About this Research Topic
A biological system consists of several functionally inter-dependent components including genes, diseases, drugs, cells, etc. Biological networks are widely used to describe interactions among these elements. Research into biological networks focuses on the construction of networks, representation of network learning, and making inferences and predictions about biological networks. Existing network-based approaches have been used for prediction of protein function, disease gene, drug effects, and precision medicine.
Recently, deep learning-based methods have been developed to address various biomedical problems, such as skin cancer classification, cell structure, and function modeling, transcription factor prediction, and DNase hypersensitivity prediction.
Research reveals that deep learning models are able to learn arbitrarily complex relationships from heterogeneous datasets with existing incorporated knowledge. Inspired by this, researchers started to apply deep learning for biological network analysis, such as detection of Polypharmacy Side Effects and prediction of drug-target interactions. Deep learning has shown great potential in biological network analysis and can be used for network denoising, disease biomarker prediction and so on.
In view of the above development of deep learning in the research of biological networks, we propose a Research Topic, aiming to provide a great opportunity for researchers to share their latest research findings, present novel methods, and discuss the challenges and opportunities in the related fields.
Papers are solicited on, but not limited to, the following topics:
- Deep learning for protein-protein network analysis
- Deep learning for multiple network integration
- Association prediction using deep learning methods
- Deep learning for drug-drug interaction analysis
- Reinforcement learning in biological network analysis
- Combining biomedical text mining with biological network
- Deep learning methods for multi-level omics
- Tools and databases based on deep learning method
- Deep learning in a biomedical ontology and directed network
Recently, deep learning-based methods have been developed to address various biomedical problems, such as skin cancer classification, cell structure, and function modeling, transcription factor prediction, and DNase hypersensitivity prediction.
Research reveals that deep learning models are able to learn arbitrarily complex relationships from heterogeneous datasets with existing incorporated knowledge. Inspired by this, researchers started to apply deep learning for biological network analysis, such as detection of Polypharmacy Side Effects and prediction of drug-target interactions. Deep learning has shown great potential in biological network analysis and can be used for network denoising, disease biomarker prediction and so on.
In view of the above development of deep learning in the research of biological networks, we propose a Research Topic, aiming to provide a great opportunity for researchers to share their latest research findings, present novel methods, and discuss the challenges and opportunities in the related fields.
Papers are solicited on, but not limited to, the following topics:
- Deep learning for protein-protein network analysis
- Deep learning for multiple network integration
- Association prediction using deep learning methods
- Deep learning for drug-drug interaction analysis
- Reinforcement learning in biological network analysis
- Combining biomedical text mining with biological network
- Deep learning methods for multi-level omics
- Tools and databases based on deep learning method
- Deep learning in a biomedical ontology and directed network
Keywords: deep learning, biomedical data analysis, data integration, biomedical ontology, biomedical network
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
