Official websites use .gov
A
.gov website belongs to an official
government organization in the United States.
Secure .gov websites use HTTPS
A lock (
) or https:// means you've safely
connected to the .gov website. Share sensitive
information only on official, secure websites.
Sizes of the raw text entries that we used to perform knowledge base lookup and the corresponding embedding sizes.
| Knowledge base | Raw size | Embedding size |
|---|---|---|
| NCBI Genea (10) | 3.9 GB | 5.5 GB |
| CTD diseases (16, 17) | 6 MB | 376 MB |
| MeSH (42) | 46 MB | 2.6 GB |
| dbSNPb (64) | – | – |
| NCBI Taxonomy (63) | 317 MB | 16 GB |
| Cellosaurus (5) | 6.3 MB | 595 MB |
| Total | 4.28 GB | 25 GB |
a We only embedded the genes for most frequent species.
b As mentioned, we use LitVar2 for performing lookups on dbSNP
