A5115603513- X-ray Diffraction in Crystallography
- Crystallization and Solubility Studies
- Machine Learning in Bioinformatics
- RNA modifications and cancer
- Computational Drug Discovery Methods
- Pancreatic and Hepatic Oncology Research
- Antimicrobial Peptides and Activities
- Catalytic Processes in Materials Science
- Protein Structure and Dynamics
- Advanced Computing and Algorithms
- Breast Cancer Treatment Studies
- RNA and protein synthesis mechanisms
- Cancer Genomics and Diagnostics
- Advanced Photocatalysis Techniques
- Genetics, Bioinformatics, and Biomedical Research
- HVDC Systems and Fault Protection
- Cancer-related molecular mechanisms research
- MicroRNA in disease regulation
- Musculoskeletal pain and rehabilitation
- Spinal Cord Injury Research
- Advanced oxidation water treatment
- Cell death mechanisms and regulation
- Vacuum and Plasma Arcs
- Chemical Synthesis and Analysis
- Immune cells in cancer
Army Medical University
2024-2025
Chongqing Medical University
2024-2025
Second Affiliated Hospital of Chongqing Medical University
2024-2025
Dalian Medical University
2024-2025
Chongqing Technology and Business University
2024
Peking University
2024
Nanjing Medical University
2011-2024
Jiangsu Province Hospital
2011-2024
Guangdong Provincial People's Hospital
2024
Beijing Tian Tan Hospital
2024
Blood-brain barrier peptides (BBPs) have a large range of biomedical applications since they can cross the blood-brain based on different mechanisms. As experimental methods for identification BBPs are laborious and expensive, computational approaches necessary to be developed predicting BBPs. In this work, we describe method, BBPpred (blood-brain prediction), that efficiently identify using logistic regression. We investigate wide variety features from amino acid sequence information, then...
Abstract The bioactive peptide has wide functions, such as lowering blood glucose levels and reducing inflammation. Meanwhile, computational methods machine learning are becoming more important for functions prediction. Most of the previous studies concentrate on single-functional peptides However, number multi-functional is increase; therefore, novel needed. In this study, we develop a method MLBP (Multi-Label deep approach determining multi-functionalities Bioactive Peptides), which can...
The expression of proteins in Escherichia coli is often essential for their characterization, modification, and subsequent application. Gene sequence the major factor contributing expression. In this study, we used data from 6438 heterologous under same condition E. to construct a deep learning classifier screening high- low-expression proteins. conjunction with conserved residue analysis minimize functional disruption, mutation predictor enhanced protein (MPEPE) was proposed identify...
The selection of appropriate treatment modalities based on the presence or absence mutations in KRAS, NRAS, BRAF , and microsatellite instability (MSI) status has become a crucial consensus colorectal cancer (CRC) therapy. However, distribution pattern these genetic prevalence MSI Chinese stage I–III CRCs remain unclear. We retrospectively analyzed clinicopathological features, NRAS genes, as well 411 patients with CRC who underwent surgery from June 2020 to December 2022 First Affiliated...
Background: Inflammatory bowel disease (IBD) comprises a group of autoimmune disorders characterized by chronicity and resistance to cure, with an unknown etiology. Recent studies on the brain-gut axis suggest that central nervous system (CNS), particularly hypothalamic-pituitary (HPA), may play crucial role in modulating immune influencing progression. However, specific mechanism HPA IBD pathogenesis remain unclear. This study aims investigate alterations its potential roles during...
Biological datasets, such as gene expression data, often suffer from high dimensionality, containing numerous irrelevant or redundant features that can lead to overfitting and increased computational complexity. Effective feature selection is essential for reducing enhancing model performance, improving interpretability. While deep neural networks, autoencoders, have shown promise in selection, their performance diminishes when confronted with noisy data. To address these challenges, we...
Abstract Protein is the most important component in organisms and plays an indispensable role life activities. In recent years, a large number of intelligent methods have been proposed to predict protein function. These obtain different types information, including sequence, structure interaction network. Among them, sequences gained significant attention where are investigated extract information from views features. However, how fully exploit for effective sequence analysis remains...
Advancements in autonomous vehicles and deep learning have notably improved vehicle trajectory prediction accuracy. However, extracting interaction features complex driving scenarios, such as vehicle-to-vehicle interactions lane constraints, presents challenges. Deep learning-based methods struggle to achieve optimal predictive performance under limited computational resources. This study introduces a global attention mechanism enhance feature extraction from scene encodings, focusing the...
The rise of large foundation models, trained on extensive datasets, is revolutionizing the field AI. Models such as SAM, DALL-E2, and GPT-4 showcase their adaptability by extracting intricate patterns performing effectively across diverse tasks, thereby serving potent building blocks for a wide range AI applications. Autonomous driving, vibrant front in applications, remains challenged lack dedicated vision models (VFMs). scarcity comprehensive training data, need multi-sensor integration,...
Abstract: Inflammatory bowel disease (IBD), including Crohn's (CD) and ulcerative colitis (UC), is a chronic resulting from the interaction of various factors such as social elements, autoimmunity, genetics, gut microbiota. Alarmingly, recent epidemiological data points to surging incidence IBD, underscoring an urgent imperative: delineate intricate mechanisms driving its onset. Such insights are paramount, not only for enhancing our comprehension IBD pathogenesis but also refining...
Multi-view clustering has received great attention in recent years for the potential performance improvement by using cooperative learning of different views. Despite considerable progress, a few issues remain: (1) real multi-view data contains redundant features and noises that lead to unsatisfactory performance; (2) most existing methods only mine shared information between views ignore specific within views; (3) are based on two-step framework learn hidden view representation then perform...
Disruption of global ribosome biogenesis selectively affects craniofacial tissues with unclear mechanisms. Craniosynostosis is a congenital disorder characterized by premature fusion cranial suture(s) loss suture mesenchymal stem cells (MSCs). Here we focused on ribosomopathy disease gene Snord118, which encodes small nucleolar RNA (snoRNA), to genetically disturb in MSCs using mouse and human induced pluripotent cell (iPSC) models. Snord118 depletion exhibited p53 activation, increased...
Process nonlinearity and time-varying behavior of industrial systems are the main factors for poor performance online soft sensors. To ensure high predictive accuracy, adaptive sensor is a common practice. In this paper, an based on moving window Gaussian process regression (GPR) presented. make strategy more efficient, just-in-time learning (JITL) algorithm used to enhance performance, which avoids selection size that original approaches have select . The effectiveness proposed method...