A5089984487- Computational Drug Discovery Methods
- vaccines and immunoinformatics approaches
- SARS-CoV-2 and COVID-19 Research
- Protein Structure and Dynamics
- Graph Theory and Algorithms
- Human Pose and Action Recognition
- Advanced Database Systems and Queries
- Data Management and Algorithms
- Bacteriophages and microbial interactions
- Synthesis and biological activity
- SARS-CoV-2 detection and testing
- Cancer Genomics and Diagnostics
- Immunotherapy and Immune Responses
- Robot Manipulation and Learning
- Machine Learning in Materials Science
- Viral Infectious Diseases and Gene Expression in Insects
- RNA modifications and cancer
- Ferroptosis and cancer prognosis
- Monoclonal and Polyclonal Antibodies Research
- Protein purification and stability
- Antimicrobial Peptides and Activities
Central South University
2018-2025
Accurate and robust prediction of drug-target interactions (DTIs) plays a vital role in drug discovery but remains challenging due to limited labeled data, cold start problems, insufficient understanding mechanisms action (MoA). Distinguishing activation inhibition is particularly critical clinical applications. Here, we propose DTIAM, unified framework for predicting interactions, binding affinities, activation/inhibition between drugs targets. DTIAM learns target representations from large...
Human leukocyte antigen (HLA) recognizes foreign threats and triggers immune responses by presenting peptides to T cells. Computationally modeling the binding patterns between peptide HLA is very important for development of tumor vaccines. However, it still a big challenge accurately predict molecules peptides. In this paper, we develop new model TripHLApan predicting integrating triple coding matrix, BiGRU + Attention models, transfer learning strategy. We have found main interaction site...
The Novel Coronavirus Disease 2019 (COVID-19) has become an international public health emergency, which poses the most serious threat to human around world. Accumulating evidences have shown that new coronavirus could not only infect beings, but also can other species might result in cross-species infections. In this research, 1056 ACE2 protein sequences are collected from NCBI database, and 173 with >60% sequence identity compared of beings selected for further analysis. We find 14 polar...
Minichromosome maintenance proteins (MCMs) are considered to be essential factors coupling DNA replication both cell cycle progression and checkpoint regulation. Previous studies have shown that dysregulation of MCMs implicated in tumorigenesis lung cancer. However, the distinct expression/mutation patterns prognostic values cancer yet systematically elucidated. In present study, we analyzed transcriptional levels, mutations, value MCM1-10 non-small (NSCLC) patients using multiple...
Predicting the interaction of protein and compound is an important task in drug discovery. Molecular docking has been a fundamental vital computer-aid tool for digging potential protein-compound pair. With recent great success artificial intelligence (AI), scoring function, as part molecular docking, achieving much better performance by incorporating AI-based models. However, models usually focus on single prediction (e.g., affinity prediction), which limited their lack extensibility....
The Coronavirus Disease 2019 (COVID-19) has become an international public health emergency, posing a serious threat to human and safety around the world. 2019-nCoV coronavirus spike protein was confirmed be highly susceptible various mutations, which can trigger apparent changes of virus transmission capacity pathogenic mechanism. In this article, binding interface obtained by analyzing interaction modes between ACE2. Based on "SIFT server" "bubble" identification mechanism, 9 amino acid...
BackgroundThe emerging mutants of the 2019-nCoV coronavirus are posing unprecedented challenges to pandemic prevention. A thorough, understanding mutational characterization responsible for pathogenic mechanisms mutations in 2019-nCoV-Spike is indispensable developing effective drugs and new vaccines.MethodsWe employed computational methods viral infection assays examine interaction pattern binding affinity between ACE2 both single- multi-mutants Spike proteins.ResultsUsing data from...
Background: Computational molecular docking plays an important role in determining the precise receptor-ligand conformation, which becomes a powerful tool for drug discovery. In past 30 years, most computational methods have treated receptor structure as rigid body, although flexible often yields higher accuracy. The main disadvantage of is its significantly cost. Due to fact that different protein pocket residues exhibit degrees flexibility, semi-flexible methods, balancing and docking,...
Subgraph matching query is to find out the sub-graphs of data graph G which match a given Q. Traditional methods can not deal with big graphs due their high computational complex. In this paper, we propose distributed top-k subgraph search method over graphs. The proposed designed at level single vertex and all vertices obtain state separately without requiring global information. Therefore, it be easily deployed in platform like Hadoop. evaluations running time, number messages supersteps...
Accurate and robust prediction of drug-target interactions (DTIs) plays a vital role in drug discovery. Despite extensive efforts have been invested predicting novel DTIs, existing approaches still suffer from insufficient labeled data cold start problems. More importantly, there is currently lack studies focusing on elucidating the mechanism action (MoA) between drugs targets. Distinguishing activation inhibition mechanisms critical challenging development. Here, we introduce unified...