Abstract Early detection is critical to achieving improved treatment outcomes for child patients with congenital heart diseases (CHDs). Therefore, developing effective CHD techniques using low-cost and non-invasive pediatric electrocardiogram are highly desirable. We propose a deep learning approach detection, CHDdECG, which automatically extracts features from wavelet transformation characteristics, integrates them key human-concept features. Developed on 65,869 cases, CHDdECG achieved...

Person re-identification addresses the problem of matching people across disjoint camera views and extensive efforts have been made to seek either robust feature representation or discriminative metrics. However, most existing approaches focus on learning a fixed distance metric for all instance pairs, while ignoring individuality each person. In this paper, we formulate person as an imbalanced classification learn classifier specifically pedestrian such that model is highly tuned...

Reconstructing a 3D hand from single-view RGB image is challenging due to various configurations and depth ambiguity. To reliably reconstruct monocular image, most state-of-the-art methods heavily rely on annotations at the training stage, but obtaining expensive. alleviate reliance labeled data, we propose S <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> HAND, self-supervised reconstruction network that can jointly estimate pose,...

Abstract DNA N6-methyladenine is an important type of modification that plays roles in multiple biological processes. Despite the recent progress developing 6mA site prediction methods, several challenges remain to be addressed. For example, although hand-crafted features are interpretable, they contain redundant information may bias model training and have a negative impact on trained model. Furthermore, deep learning (DL)-based models can perform feature extraction classification...

The metal–carbon bond plays a pivotal role in the structural stabilities and biological activities of metal-based anticancer drugs. strong M–C_imi is first introduced into sandwich-type POMs [Na_0.7M_5.3(H₂O)₂(imi)₂(Himi)(SbW₉O₃₃)₂]⁶⁻, (M = Ni^II (<bold>1</bold>), Co^II (<bold>2</bold>), imi imidazole).

The existence of peripheral oscillators has been shown, and they are critically important for organizing the metabolism whole body. Here we show that mice deficient in mPer2 markedly increase circulatory levels insulin compared with wild type mice. Insulin secretion was more effectively stimulated by glucose, alloxan, a glucose analogue, induced severe hyperglycemia ‐deficient Hepatic degrading enzyme ( Ide ) displayed an obvious day night rhythm, which impaired mPer2‐deficient mice, leading...

With the rapid development of AI techniques, Computer-aided Diagnosis has attracted much attention and been successfully deployed in many applications health care medical diagnosis. For some specific tasks, learning-based system can compare with or even outperform human experts' performance. The impressive performance owes to excellent expressiveness scalability neural networks, although models' intuition usually cannot be represented explicitly. Interpretability is, however, very important,...

Cadmium (Cd) is a major environmental stressor that induces fetal growth restriction (FGR). Also, changes in gut microbiome diversity-which can be modulated positively by melatonin (Mel) have implications on development and placental functions. Therefore, this study aimed to explore whether the role of Mel counteracting Cd-induced FGR regulating barrier injury, endoplasmic reticulum stress (ERS) mitophagy pregnant mice mediated-in part- via microbiota modulations. Pregnant were...

Image restoration is the task of aiming to obtain a high-quality image from corrupt input image, such as deblurring and deraining. In restoration, it typically necessary maintain complex balance between spatial details contextual information. Although multi-stage network can optimally these competing goals achieve significant performance, this also increases system's complexity. paper, we propose mountain-shaped single-stage design base on simple U-Net architecture, which removes or replaces...

It has been demonstrated that RNA modifications play essential roles in multiple biological processes. Accurate identification of the transcriptome is critical for providing insights into functions and mechanisms. Many tools have developed predicting at single-base resolution, which employ conventional feature engineering methods focus on design selection processes require extensive expertise may introduce redundant information. With rapid development artificial intelligence technologies,...

β-sitosterol (BSS) is a plant-derived natural bioactive compound, its cellular mechanism of anti-inflammatory activity has been proven recently. Little information available regarding the application BSS on ruminants under high grain diet. The objective this study was to evaluate effects dietary supplementation inflammatory response, ruminal fermentation characteristics and composition bacterial community Eight rumen-cannulated Hu sheep (59.7 ± 4.8 kg initial body weight) were randomly...

More than 6000 human diseases have been recorded to be caused by non-synonymous single nucleotide polymorphisms (nsSNPs). Rapid and accurate prediction of pathogenic nsSNPs can improve our understanding the principle design new drugs, which remains an unresolved challenge. In present work, a computational approach, termed MSRes-MutP, is proposed based on ResNet blocks with multi-scale kernel size predict disease-associated nsSNPs. By feeding serial concatenation extracted four types...

The accurate identification of protein-nucleotide binding residues is crucial for protein function annotation and drug discovery. Numerous computational methods have been proposed to predict these residues, achieving remarkable performance. However, due the limited availability high variability nucleotides, predicting diverse nucleotides remains a significant challenge. To address these, we propose NucGMTL, new grouped deep multi-task learning approach designed all observed in BioLiP...

Enhancing rice (Oryza sativa L.) productivity and optimizing water use efficiency (WUE) are critical for advancing sustainable agricultural practices. This study selected six mid-season indica varieties to investigate the impacts of alternate wetting drying irrigation (AWD) conventional (CI) on grain yield, WUE, filling, root traits. A two-year field experiment demonstrated that AWD significantly enhanced yield WUE. Flag leaf photosynthetic rate characteristics, including weight, length,...

Recently, Graph Neural Network based Force Field (GNNFF) models are widely used in Molecular Dynamics (MD) simulation, which is one of the most cost-effective means semiconductor material research. However, even such provide high accuracy energy and force Mean Absolute Error (MAE) over trained (in-distribution) datasets, they often become unstable during long-time MD simulation when for out-of-distribution datasets. In this paper, we propose a feature correlation method GNNFF to enhance...

Gut microbiota and bile acid metabolism play crucial roles in the progression of nonalcoholic fatty liver disease (NAFLD). Early evidence demonstrates that Ginsenoside Re (Re) possesses pharmacological effects on NAFLD, but its mechanisms action are not well understood. This study aimed to investigate hepatic protective NAFLD elucidate relevant mechanisms. The treatments (10, 20, or 40 mg/kg) against high-fat diet-induced were initially tested male C57BL/6 mice. Then, a separate mouse group...

The way in which alternate wetting and drying irrigation (AWD), as a water-saving practice promoted rice (Oryza sativa L.) production systems, could enhance the productivity water use efficiency (WUE) attracts broad attention. This study selected six mid-season indica varieties to investigate impacts of AWD conventional (CI) on grain yield, WUE, filling, root traits. A two-year field experiment demonstrated that yields WUE were significantly increased with varietal improvements. With...

Abstract Motivation RNA N6-methyladenosine (m6A) in Homo sapiens plays vital roles a variety of biological functions. Precise identification m6A modifications is thus essential to elucidation their functions and underlying molecular-level mechanisms. Currently available high-throughput single-nucleotide-resolution modification data considerably accelerated the sites through development data-driven computational methods. Nevertheless, existing methods have limitations terms coverage cell...

In the robot vision system of apple harvesting robot, key is to recognize and locate apple. To solve recognition questions such as high error rate, too much calculation time consuming, a new recognizing method, support vector machine (SVM) applied improve accuracy efficiency. At first, median filter used remove color images noise fruit. Secondly, segmentation based on region growing method properties done. Then, shape image are extracted, classification SVM for fruit used. Experimental...