A5100325794- Machine Learning in Bioinformatics
- RNA and protein synthesis mechanisms
- RNA modifications and cancer
- Zeolite Catalysis and Synthesis
- Mesoporous Materials and Catalysis
- Advanced biosensing and bioanalysis techniques
- Gene expression and cancer classification
- Polyoxometalates: Synthesis and Applications
- Herpesvirus Infections and Treatments
- Cancer Genomics and Diagnostics
- Supramolecular Self-Assembly in Materials
- Genomics and Phylogenetic Studies
- Antimicrobial Peptides and Activities
- Luminescence and Fluorescent Materials
- Artificial Intelligence in Healthcare
- Advanced Text Analysis Techniques
- Spatial Neglect and Hemispheric Dysfunction
- Web Data Mining and Analysis
- Functional Brain Connectivity Studies
- Toxoplasma gondii Research Studies
- Cancer Cells and Metastasis
- Parasitic Infections and Diagnostics
- AI in cancer detection
- Nanopore and Nanochannel Transport Studies
- Hydrogels: synthesis, properties, applications
Jilin University
2011-2024
Jilin Province Science and Technology Department
2023-2024
Jilin Medical University
2019-2020
State Key Laboratory of Supramolecular Structure and Materials
2008-2020
State Council of the People's Republic of China
2019
Union Hospital
2014
Injectable hydrogels are adapted to irregularities in the desired location by injection as a liquid and gelation <italic>in situ</italic>.
Human Leukocyte Antigen (HLA) is a type of molecule residing on the surfaces most human cells and exerts an essential role in immune system responding to invasive items. The T cell antigen receptors may recognize HLA-peptide complexes cancer destroy these through toxic lymphocytes. computational determination HLA-binding peptides will facilitate rapid development immunotherapies. This study hypothesized that natural language processing-encoded peptide features be further enriched by another...
N4-methylcytosine (4mC) is a DNA modification involving the addition of methyl group to fourth nitrogen atom cytosine base. This may influence gene regulation, providing potential insights into control mechanisms. Traditional laboratory methods for detecting 4mC methylation have limitations, but rise artificial intelligence has introduced efficient computational strategies site prediction. Despite this progress, challenges persist in terms model performance and interpretability. To tackle...
Ordered mesoporous silicas (SBA-15 or MCM-41) have been directly hydrothermally synthesized at high temperatures (160–180 °C) by using a solo hydrocarbon surfactant (P123 CTAB). 1H NMR spectra and thermogravimetric (TG) curves showed that these surfactants decomposed during the preparation process such temperatures. Accordingly, we proposed micelle plays an important role cooperative self-assembly of silicates in initial stage for formation basic mesostructure, it is no longer indispensable...
Inspired by nature, this review focuses on the construction and applications of biomimetic artificial nanochannels from perspective relationship between biological channels nanochannels.
Every user has a distinct background and specific goal when searching for information on the Web. The of Web search personalization is to tailor results particular based that user's interests preferences. This paper presents an approach engine optimization algorithm BP neural networks aiming at meeting increasing requirements modern people Internet retrieval. method makes more intelligent personalized, which strives providing optimum retrieval result users.
Abstract The characteristics of chloroplasts harvesting solar energy and conducting transfer have inspired chemists to mimic similar processes. However, accurate manipulation gain regularly displayed antenna chromophores in mimicking is a great challenge. Herein, rational design presented that combines orderly arranged with aggregation‐induced emission (AIE) develop artificial light‐harvesting systems. Tetraphenyl ethylene (TPE) molecules, which exhibited strong AIE properties, are...
Enhancers are short genomic regions exerting tissue-specific regulatory roles, usually for remote coding regions. observed in both prokaryotic and eukaryotic genomes, their detections facilitate a better understanding of the transcriptional regulation mechanism. The accurate detection strength evaluation enhancers remain major bioinformatics challenge. Most current studies utilized statistical features fixed-length nucleotide sequences. This study introduces location information each k-mer...
Neospora caninum, an apicomplexan parasite, is recognized as a major bovine abortifacient. Dense granule antigens (GRAs) play important roles in the formation and modification of parasitophorous vacuoles (PVs) Toxoplasma gondii. However, few studies investigating GRAs have been reported N. caninum. The aim present study was to characterize dense GRA6/GRA7 caninum PVs using MDBK cells host cell model. inoculated into cells, changes were observed transmission electron microscope (TEM)....
Patients at different ages have rates of cell development and metabolisms. As a result, age should be an essential part how disease diagnosis model is trained optimized. Unfortunately, most the existing studies not taken into account. This study demonstrated that models could improved by merely applying individual for patients groups. Both transcriptomes methylomes TCGA breast cancer dataset (TCGA-BRCA) were utilized analysis procedure feature selection classification. Our experimental data...
Background Vestibular migraine (VM), an intricate subtype of migraine, amalgamates the dual attributes and vestibular disorders. In clinical settings, individuals with VM frequently articulate concerns regarding manifestation subjective cognitive impairment. This dysfunction is intricately linked diminished mobility, heightened susceptibility to falls, increased absenteeism in afflicted patients. Consequently, comprehending features impairment patients holds potential significance. The...
Aim: Breast cancers at different stages have tremendous differences on both phenotypic and molecular patterns. The developmental stage is an essential factor in the clinical decision of treatment plans, but was usually formulated as a classification problem, which ignored consecutive relationships among them. Materials & methods: This study proposed regression-based procedure to detect biomarkers breast cancers. Biomarkers were detected by Lasso Ridge algorithms. Results conclusion: A...
An effective siRNA delivery platform was constructed by supramolecular self-assembly to achieve enhanced transfection efficiency and the gene silencing effect.
This work has developed a method to transfer nanoparticle array from the parent substrate target surface. A close-packed and ordered Au (Au NP) been successfully transferred using poly(lactic acid) (PLA) as mediator. For transfer, last step, i.e. removing PLA mediator, plays crucial role. The commonly-used dissolution of in organic solvents cannot maintain integrity. In this study, we have introduced wedging peel off Relative dissolution, is mild procedure able meet requirement transferring...
Breast cancer is one of main causes death for women. Most the existing survival analyses focus on features' associations with whether patients may survive five years or not. The personalized question remains largely unresolved about how long a breast patient will live. This study aims to predict patient-specific time patients. It formulates into two machine learning problems. first problem binary classification live longer than second build regression model patient's within years. methylome...
The neurological disorder mild cognitive impairment (MCI) demonstrates minor impacts on the patient's daily activities and may be ignored as status of normal aging. But some MCI patients further develop into severe statuses like Alzheimer's disease (AD). brain functional connectivity network (BFCN) was usually constructed from resting-state magnetic resonance imaging (rs-fMRI) data. This technology has been widely used to detect neurodegenerative dementia reveal intrinsic mechanism neural...
Background/Objectives: Understanding the relationship between DNA sequences and gene expression levels is of significant biological importance. Recent advancements have demonstrated ability deep learning to predict directly from genomic data. However, traditional methods are limited by basic word encoding techniques, which fail capture inherent features patterns sequences. Methods: We introduce TExCNN, a novel framework that integrates pre-trained models DNABERT DNABERT-2 generate embeddings...