A collection of biomedical knowledgebases, ontologies, datasets and publications. I hope this collection can help you to find the right resource to build your own knowledge graph. I will keep updating this list. If you have any suggestions, please feel free to post an issue or pull request.
If you only want to use the knowledge graph, you can see our other projects/websites:
-
A knowledge graph system with graph neural network for drug discovery, disease mechanism and biomarker screening.
-
A Customized Knowledge Graph for BioMedGPS Project
-
RAPEX - Response to Air Pollution EXposure; A knowledge graph system for air pollution exposure.
A knowledge graph is a powerful tool for organizing and integrating information. It's a type of database that makes use of semantic web technology to represent information in a graph format. In the context of biomedical research, a knowledge graph would contain nodes representing entities (like genes, diseases, drugs, or proteins) and edges representing relationships (like "is associated with," "causes," "is a type of," etc.) between these entities.↳
Knowledge graphs are essential in biomedical research for several reasons:
-
Data Integration: Biomedical data is often distributed across multiple databases, publications, and even raw datasets. These data sources can be diverse in terms of their format, scale, and level of detail. Knowledge graphs can help integrate this heterogeneous data into a single, standardized, interoperable format, facilitating easier analysis and interpretation.
-
Semantic Understanding: In the biomedical field, semantics (meaning and context) is critical. For instance, understanding that "aspirin" is a type of "drug" that is used to treat "pain" and "inflammation" is crucial for many applications. Knowledge graphs encode this type of semantic information in a machine-readable format, enabling sophisticated reasoning and inference.
-
Hypothesis Generation: By representing
-
Discovery of Hidden Relationships: Through the linkage of different biomedical entities, knowledge graphs can help discover hidden or implicit relationships. This feature is especially important given the complexity of biological systems and the potential for unexpected interactions between their components.
-
Machine Learning and AI: Knowledge graphs can feed structured data into AI and machine learning models, improving their performance. This structured data can enhance the ability of models to predict, classify, or make decisions, which can be especially important for applications like drug discovery or precision medicine.
Overall, knowledge graphs are an invaluable tool in biomedical research because they help to integrate, standardize, and make sense of the vast and complex array of data available in the field. They allow for more sophisticated data analysis and can help drive new discoveries in the field.