ayushnoori commited on
Commit
293a563
·
verified ·
1 Parent(s): 85f175e

Update project website link

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -20,7 +20,7 @@ license: mit
20
 
21
  # Model Card
22
 
23
- [![Website](https://img.shields.io/badge/Website-000000?style=for-the-badge)](https://zitniklab.hms.harvard.edu/PROTON)
24
  [![Paper](https://img.shields.io/badge/ArXiv-B31B1B?style=for-the-badge&logo=arxiv&logoColor=white)](https://arxiv.org)
25
  [![Code](https://img.shields.io/badge/Code-181717?style=for-the-badge&logo=github&logoColor=white)](https://github.com/mims-harvard/PROTON)
26
  [![Model](https://img.shields.io/badge/Model-FFCC00?style=for-the-badge&logo=huggingface&logoColor=black)](https://huggingface.co/mims-harvard/PROTON)
@@ -32,7 +32,7 @@ Neurological diseases are the leading global cause of disability, yet most lack
32
 
33
  ## Training Data
34
 
35
- PROTON was trained on NeuroKG, a heterogeneous, undirected biomedical knowledge graph contextualized to the human brain. NeuroKG unifies 36 human datasets and ontologies, and integrates single-nucleus RNA-sequencing atlases comprising 3,756,702 cells from the adult human brain. The knowledge graph contains 147,020 nodes across 16 entity types and 7,366,745 edges across 47 relation types. NeuroKG is available via Harvard Dataverse at DOI: [10.7910/DVN/ZDLS3K](https://doi.org/10.7910/DVN/ZDLS3K). For more details, please refer to our [project website](https://zitniklab.hms.harvard.edu/PROTON).
36
 
37
  ## Model Architecture
38
 
@@ -55,7 +55,7 @@ PROTON is a a 578-million-parameter heterogeneous graph transformer for neurolog
55
  - `embeddings.csv`: Embedding store as a CSV file.
56
  - `disease_splits/`: Directory containing embeddings of PROTON trained on disease-centric splits.
57
 
58
- Files within the `disease_splits/` directory follow the naming convention `{node_id}_{artifact}`, where `{node_id}` represents the unique identifier for the disease node in [NeuroKG](https://doi.org/10.7910/DVN/ZDLS3K). For more details, please refer to our [project website](https://zitniklab.hms.harvard.edu/PROTON).
59
 
60
 
61
  ## Usage Instructions
 
20
 
21
  # Model Card
22
 
23
+ [![Website](https://img.shields.io/badge/Website-000000?style=for-the-badge)](https://protonmodel.ai/)
24
  [![Paper](https://img.shields.io/badge/ArXiv-B31B1B?style=for-the-badge&logo=arxiv&logoColor=white)](https://arxiv.org)
25
  [![Code](https://img.shields.io/badge/Code-181717?style=for-the-badge&logo=github&logoColor=white)](https://github.com/mims-harvard/PROTON)
26
  [![Model](https://img.shields.io/badge/Model-FFCC00?style=for-the-badge&logo=huggingface&logoColor=black)](https://huggingface.co/mims-harvard/PROTON)
 
32
 
33
  ## Training Data
34
 
35
+ PROTON was trained on NeuroKG, a heterogeneous, undirected biomedical knowledge graph contextualized to the human brain. NeuroKG unifies 36 human datasets and ontologies, and integrates single-nucleus RNA-sequencing atlases comprising 3,756,702 cells from the adult human brain. The knowledge graph contains 147,020 nodes across 16 entity types and 7,366,745 edges across 47 relation types. NeuroKG is available via Harvard Dataverse at DOI: [10.7910/DVN/ZDLS3K](https://doi.org/10.7910/DVN/ZDLS3K). For more details, please refer to our [project website](https://protonmodel.ai/).
36
 
37
  ## Model Architecture
38
 
 
55
  - `embeddings.csv`: Embedding store as a CSV file.
56
  - `disease_splits/`: Directory containing embeddings of PROTON trained on disease-centric splits.
57
 
58
+ Files within the `disease_splits/` directory follow the naming convention `{node_id}_{artifact}`, where `{node_id}` represents the unique identifier for the disease node in [NeuroKG](https://doi.org/10.7910/DVN/ZDLS3K). For more details, please refer to our [project website](https://protonmodel.ai/).
59
 
60
 
61
  ## Usage Instructions