A5051597671- Biomedical Text Mining and Ontologies
- Topic Modeling
- Bioinformatics and Genomic Networks
- Natural Language Processing Techniques
- Advanced Text Analysis Techniques
- Computational Drug Discovery Methods
- Machine Learning in Bioinformatics
- Semantic Web and Ontologies
- Gene expression and cancer classification
- Advanced Graph Neural Networks
- Text and Document Classification Technologies
- Magnesium Alloys: Properties and Applications
- Microbial Metabolic Engineering and Bioproduction
- Sentiment Analysis and Opinion Mining
- Pharmacovigilance and Adverse Drug Reactions
- Advanced biosensing and bioanalysis techniques
- Machine Learning in Healthcare
- Web Data Mining and Analysis
- Gait Recognition and Analysis
- Information Retrieval and Search Behavior
- Aluminum Alloys Composites Properties
- Genomics and Phylogenetic Studies
- Gene Regulatory Network Analysis
- Advanced Image Processing Techniques
- Corrosion Behavior and Inhibition
Tianjin Medical University General Hospital
2025
Zhengzhou University
2024-2025
Tianjin Medical University
2023-2025
Beijing Institute of Technology
2023-2024
Dalian University of Technology
2015-2024
Guiyang Medical University
2024
Anhui University of Technology
2023-2024
National Center for Biotechnology Information
2024
National Institutes of Health
2024
Chongqing University
2023-2024
Abstract Distributed word representations have become an essential foundation for biomedical natural language processing (BioNLP), text mining and information retrieval. Word embeddings are traditionally computed at the level from a large corpus of unlabeled text, ignoring present in internal structure words or any available domain specific structured resources such as ontologies. However, holds potentials greatly improving quality representation, suggested some recent studies general...
Abstract Motivation In biomedical research, chemical is an important class of entities, and named entity recognition (NER) task in the field information extraction. However, most popular NER methods are based on traditional machine learning their performances heavily dependent feature engineering. Moreover, these sentence-level ones which have tagging inconsistency problem. Results this paper, we propose a neural network approach, i.e. attention-based bidirectional Long Short-Term Memory...
Detecting drug-drug interaction (DDI) has become a vital part of public health safety. Therefore, using text mining techniques to extract DDIs from biomedical literature received great attentions. However, this research is still at an early stage and its performance much room improve.In article, we present syntax convolutional neural network (SCNN) based DDI extraction method. In method, novel word embedding, proposed employ the syntactic information sentence. Then position speech features...
Most existing fine-tuned biomedical large language models (LLMs) focus on enhancing performance in monolingual question answering and conversation tasks. To investigate the effectiveness of LLMs diverse natural processing (NLP) tasks different languages, we present Taiyi, a bilingual LLM for NLP
Adverse events resulting from drug-drug interactions (DDI) pose a serious health issue. The ability to automatically extract DDIs described in the biomedical literature could further efforts for ongoing pharmacovigilance. Most of neural networks-based methods typically focus on sentence sequence identify these DDIs, however shortest dependency path (SDP) between two entities contains valuable syntactic and semantic information. Effectively exploiting such information may improve DDI...
Drug-drug interactions (DDIs) often bring unexpected side effects. The clinical recognition of DDIs is a crucial issue for both patient safety and healthcare cost control. However, although text-mining-based systems explore various methods to classify DDIs, the classification performance with regard in long complex sentences still unsatisfactory. In this study, we propose an effective model that classifies from literature by combining attention mechanism recurrent neural network short-term...
Drug discovery is the process through which potential new medicines are identified. High-throughput screening and computer-aided drug discovery/design two main methods for now, have successfully discovered a series of drugs. However, development drugs still an extremely time-consuming expensive process. Biomedical literature contains important clues identification treatments. It could support experts in biomedicine on their way towards discoveries.Here, we propose biomedical knowledge...
It is well known that the corrosion resistance of ultra-light Mg-Li alloys inferior to traditional Mg due rapid oxidation reactive Li on surface. In this study, microalloying Sn has been found improve formation Mg2Sn pits and reduction electro-potential difference. Indeed, addition not only reduced rate minimum value 4.27 mmpy but also promote dense oxide films. The volt potential difference between matrix (α-Mg β-Li) Al-X (Gd, Y, Mn) phases measured reduce from 260mV (α-Mg) 343mV (β-Li)...
Targeting oncogenic mutant p53 represents an attractive strategy for cancer treatment due to the high frequency of gain-of-function mutations and ectopic expression in various types. Despite extensive efforts, absence a druggable active site small molecules has rendered these mutants therapeutically non-actionable. Here we develop selective effective proteolysis-targeting chimera (PROTAC) p53-R175H, common hotspot with dominant-negative activity. Using novel iterative molecular...
Abstract Mg alloy suffers from its poor corrosion resistance as a result of anodic dissolution and hydrogen evolution reaction (HER) in humid environments. In this study, the effects alloying elements (Al, Zn, Y, Ce, Mn) on both processes alloys have been quantitatively predicted. Using first‐principle calculations, we first obtained substitution energies to compare their segregation preference, then analyzed influence solutes at different layers stability adsorption properties Mg(0001)...
Drug discovery is the process by which new candidate medications are discovered. Developing a drug lengthy, complex, and expensive process. Here, in this paper, we propose biomedical knowledge graph embedding-based recurrent neural network method called GrEDeL, discovers potential drugs for diseases mining published literature. GrEDeL first builds exploiting relations extracted from abstracts. Then, data converted into low dimensional space leveraging embedding methods. After that, model...
Knowledge Graph (KG) is becoming increasingly important in the biomedical field. Deriving new and reliable knowledge from existing by KG embedding technology a cutting-edge method. Some add variety of additional information to aid reasoning, namely multimodal reasoning. However, few works based on KGs are focused specific diseases.This work develops construction reasoning process Specific Disease Graphs (SDKGs). We construct SDKG-11, SDKG set including five cancers, six non-cancer diseases,...
We present the new Bokeh Effect Transformation Dataset (BETD), and review proposed solutions for this novel task at NTIRE 2023 Challenge. Recent advancements of mobile photography aim to reach visual quality full-frame cameras. Now, a goal in computational is optimize effect itself, which aesthetic blur out-of-focus areas an image. Photographers create by benefiting from lens optical properties.The work design neural network capable converting one another without harming sharp foreground...
Cancer markers are used for early cancer detection and follow-up monitoring so that patients receive the most appropriate treatment to alleviate suffering prolong life. Herein, a metal–organic framework (MOF) combined with magnetic beads (MB) is proposed as nanosensor detecting breast biomarkers based on enrichment separation. With porous structure of Cu-MOF, large number aptamers adsorbed inside pore specifically capture antigen. Then, Cu-MOF@antigen enriched separated by MB modified...
To date, the aging softening of Mg-Li-Zn based alloys has been a critical issue limiting their industrial application. Here, we design new Mg-Li alloy that exhibits exceptional mechanical stability after solution treatment and then water quenching by means hitherto unrecognized mechanism. The results indicate precipitation semi-coherent MgLi2(ZnAg) phase leads to rapid age-hardening quenching, as evidenced Ag atoms in precipitate. A massive solid β-Li strengthens retards diffusion Li from β...