node attributes more effectively. In this context, we introduce a novel model, i.e., Adaptive Message Passing and Feature Fusion (AMPFLDAP), for forecasting lncRNA-disease associations within a heterogeneous network. Firstly, we constructed a heterogeneous network involving lncRNA, microRNA (miRNA), and diseases based on established associations and employing Gaussian interaction profile kernel similarity as a measure. Then, an adaptive topological message passing mechanism is suggested to address the information aggregation for heterogeneous networks. The topological features of nodes in the heterogeneous network were extracted based on the adaptive topological message passing mechanism. Moreover, an attention mechanism is applied to integrate both topological and semantic information to achieve the multimodal features of biomolecules, which are further used to predict potential LDAs. The experimental results demonstrated that the performance of the proposed AMPFLDAP is superior to seven state-of-the-art methods. Furthermore, to validate its efficacy in practical scenarios, we conducted detailed case studies involving three distinct diseases, which conclusively demonstrated AMPFLDAP's effectiveness in the prediction of LDAs.

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

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

Personalized Driver Gene Prediction Using Graph Convolutional Networks with Conditional Random Fields

Cancer is a complex and evolutionary disease mainly driven by the accumulation of genetic variations in genes. Identifying cancer driver genes is important. However, most related studies have focused on the population level. Cancer is a disease with high heterogeneity. Thus, the discovery of driver genes at the individual level is becoming more valuable but is a great challenge. Although there have been some computational methods proposed to tackle this challenge, few can cover all patient samples well, and there is still room for performance improvement. In this study, to identify individual-level driver genes more efficiently, we propose the PDGCN method. PDGCN integrates multiple types of data features, including mutation, expression, methylation, copy number data, and system-level gene features, along with network structural features extracted using Node2vec in order to construct a sample-gene interaction network. Prediction is performed using a graphical convolutional neural network model with a conditional random field layer, which is able to better combine the network structural features with biological attribute features. Experiments on the ACC (Adrenocortical Cancer) and KICH (Kidney Chromophobe) datasets from TCGA (The Cancer Genome Atlas) demonstrated that the method performs better compared to other similar methods. It can identify not only frequently mutated driver genes, but also rare candidate driver genes and novel biomarker genes. The results of the survival and enrichment analyses of these detected genes demonstrate that the method can identify important driver genes at the individual level.

SGLMDA: A Subgraph Learning-based Method for miRNA-disease Association Prediction

MicroRNAs (miRNA) are endogenous non-coding RNAs, typically around 23 nucleotides in length. Many miRNAs have been founded to play crucial roles in gene regulation though post-transcriptional repression in animals. Existing studies suggest that the dysregulation of miRNA is closely associated with many human diseases. Discovering novel associations between miRNAs and diseases is essential for advancing our understanding of disease pathogenesis at molecular level. However, experimental validation is time-consuming and expensive. To address this challenge, numerous computational methods have been proposed for predicting miRNA-disease associations. Unfortunately, most existing methods face difficulties when applied to large-scale miRNA-disease complex networks. In this paper, we present a novel subgraph learning method named SGLMDA for predicting miRNA-disease associations. For miRNA-disease pairs, SGLMDA samples K-hop subgraphs from the global heterogeneous miRNA-disease graph. It then introduces a novel subgraph representation algorithm based on Graph Neural Network (GNN) for feature extraction and prediction. Extensive experiments conducted on benchmark datasets demonstrate that SGLMDA can effectively and robustly predict potential miRNA-disease associations. Compared to other state-of-the-art methods, SGLMDA achieves superior prediction performance in terms of Area Under the Curve (AUC) and Average Precision (AP) values during 5-fold Cross-Validation (5CV) on benchmark datasets such as HMDD v2.0 and HMDD v3.2. Additionally, case studies on Colon Neoplasms and Triple-Negative Breast Cancer (TNBC) further underscore the predictive power of SGLMDA. The dataset and source code of SGLMDA are available at https://github.com/cunmeiji/SGLMDA.

Construction of prediction model for fetal growth restriction during first trimester in an Asian population

OBJECTIVE

To construct a prediction model for fetal growth restriction (FGR) during the first trimester of pregnancy and evaluate its screening performance.

METHODS

This was a prospective cohort study of singleton pregnancies that underwent routine ultrasound screening at 11 to 13 + 6 weeks at the Affiliated Suzhou Hospital of Nanjing Medical University between January 2019 and April 2022. Basic clinical information, ultrasound indicators and serum biomarkers of pregnant women were collected. Fetal weight assessment was based on the fetal growth curve for the Southern Chinese population. FGR was diagnosed according to Delphi consensus criteria. Least absolute shrinkage and selection operator (lasso) regression was used to select variables for inclusion in the model. Discrimination, calibration and clinical effectiveness of the model were evaluated in training and validation cohorts.

RESULTS

A total of 1188 pregnant women were included, of whom 108 had FGR. Lasso regression identified seven predictive features, including history of maternal hypertension, maternal smoking or passive smoking, gravidity, uterine artery pulsatility index, ductus venosus pulsatility index and multiples of the median values of placental growth factor and soluble fms-like tyrosine kinase-1. The nomogram prediction model constructed from these seven variables accurately predicted FGR, and the area under the receiver-operating-characteristics curve in the validation cohort was 0.82 (95% CI, 0.74-0.90). The calibration curve and Hosmer-Lemeshow test demonstrated good calibration, and the clinical decision curve and clinical impact curve supported its practical value in a clinical setting.

CONCLUSION

The multi-index prediction model for FGR has good predictive value during the first trimester. © 2023 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

A clustering method for single-cell RNA-seq data based on automatic weighting penalty and low-rank representation

Advances in high-throughput single-cell RNA sequencing (scRNA-seq) technology have provided more comprehensive biological information on cell expression. Clustering analysis is a critical step in scRNA-seq research and provides clear knowledge of the cell identity. Unfortunately, the characteristics of scRNA-seq data and the limitations of existing technologies make clustering encounter a considerable challenge. Meanwhile, some existing methods treat different features equally and ignore differences in feature contributions, which leads to a loss of information. To overcome limitations, we introduce a weighted distance constraint into the construction of the similarity graph and combine the similarity constraint. We propose the Joint Automatic Weighting Similarity Graph and Low-rank Representation (JAGLRR) clustering method. Evaluating the contributions of each feature and assigning various weight values can increase the significance of valuable features while decreasing the interference of redundant features. The similarity constraint allows the model to generate a more symmetric affinity matrix. Benefitting from that affinity matrix, JAGLRR recovers the original linear relationship of the data more accurately and obtains more discriminative information. The results on simulated datasets and 8 real datasets show that JAGLRR outperforms 11 existing comparison methods in clustering experiments, with higher clustering accuracy and stability.

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

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

Fine-mapping of a major locus for Fusarium wilt resistance in flax (Linum usitatissimum L.)

KEY MESSAGE

Fine-mapping of a locus on chromosome 1 of flax identified an S-lectin receptor-like kinase (SRLK) as the most likely candidate for a major Fusarium wilt resistance gene. Fusarium wilt, caused by the soil-borne fungal pathogen Fusarium oxysporum f. sp. lini, is a devastating disease in flax. Genetic resistance can counteract this disease and limit its spread. To map major genes for Fusarium wilt resistance, a recombinant inbred line population of more than 700 individuals derived from a cross between resistant cultivar 'Bison' and susceptible cultivar 'Novelty' was phenotyped in Fusarium wilt nurseries at two sites for two and three years, respectively. The population was genotyped with 4487 single nucleotide polymorphism (SNP) markers. Twenty-four QTLs were identified with IciMapping, 18 quantitative trait nucleotides with 3VmrMLM and 108 linkage disequilibrium blocks with RTM-GWAS. All models identified a major QTL on chromosome 1 that explained 20-48% of the genetic variance for Fusarium wilt resistance. The locus was estimated to span ~ 867 Kb but included a ~ 400 Kb unresolved region. Whole-genome sequencing of 'CDC Bethune', 'Bison' and 'Novelty' produced ~ 450 Kb continuous sequences of the locus. Annotation revealed 110 genes, of which six were considered candidate genes. Fine-mapping with 12 SNPs and 15 Kompetitive allele-specific PCR (KASP) markers narrowed down the interval to ~ 69 Kb, which comprised the candidate genes Lus10025882 and Lus10025891. The latter, a G-type S-lectin receptor-like kinase (SRLK) is the most likely resistance gene because it is the only polymorphic one. In addition, Fusarium wilt resistance genes previously isolated in tomato and Arabidopsis belonged to the SRLK class. The robust KASP markers can be used in marker-assisted breeding to select for this major Fusarium wilt resistance locus.

Beyond Vision: A View from Eye to Alzheimer's Disease and Dementia

With the aging of the global population, the health care burden of Alzheimer's disease (AD) and dementia is considered to increase dramatically in the coming decades. Given the insufficiency of effective interventions for AD and dementia, clinical research on identifying potentially modifiable risk factors and early diagnostic biomarkers becomes a public health priority. Currently, extracerebral manifestations with a large proportion of ocular involvement are usually recognized to precede the symptoms of AD and dementia. Growing epidemiologic evidence also suggests that eye disorders, such as cataracts, age-related macular degeneration, glaucoma, diabetic retinopathy, and so on, are closely associated with and even have a higher incidence of AD and dementia. The eye, as an extension of the central nervous system, therefore has the potential to provide a feasible approach to detecting structural and functional abnormalities of the brain. Numerous new imaging modalities are developed and give novel insights into the detection of several neurodegenerative, vascular, neuropathological, and other ocular abnormalities of AD and dementia in scientific research and clinical application. This review provides an overview of the epidemiologic associations between eye disorders and AD or dementia and summarizes the recent advances in ocular examinations and techniques employed for the detection of AD and dementia. With more brain-and-eye interconnections being identified, the eye is becoming a noninvasive and easily accessible window for the early diagnosis and prevention of AD and dementia.

Dose-related effects of early-life intake of sn-2 palmitate, a specific positionally distributed human milk fatty acid, on the composition and metabolism of the intestinal microbiota

sn2 Palmitate in human milk plays an important role in the physiological health of infants by reducing mineral loss, improving stool hardness, and relieving constipation. Also, sn-2 palmitate modulates intestinal microbiota. However, it remains unclear whether the effects of sn-2 palmitate on infant gut microbiota are dose-dependent. In this study, we investigated the effects of low, medium, and high doses (600, 1,800, and 5,400 mg/kg body weight, respectively) of sn-2 palmitate on the structure, composition, and metabolic function of intestinal microbes in mice. Our results showed that high doses of sn-2 palmitate significantly modulated α- and β-diversity of the intestinal microbiota. The relative abundance of Lachnospiraceae_NK4A136_group decreased with increasing doses of sn-2 palmitate. In contrast, the abundances of Bacteroidetes phylum, Bacteroides, uncultured_Lachnospiraceae, and uncultured_Muribaculaceae were positively correlated with sn-2 palmitate doses. The number of genes predicted encoding autophagy-yeast, phospholipase D signaling pathway, and pentose and glucuronate interconversion metabolic functions of intestinal microbiota increased with increasing doses of sn-2 palmitate. In addition, low and medium doses of sn-2 palmitate significantly upregulated the arginine and proline metabolic pathways, and high doses of sn-2 palmitate significantly increased purine metabolism. Our results revealed that the effects of sn-2 palmitate intake early in life on the composition and metabolism of the intestinal microbiota of mice showed dose-related differences. The study is expected to provide a scientific basis for the development of infant formulas.

Risk factors for portal vein system thrombosis after partial splenic embolisation in cirrhotic patients with hypersplenism

AIM

To determine risk factors for portal venous system thrombosis (PVST) after partial splenic artery embolisation (PSAE) in cirrhotic patients with hypersplenism.

MATERIALS AND METHODS

Between March 2014 and February 2022, 428 cirrhotic patients with hypersplenism underwent partial splenic artery embolisation and from these patients 208 were enrolled and 220 were excluded. Medical records of enrolled patients were collected. Computed tomography (CT) images were reviewed by two blinded, independent radiologists. Statistical analyses were performed by using SPSS.

RESULTS

Progressive PVST was observed in 18.75% (39/208) of cirrhotic patients after PSAE. No significant differences in peripheral blood counts, liver function biomarkers, and renal function were observed between the patients with progressive PVST and the patients without progressive PVST. The imaging data showed significant differences in PVST, the diameters of the portal, splenic, and superior mesenteric veins between the progressive PVST group and non-progressive PVST group. Univariate and multivariate analysis demonstrated portal vein thrombosis, spleen infarction percentage, and the diameter of the splenic vein were independent risk factors for progressive PVST. Seventeen of 173 (9.83%) patients showed new PVST; the growth of PVST was observed in 62.86% (22/35) of the patients with pre-existing PVST. Spleen infarction percentage and the diameter of the splenic vein were independent risk factors for new PVST after PSAE.

CONCLUSION

The present study demonstrated portal vein thrombosis, spleen infarction percentage, and the diameter of the splenic vein were independent risk factors for PVST after PSAE in cirrhotic patients with hypersplenism.

AMGDTI: drug-target interaction prediction based on adaptive meta-graph learning in heterogeneous network

Prediction of drug-target interactions (DTIs) is essential in medicine field, since it benefits the identification of molecular structures potentially interacting with drugs and facilitates the discovery and reposition of drugs. Recently, much attention has been attracted to network representation learning to learn rich information from heterogeneous data. Although network representation learning algorithms have achieved success in predicting DTI, several manually designed meta-graphs limit the capability of extracting complex semantic information. To address the problem, we introduce an adaptive meta-graph-based method, termed AMGDTI, for DTI prediction. In the proposed AMGDTI, the semantic information is automatically aggregated from a heterogeneous network by training an adaptive meta-graph, thereby achieving efficient information integration without requiring domain knowledge. The effectiveness of the proposed AMGDTI is verified on two benchmark datasets. Experimental results demonstrate that the AMGDTI method overall outperforms eight state-of-the-art methods in predicting DTI and achieves the accurate identification of novel DTIs. It is also verified that the adaptive meta-graph exhibits flexibility and effectively captures complex fine-grained semantic information, enabling the learning of intricate heterogeneous network topology and the inference of potential drug-target relationship.

An Integrated Method Based on Wasserstein Distance and Graph for Cancer Subtype Discovery

Due to the complexity of cancer pathogenesis at different omics levels, it is necessary to find a comprehensive method to accurately distinguish and find cancer subtypes for cancer treatment. In this paper, we proposed a new cancer multi-omics subtype identification method, which is based on variational autoencoder measured by Wasserstein distance and graph autoencoder (WVGMO). This method depends on two foremost models. The first model is a variational autoencoder measured by Wasserstein distance (WVAE), which is used to extract potential spatial information of each omic data type. The second model is the graph autoencoder (GAE) with the second-order proximity. It has the capability to retain the topological structure information and feature information of the multi-omics data. And then, the identification of cancer subtypes via k-means clustering. Extensive experiments were conducted on seven different cancers based on four omics data from TCGA. The results show that WVGMO provides equivalent or even better results than the most of advanced synthesis methods.

An End-to-End Deep Hybrid Autoencoder Based Method for Single-Cell RNA-Seq Data Analysis

Single-cell RNA sequencing technology provides powerful support for researchers to understand the complex mechanisms of cells at the single-cell level. Due to the high sparsity, technical noise, and computational complexity of single-cell transcriptome data, the existing data analysis methods are unable to effectively extract the fine-grained characteristics of scRNA-seq data, resulting in inaccurately analyze the heterogeneity of the individual cell from a great quantity of cell mixtures. To address these shortcomings, we proposed an end-to-end analysis method called dhaSCA, which integrates the Graph convolutional neural network (GCN) feature learning and downstream tasks such as classification and imputation into a unified deep learning manner. dhaSCA uses hybrid GCN-MLP deep autoencoder and to capture structural information between cells, and learn the low dimensional cell representation. It also introduces downstream tasks as constraints to guide the model to learn more accurate cell features. We conducted various experiments to evaluate the performance of dhaSCA based on eight real RNA-Seq datasets, including classification, imputation, clustering, and visualization. The results show that dhaSCA outperforms other state-of-the-art methods in these downstream tasks. Therefore, dhaSCA is able to obtain a richer representation of cells, and provides strong support for efficient analysis of single-cell data.

[Orodental phenotype and genotype findings in 8 Chinese children with hypophosphatasia]

Objective: To analyze the oral phenotype and gene variation of children with hypophosphatasia (HPP), and explore the genotype-phenotype correlations. Methods: Eight children diagnosed with HPP from January 2008 to January 2023 in Children's Hospital,Zhejiang University School of Medicine were recruited in this study. The pathogenic genes of 5 of them were sequentially analyzed and all of their oral manifestations, laboratory tests and genetic variation types were retrospectively analyzed. Results: A total of 8 children were recruited in the study, 3 males and 5 females, aged from 20 months to 104 months, whose main complaints were premature deciduous tooth loss. Among them, 3 children were diagnosed with odonto HPP, and the other 5 children were diagnosed with childhood HPP, including 2 children was odonto HPP at the first diagnosis and modified as childhood HPP at the age of 5. The age range of first deciduous tooth loss is 9 to 18 months, and the age range of diagnosis is 20 to 104 months. The patients of odonto HPP only showed premature loss of deciduous anterior tooth, while the patients with childhood HPP also showed premature loss of multiple deciduous molars. Panoramic radiographic film revealed enlarged pulp chambers and radicular canals in some primary and permanent teeth. The enamel hypoplasia, hypoplastic short roots, and alveolar resorption of deciduous molar were observed in some cases. The serum alkaline phosphatase (ALP) (30-107 U/L) levels of all the patients were lower than that in the normal children of same age and gender, and the ALP value of the 1-3 years old girls with childhood HPP (30-33 U/L) was lower than that of the three children with odonto HPP (61-107 U/L), but there was no significant difference in statistical analysis. There were 8 variation sites of ALP liver/bone/kidney (ALPL) gene detected in 5 children and their families, all of which were missense variation, including the new variants in the mutations of c.1334C>G(p.Ser445Cys) and c.1259G>T(p.Gly420Val) that were not reported in the literature. One case was autosomal dominant inheritance and other 4 cases were complex heterozygous variation with autosomal recessive inheritance. Conclusions: Pediatric stomatologists are often the first doctors to detect childhood and odonto HPP. Diagnosis of mild HPP is often delayed. The severity of HPP is related to serum ALP level and ALPL gene mutation sites.

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

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

Temporal Structures in Positron Spectra and Charge-Sign Effects in Galactic Cosmic Rays

We present the precision measurements of 11 years of daily cosmic positron fluxes in the rigidity range from 1.00 to 41.9 GV based on 3.4×10^{6} positrons collected with the Alpha Magnetic Spectrometer (AMS) aboard the International Space Station. The positron fluxes show distinctly different time variations from the electron fluxes at short and long timescales. A hysteresis between the electron fluxes and the positron fluxes is observed with a significance greater than 5σ at rigidities below 8.5 GV. On the contrary, the positron fluxes and the proton fluxes show similar time variation. Remarkably, we found that positron fluxes are modulated more than proton fluxes with a significance greater than 5σ for rigidities below 7 GV. These continuous daily positron fluxes, together with AMS daily electron, proton, and helium fluxes over an 11-year solar cycle, provide unique input to the understanding of both the charge-sign and mass dependencies of cosmic rays in the heliosphere.

FFMAVP: a new classifier based on feature fusion and multitask learning for identifying antiviral peptides and their subclasses

Antiviral peptides (AVPs) are widely found in animals and plants, with high specificity and strong sensitivity to drug-resistant viruses. However, due to the great heterogeneity of different viruses, most of the AVPs have specific antiviral activities. Therefore, it is necessary to identify the specific activities of AVPs on virus types. Most existing studies only identify AVPs, with only a few studies identifying subclasses by training multiple binary classifiers. We develop a two-stage prediction tool named FFMAVP that can simultaneously predict AVPs and their subclasses. In the first stage, we identify whether a peptide is AVP or not. In the second stage, we predict the six virus families and eight species specifically targeted by AVPs based on two multiclass tasks. Specifically, the feature extraction module in the two-stage task of FFMAVP adopts the same neural network structure, in which one branch extracts features based on amino acid feature descriptors and the other branch extracts sequence features. Then, the two types of features are fused for the following task. Considering the correlation between the two tasks of the second stage, a multitask learning model is constructed to improve the effectiveness of the two multiclass tasks. In addition, to improve the effectiveness of the second stage, the network parameters trained through the first-stage data are used to initialize the network parameters in the second stage. As a demonstration, the cross-validation results, independent test results and visualization results show that FFMAVP achieves great advantages in both stages.

PACVP: Prediction of Anti-Coronavirus Peptides Using a Stacking Learning Strategy With Effective Feature Representation

Due to the global outbreak of COVID-19 and its variants, antiviral peptides with anti-coronavirus activity (ACVPs) represent a promising new drug candidate for the treatment of coronavirus infection. At present, several computational tools have been developed to identify ACVPs, but the overall prediction performance is still not enough to meet the actual therapeutic application. In this study, we constructed an efficient and reliable prediction model PACVP (Prediction of Anti-CoronaVirus Peptides) for identifying ACVPs based on effective feature representation and a two-layer stacking learning framework. In the first layer, we use nine feature encoding methods with different feature representation angles to characterize the rich sequence information and fuse them into a feature matrix. Secondly, data normalization and unbalanced data processing are carried out. Next, 12 baseline models are constructed by combining three feature selection methods and four machine learning classification algorithms. In the second layer, we input the optimal probability features into the logistic regression algorithm (LR) to train the final model PACVP. The experiments show that PACVP achieves favorable prediction performance on independent test dataset, with ACC of 0.9208 and AUC of 0.9465. We hope that PACVP will become a useful method for identifying, annotating and characterizing novel ACVPs.

Sparse and Hierarchical Transformer for Survival Analysis on Whole Slide Images

The Transformer-based methods provide a good opportunity for modeling the global context of gigapixel whole slide image (WSI), however, there are still two main problems in applying Transformer to WSI-based survival analysis task. First, the training data for survival analysis is limited, which makes the model prone to overfitting. This problem is even worse for Transformer-based models which require large-scale data to train. Second, WSI is of extremely high resolution (up to 150,000 x 150,000 pixels) and is typically organized as a multi-resolution pyramid. Vanilla Transformer cannot model the hierarchical structure of WSI (such as patch cluster-level relationships), which makes it incapable of learning hierarchical WSI representation. To address these problems, in this paper, we propose a novel Sparse and Hierarchical Transformer (SH-Transformer) for survival analysis. Specifically, we introduce sparse self-attention to alleviate the overfitting problem, and propose a hierarchical Transformer structure to learn the hierarchical WSI representation. Experimental results based on three WSI datasets show that the proposed framework outperforms the state-of-the-art methods.

CapsNetYY1: identifying YY1-mediated chromatin loops based on a capsule network architecture

BACKGROUND

Previous studies have identified that chromosome structure plays a very important role in gene control. The transcription factor Yin Yang 1 (YY1), a multifunctional DNA binding protein, could form a dimer to mediate chromatin loops and active enhancer-promoter interactions. The deletion of YY1 or point mutations at the YY1 binding sites significantly inhibit the enhancer-promoter interactions and affect gene expression. To date, only a few computational methods are available for identifying YY1-mediated chromatin loops.

RESULTS

We proposed a novel model named CapsNetYY1, which was based on capsule network architecture to identify whether a pair of YY1 motifs can form a chromatin loop. Firstly, we encode the DNA sequence using one-hot encoding method. Secondly, multi-scale convolution layer is used to extract local features of the sequence, and bidirectional gated recurrent unit is used to learn the features across time steps. Finally, capsule networks (convolution capsule layer and digital capsule layer) used to extract higher level features and recognize YY1-mediated chromatin loops. Compared with DeepYY1, the only prediction for YY1-mediated chromatin loops, our model CapsNetYY1 achieved the better performance on the independent datasets (AUC [Formula: see text]).

CONCLUSION

The results indicate that CapsNetYY1 is an excellent method for identifying YY1-mediated chromatin loops. We believe that the CapsNetYY1 method will be used for predictive classification of other DNA sequences.

scSemiAAE: a semi-supervised clustering model for single-cell RNA-seq data

BACKGROUND

Single-cell RNA sequencing (scRNA-seq) strives to capture cellular diversity with higher resolution than bulk RNA sequencing. Clustering analysis is critical to transcriptome research as it allows for further identification and discovery of new cell types. Unsupervised clustering cannot integrate prior knowledge where relevant information is widely available. Purely unsupervised clustering algorithms may not yield biologically interpretable clusters when confronted with the high dimensionality of scRNA-seq data and frequent dropout events, which makes identification of cell types more challenging.

RESULTS

We propose scSemiAAE, a semi-supervised clustering model for scRNA sequence analysis using deep generative neural networks. Specifically, scSemiAAE carefully designs a ZINB adversarial autoencoder-based architecture that inherently integrates adversarial training and semi-supervised modules in the latent space. In a series of experiments on scRNA-seq datasets spanning thousands to tens of thousands of cells, scSemiAAE can significantly improve clustering performance compared to dozens of unsupervised and semi-supervised algorithms, promoting clustering and interpretability of downstream analyses.

CONCLUSION

scSemiAAE is a Python-based algorithm implemented on the VSCode platform that provides efficient visualization, clustering, and cell type assignment for scRNA-seq data. The tool is available from https://github.com/WHang98/scSemiAAE .

Properties of Cosmic-Ray Sulfur and Determination of the Composition of Primary Cosmic-Ray Carbon, Neon, Magnesium, and Sulfur: Ten-Year Results from the Alpha Magnetic Spectrometer

We report the properties of primary cosmic-ray sulfur (S) in the rigidity range 2.15 GV to 3.0 TV based on 0.38×10^{6} sulfur nuclei collected by the Alpha Magnetic Spectrometer experiment (AMS). We observed that above 90 GV the rigidity dependence of the S flux is identical to the rigidity dependence of Ne-Mg-Si fluxes, which is different from the rigidity dependence of the He-C-O-Fe fluxes. We found that, similar to N, Na, and Al cosmic rays, over the entire rigidity range, the traditional primary cosmic rays S, Ne, Mg, and C all have sizeable secondary components, and the S, Ne, and Mg fluxes are well described by the weighted sum of the primary silicon flux and the secondary fluorine flux, and the C flux is well described by the weighted sum of the primary oxygen flux and the secondary boron flux. The primary and secondary contributions of the traditional primary cosmic-ray fluxes of C, Ne, Mg, and S (even Z elements) are distinctly different from the primary and secondary contributions of the N, Na, and Al (odd Z elements) fluxes. The abundance ratio at the source for S/Si is 0.167±0.006, for Ne/Si is 0.833±0.025, for Mg/Si is 0.994±0.029, and for C/O is 0.836±0.025. These values are determined independent of cosmic-ray propagation.

Temporal Structures in Electron Spectra and Charge Sign Effects in Galactic Cosmic Rays

We present the precision measurements of 11 years of daily cosmic electron fluxes in the rigidity interval from 1.00 to 41.9 GV based on 2.0×10^{8} electrons collected with the Alpha Magnetic Spectrometer (AMS) aboard the International Space Station. The electron fluxes exhibit variations on multiple timescales. Recurrent electron flux variations with periods of 27 days, 13.5 days, and 9 days are observed. We find that the electron fluxes show distinctly different time variations from the proton fluxes. Remarkably, a hysteresis between the electron flux and the proton flux is observed with a significance of greater than 6σ at rigidities below 8.5 GV. Furthermore, significant structures in the electron-proton hysteresis are observed corresponding to sharp structures in both fluxes. This continuous daily electron data provide unique input to the understanding of the charge sign dependence of cosmic rays over an 11-year solar cycle.

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

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

scTSSR-D: Gene Expression Recovery by Two-side Self-representation and Dropout Information for scRNA-seq Data

Background:

Single-cell RNA sequencing is an advanced technology that makes it possible to unravel cellular heterogeneity and conduct single-cell analysis of gene expression. However, owing to technical defects, many dropout events occur during sequencing, bringing about adverse effects on downstream analysis.

Methods:

To solve the dropout events existing in single-cell RNA sequencing, we propose an imputation method scTSSR-D, which recovers gene expression by two-side self-representation and dropout information. scTSSR-D is the first global method that combines a partial imputation method to impute dropout values. In other words, we make full use of genes, cells, and dropout information when recovering the gene expression.

objective:

scTSSR-D is the first global method that combines a partial imputation method to impute dropout values. In other words, we make full use of genes, cells, and dropout information when recovering the gene expression.

Results:

The results show scTSSR-D outperforms other existing methods in the following experiments: capturing the Gini coefficient and gene-to-gene correlations observed in single-molecule RNA fluorescence in situ hybridization, down-sampling experiments, differential expression analysis, and the accuracy of cell clustering.

Conclusion:

scTSSR-D is a more stable and reliable method to recover gene expression. Meanwhile, our method improves even more dramatically on large datasets compared to the result of existing methods.

result:

The result shows that scTSSR-D outperforms other existing methods in the following experiments: capturing the Gini coefficient and gene-to-gene correlations observed in single-molecule RNA fluorescence in situ hybridization (FISH), down-sampling experiments, DE analysis, and the accuracy of cell clustering.

other:

We make full use of genes, cells, and dropout information when recovering the gene expression.

[Association of extranodal extension and lymph node ratio with radioactive iodine-refractory papillary thyroid cancer]

Objective: To investigate the related factors of radioiodine-refractory thyroid cancer (RAIR-DTC) and the increase of cumulative iodine treatment dose. Methods: The data of patients with papillary thyroid cancer who underwent surgery and iodine treatment for the first time in the Affiliated Cancer Hospital of Zhengzhou University from January 2015 to December 2017 were retrospectively analyzed. The related factors of RAIR-DTC and the increase of cumulative iodine treatment dose were explored. Results: A total of 650 patients were enrolled, including 217 males (33.4%) and 433 females (66.6%), aged 45 (34, 53) years. There were 123 patients (18.9%) over 55 years old, 171 patients (26.3%) with extranodal extension and 18 patients (2.8%) with distant metastasis. The median lymph node ratio was 0.22 (0.11, 0.33). Twenty patients (3.1%) had an accumulated iodine treatment dose>400 mCi and 19 patients (2.9%) had RAIR-DTC. Multivariate logistic regression analysis showed that extranodal extension (OR=19.833, 95%CI: 6.057-73.325, P<0.001) was related factors for the increase of cumulative iodine treatment dose. Age>55 years old (OR=3.322, 95%CI: 1.136-9.466, P=0.024), distant metastasis (OR=10.059, 95%CI: 2.508-38.888, P<0.001), extranodal extension (OR=5.278, 95%CI: 1.707-19.813, P=0.006) and lymph node ratio (OR=34.724, 95%CI: 2.749-384.575, P=0.004) were related factors for RAIR-DTC. Conclusions: Extranodal extension and lymph node ratio are related factors for RAIR-DTC. In clinical practice, more attention should be paid to the influence of different lymph node metastasis characteristics on the occurrence of RAIR-DTC and the cumulative therapeutic dose of iodine.

Deep learning joint models for extracting entities and relations in biomedical: a survey and comparison

The rapid development of biomedicine has produced a large number of biomedical written materials. These unstructured text data create serious challenges for biomedical researchers to find information. Biomedical named entity recognition (BioNER) and biomedical relation extraction (BioRE) are the two most fundamental tasks of biomedical text mining. Accurately and efficiently identifying entities and extracting relations have become very important. Methods that perform two tasks separately are called pipeline models, and they have shortcomings such as insufficient interaction, low extraction quality and easy redundancy. To overcome the above shortcomings, many deep learning-based joint name entity recognition and relation extraction models have been proposed, and they have achieved advanced performance. This paper comprehensively summarize deep learning models for joint name entity recognition and relation extraction for biomedicine. The joint BioNER and BioRE models are discussed in the light of the challenges existing in the BioNER and BioRE tasks. Five joint BioNER and BioRE models and one pipeline model are selected for comparative experiments on four biomedical public datasets, and the experimental results are analyzed. Finally, we discuss the opportunities for future development of deep learning-based joint BioNER and BioRE models.

NeuroPred-CLQ: incorporating deep temporal convolutional networks and multi-head attention mechanism to predict neuropeptides

Neuropeptides (NPs) are a particular class of informative substances in the immune system and physiological regulation. They play a crucial role in regulating physiological functions in various biological growth and developmental stages. In addition, NPs are crucial for developing new drugs for the treatment of neurological diseases. With the development of molecular biology techniques, some data-driven tools have emerged to predict NPs. However, it is necessary to improve the predictive performance of these tools for NPs. In this study, we developed a deep learning model (NeuroPred-CLQ) based on the temporal convolutional network (TCN) and multi-head attention mechanism to identify NPs effectively and translate the internal relationships of peptide sequences into numerical features by the Word2vec algorithm. The experimental results show that NeuroPred-CLQ learns data information effectively, achieving 93.6% accuracy and 98.8% AUC on the independent test set. The model has better performance in identifying NPs than the state-of-the-art predictors. Visualization of features using t-distribution random neighbor embedding shows that the NeuroPred-CLQ can clearly distinguish the positive NPs from the negative ones. We believe the NeuroPred-CLQ can facilitate drug development and clinical trial studies to treat neurological disorders.

Prediction of circRNA-Disease Associations Based on the Combination of Multi-Head Graph Attention Network and Graph Convolutional Network

Circular RNAs (circRNAs) are covalently closed single-stranded RNA molecules, which have many biological functions. Previous experiments have shown that circRNAs are involved in numerous biological processes, especially regulatory functions. It has also been found that circRNAs are associated with complex diseases of human beings. Therefore, predicting the associations of circRNA with disease (called circRNA-disease associations) is useful for disease prevention, diagnosis and treatment. In this work, we propose a novel computational approach called GGCDA based on the Graph Attention Network (GAT) and Graph Convolutional Network (GCN) to predict circRNA-disease associations. Firstly, GGCDA combines circRNA sequence similarity, disease semantic similarity and corresponding Gaussian interaction profile kernel similarity, and then a random walk with restart algorithm (RWR) is used to obtain the preliminary features of circRNA and disease. Secondly, a heterogeneous graph is constructed from the known circRNA-disease association network and the calculated similarity of circRNAs and diseases. Thirdly, the multi-head Graph Attention Network (GAT) is adopted to obtain different weights of circRNA and disease features, and then GCN is employed to aggregate the features of adjacent nodes in the network and the features of the nodes themselves, so as to obtain multi-view circRNA and disease features. Finally, we combined a multi-layer fully connected neural network to predict the associations of circRNAs with diseases. In comparison with state-of-the-art methods, GGCDA can achieve AUC values of 0.9625 and 0.9485 under the results of fivefold cross-validation on two datasets, and AUC of 0.8227 on the independent test set. Case studies further demonstrate that our approach is promising for discovering potential circRNA-disease associations.

A Semi-Supervised Learning Method for MiRNA-Disease Association Prediction Based on Variational Autoencoder

MicroRNAs (miRNAs) are a class of non-coding RNAs that play critical role in many biological processes, such as cell growth, development, differentiation and aging. Increasing studies have revealed that miRNAs are closely involved in many human diseases. Therefore, the prediction of miRNA-disease associations is of great significance to the study of the pathogenesis, diagnosis and intervention of human disease. However, biological experimentally methods are usually expensive in time and money, while computational methods can provide an efficient way to infer the underlying disease-related miRNAs. In this study, we propose a novel method to predict potential miRNA-disease associations, called SVAEMDA. Our method mainly consider the miRNA-disease association prediction as semi-supervised learning problem. SVAEMDA integrates disease semantic similarity, miRNA functional similarity and respective Gaussian interaction profile (GIP) similarities. The integrated similarities are used to learn the representations of diseases and miRNAs. SVAEMDA trains a variational autoencoder based predictor by using known miRNA-disease associations, with the form of concatenated dense vectors. Reconstruction probability of the predictor is used to measure the correlation of the miRNA-disease pairs. Experimental results show that SVAEMDA outperforms other stat-of-the-art methods. AUC values of SVAEMDA of global leave-one-out cross validation (LOOCV) and 5-fold cross validation (5-fold CV) are 0.9464 and 0.9428 respectively. In addition, case studies of three common human diseases indicate that SVAEMDA obtains 100 percent of the top 50 predicted candidates in the benchmark databases. Therefore, SVAEMDA can efficiently and accurately predict the potential associations between diseases and miRNAs.

[Development and validation of a prognostic model based on SEER data for patients with esophageal carcinoma after esophagectomy]

OBJECTIVE

To develop a nomogram to predict the long-term survival of patients with esophageal cancer following esophagectomy.

METHODS

We collected the data of 7215 patients with esophageal carcinoma from the Surveillance, Epidemiology, and End Results (SEER) database during the period from 2004 and 2016. Of these patients, 5052 were allocated to the training cohort and the remaining 2163 patients to the internal validation cohort using bootstrap resampling, with another 435 patients treated in the Department of Cardiothoracic Surgery of Jinling Hospital between 2014 and 2016 serving as the external validation cohort.

RESULTS

In the overall cohort, the 1-, 3-, and 5-year cancer-specific mortality rates were 14.6%, 35.7% and 41.6%, respectively. Age (≥80 years vs < 50 years, P < 0.001), gender (male vs female, P < 0.001), tumor site (lower vs middle segment, P=0.013), histology (EAC vs ESCC, P=0.012), tumor grade (poorly vs well differentiated, P < 0.001), TNM stage (Ⅳ vs Ⅰ, P < 0.001), tumor size (> 50 mm vs 0-20 mm, P < 0.001), chemotherapy (yes vs no, P < 0.001), and LNR (> 0.25 vs 0, P < 0.001) were identified as independent risk factors affecting long-term survival of the patients. The nomograms established based on the model for predicting the survival probability of the patients at 1, 3 and 5 years after operation showed a C-index of 0.726 (95% CI: 0.714-0.738) for predicting the overall survival (OS) and of 0.735 (95% CI: 0.727-0.743) for cancer-specific survival (CSS) in the training cohort. In the internal validation cohort, the C-index of the nomograms was 0.752 (95% CI: 0.738-0.76) for OS and 0.804 (95% CI: 0.790-0.817) for CSS, as compared with 0.749 (95% CI: 0.736-0.767) and 0.788 (95%CI: 0.751-0.808), respectively, in the external validation cohort. The nomograms also showed a higher sensitivity than the TNM staging system for predicting long-term prognosis.

CONCLUSION

This prognostic model has a high prediction efficiency and can help to identify the high-risk patients with esophageal carcinoma after surgery and serve as a supplement for the current TNM staging system.

Properties of Daily Helium Fluxes

We present the precision measurement of 2824 daily helium fluxes in cosmic rays from May 20, 2011 to October 29, 2019 in the rigidity interval from 1.71 to 100 GV based on 7.6×10^{8} helium nuclei collected with the Alpha Magnetic Spectrometer (AMS) aboard the International Space Station. The helium flux and the helium to proton flux ratio exhibit variations on multiple timescales. In nearly all the time intervals from 2014 to 2018, we observed recurrent helium flux variations with a period of 27 days. Shorter periods of 9 days and 13.5 days are observed in 2016. The strength of all three periodicities changes with time and rigidity. In the entire time period, we found that below ∼7  GV the helium flux exhibits larger time variations than the proton flux, and above ∼7  GV the helium to proton flux ratio is time independent. Remarkably, below 2.4 GV a hysteresis between the helium to proton flux ratio and the helium flux was observed at greater than the 7σ level. This shows that at low rigidity the modulation of the helium to proton flux ratio is different before and after the solar maximum in 2014.

MDSCMF: Matrix Decomposition and Similarity-Constrained Matrix Factorization for miRNA–Disease Association Prediction

MicroRNAs (miRNAs) are small non-coding RNAs that are related to a number of complicated biological processes, and numerous studies have demonstrated that miRNAs are closely associated with many human diseases. In this study, we present a matrix decomposition and similarity-constrained matrix factorization (MDSCMF) to predict potential miRNA–disease associations. First of all, we utilized a matrix decomposition (MD) algorithm to get rid of outliers from the miRNA–disease association matrix. Then, miRNA similarity was determined by utilizing similarity kernel fusion (SKF) to integrate miRNA function similarity and Gaussian interaction profile (GIP) kernel similarity, and disease similarity was determined by utilizing SKF to integrate disease semantic similarity and GIP kernel similarity. Furthermore, we added L₂ regularization terms and similarity constraint terms to non-negative matrix factorization to form a similarity-constrained matrix factorization (SCMF) algorithm, which was applied to make prediction. MDSCMF achieved AUC values of 0.9488, 0.9540, and 0.8672 based on fivefold cross-validation (5-CV), global leave-one-out cross-validation (global LOOCV), and local leave-one-out cross-validation (local LOOCV), respectively. Case studies on three common human diseases were also implemented to demonstrate the prediction ability of MDSCMF. All experimental results confirmed that MDSCMF was effective in predicting underlying associations between miRNAs and diseases.

Nuclei-Guided Network for Breast Cancer Grading in HE-Stained Pathological Images

Breast cancer grading methods based on hematoxylin-eosin (HE) stained pathological images can be summarized into two categories. The first category is to directly extract the pathological image features for breast cancer grading. However, unlike the coarse-grained problem of breast cancer classification, breast cancer grading is a fine-grained classification problem, so general methods cannot achieve satisfactory results. The second category is to apply the three evaluation criteria of the Nottingham Grading System (NGS) separately, and then integrate the results of the three criteria to obtain the final grading result. However, NGS is only a semiquantitative evaluation method, and there may be far more image features related to breast cancer grading. In this paper, we proposed a Nuclei-Guided Network (NGNet) for breast invasive ductal carcinoma (IDC) grading in pathological images. The proposed nuclei-guided attention module plays the role of nucleus attention, so as to learn more nuclei-related feature representations for breast IDC grading. In addition, the proposed nuclei-guided fusion module in the fusion process of different branches can further enable the network to focus on learning nuclei-related features. Overall, under the guidance of nuclei-related features, the entire NGNet can learn more fine-grained features for breast IDC grading. The experimental results show that the performance of the proposed method is better than that of state-of-the-art method. In addition, we released a well-labeled dataset with 3644 pathological images for breast IDC grading. This dataset is currently the largest publicly available breast IDC grading dataset and can serve as a benchmark to facilitate a broader study of breast IDC grading.

A Robust Algorithm Based on Link Label Propagation for Identifying Functional Modules From Protein-Protein Interaction Networks

Identifying functional modules in protein-protein interaction (PPI) networks elucidates cellular organization and mechanism. Various methods have been proposed to identify the functional modules in PPI networks, but most of these methods do not consider the noisy links in PPI networks. They achieve a competitive performance on the PPI networks without noisy links, but the performance of these methods considerably deteriorates in the noisy PPI networks. Furthermore, the noisy links are inevitable in the PPI networks. In this paper, we propose a novel link-driven label propagation algorithm (LLPA) to identify functional modules in PPI networks. The LLPA first find link clusters in PPI networks, and then the functional modules are identified from the link clusters. Two strategies aimed to ensure the robustness of LLPA are proposed. One strategy involves the proposed LLPA updating the link labels in accordance with the designed weight of the link, which can reduce the incidence of noisy links. The other strategy involves the filtration of some noisy labels from the link clusters to further reduce the influence of noisy links. The performance evaluation on three real PPI networks shows that LLPA outperforms other eight state-of-the-art detection algorithms in terms of accuracy and robustness.

RNAseq reveals extensive metabolic disruptions in the sensitive SF-295 cell line treated with schweinfurthins

The schweinfurthin family of natural compounds exhibit a unique and potent differential cytotoxicity against a number of cancer cell lines and may reduce tumor growth in vivo. In some cell lines, such as SF-295 glioma cells, schweinfurthins elicit cytotoxicity at nanomolar concentrations. However, other cell lines, like A549 lung cancer cells, are resistant to schweinfurthin treatment up to micromolar concentrations. At this time, the precise mechanism of action and target for these compounds is unknown. Here, we employ RNA sequencing of cells treated with 50 nM schweinfurthin analog TTI-3066 for 6 and 24 h to elucidate potential mechanisms and pathways which may contribute to schweinfurthin sensitivity and resistance. The data was analyzed via an interaction model to observe differential behaviors between sensitive SF-295 and resistant A549 cell lines. We show that metabolic and stress-response pathways were differentially regulated in the sensitive SF-295 cell line as compared with the resistant A549 cell line. In contrast, A549 cell had significant alterations in response genes involved in translation and protein metabolism. Overall, there was a significant interaction effect for translational proteins, RNA metabolism, protein metabolism, and metabolic genes. Members of the Hedgehog pathway were differentially regulated in the resistant A549 cell line at both early and late time points, suggesting a potential mechanism of resistance. Indeed, when cotreated with the Smoothened inhibitor cyclopamine, A549 cells became more sensitive to schweinfurthin treatment. This study therefore identifies a key interplay with the Hedgehog pathway that modulates sensitivity to the schweinfurthin class of compounds.

Periodicities in the Daily Proton Fluxes from 2011 to 2019 Measured by the Alpha Magnetic Spectrometer on the International Space Station from 1 to 100 GV

We present the precision measurement of the daily proton fluxes in cosmic rays from May 20, 2011 to October 29, 2019 (a total of 2824 days or 114 Bartels rotations) in the rigidity interval from 1 to 100 GV based on 5.5×10^{9} protons collected with the Alpha Magnetic Spectrometer aboard the International Space Station. The proton fluxes exhibit variations on multiple timescales. From 2014 to 2018, we observed recurrent flux variations with a period of 27 days. Shorter periods of 9 days and 13.5 days are observed in 2016. The strength of all three periodicities changes with time and rigidity. The rigidity dependence of the 27-day periodicity is different from the rigidity dependences of 9-day and 13.5-day periods. Unexpectedly, the strength of 9-day and 13.5-day periodicities increases with increasing rigidities up to ∼10  GV and ∼20  GV, respectively. Then the strength of the periodicities decreases with increasing rigidity up to 100 GV.

Erratum: Properties of a New Group of Cosmic Nuclei: Results from the Alpha Magnetic Spectrometer on Sodium, Aluminum, and Nitrogen [Phys. Rev. Lett. 127, 021101 (2021)]

This corrects the article DOI: 10.1103/PhysRevLett.127.021101.