BioBLP: a modular framework for learning on multimodal biomedical knowledge graphs
Daniel Daza, Dimitrios Alivanistos, Payal Mitra, Thom Pijnenburg, Michael Cochez, Paul Groth · 2023
Read BioBLP: a modular framework for learning on multimodal biomedical knowledge graphs by Daniel Daza, Dimitrios Alivanistos, Payal Mitra, Thom Pijnenburg, Michael Cochez, Paul Groth (2023) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-10709903.txt.
Description
Daniel Daza and five colleagues published a 2023 paper on BioBLP, a framework for learning from biomedical knowledge graphs. Knowledge graphs store facts as networks of entities and relationships, from genes to diseases to drugs. Machine learning on them predicts new links, such as a drug's possible target.
Many biomedical entities carry rich attribute data, like protein sequences or molecular structures. Some earlier methods ignore these attributes; others wrongly assume every entity has the same kind of data. BioBLP is modular: different encoders handle different modalities, and the framework combines them into embeddings for link prediction. Modularity lets researchers plug in the right data type for each entity class in the graph.
Catalog record
| CREATOR | Daniel Daza, Dimitrios Alivanistos, Payal Mitra, Thom Pijnenburg, Michael Cochez, Paul Groth |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 100 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |