Recipe Recommendation With Hierarchical Graph Attention Network

Recipe recommendation systems play an important role in helping people find recipes that are of their interest and fit their eating habits. Unlike what has been developed for recommending recipes using content-based or collaborative filtering approaches, the relational information among users, recipes, and food items is less explored. In this paper, we leverage the relational information into recipe recommendation and propose a graph learning approach to solve it. In particular, we propose HGAT, a novel hierarchical graph attention network for recipe recommendation. The proposed model can capture user history behavior, recipe content, and relational information through several neural network modules, including type-specific transformation, node-level attention, and relation-level attention. We further introduce a ranking-based objective function to optimize the model. Thorough experiments demonstrate that HGAT outperforms numerous baseline methods.

Integrated Pharmacogenetics Analysis of the Three Fangjis Decoctions for Treating Arrhythmias Based on Molecular Network Patterns

Aim: To explore the diverse target distribution and variable mechanisms of different fangjis prescriptions when treating arrhythmias based on the systems pharmacology.Methods: The active ingredients and their corresponding targets were acquired from the three fangjis [Zhigancao Tang (ZT), Guizhigancao Longgumuli Tang (GLT), and Huanglian E'jiao Tang (HET)] and the arrhythmia-related genes were identified based on comprehensive database screening. Networks were constructed between the fangjis and arrhythmia and used to define arrhythmia modules. Common and differential gene targets were identified within the arrhythmia network modules and the cover rate (CR) matrix was applied to compare the contributions of the fangjis to the network and modules. Comparative pharmacogenetics analyses were then conducted to define the arrhythmia-related signaling pathways regulated by the fangjis prescriptions. Finally, the divergence and convergence points of the arrhythmia pathways were deciphered based on databases and the published literature.Results: A total of 187, 105, and 68 active ingredients and 1,139, 1,195, and 811 corresponding gene targets of the three fangjis were obtained and 102 arrhythmia-related genes were acquired. An arrhythmia network was constructed and subdivided into 4 modules. For the target distribution analysis, 65.4% of genes were regulated by the three fangjis within the arrhythmia network. ZT and GLT were more similar to each other, mainly regulated by module two, whereas HET was divided among all the modules. From the perspective of signal transduction, calcium-related pathways [calcium, cyclic guanosine 3′,5′-monophosphate (cGMP)-PKG, and cyclic adenosine 3′,5′-monophosphate (cAMP)] and endocrine system-related pathways (oxytocin signaling pathway and renin secretion pathways) were associated with all the three fangjis prescriptions. Nevertheless, heterogeneity existed between the biological processes and pathway distribution among the three prescriptions. GLT and HET were particularly inclined toward the conditions involving abnormal hormone secretion, whereas ZT tended toward renin-angiotensin-aldosterone system (RAAS) disorders. However, calcium signaling-related pathways prominently feature in the pharmacological activities of the decoctions. Experimental validation indicated that ZT, GLT, and HET significantly shortened the duration of ventricular arrhythmia (VA) and downregulated the expression of CALM2 and interleukin-6 (IL-6) messenger RNAs (mRNAs); GLT and HET downregulated the expression of CALM1 and NOS3 mRNAs; HET downregulated the expression of CRP mRNA.Conclusion: Comparing the various distributions of the three fangjis, pathways provide evidence with respect to precise applications toward individualized arrhythmia treatments.

Monosomy X in isogenic human iPSC-derived trophoblast model impacts expression modules preserved in human placenta

Mammalian sex chromosomes encode homologous X/Y gene pairs that were retained on the male Y and escape X chromosome inactivation (XCI) in females. Inferred to reflect X/Y-pair dosage sensitivity, monosomy X is a leading cause of miscarriage in humans with near full penetrance. This phenotype is shared with many other mammals but not the mouse, which offers sophisticated genetic tools to generate sex chromosomal aneuploidy but also tolerates its developmental impact. To address this critical gap, we generated X-monosomic human induced pluripotent stem cells (hiPSCs) alongside otherwise isogenic euploid controls from male and female mosaic samples. Phased genomic variants of these hiPSC panels enable systematic investigation of X/Y dosage-sensitive features using in vitro models of human development. Here, we demonstrate the utility of these validated hiPSC lines to test how X/Y-linked gene dosage impacts a widely-used model for the human syncytiotrophoblast. While these isogenic panels trigger a GATA2/3 and TFAP2A/C -driven trophoblast gene circuit irrespective of karyotype, differential expression implicates monosomy X in altered levels of placental genes, and in secretion of placental growth factor (PlGF) and human chorionic gonadotropin (hCG). Remarkably, weighted gene co-expression network modules that significantly reflect these changes are also preserved in first-trimester chorionic villi and term placenta. Our results suggest monosomy X may skew trophoblast cell type composition, and that the pseudoautosomal region likely plays a key role in these changes, which may facilitate prioritization of haploinsufficient drivers of 45,X extra-embryonic phenotypes.

CASP5 and CR1 as potential biomarkers for Kawasaki disease: an Integrated Bioinformatics-Experimental Study

Background Kawasaki disease (KD) is a pediatric inflammatory disorder causes coronary artery complications. The disease overlapping manifestations with a set of symptomatically like diseases such as bacterial and viral infections, juvenile idiopathic arthritis, Henoch-Schönlein purpura, infection of unknown etiology, group-A streptococcal and adenoviral infections, and incomplete KD could lead to misdiagnosis of the disease. Methods In the present study, we applied weighted gene co-expression network analysis (WGCNA) to identify network modules of co-expressed genes in GSE73464 and also, limma package was used to identify the differentially expressed genes (DEGs) in KD expression arrays composed of GSE73464, GSE18606, GSE109351, and GSE68004. By merging the results of WGCNA and limma, we detected hub genes. Then, analyzed the peripheral blood mononuclear cells (PBMCs) of 16 patients and 8 control subjects using Real-Time Polymerase Chain Reaction (RT-PCR) to evaluate the previous results. Results We assessed the diagnostic potency of the screened genes by plotting the area under curve (AUC). We finally identified 2 genes CASP5(Caspase 5) and CR1(Complement C3b/C4b Receptor 1) which were shown to potentially discriminate KD from other similar diseases and also from healthy people. Conclusions The results of RT-PCR and AUC confirmed the diagnostic potentials of two suggested biomarkers for KD.

Dynamic changes in immune gene co-expression networks predict development of type 1 diabetes

Significant progress has been made in elucidating genetic risk factors influencing Type 1 diabetes (T1D); however, features other than genetic variants that initiate and/or accelerate islet autoimmunity that lead to the development of clinical T1D remain largely unknown. We hypothesized that genetic and environmental risk factors can both contribute to T1D through dynamic alterations of molecular interactions in physiologic networks. To test this hypothesis, we utilized longitudinal blood transcriptomic profiles in The Environmental Determinants of Diabetes in the Young (TEDDY) study to generate gene co-expression networks. In network modules that contain immune response genes associated with T1D, we observed highly dynamic differences in module connectivity in the 600 days (~ 2 years) preceding clinical diagnosis of T1D. Our results suggest that gene co-expression is highly plastic and that connectivity differences in T1D-associated immune system genes influence the timing and development of clinical disease.

APPLICATION OF NEURAL NETWORK AUTO ENCODERS OF UNET TYPE FOR INVERSE PHOTOLITOGRAPHY TASKS

The paper discusses the issue of the applicability of neural networks to the problems of designing microelectronics. The integration of neural network modules into the elements of specialized EDA systems can significantly speed up the modeling processes at different stages of design. The application of a multilayer convolutional architecture of a neural network of the UNET type to the problem of direct and inverse computational photolithography is considered. Using this neural network approach, we were able to speed up the computation of a photo mask for a 90nm process technology by two orders of magnitude and achieve simulation accuracy that surpasses standard inverse photolithography (ILT) methods.

Multi-Scale Feature Mapping Network for Hyperspectral Image Super-Resolution

Hyperspectral Image (HSI) can continuously cover tens or even hundreds of spectral segments for each spatial pixel. Limited by the cost and commercialization requirements of remote sensing satellites, HSIs often lose a lot of information due to insufficient image spatial resolution. For the high-dimensional nature of HSIs and the correlation between the spectra, the existing Super-Resolution (SR) methods for HSIs have the problems of excessive parameter amount and insufficient information complementarity between the spectra. This paper proposes a Multi-Scale Feature Mapping Network (MSFMNet) based on the cascaded residual learning to adaptively learn the prior information of HSIs. MSFMNet simplifies each part of the network into a few simple yet effective network modules. To learn the spatial-spectral characteristics among different spectral segments, a multi-scale feature generation and fusion Multi-Scale Feature Mapping Block (MSFMB) based on wavelet transform and spatial attention mechanism is designed in MSFMNet to learn the spectral features between different spectral segments. To effectively improve the multiplexing rate of multi-level spectral features, a Multi-Level Feature Fusion Block (MLFFB) is designed to fuse the multi-level spectral features. In the image reconstruction stage, an optimized sub-pixel convolution module is used for the up-sampling of different spectral segments. Through a large number of verifications on the three general hyperspectral datasets, the superiority of this method compared with the existing hyperspectral SR methods is proved. In subjective and objective experiments, its experimental performance is better than its competitors.

Protein co-expression network-based profiles revealed from laser-microdissected cancerous cells of lung squamous-cell carcinomas

No therapeutic targets have been identified for lung squamous cell cancer (SqCC) which is the second most prevalent lung cancer because its molecular profiles remain unclear. This study aimed to unveil disease-related protein networks by proteomic and bioinformatic assessment of laser-microdissected cancerous cells from seven SqCCs compared with eight representative lung adenocarcinomas. We identified three network modules significant to lung SqCC using weighted gene co-expression network analysis. One module was intrinsically annotated to keratinization and cell proliferation of SqCC, accompanied by hypoxia-induced aerobic glycolysis, in which key regulators were activated (HIF1A, ROCK2, EFNA1-5) and highly suppressed (KMT2D). The other two modules were significant for translational initiation, nonsense-mediated mRNA decay, inhibited cell death, and interestingly, eIF2 signaling, in which key regulators, MYC and MLXIPL, were highly activated. Another key regulator LARP1, the master regulator in cap-dependent translation, was highly suppressed although upregulations were observed for hub proteins including EIF3F and LARP1 targeted ribosomal proteins, among which PS25 is the key ribosomal protein in IRES-dependent translation. Our results suggest an underlying progression mechanism largely caused by switching to the cap-independent, IRES-dependent translation of mRNA subsets encoding oncogenic proteins. Our findings may help to develop therapeutic strategies to improve patient outcomes.

Multi-Scale Guided Attention Network for Crowd Counting

The CNN-based crowd counting method uses image pyramid and dense connection to fuse features to solve the problems of multiscale and information loss. However, these operations lead to information redundancy and confusion between crowd and background information. In this paper, we propose a multi-scale guided attention network (MGANet) to solve the above problems. Specifically, the multilayer features of the network are fused by a top-down approach to obtain multiscale information and context information. The attention mechanism is used to guide the acquired features of each layer in space and channel so that the network pays more attention to the crowd in the image, ignores irrelevant information, and further integrates to obtain the final high-quality density map. Besides, we propose a counting loss function combining SSIM Loss, MAE Loss, and MSE Loss to achieve effective network convergence. We experiment on four major datasets and obtain good results. The effectiveness of the network modules is proved by the corresponding ablation experiments. The source code is available at https://github.com/lpfworld/MGANet.