A5000503636- Computational Drug Discovery Methods
- Protein Structure and Dynamics
- Machine Learning in Bioinformatics
- RNA and protein synthesis mechanisms
- Genomics and Phylogenetic Studies
- Machine Learning in Materials Science
- Receptor Mechanisms and Signaling
- Microbial Natural Products and Biosynthesis
- Biomedical Text Mining and Ontologies
- Influenza Virus Research Studies
- vaccines and immunoinformatics approaches
- Bioinformatics and Genomic Networks
Nanjing Medical University
2023-2024
Suzhou University of Science and Technology
2020-2022
The accurate prediction of drug-target affinity (DTA) is a crucial step in drug discovery and design. Traditional experiments are very expensive time-consuming. Recently, deep learning methods have achieved notable performance improvements DTA prediction. However, one challenge for learning-based models appropriate representations drugs targets, especially the lack effective exploration target representations. Another how to comprehensively capture interaction information between different...
Predicting G protein—coupled receptor (GPCR)—ligand binding affinity plays a crucial role in drug development. However, determining GPCR—ligand affinities is time-consuming and resource-intensive. Although many studies used data-driven methods to predict affinity, most of these required protein 3D structure, which was often unknown. Moreover, part only considered the sequence characteristics protein, ignoring secondary structure protein. The number known GPCR for prediction few thousand,...
DNA-binding proteins (DBPs) have a significant impact on many life activities, so identification of DBPs is crucial issue. And it greatly helpful to understand the mechanism protein-DNA interactions. In traditional experimental methods, time-consuming and labor-consuming identify DBPs. recent years, researchers proposed lots different DBP methods based machine learning algorithm overcome shortcomings mentioned above. However, most existing cannot get satisfactory results. this paper, we...
Background: The prediction of drug-target interactions (DTIs) plays an essential role in drug discovery. Recently, deep learning methods have been widely applied DTI prediction. However, most the existing research does not fully utilize molecular structures compounds and sequence proteins, which makes these models unable to obtain precise effective feature representations. Methods: In this study, we propose a novel framework combining transformer graph neural networks for predicting DTIs....
Background: New drugs are costly, time-consuming, and often accompanied by safety concerns. With the development of deep learning, computer-aided drug design has become more mainstream, convolutional neural networks graph have been widely used for drug–target affinity (DTA) prediction. Objective: The paper proposes a method predicting DTA using multiscale networks. Methods: We construct molecules into representation vectors learn feature expressions through attention A three-branch network...
Background: Conventional approaches to drug discovery are often characterized by lengthy and costly processes. To expedite the of new drugs, integration artificial intelligence (AI) in predicting drug-target binding affinity (DTA) has emerged as a crucial approach. Despite proliferation deep learning methods for DTA prediction, many these primarily concentrate on amino acid sequence proteins. Yet, interactions between compounds targets occur within distinct segments protein structures,...
In the drug discovery process, accurate prediction of drug-target interactions is crucial to accelerate development new drugs. However, existing methods still face many challenges in dealing with complex biomolecular interactions. To this end, we propose a deep learning framework that combines structural information and sequence features proteins provide comprehensive feature representation through bimodal fusion. This not only integrates topological adaptive graph convolutional network...
<abstract> <p>The study of DNA binding proteins (DBPs) is great importance in the biomedical field and plays a key role this field. At present, many researchers are working on prediction detection DBPs. Traditional DBP mainly uses machine learning methods. Although these methods can obtain relatively high pre-diction accuracy, they consume large quantities human effort material resources. Transfer has certain advantages dealing with such problems. Therefore, present study, two...
G protein-coupled receptors (GPCRs) account for about 40% to 50% of drug targets. Many human diseases are related protein coupled receptors. Accurate prediction GPCR interaction is not only essential understand its structural role, but also helps design more effective drugs. At present, the mainly uses machine learning methods. Machine methods generally require a large number independent and identically distributed samples achieve good results. However, available that have been marked...
<abstract> <p>DNA-protein binding is crucial for the normal development and function of organisms. The significance accurately identifying DNA-protein sites lies in its role disease prevention innovative approaches to treatment. In present study, we introduce a precise robust identifier residues. context protein representation, combine evolutionary information protein, represented by position-specific scoring matrix, with spatial protein's secondary structure, enriching overall...