A5047054776- Advanced Computational Techniques and Applications
- Text and Document Classification Technologies
- Advanced Text Analysis Techniques
- Machine Learning in Bioinformatics
- Rough Sets and Fuzzy Logic
- Web Data Mining and Analysis
- Diabetes Treatment and Management
- Metaheuristic Optimization Algorithms Research
- Protein Tyrosine Phosphatases
- Algorithms and Data Compression
- Peptidase Inhibition and Analysis
- Image Processing and 3D Reconstruction
- DNA and Biological Computing
- Biomedical Text Mining and Ontologies
- Bioinformatics and Genomic Networks
- Anomaly Detection Techniques and Applications
- Metabolomics and Mass Spectrometry Studies
- Topic Modeling
- Computational Drug Discovery Methods
- Face and Expression Recognition
- Brain Tumor Detection and Classification
- Microbial Metabolic Engineering and Bioproduction
- Generative Adversarial Networks and Image Synthesis
- Genetics, Bioinformatics, and Biomedical Research
- Time Series Analysis and Forecasting
Minzu University of China
2025
University of South China
2024
Hunan Cancer Hospital
2024
Inner Mongolia University for Nationalities
2013-2022
National University of Mongolia
2012-2018
Inner Mongolia University
2010-2014
Jilin University
2007-2013
Jilin Medical University
2012
Jilin Province Science and Technology Department
2007-2009
Kyoto Institute of Technology
1998
Biocatalysis has emerged as a transformative technology in pharmaceutical synthesis, enabling efficient and sustainable production of chiral bioactive compounds. This review focuses on recent advancements biocatalytic methods, highlighting key enzyme systems, such ketoreductases, aminotransferases, imine reductases, which facilitate the synthesis alcohols, amines, other intermediates with high enantiomeric purity. Directed evolution protein engineering have significantly enhanced stability,...
Despite recent technological advances in quantifying antibody drug conjugate (ADC) species, such as total antibody, conjugated drug, and payload circulation, the correlation of their exposures with efficacy ADC outcomes vivo remains challenging. Here, chemical structures concentrations intratumor catabolites were investigated to better understand drivers efficacy. Anti-CD22 disulfide-linked pyrrolobenzodiazepine (PBD-dimer) conjugates containing methyl- cyclobutyl-substituted disulfide...
In this paper, we introduce two improvements on ant colony optimization (ACO) algorithm: route and individual variation. The first is an optimized implementation of ACO, by which the running time ants routing largely reduced. results simulated experiments show that improved algorithm not only reduces number in ACO but also surpasses existing algorithms performance solving large-scale TSP problems. second improvement, variation to have different strategies. Simulation speed convergence could...
In this paper, we present a hybrid optimisation algorithm with artificial bee colony (ABC) and particle swarm (PSO). Due to the fast convergent speed, PSO is main methodology of algorithm, as well ABC used optimise parameters. To investigate performance, it applied solve travelling salesman problem. Simulation results show effective.
Breast cancer is estimated to be the leading type among new cases in American women. Core biopsy data have shown a close association between breast hyperplasia and cancer. The early diagnosis treatment of are extremely important prevent Mongolian medicine RuXian-I traditional drug that has achieved high level efficacy low incidence side effects its clinical use. However, for detecting RuXian-I, rapid accurate evaluation method based on metabolomic still lacking. Therefore, we proposed...
Affinity propagation is an impressive clustering algorithm which was published in Science, 2007. However, the original couldn't cope with part known data directly. Focusing on this issue, a semi-supervised scheme called incremental affinity proposed paper. In scheme, pre-known information represented by adjusting similarity matrix. Moreover, study applied to amplify prior knowledge. To examine effectiveness of method, we concentrate it text problem and describe specific method accordingly....
To investigate the regulatory effect of glycyrrhizin (GL) on release neutrophil extracellular traps (NETs) from neutrophils in sepsis. HL-60 cells were induced to differentiate into neutrophil-like dHL-60 establish a sepsis model. Expression levels high-mobility group box 1 (HMGB1), citrullinated histone H3 (Cit-H3), and Toll-like receptor 9 (TLR9) assessed by Western blotting. Free DNA, component NETs, was quantified using fluorescence microplate reader. Cellular immunofluorescence analysis...
As a traditional Mongolian medicine, Sendeng‐4 (SD) has been widely used to treat rheumatoid arthritis (RA) in Inner Mongolia and exhibits good curative effect. Unfortunately, due geographical factors, it is difficult popularize this drug throughout the whole country, mechanism of action SD unclear. In study, serum metabolite profile analysis was performed identify potential biomarkers associated with adjuvant‐induced RA investigate SD. Ultraperformance liquid chromatography coupled...
Text classification is an important research field of data mining topics. This article brings a mutual information and entropy pair based feature selection method (MIIEP_FS) on the theory concept. measure effect using by show difference extent between features being selected ones entropy. The experimental results that MIIEP_FS proposed more effective than MI CHI methods. Macro F1 degrees different kinds machine learning algorithms: Naive Bayes KNN are higher method, sometimes even support...
Naru3 (NR) is a traditional Mongolian medicine with high clinical efficacy and low incidence of side effects. Metabolomics an approach that can facilitate the development drugs. However, metabolomic data have throughput, sparse, high-dimensional, small sample nature, their classification challenging. Although deep learning methods wide range applications, learning-based studies not been widely performed. We aimed to develop improved stacked autoencoder (SAE) for classification. established...
The new information about potential biological virus is present in the network public opinion, spread of hot-spot viruses' events on easier to tap characteristics, and with as opinion analysis axis, it more targeted. discovery tracking event hot spot research area. mainly dependent Topic Detection Tracking (TDT). paper focuses construction project-level available distributed systems, proposed a methods, introduced concept task allocation mechanism, defined rule marks, domain ontology-based...
Imbalanced data classification problem has always been one of the hot issues in field machine learning. Synthetic minority over-sampling technique (SMOTE) is a classical approach to balance datasets, but it may give rise such as noise. Stacked De-noising Auto-Encoder neural network (SDAE), can effectively reduce redundancy and noise through unsupervised layer-wise greedy Aiming at shortcomings SMOTE algorithm when synthesizing new class samples, paper proposed based on SMOTE, SMOTE-SDAE,...
Background: Various properties of Protein-Protein Interaction (PPI) network have been widely exploited to discover the topological organizing principle and crucial function motifs involving specific biological pathway or disease process. The current PPI are either detected by topology-based coarse grain algorithms, i.e. community discovering, depended on limited-accessible protein annotation data derived precise algorithms. However, identified hardly compatible with well-defined functions...
It has great significance to efficiently distinguish the type of samples' data in decision table after discretization for course machine learning and mining afterwards. This paper puts forward an annotation method distinguishing based on attributes importance samples entropy, processed simulation test using part UCI database which was artificially modified, it turns out is able identify with high accuracy, low misidentification rate reject rate.