knowledge graphs
Structured representations of knowledge where entities (people, genes, diseases, drugs) are nodes and their relationships (interactions, associations, causality) are edges, enabling reasoning about connections and inferences across domains.
As defined in MIT Scientist on Unifying Cognition and Biology | Manolis Kellis
Where it comes up · 1
Most important claims · 3 of 3Search all claims for “knowledge graphs” →
- We can now understand gene function through multiple modalities: literature via large language models, knowledge graphs of disease-gene-drug interactions, protein structure predictions, gene expression patterns across thousands of datasets, and protein-protein interaction networks, allowing convergent multi-faceted representations of single genes.MIT Scientist on Unifying Cognition and Biology | Manolis Kellis
- We can now understand a gene's function through multiple facets: literature via large language models, knowledge graphs showing disease interactions and chemicals, protein structure via protein language models, expression patterns across datasets, and protein-protein interaction networks.MIT Scientist on Unifying Cognition and Biology | Manolis Kellis
- It seemed mad for one research group to work on genetics, gene regulatory elements, epigenomics, protein structure, knowledge graphs, patient data, and electronic health records separately, but now there is method to the madness because you must integrate all information to understand complex diseases like Alzheimer's, obesity, schizophrenia, cardiovascular disease, immune disorders, cancer.MIT Scientist on Unifying Cognition and Biology | Manolis Kellis