A5106747022- Topic Modeling
- Biomedical Text Mining and Ontologies
- Advanced Text Analysis Techniques
- Semantic Web and Ontologies
- Natural Language Processing Techniques
- Bioinformatics and Genomic Networks
- Machine Learning in Bioinformatics
- SARS-CoV-2 and COVID-19 Research
- Text and Document Classification Technologies
- Enzyme Structure and Function
- Sentiment Analysis and Opinion Mining
- Enzyme Production and Characterization
- SARS-CoV-2 detection and testing
- Infection Control and Ventilation
- Software Engineering Research
- Protein Structure and Dynamics
Dalian University of Technology
2016-2023
Dalian University
2022-2023
Identifying chemical–disease relations (CDR) from biomedical literature could improve chemical safety and toxicity studies. This article proposes a novel syntactic semantic information exploitation method for CDR extraction. The proposed consists of feature-based model, tree kernel-based model neural network model. exploits lexical features, the captures structure generates representations. motivation our is to fully utilize nice properties three models explore diverse Experiments on...
Automatically extracting protein–protein interactions (PPIs) from biomedical literature provides additional support for precision medicine efforts. This paper proposes a novel memory network-based model (MNM) PPI extraction, which leverages prior knowledge about pairs with networks. The proposed MNM captures important context clues related to representations learned bases. Both entity embeddings and relation of are effective in improving the extraction model, leading new state-of-the-art...
Microbial fatty acids are synthesized by Type II acid synthase and could be tailored acyl-ACP thioesterase. With the prospects of medium-chain fatty-acid-derivative biofuels, selectivity thioesterase has been studied to control product chain length. Here, we report an alternative approach manipulating acyl carrier protein portion switch length propensity It was demonstrated that ChFatB2 from Cuphea hookeriana preferred C10-ACP C8-ACP with ACP E. coli, while converting preference lanceolate....
Chinese hedge scope detection is dependent on syntactic and semantic information. Most previous methods typically use lexical information as a basic unit of classification, which make these lose part the effective structure In order to enhance performance, we take phrase, are extracted from parse tree by some heuristic rules, classification (candidate phrase). Furthermore, novel hierarchical neural network proposed learn representation phrase its context. Experiments Biomedical Hedge...